From 06e472acf964649a58b7de35fc9cdc3151acb970 Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Fri, 28 Oct 2022 14:46:55 +0530
Subject: [PATCH 0001/1167] scsi: mpt3sas: Remove usage of
dma_get_required_mask() API
Remove the usage of dma_get_required_mask() API. Directly set the DMA mask
to 63/64 if the system is a 64bit machine.
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Link: https://lore.kernel.org/r/20221028091655.17741-2-sreekanth.reddy@broadcom.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/mpt3sas/mpt3sas_base.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 4e981ccaac416..69061545d9d2f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2992,8 +2992,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev)
struct sysinfo s;
u64 coherent_dma_mask, dma_mask;
- if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 ||
- dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) {
+ if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) {
ioc->dma_mask = 32;
coherent_dma_mask = dma_mask = DMA_BIT_MASK(32);
/* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
--
GitLab
From d347a951906b506c485ee9ffb76fe473b41f3e10 Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Fri, 11 Nov 2022 15:52:46 +0530
Subject: [PATCH 0002/1167] scsi: mpi3mr: Remove usage of
dma_get_required_mask() API
Remove the usage of dma_get_required_mask() API. Directly set the DMA mask
to 63/64 if the system is a 64bit machine.
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Link: https://lore.kernel.org/r/20221111102246.19995-2-sreekanth.reddy@broadcom.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/mpi3mr/mpi3mr_fw.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c
index 0c4aabaefdcc4..286a44506578b 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_fw.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c
@@ -3633,8 +3633,7 @@ int mpi3mr_setup_resources(struct mpi3mr_ioc *mrioc)
int i, retval = 0, capb = 0;
u16 message_control;
u64 dma_mask = mrioc->dma_mask ? mrioc->dma_mask :
- (((dma_get_required_mask(&pdev->dev) > DMA_BIT_MASK(32)) &&
- (sizeof(dma_addr_t) > 4)) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
+ ((sizeof(dma_addr_t) > 4) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
if (pci_enable_device_mem(pdev)) {
ioc_err(mrioc, "pci_enable_device_mem: failed\n");
--
GitLab
From 02228f6aa6a64d588bc31e3267d05ff184d772eb Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Sun, 27 Nov 2022 22:06:02 +0100
Subject: [PATCH 0003/1167] regulator: da9211: Use irq handler when ready
If the system does not come from reset (like when it is kexec()), the
regulator might have an IRQ waiting for us.
If we enable the IRQ handler before its structures are ready, we crash.
This patch fixes:
[ 1.141839] Unable to handle kernel read from unreadable memory at virtual address 0000000000000078
[ 1.316096] Call trace:
[ 1.316101] blocking_notifier_call_chain+0x20/0xa8
[ 1.322757] cpu cpu0: dummy supplies not allowed for exclusive requests
[ 1.327823] regulator_notifier_call_chain+0x1c/0x2c
[ 1.327825] da9211_irq_handler+0x68/0xf8
[ 1.327829] irq_thread+0x11c/0x234
[ 1.327833] kthread+0x13c/0x154
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Reviewed-by: Adam Ward <DLG-Adam.Ward.opensource@dm.renesas.com>
Link: https://lore.kernel.org/r/20221124-da9211-v2-0-1779e3c5d491@chromium.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/regulator/da9211-regulator.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index e01b32d1fa17d..00828f5baa972 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -498,6 +498,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c)
chip->chip_irq = i2c->irq;
+ ret = da9211_regulator_init(chip);
+ if (ret < 0) {
+ dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
+ return ret;
+ }
+
if (chip->chip_irq != 0) {
ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL,
da9211_irq_handler,
@@ -512,11 +518,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c)
dev_warn(chip->dev, "No IRQ configured\n");
}
- ret = da9211_regulator_init(chip);
-
- if (ret < 0)
- dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
-
return ret;
}
--
GitLab
From aff234839f8b80ac101e6c2f14d0e44b236efa48 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Fri, 9 Dec 2022 16:44:46 +0000
Subject: [PATCH 0004/1167] KVM: arm64: PMU: Fix PMCR_EL0 reset value
ARMV8_PMU_PMCR_N_MASK is an unshifted value which results in the wrong
reset value for PMCR_EL0, so shift it to fix it.
This fixes the following error when running qemu:
$ qemu-system-aarch64 -cpu host -machine type=virt,accel=kvm -kernel ...
target/arm/helper.c:1813: pmevcntr_rawwrite: Assertion `counter < pmu_num_counters(env)' failed.
Fixes: 292e8f149476 ("KVM: arm64: PMU: Simplify PMCR_EL0 reset handling")
Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221209164446.1972014-2-james.clark@arm.com
---
arch/arm64/kvm/sys_regs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d5ee52d6bf732..c6cbfe6b854b3 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -646,7 +646,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
return;
/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
- pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+ pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
if (!kvm_supports_32bit_el0())
pmcr |= ARMV8_PMU_PMCR_LC;
--
GitLab
From f728a5ea27c92133893590e731ce10f6561ced87 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Tue, 6 Dec 2022 14:07:49 +0100
Subject: [PATCH 0005/1167] dma-buf: fix dma_buf_export init order v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The init order and resulting error handling in dma_buf_export
was pretty messy.
Subordinate objects like the file and the sysfs kernel objects
were initializing and wiring itself up with the object in the
wrong order resulting not only in complicating and partially
incorrect error handling, but also in publishing only halve
initialized DMA-buf objects.
Clean this up thoughtfully by allocating the file independent
of the DMA-buf object. Then allocate and initialize the DMA-buf
object itself, before publishing it through sysfs. If everything
works as expected the file is then connected with the DMA-buf
object and publish it through debugfs.
Also adds the missing dma_resv_fini() into the error handling.
v2: add some missing changes to dma_bug_getfile() and a missing NULL
check in dma_buf_file_release()
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: T.J. Mercier <tjmercier@google.com>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20221209071535.933698-1-christian.koenig@amd.com
---
drivers/dma-buf/dma-buf-sysfs-stats.c | 7 +--
drivers/dma-buf/dma-buf-sysfs-stats.h | 4 +-
drivers/dma-buf/dma-buf.c | 84 +++++++++++++--------------
3 files changed, 43 insertions(+), 52 deletions(-)
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c
index 2bba0babcb62b..4b680e10c15a3 100644
--- a/drivers/dma-buf/dma-buf-sysfs-stats.c
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.c
@@ -168,14 +168,11 @@ void dma_buf_uninit_sysfs_statistics(void)
kset_unregister(dma_buf_stats_kset);
}
-int dma_buf_stats_setup(struct dma_buf *dmabuf)
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
struct dma_buf_sysfs_entry *sysfs_entry;
int ret;
- if (!dmabuf || !dmabuf->file)
- return -EINVAL;
-
if (!dmabuf->exp_name) {
pr_err("exporter name must not be empty if stats needed\n");
return -EINVAL;
@@ -192,7 +189,7 @@ int dma_buf_stats_setup(struct dma_buf *dmabuf)
/* create the directory for buffer stats */
ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
- "%lu", file_inode(dmabuf->file)->i_ino);
+ "%lu", file_inode(file)->i_ino);
if (ret)
goto err_sysfs_dmabuf;
diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h
index a49c6e2650ccc..7a8a995b75bae 100644
--- a/drivers/dma-buf/dma-buf-sysfs-stats.h
+++ b/drivers/dma-buf/dma-buf-sysfs-stats.h
@@ -13,7 +13,7 @@
int dma_buf_init_sysfs_statistics(void);
void dma_buf_uninit_sysfs_statistics(void);
-int dma_buf_stats_setup(struct dma_buf *dmabuf);
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file);
void dma_buf_stats_teardown(struct dma_buf *dmabuf);
#else
@@ -25,7 +25,7 @@ static inline int dma_buf_init_sysfs_statistics(void)
static inline void dma_buf_uninit_sysfs_statistics(void) {}
-static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
return 0;
}
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e6f36c014c4cd..eb6b59363c4f5 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -95,10 +95,11 @@ static int dma_buf_file_release(struct inode *inode, struct file *file)
return -EINVAL;
dmabuf = file->private_data;
-
- mutex_lock(&db_list.lock);
- list_del(&dmabuf->list_node);
- mutex_unlock(&db_list.lock);
+ if (dmabuf) {
+ mutex_lock(&db_list.lock);
+ list_del(&dmabuf->list_node);
+ mutex_unlock(&db_list.lock);
+ }
return 0;
}
@@ -523,17 +524,17 @@ static inline int is_dma_buf_file(struct file *file)
return file->f_op == &dma_buf_fops;
}
-static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags)
+static struct file *dma_buf_getfile(size_t size, int flags)
{
static atomic64_t dmabuf_inode = ATOMIC64_INIT(0);
- struct file *file;
struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb);
+ struct file *file;
if (IS_ERR(inode))
return ERR_CAST(inode);
- inode->i_size = dmabuf->size;
- inode_set_bytes(inode, dmabuf->size);
+ inode->i_size = size;
+ inode_set_bytes(inode, size);
/*
* The ->i_ino acquired from get_next_ino() is not unique thus
@@ -547,8 +548,6 @@ static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags)
flags, &dma_buf_fops);
if (IS_ERR(file))
goto err_alloc_file;
- file->private_data = dmabuf;
- file->f_path.dentry->d_fsdata = dmabuf;
return file;
@@ -614,19 +613,11 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
size_t alloc_size = sizeof(struct dma_buf);
int ret;
- if (!exp_info->resv)
- alloc_size += sizeof(struct dma_resv);
- else
- /* prevent &dma_buf[1] == dma_buf->resv */
- alloc_size += 1;
-
- if (WARN_ON(!exp_info->priv
- || !exp_info->ops
- || !exp_info->ops->map_dma_buf
- || !exp_info->ops->unmap_dma_buf
- || !exp_info->ops->release)) {
+ if (WARN_ON(!exp_info->priv || !exp_info->ops
+ || !exp_info->ops->map_dma_buf
+ || !exp_info->ops->unmap_dma_buf
+ || !exp_info->ops->release))
return ERR_PTR(-EINVAL);
- }
if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
(exp_info->ops->pin || exp_info->ops->unpin)))
@@ -638,10 +629,21 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
if (!try_module_get(exp_info->owner))
return ERR_PTR(-ENOENT);
+ file = dma_buf_getfile(exp_info->size, exp_info->flags);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err_module;
+ }
+
+ if (!exp_info->resv)
+ alloc_size += sizeof(struct dma_resv);
+ else
+ /* prevent &dma_buf[1] == dma_buf->resv */
+ alloc_size += 1;
dmabuf = kzalloc(alloc_size, GFP_KERNEL);
if (!dmabuf) {
ret = -ENOMEM;
- goto err_module;
+ goto err_file;
}
dmabuf->priv = exp_info->priv;
@@ -653,44 +655,36 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
init_waitqueue_head(&dmabuf->poll);
dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll;
dmabuf->cb_in.active = dmabuf->cb_out.active = 0;
+ mutex_init(&dmabuf->lock);
+ INIT_LIST_HEAD(&dmabuf->attachments);
if (!resv) {
- resv = (struct dma_resv *)&dmabuf[1];
- dma_resv_init(resv);
+ dmabuf->resv = (struct dma_resv *)&dmabuf[1];
+ dma_resv_init(dmabuf->resv);
+ } else {
+ dmabuf->resv = resv;
}
- dmabuf->resv = resv;
- file = dma_buf_getfile(dmabuf, exp_info->flags);
- if (IS_ERR(file)) {
- ret = PTR_ERR(file);
+ ret = dma_buf_stats_setup(dmabuf, file);
+ if (ret)
goto err_dmabuf;
- }
+ file->private_data = dmabuf;
+ file->f_path.dentry->d_fsdata = dmabuf;
dmabuf->file = file;
- mutex_init(&dmabuf->lock);
- INIT_LIST_HEAD(&dmabuf->attachments);
-
mutex_lock(&db_list.lock);
list_add(&dmabuf->list_node, &db_list.head);
mutex_unlock(&db_list.lock);
- ret = dma_buf_stats_setup(dmabuf);
- if (ret)
- goto err_sysfs;
-
return dmabuf;
-err_sysfs:
- /*
- * Set file->f_path.dentry->d_fsdata to NULL so that when
- * dma_buf_release() gets invoked by dentry_ops, it exits
- * early before calling the release() dma_buf op.
- */
- file->f_path.dentry->d_fsdata = NULL;
- fput(file);
err_dmabuf:
+ if (!resv)
+ dma_resv_fini(dmabuf->resv);
kfree(dmabuf);
+err_file:
+ fput(file);
err_module:
module_put(exp_info->owner);
return ERR_PTR(ret);
--
GitLab
From a3be19b91ea7121d388084e8c07f5b1b982eb40c Mon Sep 17 00:00:00 2001
From: Wenchao Hao <haowenchao@huawei.com>
Date: Sat, 26 Nov 2022 09:07:52 +0800
Subject: [PATCH 0006/1167] scsi: iscsi: Fix multiple iSCSI session unbind
events sent to userspace
It was observed that the kernel would potentially send
ISCSI_KEVENT_UNBIND_SESSION multiple times. Introduce 'target_state' in
iscsi_cls_session() to make sure session will send only one unbind session
event.
This introduces a regression wrt. the issue fixed in commit 13e60d3ba287
("scsi: iscsi: Report unbind session event when the target has been
removed"). If iscsid dies for any reason after sending an unbind session to
kernel, once iscsid is restarted, the kernel's ISCSI_KEVENT_UNBIND_SESSION
event is lost and userspace is then unable to logout. However, the session
is actually in invalid state (its target_id is INVALID) so iscsid should
not sync this session during restart.
Consequently we need to check the session's target state during iscsid
restart. If session is in unbound state, do not sync this session and
perform session teardown. This is OK because once a session is unbound, we
can not recover it any more (mainly because its target id is INVALID).
Signed-off-by: Wenchao Hao <haowenchao@huawei.com>
Link: https://lore.kernel.org/r/20221126010752.231917-1-haowenchao@huawei.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Wu Bo <wubo40@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/scsi_transport_iscsi.c | 50 ++++++++++++++++++++++++++---
include/scsi/scsi_transport_iscsi.h | 9 ++++++
2 files changed, 54 insertions(+), 5 deletions(-)
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index c3fe5ecfee59e..3eb58db1399d8 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1676,6 +1676,13 @@ static const char *iscsi_session_state_name(int state)
return name;
}
+static char *iscsi_session_target_state_name[] = {
+ [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND",
+ [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED",
+ [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED",
+ [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING",
+};
+
int iscsi_session_chkready(struct iscsi_cls_session *session)
{
int err;
@@ -1785,9 +1792,13 @@ static int iscsi_user_scan_session(struct device *dev, void *data)
if ((scan_data->channel == SCAN_WILD_CARD ||
scan_data->channel == 0) &&
(scan_data->id == SCAN_WILD_CARD ||
- scan_data->id == id))
+ scan_data->id == id)) {
scsi_scan_target(&session->dev, 0, id,
scan_data->lun, scan_data->rescan);
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_SCANNED;
+ spin_unlock_irqrestore(&session->lock, flags);
+ }
}
user_scan_exit:
@@ -1960,31 +1971,41 @@ static void __iscsi_unbind_session(struct work_struct *work)
struct iscsi_cls_host *ihost = shost->shost_data;
unsigned long flags;
unsigned int target_id;
+ bool remove_target = true;
ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n");
/* Prevent new scans and make sure scanning is not in progress */
mutex_lock(&ihost->mutex);
spin_lock_irqsave(&session->lock, flags);
- if (session->target_id == ISCSI_MAX_TARGET) {
+ if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) {
+ remove_target = false;
+ } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) {
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- goto unbind_session_exit;
+ ISCSI_DBG_TRANS_SESSION(session,
+ "Skipping target unbinding: Session is unbound/unbinding.\n");
+ return;
}
+ session->target_state = ISCSI_SESSION_TARGET_UNBINDING;
target_id = session->target_id;
session->target_id = ISCSI_MAX_TARGET;
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- scsi_remove_target(&session->dev);
+ if (remove_target)
+ scsi_remove_target(&session->dev);
if (session->ida_used)
ida_free(&iscsi_sess_ida, target_id);
-unbind_session_exit:
iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
+
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_UNBOUND;
+ spin_unlock_irqrestore(&session->lock, flags);
}
static void __iscsi_destroy_session(struct work_struct *work)
@@ -2061,6 +2082,9 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id)
session->ida_used = true;
} else
session->target_id = target_id;
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_ALLOCATED;
+ spin_unlock_irqrestore(&session->lock, flags);
dev_set_name(&session->dev, "session%u", session->sid);
err = device_add(&session->dev);
@@ -4368,6 +4392,19 @@ iscsi_session_attr(def_taskmgmt_tmo, ISCSI_PARAM_DEF_TASKMGMT_TMO, 0);
iscsi_session_attr(discovery_parent_idx, ISCSI_PARAM_DISCOVERY_PARENT_IDX, 0);
iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0);
+static ssize_t
+show_priv_session_target_state(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent);
+
+ return sysfs_emit(buf, "%s\n",
+ iscsi_session_target_state_name[session->target_state]);
+}
+
+static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO,
+ show_priv_session_target_state, NULL);
+
static ssize_t
show_priv_session_state(struct device *dev, struct device_attribute *attr,
char *buf)
@@ -4470,6 +4507,7 @@ static struct attribute *iscsi_session_attrs[] = {
&dev_attr_sess_boot_target.attr,
&dev_attr_priv_sess_recovery_tmo.attr,
&dev_attr_priv_sess_state.attr,
+ &dev_attr_priv_sess_target_state.attr,
&dev_attr_priv_sess_creator.attr,
&dev_attr_sess_chap_out_idx.attr,
&dev_attr_sess_chap_in_idx.attr,
@@ -4583,6 +4621,8 @@ static umode_t iscsi_session_attr_is_visible(struct kobject *kobj,
return S_IRUGO | S_IWUSR;
else if (attr == &dev_attr_priv_sess_state.attr)
return S_IRUGO;
+ else if (attr == &dev_attr_priv_sess_target_state.attr)
+ return S_IRUGO;
else if (attr == &dev_attr_priv_sess_creator.attr)
return S_IRUGO;
else if (attr == &dev_attr_priv_sess_target_id.attr)
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index cab52b0f11d0c..34c03707fb6ef 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -236,6 +236,14 @@ enum {
ISCSI_SESSION_FREE,
};
+enum {
+ ISCSI_SESSION_TARGET_UNBOUND,
+ ISCSI_SESSION_TARGET_ALLOCATED,
+ ISCSI_SESSION_TARGET_SCANNED,
+ ISCSI_SESSION_TARGET_UNBINDING,
+ ISCSI_SESSION_TARGET_MAX,
+};
+
#define ISCSI_MAX_TARGET -1
struct iscsi_cls_session {
@@ -264,6 +272,7 @@ struct iscsi_cls_session {
*/
pid_t creator;
int state;
+ int target_state; /* session target bind state */
int sid; /* session id */
void *dd_data; /* LLD private data */
struct device dev; /* sysfs transport/container device */
--
GitLab
From 67ff3d0a49f3d445c3922e30a54e03c161da561e Mon Sep 17 00:00:00 2001
From: Michael Kelley <mikelley@microsoft.com>
Date: Sun, 4 Dec 2022 11:52:44 -0800
Subject: [PATCH 0007/1167] scsi: storvsc: Fix swiotlb bounce buffer leak in
confidential VM
storvsc_queuecommand() maps the scatter/gather list using scsi_dma_map(),
which in a confidential VM allocates swiotlb bounce buffers. If the I/O
submission fails in storvsc_do_io(), the I/O is typically retried by higher
level code, but the bounce buffer memory is never freed. The mostly like
cause of I/O submission failure is a full VMBus channel ring buffer, which
is not uncommon under high I/O loads. Eventually enough bounce buffer
memory leaks that the confidential VM can't do any I/O. The same problem
can arise in a non-confidential VM with kernel boot parameter
swiotlb=force.
Fix this by doing scsi_dma_unmap() in the case of an I/O submission
error, which frees the bounce buffer memory.
Fixes: 743b237c3a7b ("scsi: storvsc: Add Isolation VM support for storvsc driver")
Signed-off-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/1670183564-76254-1-git-send-email-mikelley@microsoft.com
Tested-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/storvsc_drv.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index a84194d823471..0252ee2dd844b 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1824,6 +1824,9 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
ret = storvsc_do_io(dev, cmd_request, get_cpu());
put_cpu();
+ if (ret)
+ scsi_dma_unmap(scmnd);
+
if (ret == -EAGAIN) {
/* no more space */
ret = SCSI_MLQUEUE_DEVICE_BUSY;
--
GitLab
From d0b9025540ef57cc4464ab2fc64ed8ddc49b5658 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Tue, 6 Dec 2022 14:13:45 +0100
Subject: [PATCH 0008/1167] scsi: core: scsi_error: Do not queue pointless
abort workqueue functions
If a host template doesn't implement the .eh_abort_handler() there is no
point in queueing the abort workqueue function; all it does is invoking
SCSI EH anyway. So return 'FAILED' from scsi_abort_command() if the
.eh_abort_handler() is not implemented and save us from having to wait for
the abort workqueue function to complete.
Cc: Niklas Cassel <niklas.cassel@wdc.com>
Cc: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Cc: John Garry <john.g.garry@oracle.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
[niklas: moved the check to the top of scsi_abort_command()]
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Link: https://lore.kernel.org/r/20221206131346.2045375-1-niklas.cassel@wdc.com
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/scsi_error.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 613d5aeb1e3ce..955ee1bfde8f3 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -231,6 +231,11 @@ scsi_abort_command(struct scsi_cmnd *scmd)
struct Scsi_Host *shost = sdev->host;
unsigned long flags;
+ if (!shost->hostt->eh_abort_handler) {
+ /* No abort handler, fail command directly */
+ return FAILED;
+ }
+
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
/*
* Retry after abort failed, escalate to next level.
--
GitLab
From f0a43ba6c66cc0688e2748d986a1459fdd3442ef Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Wed, 7 Dec 2022 11:36:59 +0900
Subject: [PATCH 0009/1167] scsi: mpi3mr: Refer CONFIG_SCSI_MPI3MR in Makefile
When Kconfig item CONFIG_SCSI_MPI3MR was introduced for mpi3mr driver, the
Makefile of the driver was not modified to refer the Kconfig item.
As a result, mpi3mr.ko is built regardless of the Kconfig item value y or
m. Also, if 'make localmodconfig' can not find the Kconfig item in the
Makefile, then it does not generate CONFIG_SCSI_MPI3MR=m even when
mpi3mr.ko is loaded on the system.
Refer to the Kconfig item to avoid the issues.
Fixes: c4f7ac64616e ("scsi: mpi3mr: Add mpi30 Rev-R headers and Kconfig")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Link: https://lore.kernel.org/r/20221207023659.2411785-1-shinichiro.kawasaki@wdc.com
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Acked-by: Sathya Prakash Veerichetty <sathya.prakash@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/mpi3mr/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/mpi3mr/Makefile b/drivers/scsi/mpi3mr/Makefile
index ef86ca46646b8..3bf8cf34e1c3f 100644
--- a/drivers/scsi/mpi3mr/Makefile
+++ b/drivers/scsi/mpi3mr/Makefile
@@ -1,5 +1,5 @@
# mpi3mr makefile
-obj-m += mpi3mr.o
+obj-$(CONFIG_SCSI_MPI3MR) += mpi3mr.o
mpi3mr-y += mpi3mr_os.o \
mpi3mr_fw.o \
mpi3mr_app.o \
--
GitLab
From c411a42fb91f452509c312e4dda713699a22a995 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Tue, 13 Dec 2022 14:21:22 +0000
Subject: [PATCH 0010/1167] scsi: scsi_debug: Delete unreachable code in
inquiry_vpd_b0()
The 2nd return statement in inquiry_vpd_b0() is unreachable, so delete it.
Signed-off-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20221213142122.1011886-1-john.g.garry@oracle.com
Reviewed-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/scsi_debug.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index de3d3b1edaf56..6fa08857d6b99 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1511,8 +1511,6 @@ static int inquiry_vpd_b0(unsigned char *arr)
put_unaligned_be64(sdebug_write_same_length, &arr[32]);
return 0x3c; /* Mandatory page length for Logical Block Provisioning */
-
- return sizeof(vpdb0_data);
}
/* Block device characteristics VPD page (SBC-3) */
--
GitLab
From 1a5665fc8d7a000671ebd3fe69c6f9acf1e0dcd9 Mon Sep 17 00:00:00 2001
From: Peter Wang <peter.wang@mediatek.com>
Date: Thu, 8 Dec 2022 15:25:20 +0800
Subject: [PATCH 0011/1167] scsi: ufs: core: WLUN suspend SSU/enter hibern8
fail recovery
When SSU/enter hibern8 fail in WLUN suspend flow, trigger the error handler
and return busy to break the suspend. Otherwise the consumer will get
stuck in runtime suspend status.
Fixes: b294ff3e3449 ("scsi: ufs: core: Enable power management for wlun")
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
Link: https://lore.kernel.org/r/20221208072520.26210-1-peter.wang@mediatek.com
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/ufs/core/ufshcd.c | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 2dbe24977822f..c63cd8bbe5c6d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6056,6 +6056,14 @@ void ufshcd_schedule_eh_work(struct ufs_hba *hba)
}
}
+static void ufshcd_force_error_recovery(struct ufs_hba *hba)
+{
+ spin_lock_irq(hba->host->host_lock);
+ hba->force_reset = true;
+ ufshcd_schedule_eh_work(hba);
+ spin_unlock_irq(hba->host->host_lock);
+}
+
static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow)
{
down_write(&hba->clk_scaling_lock);
@@ -9083,6 +9091,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
if (!hba->dev_info.b_rpm_dev_flush_capable) {
ret = ufshcd_set_dev_pwr_mode(hba, req_dev_pwr_mode);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto enable_scaling;
}
@@ -9094,6 +9111,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
*/
check_for_bkops = !ufshcd_is_ufs_dev_deepsleep(hba);
ret = ufshcd_link_state_transition(hba, req_link_state, check_for_bkops);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto set_dev_active;
--
GitLab
From 01258b62c62710297dab4e2b72f46e01be392cc6 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Fri, 9 Dec 2022 10:59:37 +0100
Subject: [PATCH 0012/1167] wifi: ti: remove obsolete lines in the Makefile
Commit 06463f6e98df ("wifi: wl1251: drop support for platform data")
removes TI WiLink platform data, but leaves some dead lines in the
Makefile.
Remove these obsolete lines in the Makefile.
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221209095937.17773-1-lukas.bulwahn@gmail.com
---
drivers/net/wireless/ti/Makefile | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/wireless/ti/Makefile b/drivers/net/wireless/ti/Makefile
index 0530dd744275c..05ee016594f8c 100644
--- a/drivers/net/wireless/ti/Makefile
+++ b/drivers/net/wireless/ti/Makefile
@@ -3,6 +3,3 @@ obj-$(CONFIG_WLCORE) += wlcore/
obj-$(CONFIG_WL12XX) += wl12xx/
obj-$(CONFIG_WL1251) += wl1251/
obj-$(CONFIG_WL18XX) += wl18xx/
-
-# small builtin driver bit
-obj-$(CONFIG_WILINK_PLATFORM_DATA) += wilink_platform_data.o
--
GitLab
From 7cffcade57a429667447c4f41d8414bbcf1b3aaa Mon Sep 17 00:00:00 2001
From: Dawei Li <set_pte_at@outlook.com>
Date: Tue, 13 Dec 2022 23:46:52 +0800
Subject: [PATCH 0013/1167] xen: make remove callback of xen driver void
returned
Since commit fc7a6209d571 ("bus: Make remove callback return void")
forces bus_type::remove be void-returned, it doesn't make much sense for
any bus based driver implementing remove callbalk to return non-void to
its caller.
This change is for xen bus based drivers.
Acked-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Dawei Li <set_pte_at@outlook.com>
Link: https://lore.kernel.org/r/TYCP286MB23238119AB4DF190997075C9CAE39@TYCP286MB2323.JPNP286.PROD.OUTLOOK.COM
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/block/xen-blkback/xenbus.c | 4 +---
drivers/block/xen-blkfront.c | 3 +--
drivers/char/tpm/xen-tpmfront.c | 3 +--
drivers/gpu/drm/xen/xen_drm_front.c | 3 +--
drivers/input/misc/xen-kbdfront.c | 5 ++---
drivers/net/xen-netback/xenbus.c | 3 +--
drivers/net/xen-netfront.c | 4 +---
drivers/pci/xen-pcifront.c | 4 +---
drivers/scsi/xen-scsifront.c | 4 +---
drivers/tty/hvc/hvc_xen.c | 4 ++--
drivers/usb/host/xen-hcd.c | 4 +---
drivers/video/fbdev/xen-fbfront.c | 6 ++----
drivers/xen/pvcalls-back.c | 3 +--
drivers/xen/pvcalls-front.c | 3 +--
drivers/xen/xen-pciback/xenbus.c | 4 +---
drivers/xen/xen-scsiback.c | 4 +---
include/xen/xenbus.h | 2 +-
net/9p/trans_xen.c | 3 +--
sound/xen/xen_snd_front.c | 3 +--
19 files changed, 22 insertions(+), 47 deletions(-)
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index c0227dfa46887..4807af1d58059 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -524,7 +524,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
return 0;
}
-static int xen_blkbk_remove(struct xenbus_device *dev)
+static void xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -547,8 +547,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev)
/* Put the reference we set in xen_blkif_alloc(). */
xen_blkif_put(be->blkif);
}
-
- return 0;
}
int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 35b9bcad9db90..e68576ded7cb8 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2468,7 +2468,7 @@ static void blkback_changed(struct xenbus_device *dev,
}
}
-static int blkfront_remove(struct xenbus_device *xbdev)
+static void blkfront_remove(struct xenbus_device *xbdev)
{
struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
@@ -2489,7 +2489,6 @@ static int blkfront_remove(struct xenbus_device *xbdev)
}
kfree(info);
- return 0;
}
static int blkfront_is_ready(struct xenbus_device *dev)
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 3792918262617..80cca3b83b226 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -360,14 +360,13 @@ static int tpmfront_probe(struct xenbus_device *dev,
return tpm_chip_register(priv->chip);
}
-static int tpmfront_remove(struct xenbus_device *dev)
+static void tpmfront_remove(struct xenbus_device *dev)
{
struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
struct tpm_private *priv = dev_get_drvdata(&chip->dev);
tpm_chip_unregister(chip);
ring_free(priv);
dev_set_drvdata(&chip->dev, NULL);
- return 0;
}
static int tpmfront_resume(struct xenbus_device *dev)
diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 0d8e6bd1ccbf2..90996c108146d 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -717,7 +717,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
@@ -751,7 +751,6 @@ static int xen_drv_remove(struct xenbus_device *dev)
xen_drm_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_driver_ids[] = {
diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c
index 8d8ebdc2039b8..67f1c7364c95d 100644
--- a/drivers/input/misc/xen-kbdfront.c
+++ b/drivers/input/misc/xen-kbdfront.c
@@ -51,7 +51,7 @@ module_param_array(ptr_size, int, NULL, 0444);
MODULE_PARM_DESC(ptr_size,
"Pointing device width, height in pixels (default 800,600)");
-static int xenkbd_remove(struct xenbus_device *);
+static void xenkbd_remove(struct xenbus_device *);
static int xenkbd_connect_backend(struct xenbus_device *, struct xenkbd_info *);
static void xenkbd_disconnect_backend(struct xenkbd_info *);
@@ -404,7 +404,7 @@ static int xenkbd_resume(struct xenbus_device *dev)
return xenkbd_connect_backend(dev, info);
}
-static int xenkbd_remove(struct xenbus_device *dev)
+static void xenkbd_remove(struct xenbus_device *dev)
{
struct xenkbd_info *info = dev_get_drvdata(&dev->dev);
@@ -417,7 +417,6 @@ static int xenkbd_remove(struct xenbus_device *dev)
input_unregister_device(info->mtouch);
free_page((unsigned long)info->page);
kfree(info);
- return 0;
}
static int xenkbd_connect_backend(struct xenbus_device *dev,
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index c1ba4294f3647..001636901ddae 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -977,7 +977,7 @@ static int read_xenbus_vif_flags(struct backend_info *be)
return 0;
}
-static int netback_remove(struct xenbus_device *dev)
+static void netback_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -992,7 +992,6 @@ static int netback_remove(struct xenbus_device *dev)
kfree(be->hotplug_script);
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
- return 0;
}
/*
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 9af2b027c19c6..bc17f5391b1a0 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -2640,7 +2640,7 @@ static void xennet_bus_close(struct xenbus_device *dev)
} while (!ret);
}
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
@@ -2656,8 +2656,6 @@ static int xennet_remove(struct xenbus_device *dev)
rtnl_unlock();
}
xennet_free_netdev(info->netdev);
-
- return 0;
}
static const struct xenbus_device_id netfront_ids[] = {
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 7378e2f3e525f..fcd029ca2eb18 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -1055,14 +1055,12 @@ static int pcifront_xenbus_probe(struct xenbus_device *xdev,
return err;
}
-static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+static void pcifront_xenbus_remove(struct xenbus_device *xdev)
{
struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
if (pdev)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xenpci_ids[] = {
diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c
index 66b316d173b0b..71a3bb83984c0 100644
--- a/drivers/scsi/xen-scsifront.c
+++ b/drivers/scsi/xen-scsifront.c
@@ -995,7 +995,7 @@ static int scsifront_suspend(struct xenbus_device *dev)
return err;
}
-static int scsifront_remove(struct xenbus_device *dev)
+static void scsifront_remove(struct xenbus_device *dev)
{
struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev);
@@ -1011,8 +1011,6 @@ static int scsifront_remove(struct xenbus_device *dev)
scsifront_free_ring(info);
scsi_host_put(info->host);
-
- return 0;
}
static void scsifront_disconnect(struct vscsifrnt_info *info)
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 7c23112dc923f..c879f922c716b 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -394,9 +394,9 @@ static int xen_console_remove(struct xencons_info *info)
return 0;
}
-static int xencons_remove(struct xenbus_device *dev)
+static void xencons_remove(struct xenbus_device *dev)
{
- return xen_console_remove(dev_get_drvdata(&dev->dev));
+ xen_console_remove(dev_get_drvdata(&dev->dev));
}
static int xencons_connect_backend(struct xenbus_device *dev,
diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c
index de1b091583183..46fdab940092e 100644
--- a/drivers/usb/host/xen-hcd.c
+++ b/drivers/usb/host/xen-hcd.c
@@ -1530,15 +1530,13 @@ static void xenhcd_backend_changed(struct xenbus_device *dev,
}
}
-static int xenhcd_remove(struct xenbus_device *dev)
+static void xenhcd_remove(struct xenbus_device *dev)
{
struct xenhcd_info *info = dev_get_drvdata(&dev->dev);
struct usb_hcd *hcd = xenhcd_info_to_hcd(info);
xenhcd_destroy_rings(info);
usb_put_hcd(hcd);
-
- return 0;
}
static int xenhcd_probe(struct xenbus_device *dev,
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index 4d2694d904aab..ae8a50ecdbd3a 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -67,7 +67,7 @@ MODULE_PARM_DESC(video,
"Video memory size in MB, width, height in pixels (default 2,800,600)");
static void xenfb_make_preferred_console(void);
-static int xenfb_remove(struct xenbus_device *);
+static void xenfb_remove(struct xenbus_device *);
static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *);
static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *);
static void xenfb_disconnect_backend(struct xenfb_info *);
@@ -527,7 +527,7 @@ static int xenfb_resume(struct xenbus_device *dev)
return xenfb_connect_backend(dev, info);
}
-static int xenfb_remove(struct xenbus_device *dev)
+static void xenfb_remove(struct xenbus_device *dev)
{
struct xenfb_info *info = dev_get_drvdata(&dev->dev);
@@ -542,8 +542,6 @@ static int xenfb_remove(struct xenbus_device *dev)
vfree(info->gfns);
vfree(info->fb);
kfree(info);
-
- return 0;
}
static unsigned long vmalloc_to_gfn(void *address)
diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c
index d6f945fd41474..ea52a2092bb82 100644
--- a/drivers/xen/pvcalls-back.c
+++ b/drivers/xen/pvcalls-back.c
@@ -1181,9 +1181,8 @@ static void pvcalls_back_changed(struct xenbus_device *dev,
}
}
-static int pvcalls_back_remove(struct xenbus_device *dev)
+static void pvcalls_back_remove(struct xenbus_device *dev)
{
- return 0;
}
static int pvcalls_back_uevent(struct xenbus_device *xdev,
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index 1826e8e671251..5328f4d35f25e 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -1085,7 +1085,7 @@ static const struct xenbus_device_id pvcalls_front_ids[] = {
{ "" }
};
-static int pvcalls_front_remove(struct xenbus_device *dev)
+static void pvcalls_front_remove(struct xenbus_device *dev)
{
struct pvcalls_bedata *bedata;
struct sock_mapping *map = NULL, *n;
@@ -1121,7 +1121,6 @@ static int pvcalls_front_remove(struct xenbus_device *dev)
kfree(bedata->ring.sring);
kfree(bedata);
xenbus_switch_state(dev, XenbusStateClosed);
- return 0;
}
static int pvcalls_front_probe(struct xenbus_device *dev,
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index d171091eec123..b11e401f1b1ee 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -716,14 +716,12 @@ static int xen_pcibk_xenbus_probe(struct xenbus_device *dev,
return err;
}
-static int xen_pcibk_xenbus_remove(struct xenbus_device *dev)
+static void xen_pcibk_xenbus_remove(struct xenbus_device *dev)
{
struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev);
if (pdev != NULL)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xen_pcibk_ids[] = {
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 6106ed93817d6..954188b0b858a 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1249,7 +1249,7 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info)
spin_unlock_irqrestore(&info->v2p_lock, flags);
}
-static int scsiback_remove(struct xenbus_device *dev)
+static void scsiback_remove(struct xenbus_device *dev)
{
struct vscsibk_info *info = dev_get_drvdata(&dev->dev);
@@ -1261,8 +1261,6 @@ static int scsiback_remove(struct xenbus_device *dev)
gnttab_page_cache_shrink(&info->free_pages, 0);
dev_set_drvdata(&dev->dev, NULL);
-
- return 0;
}
static int scsiback_probe(struct xenbus_device *dev,
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index eaa932b99d8ac..ad4fb4eab753d 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -117,7 +117,7 @@ struct xenbus_driver {
const struct xenbus_device_id *id);
void (*otherend_changed)(struct xenbus_device *dev,
enum xenbus_state backend_state);
- int (*remove)(struct xenbus_device *dev);
+ void (*remove)(struct xenbus_device *dev);
int (*suspend)(struct xenbus_device *dev);
int (*resume)(struct xenbus_device *dev);
int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *);
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index aaa5fd364691b..9950e1a5acb74 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -303,13 +303,12 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv)
kfree(priv);
}
-static int xen_9pfs_front_remove(struct xenbus_device *dev)
+static void xen_9pfs_front_remove(struct xenbus_device *dev)
{
struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);
dev_set_drvdata(&dev->dev, NULL);
xen_9pfs_front_free(priv);
- return 0;
}
static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c
index 4041748c12e51..b66e037710d0d 100644
--- a/sound/xen/xen_snd_front.c
+++ b/sound/xen/xen_snd_front.c
@@ -311,7 +311,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
@@ -345,7 +345,6 @@ static int xen_drv_remove(struct xenbus_device *dev)
xen_snd_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_drv_ids[] = {
--
GitLab
From abe3bf7425fb695a9b37394af18b9ea58a800802 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 12 Dec 2022 21:14:17 +0100
Subject: [PATCH 0014/1167] btrfs: fix an error handling path in btrfs_rename()
If new_whiteout_inode() fails, some resources need to be freed.
Add the missing goto to the error handling path.
Fixes: ab3c5c18e8fa ("btrfs: setup qstr from dentrys using fscrypt helper")
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/inode.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 905ea19df125b..bfcbe64eb8b3a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9377,8 +9377,10 @@ static int btrfs_rename(struct user_namespace *mnt_userns,
if (flags & RENAME_WHITEOUT) {
whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
- if (!whiteout_args.inode)
- return -ENOMEM;
+ if (!whiteout_args.inode) {
+ ret = -ENOMEM;
+ goto out_fscrypt_names;
+ }
ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
if (ret)
goto out_whiteout_inode;
--
GitLab
From db0a4a7b8e95f9312a59a67cbd5bc589f090e13d Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 12 Dec 2022 21:01:43 +0100
Subject: [PATCH 0015/1167] btrfs: fix an error handling path in
btrfs_defrag_leaves()
All error handling paths end to 'out', except this memory allocation
failure.
This is spurious. So branch to the error handling path also in this case.
It will add a call to:
memset(&root->defrag_progress, 0,
sizeof(root->defrag_progress));
Fixes: 6702ed490ca0 ("Btrfs: Add run time btree defrag, and an ioctl to force btree defrag")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/defrag.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index 0a3c261b69c9f..d81b764a76446 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -358,8 +358,10 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
goto out;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
level = btrfs_header_level(root->node);
--
GitLab
From c68f72900a12a56c5e9890e6f2ca5119234c9a75 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 13 Dec 2022 10:42:26 +0000
Subject: [PATCH 0016/1167] btrfs: fix leak of fs devices after removing btrfs
module
When removing the btrfs module we are not calling btrfs_cleanup_fs_uuids()
which results in leaking btrfs_fs_devices structures and other resources.
This is a regression recently introduced by a refactoring of the module
initialization and exit sequence, which simply removed the call to
btrfs_cleanup_fs_uuids() in the exit path, resulting in the leaks.
So fix this by calling btrfs_cleanup_fs_uuids() at exit_btrfs_fs().
Fixes: 5565b8e0adcd ("btrfs: make module init/exit match their sequence")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/super.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 93f52ee85f6fe..d5de18d6517e7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2514,6 +2514,7 @@ static __always_inline void btrfs_exit_btrfs_fs(void)
static void __exit exit_btrfs_fs(void)
{
btrfs_exit_btrfs_fs();
+ btrfs_cleanup_fs_uuids();
}
static int __init init_btrfs_fs(void)
--
GitLab
From f1f0460c0ca97a4a6570f211c81579294a6cc7be Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 13 Dec 2022 16:57:44 -0500
Subject: [PATCH 0017/1167] btrfs: restore BTRFS_SEQ_LAST when looking up
qgroup backref lookup
In the patch a2c8d27e5ee8 ("btrfs: use a structure to pass arguments to
backref walking functions") Filipe converted everybody to using a new
context struct to use for backref lookups, but accidentally dropped the
BTRFS_SEQ_LAST usage that exists for qgroups. Add this back so we have
the previous behavior.
Fixes: a2c8d27e5ee8 ("btrfs: use a structure to pass arguments to backref walking functions")
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/qgroup.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5c636e00d77da..d275bf24b250b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2787,6 +2787,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
* current root. It's safe inside commit_transaction().
*/
ctx.trans = trans;
+ ctx.time_seq = BTRFS_SEQ_LAST;
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
goto cleanup;
--
GitLab
From 0a3212de8ab3e2ce5808c6265855e528d4a6767b Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 14 Dec 2022 11:06:07 +0900
Subject: [PATCH 0018/1167] btrfs: fix trace event name typo for
FLUSH_DELAYED_REFS
Fix a typo of printing FLUSH_DELAYED_REFS event in flush_space() as
FLUSH_ELAYED_REFS.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
include/trace/events/btrfs.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 0bce0b4ff2faf..6548b5b5aa608 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -98,7 +98,7 @@ struct raid56_bio_trace_info;
EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \
EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \
EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \
- EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \
+ EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \
EM( ALLOC_CHUNK, "ALLOC_CHUNK") \
EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \
EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \
--
GitLab
From b18cba09e374637a0a3759d856a6bca94c133952 Mon Sep 17 00:00:00 2001
From: minoura makoto <minoura@valinux.co.jp>
Date: Tue, 13 Dec 2022 13:14:31 +0900
Subject: [PATCH 0019/1167] SUNRPC: ensure the matching upcall is in-flight
upon downcall
Commit 9130b8dbc6ac ("SUNRPC: allow for upcalls for the same uid
but different gss service") introduced `auth` argument to
__gss_find_upcall(), but in gss_pipe_downcall() it was left as NULL
since it (and auth->service) was not (yet) determined.
When multiple upcalls with the same uid and different service are
ongoing, it could happen that __gss_find_upcall(), which returns the
first match found in the pipe->in_downcall list, could not find the
correct gss_msg corresponding to the downcall we are looking for.
Moreover, it might return a msg which is not sent to rpc.gssd yet.
We could see mount.nfs process hung in D state with multiple mount.nfs
are executed in parallel. The call trace below is of CentOS 7.9
kernel-3.10.0-1160.24.1.el7.x86_64 but we observed the same hang w/
elrepo kernel-ml-6.0.7-1.el7.
PID: 71258 TASK: ffff91ebd4be0000 CPU: 36 COMMAND: "mount.nfs"
#0 [ffff9203ca3234f8] __schedule at ffffffffa3b8899f
#1 [ffff9203ca323580] schedule at ffffffffa3b88eb9
#2 [ffff9203ca323590] gss_cred_init at ffffffffc0355818 [auth_rpcgss]
#3 [ffff9203ca323658] rpcauth_lookup_credcache at ffffffffc0421ebc
[sunrpc]
#4 [ffff9203ca3236d8] gss_lookup_cred at ffffffffc0353633 [auth_rpcgss]
#5 [ffff9203ca3236e8] rpcauth_lookupcred at ffffffffc0421581 [sunrpc]
#6 [ffff9203ca323740] rpcauth_refreshcred at ffffffffc04223d3 [sunrpc]
#7 [ffff9203ca3237a0] call_refresh at ffffffffc04103dc [sunrpc]
#8 [ffff9203ca3237b8] __rpc_execute at ffffffffc041e1c9 [sunrpc]
#9 [ffff9203ca323820] rpc_execute at ffffffffc0420a48 [sunrpc]
The scenario is like this. Let's say there are two upcalls for
services A and B, A -> B in pipe->in_downcall, B -> A in pipe->pipe.
When rpc.gssd reads pipe to get the upcall msg corresponding to
service B from pipe->pipe and then writes the response, in
gss_pipe_downcall the msg corresponding to service A will be picked
because only uid is used to find the msg and it is before the one for
B in pipe->in_downcall. And the process waiting for the msg
corresponding to service A will be woken up.
Actual scheduing of that process might be after rpc.gssd processes the
next msg. In rpc_pipe_generic_upcall it clears msg->errno (for A).
The process is scheduled to see gss_msg->ctx == NULL and
gss_msg->msg.errno == 0, therefore it cannot break the loop in
gss_create_upcall and is never woken up after that.
This patch adds a simple check to ensure that a msg which is not
sent to rpc.gssd yet is not chosen as the matching upcall upon
receiving a downcall.
Signed-off-by: minoura makoto <minoura@valinux.co.jp>
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@nec.com>
Tested-by: Hiroshi Shimamoto <h-shimamoto@nec.com>
Cc: Trond Myklebust <trondmy@hammerspace.com>
Fixes: 9130b8dbc6ac ("SUNRPC: allow for upcalls for same uid but different gss service")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
include/linux/sunrpc/rpc_pipe_fs.h | 5 +++++
net/sunrpc/auth_gss/auth_gss.c | 19 +++++++++++++++++--
2 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index cd188a527d169..3b35b6f6533aa 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -92,6 +92,11 @@ extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *,
char __user *, size_t);
extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
+/* returns true if the msg is in-flight, i.e., already eaten by the peer */
+static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
+ return (msg->copied != 0 && list_empty(&msg->list));
+}
+
struct rpc_clnt;
extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
extern int rpc_remove_client_dir(struct rpc_clnt *);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 7bb247c51e2f6..2d7b1e03110ae 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -302,7 +302,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
- if (auth && pos->auth->service != auth->service)
+ if (pos->auth->service != auth->service)
continue;
refcount_inc(&pos->count);
return pos;
@@ -686,6 +686,21 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
return err;
}
+static struct gss_upcall_msg *
+gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid)
+{
+ struct gss_upcall_msg *pos;
+ list_for_each_entry(pos, &pipe->in_downcall, list) {
+ if (!uid_eq(pos->uid, uid))
+ continue;
+ if (!rpc_msg_is_inflight(&pos->msg))
+ continue;
+ refcount_inc(&pos->count);
+ return pos;
+ }
+ return NULL;
+}
+
#define MSG_BUF_MAXSIZE 1024
static ssize_t
@@ -732,7 +747,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid, NULL);
+ gss_msg = gss_find_downcall(pipe, uid);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;
--
GitLab
From 4e699e34f923188175986ad8a74ab99f7034075e Mon Sep 17 00:00:00 2001
From: Ma Jun <majun@amd.com>
Date: Fri, 16 Dec 2022 11:05:26 +0800
Subject: [PATCH 0020/1167] drm/plane-helper: Add the missing declaration of
drm_atomic_state
Add the missing declaration of struct drm_atomic_state to fix the
compile error below:
error: 'struct drm_atomic_state' declared inside parameter
list will not be visible outside of this definition or declaration [-Werror]
Signed-off-by: Ma Jun <majun@amd.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 8401bd361f59 ("drm/plane-helper: Add a drm_plane_helper_atomic_check() helper")
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.1+
Link: https://patchwork.freedesktop.org/patch/msgid/20221216030526.1335609-1-majun@amd.com
---
include/drm/drm_plane_helper.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h
index ff83d26216876..3a574e8cd22f4 100644
--- a/include/drm/drm_plane_helper.h
+++ b/include/drm/drm_plane_helper.h
@@ -26,6 +26,7 @@
#include <linux/types.h>
+struct drm_atomic_state;
struct drm_crtc;
struct drm_framebuffer;
struct drm_modeset_acquire_ctx;
--
GitLab
From 3c44e2b6cde674797b76e76d3a903a63ce8a18bb Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 16 Dec 2022 13:15:34 -0800
Subject: [PATCH 0021/1167] Revert "Input: synaptics - switch touchpad on HP
Laptop 15-da3001TU to RMI mode"
This reverts commit ac5408991ea6b06e29129b4d4861097c4c3e0d59 because
it causes loss of keyboard on HP 15-da1xxx.
Fixes: ac5408991ea6 ("Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode")
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/824effa5-8b9a-c28a-82bb-9b0ab24623e1@kernel.org
Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1206358
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
drivers/input/mouse/synaptics.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index b0f776448a1cd..fa021af8506e4 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -192,7 +192,6 @@ static const char * const smbus_pnp_ids[] = {
"SYN3221", /* HP 15-ay000 */
"SYN323d", /* HP Spectre X360 13-w013dx */
"SYN3257", /* HP Envy 13-ad105ng */
- "SYN3286", /* HP Laptop 15-da3001TU */
NULL
};
--
GitLab
From cc074822465d18a2d39e0b3e2b48b6766a568db2 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Sat, 17 Dec 2022 14:21:44 +0800
Subject: [PATCH 0022/1167] bpf: Define sock security related BTF IDs under
CONFIG_SECURITY_NETWORK
There are warnings reported from resolve_btfids when building vmlinux
with CONFIG_SECURITY_NETWORK disabled:
WARN: resolve_btfids: unresolved symbol bpf_lsm_sk_free_security
WARN: resolve_btfids: unresolved symbol bpf_lsm_sk_alloc_security
So only define BTF IDs for these LSM hooks when CONFIG_SECURITY_NETWORK
is enabled.
Fixes: c0c852dd1876 ("bpf: Do not mark certain LSM hook arguments as trusted")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221217062144.2507222-1-houtao@huaweicloud.com
---
kernel/bpf/bpf_lsm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 9ea42a45da470..a4a41ee3e80b5 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -351,8 +351,10 @@ BTF_ID(func, bpf_lsm_bpf_prog_alloc_security)
BTF_ID(func, bpf_lsm_bpf_prog_free_security)
BTF_ID(func, bpf_lsm_file_alloc_security)
BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
BTF_ID(func, bpf_lsm_sk_alloc_security)
BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
BTF_ID(func, bpf_lsm_task_free)
BTF_SET_END(untrusted_lsm_hooks)
--
GitLab
From 1c4c0b28b517d778d37900deedfe91088839f07a Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 13 Dec 2022 23:15:04 +0200
Subject: [PATCH 0023/1167] wifi: iwlwifi: fw: skip PPAG for JF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
For JF RFs we don't support PPAG, but many firmware
images lie about it. Always skip support for JF to
avoid firmware errors when sending the command.
Reported-and-tested-by: Ãñigo Huguet <ihuguet@redhat.com>
Link: https://lore.kernel.org/linux-wireless/CACT4oufQsqHGp6bah2c4+jPn2wG1oZqY=UKa_TmPx=F6Lxng8Q@mail.gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Gregory Greenman <gregory.greenman@intel.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221213225723.2a43415d8990.I9ac210740a45b41f1b2e15274e1daf4284f2808a@changeid
---
drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index e6d64152c81a7..a02e5a67b7066 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -1106,6 +1106,11 @@ int iwl_read_ppag_table(struct iwl_fw_runtime *fwrt, union iwl_ppag_table_cmd *c
int i, j, num_sub_bands;
s8 *gain;
+ /* many firmware images for JF lie about this */
+ if (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id) ==
+ CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF))
+ return -EOPNOTSUPP;
+
if (!fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SET_PPAG)) {
IWL_DEBUG_RADIO(fwrt,
"PPAG capability not supported by FW, command not sent.\n");
--
GitLab
From 37fc9ad1617a303bbfd28870eb25aaa4766e79ab Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:31:10 +0100
Subject: [PATCH 0024/1167] wifi: mt76: mt7996: select CONFIG_RELAY
Without CONFIG_RELAY, the driver fails to link:
ERROR: modpost: "relay_flush" [drivers/net/wireless/mediatek/mt76/mt7996/mt7996e.ko] undefined!
ERROR: modpost: "relay_switch_subbuf" [drivers/net/wireless/mediatek/mt76/mt7996/mt7996e.ko] undefined!
ERROR: modpost: "relay_open" [drivers/net/wireless/mediatek/mt76/mt7996/mt7996e.ko] undefined!
ERROR: modpost: "relay_reset" [drivers/net/wireless/mediatek/mt76/mt7996/mt7996e.ko] undefined!
ERROR: modpost: "relay_file_operations" [drivers/net/wireless/mediatek/mt76/mt7996/mt7996e.ko] undefined!
The same change was done in mt7915 for the corresponding copy of the code.
Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
See-also: 988845c9361a ("mt76: mt7915: add support for passing chip/firmware debug data to user space")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221215163133.4152299-1-arnd@kernel.org
---
drivers/net/wireless/mediatek/mt76/mt7996/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
index 5c5fc569e6d59..79fb47a73c91d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/Kconfig
@@ -2,6 +2,7 @@
config MT7996E
tristate "MediaTek MT7996 (PCIe) support"
select MT76_CONNAC_LIB
+ select RELAY
depends on MAC80211
depends on PCI
help
--
GitLab
From b7dc753fe33a707379e2254317794a4dad6c0fe2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:55:42 +0100
Subject: [PATCH 0025/1167] wifi: ath9k: use proper statements in conditionals
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A previous cleanup patch accidentally broke some conditional
expressions by replacing the safe "do {} while (0)" constructs
with empty macros. gcc points this out when extra warnings
are enabled:
drivers/net/wireless/ath/ath9k/hif_usb.c: In function 'ath9k_skb_queue_complete':
drivers/net/wireless/ath/ath9k/hif_usb.c:251:57: error: suggest braces around empty body in an 'else' statement [-Werror=empty-body]
251 | TX_STAT_INC(hif_dev, skb_failed);
Make both sets of macros proper expressions again.
Fixes: d7fc76039b74 ("ath9k: htc: clean up statistics macros")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20221215165553.1950307-1-arnd@kernel.org
---
drivers/net/wireless/ath/ath9k/htc.h | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h
index 30f0765fb9fd8..237f4ec2cffd7 100644
--- a/drivers/net/wireless/ath/ath9k/htc.h
+++ b/drivers/net/wireless/ath/ath9k/htc.h
@@ -327,9 +327,9 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb)
}
#ifdef CONFIG_ATH9K_HTC_DEBUGFS
-#define __STAT_SAFE(hif_dev, expr) ((hif_dev)->htc_handle->drv_priv ? (expr) : 0)
-#define CAB_STAT_INC(priv) ((priv)->debug.tx_stats.cab_queued++)
-#define TX_QSTAT_INC(priv, q) ((priv)->debug.tx_stats.queue_stats[q]++)
+#define __STAT_SAFE(hif_dev, expr) do { ((hif_dev)->htc_handle->drv_priv ? (expr) : 0); } while (0)
+#define CAB_STAT_INC(priv) do { ((priv)->debug.tx_stats.cab_queued++); } while (0)
+#define TX_QSTAT_INC(priv, q) do { ((priv)->debug.tx_stats.queue_stats[q]++); } while (0)
#define TX_STAT_INC(hif_dev, c) \
__STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++)
@@ -378,10 +378,10 @@ void ath9k_htc_get_et_stats(struct ieee80211_hw *hw,
struct ethtool_stats *stats, u64 *data);
#else
-#define TX_STAT_INC(hif_dev, c)
-#define TX_STAT_ADD(hif_dev, c, a)
-#define RX_STAT_INC(hif_dev, c)
-#define RX_STAT_ADD(hif_dev, c, a)
+#define TX_STAT_INC(hif_dev, c) do { } while (0)
+#define TX_STAT_ADD(hif_dev, c, a) do { } while (0)
+#define RX_STAT_INC(hif_dev, c) do { } while (0)
+#define RX_STAT_ADD(hif_dev, c, a) do { } while (0)
#define CAB_STAT_INC(priv)
#define TX_QSTAT_INC(priv, c)
--
GitLab
From a6b9d2fa0024e7e399c26facd0fb466b7396e2b9 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <olga.kornievskaia@gmail.com>
Date: Tue, 20 Dec 2022 12:31:29 -0500
Subject: [PATCH 0026/1167] pNFS/filelayout: Fix coalescing test for single DS
When there is a single DS no striping constraints need to be placed on
the IO. When such constraint is applied then buffered reads don't
coalesce to the DS's rsize.
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
fs/nfs/filelayout/filelayout.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index ad34a33b0737c..4974cd18ca468 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -783,6 +783,12 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
return &fl->generic_hdr;
}
+static bool
+filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
+{
+ return flseg->num_fh > 1;
+}
+
/*
* filelayout_pg_test(). Called by nfs_can_coalesce_requests()
*
@@ -803,6 +809,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
size = pnfs_generic_pg_test(pgio, prev, req);
if (!size)
return 0;
+ else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg)))
+ return size;
/* see if req and prev are in the same stripe */
if (prev) {
--
GitLab
From 560840afc3e63bbe5d9c5ef6b2ecf8f3589adff6 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 14 Dec 2022 15:05:08 -0800
Subject: [PATCH 0027/1167] btrfs: fix resolving backrefs for inline extent
followed by prealloc
If a file consists of an inline extent followed by a regular or prealloc
extent, then a legitimate attempt to resolve a logical address in the
non-inline region will result in add_all_parents reading the invalid
offset field of the inline extent. If the inline extent item is placed
in the leaf eb s.t. it is the first item, attempting to access the
offset field will not only be meaningless, it will go past the end of
the eb and cause this panic:
[17.626048] BTRFS warning (device dm-2): bad eb member end: ptr 0x3fd4 start 30834688 member offset 16377 size 8
[17.631693] general protection fault, probably for non-canonical address 0x5088000000000: 0000 [#1] SMP PTI
[17.635041] CPU: 2 PID: 1267 Comm: btrfs Not tainted 5.12.0-07246-g75175d5adc74-dirty #199
[17.637969] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014
[17.641995] RIP: 0010:btrfs_get_64+0xe7/0x110
[17.649890] RSP: 0018:ffffc90001f73a08 EFLAGS: 00010202
[17.651652] RAX: 0000000000000001 RBX: ffff88810c42d000 RCX: 0000000000000000
[17.653921] RDX: 0005088000000000 RSI: ffffc90001f73a0f RDI: 0000000000000001
[17.656174] RBP: 0000000000000ff9 R08: 0000000000000007 R09: c0000000fffeffff
[17.658441] R10: ffffc90001f73790 R11: ffffc90001f73788 R12: ffff888106afe918
[17.661070] R13: 0000000000003fd4 R14: 0000000000003f6f R15: cdcdcdcdcdcdcdcd
[17.663617] FS: 00007f64e7627d80(0000) GS:ffff888237c80000(0000) knlGS:0000000000000000
[17.666525] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[17.668664] CR2: 000055d4a39152e8 CR3: 000000010c596002 CR4: 0000000000770ee0
[17.671253] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[17.673634] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[17.676034] PKRU: 55555554
[17.677004] Call Trace:
[17.677877] add_all_parents+0x276/0x480
[17.679325] find_parent_nodes+0xfae/0x1590
[17.680771] btrfs_find_all_leafs+0x5e/0xa0
[17.682217] iterate_extent_inodes+0xce/0x260
[17.683809] ? btrfs_inode_flags_to_xflags+0x50/0x50
[17.685597] ? iterate_inodes_from_logical+0xa1/0xd0
[17.687404] iterate_inodes_from_logical+0xa1/0xd0
[17.689121] ? btrfs_inode_flags_to_xflags+0x50/0x50
[17.691010] btrfs_ioctl_logical_to_ino+0x131/0x190
[17.692946] btrfs_ioctl+0x104a/0x2f60
[17.694384] ? selinux_file_ioctl+0x182/0x220
[17.695995] ? __x64_sys_ioctl+0x84/0xc0
[17.697394] __x64_sys_ioctl+0x84/0xc0
[17.698697] do_syscall_64+0x33/0x40
[17.700017] entry_SYSCALL_64_after_hwframe+0x44/0xae
[17.701753] RIP: 0033:0x7f64e72761b7
[17.709355] RSP: 002b:00007ffefb067f58 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[17.712088] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f64e72761b7
[17.714667] RDX: 00007ffefb067fb0 RSI: 00000000c0389424 RDI: 0000000000000003
[17.717386] RBP: 00007ffefb06d188 R08: 000055d4a390d2b0 R09: 00007f64e7340a60
[17.719938] R10: 0000000000000231 R11: 0000000000000246 R12: 0000000000000001
[17.722383] R13: 0000000000000000 R14: 00000000c0389424 R15: 000055d4a38fd2a0
[17.724839] Modules linked in:
Fix the bug by detecting the inline extent item in add_all_parents and
skipping to the next extent item.
CC: stable@vger.kernel.org # 4.9+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/backref.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 21c92c74bf71a..46851511b661b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -484,6 +484,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx,
u64 wanted_disk_byte = ref->wanted_disk_byte;
u64 count = 0;
u64 data_offset;
+ u8 type;
if (level != 0) {
eb = path->nodes[level];
@@ -538,6 +539,9 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx,
continue;
}
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(eb, fi);
+ if (type == BTRFS_FILE_EXTENT_INLINE)
+ goto next;
disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
data_offset = btrfs_file_extent_offset(eb, fi);
--
GitLab
From e7fc357ec03ee109da503af0dd31bbf68514e481 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Fri, 16 Dec 2022 11:48:00 -0500
Subject: [PATCH 0028/1167] btrfs: scrub: fix uninitialized return value in
recover_scrub_rbio
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit 75b470332965 ("btrfs: raid56: migrate recovery and scrub recovery
path to use error_bitmap") introduced an uninitialized return variable.
This can be caught by gcc 12.1 by -Wmaybe-uninitialized:
CC [M] fs/btrfs/raid56.o
fs/btrfs/raid56.c: In function ‘scrub_rbio’:
fs/btrfs/raid56.c:2801:15: warning: ‘ret’ may be used uninitialized [-Wmaybe-uninitialized]
2801 | ret = recover_scrub_rbio(rbio);
| ^~~~~~~~~~~~~~~~~~~~~~~~
fs/btrfs/raid56.c:2649:13: note: ‘ret’ was declared here
2649 | int ret;
The warning is disabled by default so we haven't caught that.
Due to the bug the raid56 scrub fstests have been failing since the
patch was merged, so initialize that.
Fixes: 75b470332965 ("btrfs: raid56: migrate recovery and scrub recovery path to use error_bitmap")
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/raid56.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 2d90a6b5eb00e..6a2cf754912df 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2646,7 +2646,7 @@ static int recover_scrub_rbio(struct btrfs_raid_bio *rbio)
void **pointers = NULL;
void **unmap_array = NULL;
int sector_nr;
- int ret;
+ int ret = 0;
/*
* @pointers array stores the pointer for each sector.
--
GitLab
From fee4c19937439693f2420a916169d08e88576e8e Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 20 Dec 2022 11:13:33 +0000
Subject: [PATCH 0029/1167] btrfs: fix fscrypt name leak after failure to join
log transaction
When logging a new name, we don't expect to fail joining a log transaction
since we know at least one of the inodes was logged before in the current
transaction. However if we fail for some unexpected reason, we end up not
freeing the fscrypt name we previously allocated. So fix that by freeing
the name in case we failed to join a log transaction.
Fixes: ab3c5c18e8fa ("btrfs: setup qstr from dentrys using fscrypt helper")
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index a3c43f0b1c95c..fb52aa0600930 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -7459,8 +7459,11 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
* not fail, but if it does, it's not serious, just bail out and
* mark the log for a full commit.
*/
- if (WARN_ON_ONCE(ret < 0))
+ if (WARN_ON_ONCE(ret < 0)) {
+ fscrypt_free_filename(&fname);
goto out;
+ }
+
log_pinned = true;
path = btrfs_alloc_path();
--
GitLab
From 54c3f1a81421f85e60ae2eaae7be3727a09916ee Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 19 Dec 2022 16:47:00 -0800
Subject: [PATCH 0030/1167] bpf: pull before calling skb_postpull_rcsum()
Anand hit a BUG() when pulling off headers on egress to a SW tunnel.
We get to skb_checksum_help() with an invalid checksum offset
(commit d7ea0d9df2a6 ("net: remove two BUG() from skb_checksum_help()")
converted those BUGs to WARN_ONs()).
He points out oddness in how skb_postpull_rcsum() gets used.
Indeed looks like we should pull before "postpull", otherwise
the CHECKSUM_PARTIAL fixup from skb_postpull_rcsum() will not
be able to do its job:
if (skb->ip_summed == CHECKSUM_PARTIAL &&
skb_checksum_start_offset(skb) < 0)
skb->ip_summed = CHECKSUM_NONE;
Reported-by: Anand Parthasarathy <anpartha@meta.com>
Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20221220004701.402165-1-kuba@kernel.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
net/core/filter.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/core/filter.c b/net/core/filter.c
index 929358677183d..43cc1fe58a2c6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3180,15 +3180,18 @@ static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
{
+ void *old_data;
+
/* skb_ensure_writable() is not needed here, as we're
* already working on an uncloned skb.
*/
if (unlikely(!pskb_may_pull(skb, off + len)))
return -ENOMEM;
- skb_postpull_rcsum(skb, skb->data + off, len);
- memmove(skb->data + len, skb->data, off);
+ old_data = skb->data;
__skb_pull(skb, len);
+ skb_postpull_rcsum(skb, old_data + off, len);
+ memmove(skb->data, old_data, off);
return 0;
}
--
GitLab
From 6f95eec6fb89e195dbdf30de65553c7fc57d9372 Mon Sep 17 00:00:00 2001
From: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Date: Tue, 20 Dec 2022 14:56:27 +0200
Subject: [PATCH 0031/1167] ASoC: SOF: pm: Set target state earlier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If the DSP crashes before the system suspends, the setting of target state
will be skipped because the firmware state will no longer be
SOF_FW_BOOT_COMPLETE. This leads to the incorrect assumption that the
DSP should suspend to D0I3 instead of suspending to D3. To fix this,
set the target_state before we skip to DSP suspend even when the DSP has
crashed.
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Curtis Malainey <cujomalainey@chromium.org>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://lore.kernel.org/r/20221220125629.8469-2-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/pm.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index df740be645e84..5f88c4a01fa3f 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -182,7 +182,7 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
const struct sof_ipc_tplg_ops *tplg_ops = sdev->ipc->ops->tplg;
pm_message_t pm_state;
- u32 target_state = 0;
+ u32 target_state = snd_sof_dsp_power_target(sdev);
int ret;
/* do nothing if dsp suspend callback is not set */
@@ -206,7 +206,6 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
}
}
- target_state = snd_sof_dsp_power_target(sdev);
pm_state.event = target_state;
/* Skip to platform-specific suspend if DSP is entering D0 */
--
GitLab
From d185e0689abc98ef55fb7a7d75aa0c48a0ed5838 Mon Sep 17 00:00:00 2001
From: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Date: Tue, 20 Dec 2022 14:56:28 +0200
Subject: [PATCH 0032/1167] ASoC: SOF: pm: Always tear down pipelines before
DSP suspend
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When the DSP is suspended while the firmware is in the crashed state, we
skip tearing down the pipelines. This means that the widget reference
counts will not get to reset to 0 before suspend. This will lead to
errors with resuming audio after system resume. To fix this, invoke the
tear_down_all_pipelines op before skipping to DSP suspend.
Signed-off-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Curtis Malainey <cujomalainey@chromium.org>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://lore.kernel.org/r/20221220125629.8469-3-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/pm.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c
index 5f88c4a01fa3f..8722bbd7fd3d7 100644
--- a/sound/soc/sof/pm.c
+++ b/sound/soc/sof/pm.c
@@ -192,6 +192,9 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
if (runtime_suspend && !sof_ops(sdev)->runtime_suspend)
return 0;
+ if (tplg_ops && tplg_ops->tear_down_all_pipelines)
+ tplg_ops->tear_down_all_pipelines(sdev, false);
+
if (sdev->fw_state != SOF_FW_BOOT_COMPLETE)
goto suspend;
@@ -216,9 +219,6 @@ static int sof_suspend(struct device *dev, bool runtime_suspend)
goto suspend;
}
- if (tplg_ops->tear_down_all_pipelines)
- tplg_ops->tear_down_all_pipelines(sdev, false);
-
/* suspend DMA trace */
sof_fw_trace_suspend(sdev, pm_state);
--
GitLab
From 9a9134fd56f6ba614ff7b2b3b0bac0bf1d0dc0c9 Mon Sep 17 00:00:00 2001
From: Curtis Malainey <cujomalainey@chromium.org>
Date: Tue, 20 Dec 2022 14:56:29 +0200
Subject: [PATCH 0033/1167] ASoC: SOF: Add FW state to debugfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Allow system health detection mechanisms to check the FW state, this
will allow them to check if the FW is in its "crashed" state going
forward to help automatically diagnose driver state.
Signed-off-by: Curtis Malainey <cujomalainey@chromium.org>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://lore.kernel.org/r/20221220125629.8469-4-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/sof/debug.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index d9a3ce7b69e16..ade0507328af4 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -353,7 +353,9 @@ int snd_sof_dbg_init(struct snd_sof_dev *sdev)
return err;
}
- return 0;
+ return snd_sof_debugfs_buf_item(sdev, &sdev->fw_state,
+ sizeof(sdev->fw_state),
+ "fw_state", 0444);
}
EXPORT_SYMBOL_GPL(snd_sof_dbg_init);
--
GitLab
From 4217c6ac817451d5116687f3cc6286220dc43d49 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Mon, 19 Dec 2022 14:01:30 +0000
Subject: [PATCH 0034/1167] drm/panfrost: Fix GEM handle creation ref-counting
panfrost_gem_create_with_handle() previously returned a BO but with the
only reference being from the handle, which user space could in theory
guess and release, causing a use-after-free. Additionally if the call to
panfrost_gem_mapping_get() in panfrost_ioctl_create_bo() failed then
a(nother) reference on the BO was dropped.
The _create_with_handle() is a problematic pattern, so ditch it and
instead create the handle in panfrost_ioctl_create_bo(). If the call to
panfrost_gem_mapping_get() fails then this means that user space has
indeed gone behind our back and freed the handle. In which case just
return an error code.
Reported-by: Rob Clark <robdclark@chromium.org>
Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver")
Signed-off-by: Steven Price <steven.price@arm.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221219140130.410578-1-steven.price@arm.com
---
drivers/gpu/drm/panfrost/panfrost_drv.c | 27 ++++++++++++++++---------
drivers/gpu/drm/panfrost/panfrost_gem.c | 16 +--------------
drivers/gpu/drm/panfrost/panfrost_gem.h | 5 +----
3 files changed, 20 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 2fa5afe212889..919e6cc049828 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -82,6 +82,7 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
struct panfrost_gem_object *bo;
struct drm_panfrost_create_bo *args = data;
struct panfrost_gem_mapping *mapping;
+ int ret;
if (!args->size || args->pad ||
(args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
@@ -92,21 +93,29 @@ static int panfrost_ioctl_create_bo(struct drm_device *dev, void *data,
!(args->flags & PANFROST_BO_NOEXEC))
return -EINVAL;
- bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags,
- &args->handle);
+ bo = panfrost_gem_create(dev, args->size, args->flags);
if (IS_ERR(bo))
return PTR_ERR(bo);
+ ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+ if (ret)
+ goto out;
+
mapping = panfrost_gem_mapping_get(bo, priv);
- if (!mapping) {
- drm_gem_object_put(&bo->base.base);
- return -EINVAL;
+ if (mapping) {
+ args->offset = mapping->mmnode.start << PAGE_SHIFT;
+ panfrost_gem_mapping_put(mapping);
+ } else {
+ /* This can only happen if the handle from
+ * drm_gem_handle_create() has already been guessed and freed
+ * by user space
+ */
+ ret = -EINVAL;
}
- args->offset = mapping->mmnode.start << PAGE_SHIFT;
- panfrost_gem_mapping_put(mapping);
-
- return 0;
+out:
+ drm_gem_object_put(&bo->base.base);
+ return ret;
}
/**
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 293e799e2fe81..3c812fbd126fd 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -235,12 +235,8 @@ struct drm_gem_object *panfrost_gem_create_object(struct drm_device *dev, size_t
}
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle)
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
{
- int ret;
struct drm_gem_shmem_object *shmem;
struct panfrost_gem_object *bo;
@@ -256,16 +252,6 @@ panfrost_gem_create_with_handle(struct drm_file *file_priv,
bo->noexec = !!(flags & PANFROST_BO_NOEXEC);
bo->is_heap = !!(flags & PANFROST_BO_HEAP);
- /*
- * Allocate an id of idr table where the obj is registered
- * and handle has the id what user can see.
- */
- ret = drm_gem_handle_create(file_priv, &shmem->base, handle);
- /* drop reference from allocate - handle holds it now. */
- drm_gem_object_put(&shmem->base);
- if (ret)
- return ERR_PTR(ret);
-
return bo;
}
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h
index 8088d5fd8480e..ad2877eeeccdf 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.h
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.h
@@ -69,10 +69,7 @@ panfrost_gem_prime_import_sg_table(struct drm_device *dev,
struct sg_table *sgt);
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle);
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags);
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
void panfrost_gem_close(struct drm_gem_object *obj,
--
GitLab
From 5eb119da94ac5d67a31eaa869621dc6e25eb125e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 15 Dec 2022 15:16:33 +0100
Subject: [PATCH 0035/1167] netfilter: conntrack: fix ipv6 exthdr error check
smatch warnings:
net/netfilter/nf_conntrack_proto.c:167 nf_confirm() warn: unsigned 'protoff' is never less than zero.
We need to check if ipv6_skip_exthdr() returned an error, but protoff is
unsigned. Use a signed integer for this.
Fixes: a70e483460d5 ("netfilter: conntrack: merge ipv4+ipv6 confirm functions")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_proto.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 99323fb12d0f5..ccef340be575e 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -141,6 +141,7 @@ unsigned int nf_confirm(void *priv,
struct nf_conn *ct;
bool seqadj_needed;
__be16 frag_off;
+ int start;
u8 pnum;
ct = nf_ct_get(skb, &ctinfo);
@@ -163,9 +164,11 @@ unsigned int nf_confirm(void *priv,
break;
case NFPROTO_IPV6:
pnum = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+ start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
+ if (start < 0 || (frag_off & htons(~0x7)) != 0)
return nf_conntrack_confirm(skb);
+
+ protoff = start;
break;
default:
return nf_conntrack_confirm(skb);
--
GitLab
From bed4a63ea4ae77cfe5aae004ef87379f0655260a Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 19 Dec 2022 20:07:52 +0100
Subject: [PATCH 0036/1167] netfilter: nf_tables: consolidate set description
Add the following fields to the set description:
- key type
- data type
- object type
- policy
- gc_int: garbage collection interval)
- timeout: element timeout
This prepares for stricter set type checks on updates in a follow up
patch.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tables.h | 12 +++++++
net/netfilter/nf_tables_api.c | 58 +++++++++++++++----------------
2 files changed, 40 insertions(+), 30 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e69ce23566eab..4957b4775757b 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -312,17 +312,29 @@ struct nft_set_iter {
/**
* struct nft_set_desc - description of set elements
*
+ * @ktype: key type
* @klen: key length
+ * @dtype: data type
* @dlen: data length
+ * @objtype: object type
+ * @flags: flags
* @size: number of set elements
+ * @policy: set policy
+ * @gc_int: garbage collector interval
* @field_len: length of each field in concatenation, bytes
* @field_count: number of concatenated fields in element
* @expr: set must support for expressions
*/
struct nft_set_desc {
+ u32 ktype;
unsigned int klen;
+ u32 dtype;
unsigned int dlen;
+ u32 objtype;
unsigned int size;
+ u32 policy;
+ u32 gc_int;
+ u64 timeout;
u8 field_len[NFT_REG32_COUNT];
u8 field_count;
bool expr;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 832b881f7c174..1deecc1a6c003 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3780,8 +3780,7 @@ static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags)
static const struct nft_set_ops *
nft_select_set_ops(const struct nft_ctx *ctx,
const struct nlattr * const nla[],
- const struct nft_set_desc *desc,
- enum nft_set_policies policy)
+ const struct nft_set_desc *desc)
{
struct nftables_pernet *nft_net = nft_pernet(ctx->net);
const struct nft_set_ops *ops, *bops;
@@ -3810,7 +3809,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
if (!ops->estimate(desc, flags, &est))
continue;
- switch (policy) {
+ switch (desc->policy) {
case NFT_SET_POL_PERFORMANCE:
if (est.lookup < best.lookup)
break;
@@ -4392,7 +4391,6 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
- u32 ktype, dtype, flags, policy, gc_int, objtype;
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_next(info->net);
u8 family = info->nfmsg->nfgen_family;
@@ -4405,10 +4403,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
struct nft_set *set;
struct nft_ctx ctx;
size_t alloc_size;
- u64 timeout;
char *name;
int err, i;
u16 udlen;
+ u32 flags;
u64 size;
if (nla[NFTA_SET_TABLE] == NULL ||
@@ -4419,10 +4417,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
memset(&desc, 0, sizeof(desc));
- ktype = NFT_DATA_VALUE;
+ desc.ktype = NFT_DATA_VALUE;
if (nla[NFTA_SET_KEY_TYPE] != NULL) {
- ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
- if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
+ desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
+ if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
return -EINVAL;
}
@@ -4447,17 +4445,17 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
return -EOPNOTSUPP;
}
- dtype = 0;
+ desc.dtype = 0;
if (nla[NFTA_SET_DATA_TYPE] != NULL) {
if (!(flags & NFT_SET_MAP))
return -EINVAL;
- dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
- if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
- dtype != NFT_DATA_VERDICT)
+ desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
+ if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
+ desc.dtype != NFT_DATA_VERDICT)
return -EINVAL;
- if (dtype != NFT_DATA_VERDICT) {
+ if (desc.dtype != NFT_DATA_VERDICT) {
if (nla[NFTA_SET_DATA_LEN] == NULL)
return -EINVAL;
desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
@@ -4472,34 +4470,34 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (!(flags & NFT_SET_OBJECT))
return -EINVAL;
- objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
- if (objtype == NFT_OBJECT_UNSPEC ||
- objtype > NFT_OBJECT_MAX)
+ desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
+ if (desc.objtype == NFT_OBJECT_UNSPEC ||
+ desc.objtype > NFT_OBJECT_MAX)
return -EOPNOTSUPP;
} else if (flags & NFT_SET_OBJECT)
return -EINVAL;
else
- objtype = NFT_OBJECT_UNSPEC;
+ desc.objtype = NFT_OBJECT_UNSPEC;
- timeout = 0;
+ desc.timeout = 0;
if (nla[NFTA_SET_TIMEOUT] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout);
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
if (err)
return err;
}
- gc_int = 0;
+ desc.gc_int = 0;
if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
+ desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
}
- policy = NFT_SET_POL_PERFORMANCE;
+ desc.policy = NFT_SET_POL_PERFORMANCE;
if (nla[NFTA_SET_POLICY] != NULL)
- policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+ desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
if (nla[NFTA_SET_DESC] != NULL) {
err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
@@ -4544,7 +4542,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
return -ENOENT;
- ops = nft_select_set_ops(&ctx, nla, &desc, policy);
+ ops = nft_select_set_ops(&ctx, nla, &desc);
if (IS_ERR(ops))
return PTR_ERR(ops);
@@ -4584,18 +4582,18 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
set->table = table;
write_pnet(&set->net, net);
set->ops = ops;
- set->ktype = ktype;
+ set->ktype = desc.ktype;
set->klen = desc.klen;
- set->dtype = dtype;
- set->objtype = objtype;
+ set->dtype = desc.dtype;
+ set->objtype = desc.objtype;
set->dlen = desc.dlen;
set->flags = flags;
set->size = desc.size;
- set->policy = policy;
+ set->policy = desc.policy;
set->udlen = udlen;
set->udata = udata;
- set->timeout = timeout;
- set->gc_int = gc_int;
+ set->timeout = desc.timeout;
+ set->gc_int = desc.gc_int;
set->field_count = desc.field_count;
for (i = 0; i < desc.field_count; i++)
--
GitLab
From a8fe4154fa5a1bae590b243ed60f871e5a5e1378 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 19 Dec 2022 18:00:10 +0100
Subject: [PATCH 0037/1167] netfilter: nf_tables: add function to create set
stateful expressions
Add a helper function to allocate and initialize the stateful expressions
that are defined in a set.
This patch allows to reuse this code from the set update path, to check
that type of the update matches the existing set in the kernel.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 106 ++++++++++++++++++++++------------
1 file changed, 68 insertions(+), 38 deletions(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 1deecc1a6c003..b9b0ae29f5f60 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4388,6 +4388,59 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
return err;
}
+static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set,
+ const struct nlattr * const *nla,
+ struct nft_expr **exprs, int *num_exprs,
+ u32 flags)
+{
+ struct nft_expr *expr;
+ int err, i;
+
+ if (nla[NFTA_SET_EXPR]) {
+ expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[0] = expr;
+ (*num_exprs)++;
+ } else if (nla[NFTA_SET_EXPRESSIONS]) {
+ struct nlattr *tmp;
+ int left;
+
+ if (!(flags & NFT_SET_EXPR)) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ i = 0;
+ nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+ if (i == NFT_SET_EXPR_MAX) {
+ err = -E2BIG;
+ goto err_set_expr_alloc;
+ }
+ if (nla_type(tmp) != NFTA_LIST_ELEM) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ expr = nft_set_elem_expr_alloc(ctx, set, tmp);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[i++] = expr;
+ (*num_exprs)++;
+ }
+ }
+
+ return 0;
+
+err_set_expr_alloc:
+ for (i = 0; i < *num_exprs; i++)
+ nft_expr_destroy(ctx, exprs[i]);
+
+ return err;
+}
+
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
@@ -4395,7 +4448,6 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
u8 genmask = nft_genmask_next(info->net);
u8 family = info->nfmsg->nfgen_family;
const struct nft_set_ops *ops;
- struct nft_expr *expr = NULL;
struct net *net = info->net;
struct nft_set_desc desc;
struct nft_table *table;
@@ -4403,6 +4455,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
struct nft_set *set;
struct nft_ctx ctx;
size_t alloc_size;
+ int num_exprs = 0;
char *name;
int err, i;
u16 udlen;
@@ -4529,6 +4582,8 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
return PTR_ERR(set);
}
} else {
+ struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {};
+
if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
return -EEXIST;
@@ -4536,6 +4591,13 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
+ err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i < num_exprs; i++)
+ nft_expr_destroy(&ctx, exprs[i]);
+
return 0;
}
@@ -4603,43 +4665,11 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (err < 0)
goto err_set_init;
- if (nla[NFTA_SET_EXPR]) {
- expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[0] = expr;
- set->num_exprs++;
- } else if (nla[NFTA_SET_EXPRESSIONS]) {
- struct nft_expr *expr;
- struct nlattr *tmp;
- int left;
-
- if (!(flags & NFT_SET_EXPR)) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- i = 0;
- nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
- if (i == NFT_SET_EXPR_MAX) {
- err = -E2BIG;
- goto err_set_expr_alloc;
- }
- if (nla_type(tmp) != NFTA_LIST_ELEM) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[i++] = expr;
- set->num_exprs++;
- }
- }
+ err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags);
+ if (err < 0)
+ goto err_set_destroy;
+ set->num_exprs = num_exprs;
set->handle = nf_tables_alloc_handle(table);
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
@@ -4653,7 +4683,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
err_set_expr_alloc:
for (i = 0; i < set->num_exprs; i++)
nft_expr_destroy(&ctx, set->exprs[i]);
-
+err_set_destroy:
ops->destroy(set);
err_set_init:
kfree(set->name);
--
GitLab
From f6594c372afd5cec8b1e9ee9ea8f8819d59c6fb1 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 19 Dec 2022 20:09:00 +0100
Subject: [PATCH 0038/1167] netfilter: nf_tables: perform type checking for
existing sets
If a ruleset declares a set name that matches an existing set in the
kernel, then validate that this declaration really refers to the same
set, otherwise bail out with EEXIST.
Currently, the kernel reports success when adding a set that already
exists in the kernel. This usually results in EINVAL errors at a later
stage, when the user adds elements to the set, if the set declaration
mismatches the existing set representation in the kernel.
Add a new function to check that the set declaration really refers to
the same existing set in the kernel.
Fixes: 96518518cc41 ("netfilter: add nftables")
Reported-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 36 ++++++++++++++++++++++++++++++++++-
1 file changed, 35 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b9b0ae29f5f60..319887f4d3ef7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4441,6 +4441,34 @@ static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set,
return err;
}
+static bool nft_set_is_same(const struct nft_set *set,
+ const struct nft_set_desc *desc,
+ struct nft_expr *exprs[], u32 num_exprs, u32 flags)
+{
+ int i;
+
+ if (set->ktype != desc->ktype ||
+ set->dtype != desc->dtype ||
+ set->flags != flags ||
+ set->klen != desc->klen ||
+ set->dlen != desc->dlen ||
+ set->field_count != desc->field_count ||
+ set->num_exprs != num_exprs)
+ return false;
+
+ for (i = 0; i < desc->field_count; i++) {
+ if (set->field_len[i] != desc->field_len[i])
+ return false;
+ }
+
+ for (i = 0; i < num_exprs; i++) {
+ if (set->exprs[i]->ops != exprs[i]->ops)
+ return false;
+ }
+
+ return true;
+}
+
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
@@ -4595,10 +4623,16 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (err < 0)
return err;
+ err = 0;
+ if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
+ err = -EEXIST;
+ }
+
for (i = 0; i < num_exprs; i++)
nft_expr_destroy(&ctx, exprs[i]);
- return 0;
+ return err;
}
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
--
GitLab
From 70a00e2f1dbae11dc3444444c6bd7555763d8421 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <martin.lau@kernel.org>
Date: Wed, 21 Dec 2022 10:56:53 -0800
Subject: [PATCH 0039/1167] selftests/bpf: Test bpf_skb_adjust_room on
CHECKSUM_PARTIAL
When the bpf_skb_adjust_room() shrinks the skb such that its csum_start
is invalid, the skb->ip_summed should be reset from CHECKSUM_PARTIAL to
CHECKSUM_NONE.
The commit 54c3f1a81421 ("bpf: pull before calling skb_postpull_rcsum()")
fixed it.
This patch adds a test to ensure the skb->ip_summed changed from
CHECKSUM_PARTIAL to CHECKSUM_NONE after bpf_skb_adjust_room().
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20221221185653.1589961-1-martin.lau@linux.dev
---
tools/testing/selftests/bpf/DENYLIST.s390x | 1 +
.../selftests/bpf/prog_tests/decap_sanity.c | 85 +++++++++++++++++++
.../selftests/bpf/progs/bpf_tracing_net.h | 6 ++
.../selftests/bpf/progs/decap_sanity.c | 68 +++++++++++++++
4 files changed, 160 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/decap_sanity.c
create mode 100644 tools/testing/selftests/bpf/progs/decap_sanity.c
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 585fcf73c7314..3fc3e54b19aad 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -14,6 +14,7 @@ cgrp_kfunc # JIT does not support calling kernel f
cgrp_local_storage # prog_attach unexpected error: -524 (trampoline)
core_read_macros # unknown func bpf_probe_read#4 (overlapping)
d_path # failed to auto-attach program 'prog_stat': -524 (trampoline)
+decap_sanity # JIT does not support calling kernel function (kfunc)
deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline)
dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline)
fentry_fexit # fentry attach failed: -524 (trampoline)
diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
new file mode 100644
index 0000000000000..0b2f73b88c53d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/in6.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define SYS(fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ if (!ASSERT_OK(system(cmd), cmd)) \
+ goto fail; \
+ })
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+ LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+ struct nstoken *nstoken = NULL;
+ struct decap_sanity *skel;
+ struct sockaddr_in6 addr;
+ socklen_t addrlen;
+ char buf[128] = {};
+ int sockfd, err;
+
+ skel = decap_sanity__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+ return;
+
+ SYS("ip netns add %s", NS_TEST);
+ SYS("ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+ SYS("ip -net %s link set dev lo up", NS_TEST);
+
+ nstoken = open_netns(NS_TEST);
+ if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+ goto fail;
+
+ qdisc_hook.ifindex = if_nametoindex("lo");
+ if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+ goto fail;
+
+ err = bpf_tc_hook_create(&qdisc_hook);
+ if (!ASSERT_OK(err, "create qdisc hook"))
+ goto fail;
+
+ tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+ err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+ if (!ASSERT_OK(err, "attach filter"))
+ goto fail;
+
+ addrlen = sizeof(addr);
+ err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+ (void *)&addr, &addrlen);
+ if (!ASSERT_OK(err, "make_sockaddr"))
+ goto fail;
+ sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+ if (!ASSERT_NEQ(sockfd, -1, "socket"))
+ goto fail;
+ err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+ close(sockfd);
+ if (!ASSERT_EQ(err, sizeof(buf), "send"))
+ goto fail;
+
+ ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+ ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+ ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+ if (nstoken) {
+ bpf_tc_hook_destroy(&qdisc_hook);
+ close_netns(nstoken);
+ }
+ system("ip netns del " NS_TEST " >& /dev/null");
+ decap_sanity__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index b394817126cf9..cfed4df490f35 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -50,6 +50,12 @@
#define ICSK_TIME_LOSS_PROBE 5
#define ICSK_TIME_REO_TIMEOUT 6
+#define ETH_HLEN 14
+#define ETH_P_IPV6 0x86DD
+
+#define CHECKSUM_NONE 0
+#define CHECKSUM_PARTIAL 3
+
#define IFNAMSIZ 16
#define RTF_GATEWAY 0x0002
diff --git a/tools/testing/selftests/bpf/progs/decap_sanity.c b/tools/testing/selftests/bpf/progs/decap_sanity.c
new file mode 100644
index 0000000000000..bd3c657c58a79
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/decap_sanity.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+ return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+ return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+ return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+ struct sk_buff *kskb;
+ struct ipv6hdr ip6h;
+ struct udphdr udph;
+ int err;
+
+ if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+ return TC_ACT_SHOT;
+
+ if (ip6h.nexthdr != IPPROTO_UDP)
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+ return TC_ACT_SHOT;
+
+ if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+ return TC_ACT_SHOT;
+
+ kskb = bpf_cast_to_kern_ctx(skb);
+ init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+ err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+ 1, BPF_F_ADJ_ROOM_FIXED_GSO);
+ if (err)
+ return TC_ACT_SHOT;
+ final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+ if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+ (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+ broken_csum_start = true;
+
+ return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";
--
GitLab
From 53fc61be273a1e76dd5e356f91805dce00ff2d2c Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 20 Dec 2022 09:54:48 -0800
Subject: [PATCH 0040/1167] ice: xsk: do not use xdp_return_frame() on
tx_buf->raw_buf
Previously ice XDP xmit routine was changed in a way that it avoids
xdp_buff->xdp_frame conversion as it is simply not needed for handling
XDP_TX action and what is more it saves us CPU cycles. This routine is
re-used on ZC driver to handle XDP_TX action.
Although for XDP_TX on Rx ZC xdp_buff that comes from xsk_buff_pool is
converted to xdp_frame, xdp_frame itself is not stored inside
ice_tx_buf, we only store raw data pointer. Casting this pointer to
xdp_frame and calling against it xdp_return_frame in
ice_clean_xdp_tx_buf() results in undefined behavior.
To fix this, simply call page_frag_free() on tx_buf->raw_buf.
Later intention is to remove the buff->frame conversion in order to
simplify the codebase and improve XDP_TX performance on ZC.
Fixes: 126cdfe1007a ("ice: xsk: Improve AF_XDP ZC Tx and use batching API")
Reported-and-tested-by: Robin Cowley <robin.cowley@thehutgroup.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Reviewed-by: Piotr Raczynski <piotr.raczynski@.intel.com>
Link: https://lore.kernel.org/r/20221220175448.693999-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 907055b77af0e..7105de6fb3444 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -783,7 +783,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
static void
ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
{
- xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
+ page_frag_free(tx_buf->raw_buf);
xdp_ring->xdp_tx_active--;
dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
--
GitLab
From f2575c8f404911da83f25b688e12afcf4273e640 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 20 Dec 2022 18:18:25 +0100
Subject: [PATCH 0041/1167] net: vrf: determine the dst using the original
ifindex for multicast
Multicast packets received on an interface bound to a VRF are marked as
belonging to the VRF and the skb device is updated to point to the VRF
device itself. This was fine even when a route was associated to a
device as when performing a fib table lookup 'oif' in fib6_table_lookup
(coming from 'skb->dev->ifindex' in ip6_route_input) was set to 0 when
FLOWI_FLAG_SKIP_NH_OIF was set.
With commit 40867d74c374 ("net: Add l3mdev index to flow struct and
avoid oif reset for port devices") this is not longer true and multicast
traffic is not received on the original interface.
Instead of adding back a similar check in fib6_table_lookup determine
the dst using the original ifindex for multicast VRF traffic. To make
things consistent across the function do the above for all strict
packets, which was the logic before commit 6f12fa775530 ("vrf: mark skb
for multicast or link-local as enslaved to VRF"). Note that reverting to
this behavior should be fine as the change was about marking packets
belonging to the VRF, not about their dst.
Fixes: 40867d74c374 ("net: Add l3mdev index to flow struct and avoid oif reset for port devices")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20221220171825.1172237-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/vrf.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6b5a4d036d153..bdb3a76a352e4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1385,8 +1385,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
/* loopback, multicast & non-ND link-local traffic; do not push through
* packet taps again. Reset pkt_type for upper layers to process skb.
- * For strict packets with a source LLA, determine the dst using the
- * original ifindex.
+ * For non-loopback strict packets, determine the dst using the original
+ * ifindex.
*/
if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
skb->dev = vrf_dev;
@@ -1395,7 +1395,7 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
if (skb->pkt_type == PACKET_LOOPBACK)
skb->pkt_type = PACKET_HOST;
- else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
+ else
vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
goto out;
--
GitLab
From 95637d91fefdb94d6e7389222ba9ddab0e9f5abe Mon Sep 17 00:00:00 2001
From: Aaron Conole <aconole@redhat.com>
Date: Tue, 20 Dec 2022 16:27:17 -0500
Subject: [PATCH 0042/1167] net: openvswitch: release vport resources on
failure
A recent commit introducing upcall packet accounting failed to properly
release the vport object when the per-cpu stats struct couldn't be
allocated. This can cause dangling pointers to dp objects long after
they've been released.
Cc: wangchuanlei <wangchuanlei@inspur.com>
Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets")
Reported-by: syzbot+8f4e2dcfcb3209ac35f9@syzkaller.appspotmail.com
Signed-off-by: Aaron Conole <aconole@redhat.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://lore.kernel.org/r/20221220212717.526780-1-aconole@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/openvswitch/datapath.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 9ca721c9fa718..a71795355aecf 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1861,7 +1861,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto err_destroy_portids;
+ goto err_destroy_vport;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1876,6 +1876,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
+err_destroy_vport:
+ ovs_dp_detach_port(vport);
err_destroy_portids:
kfree(rcu_dereference_raw(dp->upcall_portids));
err_unlock_and_destroy_meters:
@@ -2323,7 +2325,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto exit_unlock_free;
+ goto exit_unlock_free_vport;
}
err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
@@ -2343,6 +2345,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_vport_genl_family, reply, info);
return 0;
+exit_unlock_free_vport:
+ ovs_dp_detach_port(vport);
exit_unlock_free:
ovs_unlock();
kfree_skb(reply);
--
GitLab
From 3d8f2c4269d08f8793e946279dbdf5e972cc4911 Mon Sep 17 00:00:00 2001
From: Ronak Doshi <doshir@vmware.com>
Date: Tue, 20 Dec 2022 12:25:55 -0800
Subject: [PATCH 0043/1167] vmxnet3: correctly report csum_level for
encapsulated packet
Commit dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload
support") added support for encapsulation offload. However, the
pathc did not report correctly the csum_level for encapsulated packet.
This patch fixes this issue by reporting correct csum level for the
encapsulated packet.
Fixes: dacce2be3312 ("vmxnet3: add geneve and vxlan tunnel offload support")
Signed-off-by: Ronak Doshi <doshir@vmware.com>
Acked-by: Peng Li <lpeng@vmware.com>
Link: https://lore.kernel.org/r/20221220202556.24421-1-doshir@vmware.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 6f1e560fb15c4..56267c327f0b7 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1288,6 +1288,10 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter,
(le32_to_cpu(gdesc->dword[3]) &
VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
@@ -1297,6 +1301,10 @@ vmxnet3_rx_csum(struct vmxnet3_adapter *adapter,
} else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) &
(1 << VMXNET3_RCD_TUC_SHIFT))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
--
GitLab
From e20aa071cd955aabc15be0ec1e914283592ddef4 Mon Sep 17 00:00:00 2001
From: Yinjun Zhang <yinjun.zhang@corigine.com>
Date: Tue, 20 Dec 2022 16:21:00 +0100
Subject: [PATCH 0044/1167] nfp: fix schedule in atomic context when sync mc
address
The callback `.ndo_set_rx_mode` is called in atomic context, sleep
is not allowed in the implementation. Now use workqueue mechanism
to avoid this issue.
Fixes: de6248644966 ("nfp: add support for multicast filter")
Signed-off-by: Yinjun Zhang <yinjun.zhang@corigine.com>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20221220152100.1042774-1-simon.horman@corigine.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/netronome/nfp/nfp_net.h | 7 +++
.../ethernet/netronome/nfp/nfp_net_common.c | 61 +++++++++++++++++--
2 files changed, 64 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index da33f09facb91..432d79d691c29 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -617,6 +617,9 @@ struct nfp_net_dp {
* @vnic_no_name: For non-port PF vNIC make ndo_get_phys_port_name return
* -EOPNOTSUPP to keep backwards compatibility (set by app)
* @port: Pointer to nfp_port structure if vNIC is a port
+ * @mc_lock: Protect mc_addrs list
+ * @mc_addrs: List of mc addrs to add/del to HW
+ * @mc_work: Work to update mc addrs
* @app_priv: APP private data for this vNIC
*/
struct nfp_net {
@@ -718,6 +721,10 @@ struct nfp_net {
struct nfp_port *port;
+ spinlock_t mc_lock;
+ struct list_head mc_addrs;
+ struct work_struct mc_work;
+
void *app_priv;
};
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 09053373288fe..18fc9971f1c8f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1334,9 +1334,14 @@ int nfp_ctrl_open(struct nfp_net *nn)
return err;
}
-static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr, const u32 cmd)
+struct nfp_mc_addr_entry {
+ u8 addr[ETH_ALEN];
+ u32 cmd;
+ struct list_head list;
+};
+
+static int nfp_net_mc_cfg(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
{
- struct nfp_net *nn = netdev_priv(netdev);
int ret;
ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ);
@@ -1351,6 +1356,25 @@ static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr,
return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
}
+static int nfp_net_mc_prep(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
+{
+ struct nfp_mc_addr_entry *entry;
+
+ entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+
+ ether_addr_copy(entry->addr, addr);
+ entry->cmd = cmd;
+ spin_lock_bh(&nn->mc_lock);
+ list_add_tail(&entry->list, &nn->mc_addrs);
+ spin_unlock_bh(&nn->mc_lock);
+
+ schedule_work(&nn->mc_work);
+
+ return 0;
+}
+
static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr)
{
struct nfp_net *nn = netdev_priv(netdev);
@@ -1361,12 +1385,35 @@ static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr)
return -EINVAL;
}
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
+ return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
}
static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr)
{
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+}
+
+static void nfp_net_mc_addr_config(struct work_struct *work)
+{
+ struct nfp_net *nn = container_of(work, struct nfp_net, mc_work);
+ struct nfp_mc_addr_entry *entry, *tmp;
+ struct list_head tmp_list;
+
+ INIT_LIST_HEAD(&tmp_list);
+
+ spin_lock_bh(&nn->mc_lock);
+ list_splice_init(&nn->mc_addrs, &tmp_list);
+ spin_unlock_bh(&nn->mc_lock);
+
+ list_for_each_entry_safe(entry, tmp, &tmp_list, list) {
+ if (nfp_net_mc_cfg(nn, entry->addr, entry->cmd))
+ nn_err(nn, "Config mc address to HW failed.\n");
+
+ list_del(&entry->list);
+ kfree(entry);
+ }
}
static void nfp_net_set_rx_mode(struct net_device *netdev)
@@ -2633,6 +2680,11 @@ int nfp_net_init(struct nfp_net *nn)
if (!nn->dp.netdev)
return 0;
+
+ spin_lock_init(&nn->mc_lock);
+ INIT_LIST_HEAD(&nn->mc_addrs);
+ INIT_WORK(&nn->mc_work, nfp_net_mc_addr_config);
+
return register_netdev(nn->dp.netdev);
err_clean_mbox:
@@ -2652,5 +2704,6 @@ void nfp_net_clean(struct nfp_net *nn)
unregister_netdev(nn->dp.netdev);
nfp_net_ipsec_clean(nn);
nfp_ccm_mbox_clean(nn);
+ flush_work(&nn->mc_work);
nfp_net_reconfig_wait_posted(nn);
}
--
GitLab
From 7d803344fdc3e38079fabcf38b1e4cb6f8faa655 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 20 Dec 2022 11:52:14 -0800
Subject: [PATCH 0045/1167] mptcp: fix deadlock in fastopen error path
MatM reported a deadlock at fastopening time:
INFO: task syz-executor.0:11454 blocked for more than 143 seconds.
Tainted: G S 6.1.0-rc5-03226-gdb0157db5153 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:syz-executor.0 state:D stack:25104 pid:11454 ppid:424 flags:0x00004006
Call Trace:
<TASK>
context_switch kernel/sched/core.c:5191 [inline]
__schedule+0x5c2/0x1550 kernel/sched/core.c:6503
schedule+0xe8/0x1c0 kernel/sched/core.c:6579
__lock_sock+0x142/0x260 net/core/sock.c:2896
lock_sock_nested+0xdb/0x100 net/core/sock.c:3466
__mptcp_close_ssk+0x1a3/0x790 net/mptcp/protocol.c:2328
mptcp_destroy_common+0x16a/0x650 net/mptcp/protocol.c:3171
mptcp_disconnect+0xb8/0x450 net/mptcp/protocol.c:3019
__inet_stream_connect+0x897/0xa40 net/ipv4/af_inet.c:720
tcp_sendmsg_fastopen+0x3dd/0x740 net/ipv4/tcp.c:1200
mptcp_sendmsg_fastopen net/mptcp/protocol.c:1682 [inline]
mptcp_sendmsg+0x128a/0x1a50 net/mptcp/protocol.c:1721
inet6_sendmsg+0x11f/0x150 net/ipv6/af_inet6.c:663
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg+0xf7/0x190 net/socket.c:734
____sys_sendmsg+0x336/0x970 net/socket.c:2476
___sys_sendmsg+0x122/0x1c0 net/socket.c:2530
__sys_sendmmsg+0x18d/0x460 net/socket.c:2616
__do_sys_sendmmsg net/socket.c:2645 [inline]
__se_sys_sendmmsg net/socket.c:2642 [inline]
__x64_sys_sendmmsg+0x9d/0x110 net/socket.c:2642
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f5920a75e7d
RSP: 002b:00007f59201e8028 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00007f5920bb4f80 RCX: 00007f5920a75e7d
RDX: 0000000000000001 RSI: 0000000020002940 RDI: 0000000000000005
RBP: 00007f5920ae7593 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000020004050 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007f5920bb4f80 R15: 00007f59201c8000
</TASK>
In the error path, tcp_sendmsg_fastopen() ends-up calling
mptcp_disconnect(), and the latter tries to close each
subflow, acquiring the socket lock on each of them.
At fastopen time, we have a single subflow, and such subflow
socket lock is already held by the called, causing the deadlock.
We already track the 'fastopen in progress' status inside the msk
socket. Use it to address the issue, making mptcp_disconnect() a
no op when invoked from the fastopen (error) path and doing the
relevant cleanup after releasing the subflow socket lock.
While at the above, rename the fastopen status bit to something
more meaningful.
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/321
Fixes: fa9e57468aa1 ("mptcp: fix abba deadlock on fastopen")
Reported-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/mptcp/protocol.c | 18 +++++++++++++++---
net/mptcp/protocol.h | 2 +-
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f6f93957275b8..907b435e29842 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1662,6 +1662,8 @@ static void mptcp_set_nospace(struct sock *sk)
set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
}
+static int mptcp_disconnect(struct sock *sk, int flags);
+
static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
size_t len, int *copied_syn)
{
@@ -1672,9 +1674,9 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
lock_sock(ssk);
msg->msg_flags |= MSG_DONTWAIT;
msk->connect_flags = O_NONBLOCK;
- msk->is_sendmsg = 1;
+ msk->fastopening = 1;
ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
- msk->is_sendmsg = 0;
+ msk->fastopening = 0;
msg->msg_flags = saved_flags;
release_sock(ssk);
@@ -1688,6 +1690,8 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msgh
*/
if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
*copied_syn = 0;
+ } else if (ret && ret != -EINPROGRESS) {
+ mptcp_disconnect(sk, 0);
}
return ret;
@@ -2989,6 +2993,14 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ /* We are on the fastopen error path. We can't call straight into the
+ * subflows cleanup code due to lock nesting (we are already under
+ * msk->firstsocket lock). Do nothing and leave the cleanup to the
+ * caller.
+ */
+ if (msk->fastopening)
+ return 0;
+
inet_sk_state_store(sk, TCP_CLOSE);
mptcp_stop_timer(sk);
@@ -3532,7 +3544,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
/* if reaching here via the fastopen/sendmsg path, the caller already
* acquired the subflow socket lock, too.
*/
- if (msk->is_sendmsg)
+ if (msk->fastopening)
err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
else
err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 955fb3d88eb3a..f47d3e4018b51 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -295,7 +295,7 @@ struct mptcp_sock {
u8 recvmsg_inq:1,
cork:1,
nodelay:1,
- is_sendmsg:1;
+ fastopening:1;
int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
--
GitLab
From fec3adfd754ccc99a7230e8ab9f105b65fb07bcc Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 20 Dec 2022 11:52:15 -0800
Subject: [PATCH 0046/1167] mptcp: fix lockdep false positive
MattB reported a lockdep splat in the mptcp listener code cleanup:
WARNING: possible circular locking dependency detected
packetdrill/14278 is trying to acquire lock:
ffff888017d868f0 ((work_completion)(&msk->work)){+.+.}-{0:0}, at: __flush_work (kernel/workqueue.c:3069)
but task is already holding lock:
ffff888017d84130 (sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close (net/mptcp/protocol.c:2973)
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (sk_lock-AF_INET){+.+.}-{0:0}:
__lock_acquire (kernel/locking/lockdep.c:5055)
lock_acquire (kernel/locking/lockdep.c:466)
lock_sock_nested (net/core/sock.c:3463)
mptcp_worker (net/mptcp/protocol.c:2614)
process_one_work (kernel/workqueue.c:2294)
worker_thread (include/linux/list.h:292)
kthread (kernel/kthread.c:376)
ret_from_fork (arch/x86/entry/entry_64.S:312)
-> #0 ((work_completion)(&msk->work)){+.+.}-{0:0}:
check_prev_add (kernel/locking/lockdep.c:3098)
validate_chain (kernel/locking/lockdep.c:3217)
__lock_acquire (kernel/locking/lockdep.c:5055)
lock_acquire (kernel/locking/lockdep.c:466)
__flush_work (kernel/workqueue.c:3070)
__cancel_work_timer (kernel/workqueue.c:3160)
mptcp_cancel_work (net/mptcp/protocol.c:2758)
mptcp_subflow_queue_clean (net/mptcp/subflow.c:1817)
__mptcp_close_ssk (net/mptcp/protocol.c:2363)
mptcp_destroy_common (net/mptcp/protocol.c:3170)
mptcp_destroy (include/net/sock.h:1495)
__mptcp_destroy_sock (net/mptcp/protocol.c:2886)
__mptcp_close (net/mptcp/protocol.c:2959)
mptcp_close (net/mptcp/protocol.c:2974)
inet_release (net/ipv4/af_inet.c:432)
__sock_release (net/socket.c:651)
sock_close (net/socket.c:1367)
__fput (fs/file_table.c:320)
task_work_run (kernel/task_work.c:181 (discriminator 1))
exit_to_user_mode_prepare (include/linux/resume_user_mode.h:49)
syscall_exit_to_user_mode (kernel/entry/common.c:130)
do_syscall_64 (arch/x86/entry/common.c:87)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(sk_lock-AF_INET);
lock((work_completion)(&msk->work));
lock(sk_lock-AF_INET);
lock((work_completion)(&msk->work));
*** DEADLOCK ***
The report is actually a false positive, since the only existing lock
nesting is the msk socket lock acquired by the mptcp work.
cancel_work_sync() is invoked without the relevant socket lock being
held, but under a different (the msk listener) socket lock.
We could silence the splat adding a per workqueue dynamic lockdep key,
but that looks overkill. Instead just tell lockdep the msk socket lock
is not held around cancel_work_sync().
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/322
Fixes: 30e51b923e43 ("mptcp: fix unreleased socket in accept queue")
Reported-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/mptcp/protocol.c | 2 +-
net/mptcp/protocol.h | 2 +-
net/mptcp/subflow.c | 19 +++++++++++++++++--
3 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 907b435e29842..b7ad030dfe891 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2357,7 +2357,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
/* otherwise tcp will dispose of the ssk and subflow ctx */
if (ssk->sk_state == TCP_LISTEN) {
tcp_set_state(ssk, TCP_CLOSE);
- mptcp_subflow_queue_clean(ssk);
+ mptcp_subflow_queue_clean(sk, ssk);
inet_csk_listen_stop(ssk);
mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f47d3e4018b51..a0d1658ce59ee 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -628,7 +628,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow);
void __mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
-void mptcp_subflow_queue_clean(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
bool __mptcp_close(struct sock *sk, long timeout);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index d1d32a66ae3f7..bd387d4b5a38f 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1791,7 +1791,7 @@ static void subflow_state_change(struct sock *sk)
}
}
-void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
{
struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
struct mptcp_sock *msk, *next, *head = NULL;
@@ -1840,8 +1840,23 @@ void mptcp_subflow_queue_clean(struct sock *listener_ssk)
do_cancel_work = __mptcp_close(sk, 0);
release_sock(sk);
- if (do_cancel_work)
+ if (do_cancel_work) {
+ /* lockdep will report a false positive ABBA deadlock
+ * between cancel_work_sync and the listener socket.
+ * The involved locks belong to different sockets WRT
+ * the existing AB chain.
+ * Using a per socket key is problematic as key
+ * deregistration requires process context and must be
+ * performed at socket disposal time, in atomic
+ * context.
+ * Just tell lockdep to consider the listener socket
+ * released here.
+ */
+ mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
mptcp_cancel_work(sk);
+ mutex_acquire(&listener_sk->sk_lock.dep_map,
+ SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+ }
sock_put(sk);
}
--
GitLab
From 123b99619cca94bdca0bf7bde9abe28f0a0dfe06 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 19 Dec 2022 20:10:12 +0100
Subject: [PATCH 0047/1167] netfilter: nf_tables: honor set timeout and garbage
collection updates
Set timeout and garbage collection interval updates are ignored on
updates. Add transaction to update global set element timeout and
garbage collection interval.
Fixes: 96518518cc41 ("netfilter: add nftables")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tables.h | 13 ++++++-
net/netfilter/nf_tables_api.c | 63 ++++++++++++++++++++++---------
2 files changed, 57 insertions(+), 19 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4957b4775757b..9430128aae991 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -597,7 +597,9 @@ void *nft_set_catchall_gc(const struct nft_set *set);
static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
{
- return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
+ u32 gc_int = READ_ONCE(set->gc_int);
+
+ return gc_int ? msecs_to_jiffies(gc_int) : HZ;
}
/**
@@ -1570,6 +1572,9 @@ struct nft_trans_rule {
struct nft_trans_set {
struct nft_set *set;
u32 set_id;
+ u32 gc_int;
+ u64 timeout;
+ bool update;
bool bound;
};
@@ -1579,6 +1584,12 @@ struct nft_trans_set {
(((struct nft_trans_set *)trans->data)->set_id)
#define nft_trans_set_bound(trans) \
(((struct nft_trans_set *)trans->data)->bound)
+#define nft_trans_set_update(trans) \
+ (((struct nft_trans_set *)trans->data)->update)
+#define nft_trans_set_timeout(trans) \
+ (((struct nft_trans_set *)trans->data)->timeout)
+#define nft_trans_set_gc_int(trans) \
+ (((struct nft_trans_set *)trans->data)->gc_int)
struct nft_trans_chain {
bool update;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 319887f4d3ef7..8c09e4d12ac1e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -465,8 +465,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx)
return 0;
}
-static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
- struct nft_set *set)
+static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set,
+ const struct nft_set_desc *desc)
{
struct nft_trans *trans;
@@ -474,17 +475,28 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
if (trans == NULL)
return -ENOMEM;
- if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+ if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) {
nft_trans_set_id(trans) =
ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
nft_activate_next(ctx->net, set);
}
nft_trans_set(trans) = set;
+ if (desc) {
+ nft_trans_set_update(trans) = true;
+ nft_trans_set_gc_int(trans) = desc->gc_int;
+ nft_trans_set_timeout(trans) = desc->timeout;
+ }
nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
+static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set)
+{
+ return __nft_trans_set_add(ctx, msg_type, set, NULL);
+}
+
static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
{
int err;
@@ -4044,8 +4056,10 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb,
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
- struct nlmsghdr *nlh;
+ u64 timeout = READ_ONCE(set->timeout);
+ u32 gc_int = READ_ONCE(set->gc_int);
u32 portid = ctx->portid;
+ struct nlmsghdr *nlh;
struct nlattr *nest;
u32 seq = ctx->seq;
int i;
@@ -4081,13 +4095,13 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype)))
goto nla_put_failure;
- if (set->timeout &&
+ if (timeout &&
nla_put_be64(skb, NFTA_SET_TIMEOUT,
- nf_jiffies64_to_msecs(set->timeout),
+ nf_jiffies64_to_msecs(timeout),
NFTA_SET_PAD))
goto nla_put_failure;
- if (set->gc_int &&
- nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
+ if (gc_int &&
+ nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int)))
goto nla_put_failure;
if (set->policy != NFT_SET_POL_PERFORMANCE) {
@@ -4632,7 +4646,10 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
for (i = 0; i < num_exprs; i++)
nft_expr_destroy(&ctx, exprs[i]);
- return err;
+ if (err < 0)
+ return err;
+
+ return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc);
}
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -6070,7 +6087,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
return err;
} else if (set->flags & NFT_SET_TIMEOUT &&
!(flags & NFT_SET_ELEM_INTERVAL_END)) {
- timeout = set->timeout;
+ timeout = READ_ONCE(set->timeout);
}
expiration = 0;
@@ -6171,7 +6188,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
if (err < 0)
goto err_parse_key_end;
- if (timeout != set->timeout) {
+ if (timeout != READ_ONCE(set->timeout)) {
err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
if (err < 0)
goto err_parse_key_end;
@@ -9093,14 +9110,20 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nft_flow_rule_destroy(nft_trans_flow_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_clear(net, nft_trans_set(trans));
- /* This avoids hitting -EBUSY when deleting the table
- * from the transaction.
- */
- if (nft_set_is_anonymous(nft_trans_set(trans)) &&
- !list_empty(&nft_trans_set(trans)->bindings))
- trans->ctx.table->use--;
+ if (nft_trans_set_update(trans)) {
+ struct nft_set *set = nft_trans_set(trans);
+ WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans));
+ WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans));
+ } else {
+ nft_clear(net, nft_trans_set(trans));
+ /* This avoids hitting -EBUSY when deleting the table
+ * from the transaction.
+ */
+ if (nft_set_is_anonymous(nft_trans_set(trans)) &&
+ !list_empty(&nft_trans_set(trans)->bindings))
+ trans->ctx.table->use--;
+ }
nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
NFT_MSG_NEWSET, GFP_KERNEL);
nft_trans_destroy(trans);
@@ -9322,6 +9345,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
+ if (nft_trans_set_update(trans)) {
+ nft_trans_destroy(trans);
+ break;
+ }
trans->ctx.table->use--;
if (nft_trans_set_bound(trans)) {
nft_trans_destroy(trans);
--
GitLab
From 42c7ded0eeacd2ba5db599205c71c279dc715de7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Dec 2022 13:08:31 +0000
Subject: [PATCH 0048/1167] bonding: fix lockdep splat in bond_miimon_commit()
bond_miimon_commit() is run while RTNL is held, not RCU.
WARNING: suspicious RCU usage
6.1.0-syzkaller-09671-g89529367293c #0 Not tainted
-----------------------------
drivers/net/bonding/bond_main.c:2704 suspicious rcu_dereference_check() usage!
Fixes: e95cc44763a4 ("bonding: do failover when high prio link up")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Hangbin Liu <liuhangbin@gmail.com>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Link: https://lore.kernel.org/r/20221220130831.1480888-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/bonding/bond_main.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b4c65783960a5..0363ce5976614 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2654,10 +2654,12 @@ static void bond_miimon_link_change(struct bonding *bond,
static void bond_miimon_commit(struct bonding *bond)
{
- struct slave *slave, *primary;
+ struct slave *slave, *primary, *active;
bool do_failover = false;
struct list_head *iter;
+ ASSERT_RTNL();
+
bond_for_each_slave(bond, slave, iter) {
switch (slave->link_new_state) {
case BOND_LINK_NOCHANGE:
@@ -2700,8 +2702,8 @@ static void bond_miimon_commit(struct bonding *bond)
bond_miimon_link_change(bond, slave, BOND_LINK_UP);
- if (!rcu_access_pointer(bond->curr_active_slave) || slave == primary ||
- slave->prio > rcu_dereference(bond->curr_active_slave)->prio)
+ active = rtnl_dereference(bond->curr_active_slave);
+ if (!active || slave == primary || slave->prio > active->prio)
do_failover = true;
continue;
--
GitLab
From d717f9474e3fb7e6bd3e43ca16e131f04320ed6f Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Wed, 21 Dec 2022 10:33:15 +0100
Subject: [PATCH 0049/1167] net: lan966x: Fix configuration of the PCS
When the PCS was taken out of reset, we were changing by mistake also
the speed to 100 Mbit. But in case the link was going down, the link
up routine was setting correctly the link speed. If the link was not
getting down then the speed was forced to run at 100 even if the
speed was something else.
On lan966x, to set the speed link to 1G or 2.5G a value of 1 needs to be
written in DEV_CLOCK_CFG_LINK_SPEED. This is similar to the procedure in
lan966x_port_init.
The issue was reproduced using 1000base-x sfp module using the commands:
ip link set dev eth2 up
ip link addr add 10.97.10.2/24 dev eth2
ethtool -s eth2 speed 1000 autoneg off
Fixes: d28d6d2e37d1 ("net: lan966x: add port module support")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com>
Link: https://lore.kernel.org/r/20221221093315.939133-1-horatiu.vultur@microchip.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/microchip/lan966x/lan966x_port.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
index 1a61c6cdb0779..0050fcb988b75 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c
@@ -381,7 +381,7 @@ int lan966x_port_pcs_set(struct lan966x_port *port,
}
/* Take PCS out of reset */
- lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(2) |
+ lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(LAN966X_SPEED_1000) |
DEV_CLOCK_CFG_PCS_RX_RST_SET(0) |
DEV_CLOCK_CFG_PCS_TX_RST_SET(0),
DEV_CLOCK_CFG_LINK_SPEED |
--
GitLab
From fa349e396e4886d742fd6501c599ec627ef1353b Mon Sep 17 00:00:00 2001
From: Shawn Bohrer <sbohrer@cloudflare.com>
Date: Tue, 20 Dec 2022 12:59:03 -0600
Subject: [PATCH 0050/1167] veth: Fix race with AF_XDP exposing old or
uninitialized descriptors
When AF_XDP is used on on a veth interface the RX ring is updated in two
steps. veth_xdp_rcv() removes packet descriptors from the FILL ring
fills them and places them in the RX ring updating the cached_prod
pointer. Later xdp_do_flush() syncs the RX ring prod pointer with the
cached_prod pointer allowing user-space to see the recently filled in
descriptors. The rings are intended to be SPSC, however the existing
order in veth_poll allows the xdp_do_flush() to run concurrently with
another CPU creating a race condition that allows user-space to see old
or uninitialized descriptors in the RX ring. This bug has been observed
in production systems.
To summarize, we are expecting this ordering:
CPU 0 __xsk_rcv_zc()
CPU 0 __xsk_map_flush()
CPU 2 __xsk_rcv_zc()
CPU 2 __xsk_map_flush()
But we are seeing this order:
CPU 0 __xsk_rcv_zc()
CPU 2 __xsk_rcv_zc()
CPU 0 __xsk_map_flush()
CPU 2 __xsk_map_flush()
This occurs because we rely on NAPI to ensure that only one napi_poll
handler is running at a time for the given veth receive queue.
napi_schedule_prep() will prevent multiple instances from getting
scheduled. However calling napi_complete_done() signals that this
napi_poll is complete and allows subsequent calls to
napi_schedule_prep() and __napi_schedule() to succeed in scheduling a
concurrent napi_poll before the xdp_do_flush() has been called. For the
veth driver a concurrent call to napi_schedule_prep() and
__napi_schedule() can occur on a different CPU because the veth xmit
path can additionally schedule a napi_poll creating the race.
The fix as suggested by Magnus Karlsson, is to simply move the
xdp_do_flush() call before napi_complete_done(). This syncs the
producer ring pointers before another instance of napi_poll can be
scheduled on another CPU. It will also slightly improve performance by
moving the flush closer to when the descriptors were placed in the
RX ring.
Fixes: d1396004dd86 ("veth: Add XDP TX and REDIRECT")
Suggested-by: Magnus Karlsson <magnus.karlsson@gmail.com>
Signed-off-by: Shawn Bohrer <sbohrer@cloudflare.com>
Link: https://lore.kernel.org/r/20221220185903.1105011-1-sbohrer@cloudflare.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/veth.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ac7c0653695f0..dfc7d87fad59f 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -974,6 +974,9 @@ static int veth_poll(struct napi_struct *napi, int budget)
xdp_set_return_frame_no_direct();
done = veth_xdp_rcv(rq, budget, &bq, &stats);
+ if (stats.xdp_redirect > 0)
+ xdp_do_flush();
+
if (done < budget && napi_complete_done(napi, done)) {
/* Write rx_notify_masked before reading ptr_ring */
smp_store_mb(rq->rx_notify_masked, false);
@@ -987,8 +990,6 @@ static int veth_poll(struct napi_struct *napi, int budget)
if (stats.xdp_tx > 0)
veth_xdp_flush(rq, &bq);
- if (stats.xdp_redirect > 0)
- xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
--
GitLab
From 789e1e10f214c00ca18fc6610824c5b9876ba5f2 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 22 Dec 2022 09:51:30 -0500
Subject: [PATCH 0051/1167] nfsd: shut down the NFSv4 state objects before the
filecache
Currently, we shut down the filecache before trying to clean up the
stateids that depend on it. This leads to the kernel trying to free an
nfsd_file twice, and a refcount overput on the nf_mark.
Change the shutdown procedure to tear down all of the stateids prior
to shutting down the filecache.
Reported-and-tested-by: Wang Yugui <wangyugui@e16-tech.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Fixes: 5e113224c17e ("nfsd: nfsd_file cache entries should be per net namespace")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfssvc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 56fba1cba3af7..325d3d3f12110 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -453,8 +453,8 @@ static void nfsd_shutdown_net(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfsd_file_cache_shutdown_net(net);
nfs4_state_shutdown_net(net);
+ nfsd_file_cache_shutdown_net(net);
if (nn->lockd_up) {
lockd_down(net);
nn->lockd_up = false;
--
GitLab
From 55171f2930be98c8a49991435cdf3a8b574353b6 Mon Sep 17 00:00:00 2001
From: Anton Protopopov <aspsk@isovalent.com>
Date: Thu, 22 Dec 2022 10:26:27 +0000
Subject: [PATCH 0052/1167] bpftool: Fix linkage with statically built libllvm
Since the commit eb9d1acf634b ("bpftool: Add LLVM as default library for
disassembling JIT-ed programs") we might link the bpftool program with the
libllvm library. This works fine when a shared libllvm library is available,
but fails if we want to link bpftool with a statically built LLVM:
[...]
/usr/bin/ld: /usr/local/lib/libLLVMSupport.a(CrashRecoveryContext.cpp.o): in function `llvm::CrashRecoveryContextCleanup::~CrashRecoveryContextCleanup()':
CrashRecoveryContext.cpp:(.text._ZN4llvm27CrashRecoveryContextCleanupD0Ev+0x17): undefined reference to `operator delete(void*, unsigned long)'
/usr/bin/ld: /usr/local/lib/libLLVMSupport.a(CrashRecoveryContext.cpp.o): in function `llvm::CrashRecoveryContext::~CrashRecoveryContext()':
CrashRecoveryContext.cpp:(.text._ZN4llvm20CrashRecoveryContextD2Ev+0xc8): undefined reference to `operator delete(void*, unsigned long)'
[...]
So in the case of static libllvm we need to explicitly link bpftool with
required libraries, namely, libstdc++ and those provided by the `llvm-config
--system-libs` command. We can distinguish between the shared and static cases
by using the `llvm-config --shared-mode` command.
Fixes: eb9d1acf634b ("bpftool: Add LLVM as default library for disassembling JIT-ed programs")
Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20221222102627.1643709-1-aspsk@isovalent.com
---
tools/bpf/bpftool/Makefile | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 787b857d3fb5f..f610e184ce02a 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -145,6 +145,10 @@ ifeq ($(feature-llvm),1)
LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS))
LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static)
+ LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ LIBS += -lstdc++
+ endif
LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
else
# Fall back on libbfd
--
GitLab
From 8374bfd5a3c90a5b250f7c087c4d2b8ac467b12e Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Thu, 22 Dec 2022 10:44:13 +0800
Subject: [PATCH 0053/1167] bpf: fix nullness propagation for reg to reg
comparisons
After befae75856ab, the verifier would propagate null information after
JEQ/JNE, e.g., if two pointers, one is maybe_null and the other is not,
the former would be marked as non-null in eq path. However, as comment
"PTR_TO_BTF_ID points to a kernel struct that does not need to be null
checked by the BPF program ... The verifier must keep this in mind and
can make no assumptions about null or non-null when doing branch ...".
If one pointer is maybe_null and the other is PTR_TO_BTF, the former is
incorrectly marked non-null. The following BPF prog can trigger a
null-ptr-deref, also see this report for more details[1]:
0: (18) r1 = map_fd ; R1_w=map_ptr(ks=4, vs=4)
2: (79) r6 = *(u64 *)(r1 +8) ; R6_w=bpf_map->inner_map_data
; R6 is PTR_TO_BTF_ID
; equals to null at runtime
3: (bf) r2 = r10
4: (07) r2 += -4
5: (62) *(u32 *)(r2 +0) = 0
6: (85) call bpf_map_lookup_elem#1 ; R0_w=map_value_or_null
7: (1d) if r6 == r0 goto pc+1
8: (95) exit
; from 7 to 9: R0=map_value R6=ptr_bpf_map
9: (61) r0 = *(u32 *)(r0 +0) ; null-ptr-deref
10: (95) exit
So, make the verifier propagate nullness information for reg to reg
comparisons only if neither reg is PTR_TO_BTF_ID.
[1] https://lore.kernel.org/bpf/CACkBjsaFJwjC5oiw-1KXvcazywodwXo4zGYsRHwbr2gSG9WcSw@mail.gmail.com/T/#u
Fixes: befae75856ab ("bpf: propagate nullness information for reg to reg comparisons")
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221222024414.29539-1-sunhao.th@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
kernel/bpf/verifier.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a5255a0dcbb68..243d06ce68426 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11822,10 +11822,17 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
* register B - not null
* for JNE A, B, ... - A is not null in the false branch;
* for JEQ A, B, ... - A is not null in the true branch.
+ *
+ * Since PTR_TO_BTF_ID points to a kernel struct that does
+ * not need to be null checked by the BPF program, i.e.,
+ * could be null even without PTR_MAYBE_NULL marking, so
+ * only propagate nullness when neither reg is that type.
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
__is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
- type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+ type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+ base_type(src_reg->type) != PTR_TO_BTF_ID &&
+ base_type(dst_reg->type) != PTR_TO_BTF_ID) {
eq_branch_regs = NULL;
switch (opcode) {
case BPF_JEQ:
--
GitLab
From cedebd74cf3883f0384af9ec26b4e6f8f1964dd4 Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Thu, 22 Dec 2022 10:44:14 +0800
Subject: [PATCH 0054/1167] selftests/bpf: check null propagation only neither
reg is PTR_TO_BTF_ID
Verify that nullness information is not porpagated in the branches
of register to register JEQ and JNE operations if one of them is
PTR_TO_BTF_ID. Implement this in C level so we can use CO-RE.
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20221222024414.29539-2-sunhao.th@gmail.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
.../bpf/prog_tests/jeq_infer_not_null.c | 9 ++++
.../bpf/progs/jeq_infer_not_null_fail.c | 42 +++++++++++++++++++
2 files changed, 51 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c
create mode 100644 tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c
diff --git a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c
new file mode 100644
index 0000000000000..3add34df57678
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+ RUN_TESTS(jeq_infer_not_null_fail);
+}
diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c
new file mode 100644
index 0000000000000..f46965053acb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, u64);
+ __type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+ struct bpf_map *map = (struct bpf_map *)&m_hash;
+ struct bpf_map *inner_map = map->inner_map_meta;
+ u64 key = 0, ret = 0, *val;
+
+ val = bpf_map_lookup_elem(map, &key);
+ /* Do not mark ptr as non-null if one of them is
+ * PTR_TO_BTF_ID (R9), reject because of invalid
+ * access to map value (R8).
+ *
+ * Here, we need to inline those insns to access
+ * R8 directly, since compiler may use other reg
+ * once it figures out val==inner_map.
+ */
+ asm volatile("r8 = %[val];\n"
+ "r9 = %[inner_map];\n"
+ "if r8 != r9 goto +1;\n"
+ "%[ret] = *(u64 *)(r8 +0);\n"
+ : [ret] "+r"(ret)
+ : [inner_map] "r"(inner_map), [val] "r"(val)
+ : "r8", "r9");
+
+ return ret;
+}
--
GitLab
From 8d8bee13ae9e316443c6666286360126a19c8d94 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@seco.com>
Date: Fri, 16 Dec 2022 12:29:37 -0500
Subject: [PATCH 0055/1167] powerpc: dts: t208x: Disable 10G on MAC1 and MAC2
There aren't enough resources to run these ports at 10G speeds. Disable
10G for these ports, reverting to the previous speed.
Fixes: 36926a7d70c2 ("powerpc: dts: t208x: Mark MAC1 and MAC2 as 10G")
Reported-by: Camelia Alexandra Groza <camelia.groza@nxp.com>
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Reviewed-by: Camelia Groza <camelia.groza@nxp.com>
Tested-by: Camelia Groza <camelia.groza@nxp.com>
Link: https://lore.kernel.org/r/20221216172937.2960054-1-sean.anderson@seco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
arch/powerpc/boot/dts/fsl/t2081si-post.dtsi | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index 74e17e134387d..27714dc2f04a5 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -659,3 +659,19 @@ L2_1: l2-cache-controller@c20000 {
interrupts = <16 2 1 9>;
};
};
+
+&fman0_rx_0x08 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x28 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_rx_0x09 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x29 {
+ /delete-property/ fsl,fman-10g-port;
+};
--
GitLab
From 7fac54b93ad13e5e7ac237af33eb2a0940eaeea0 Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Wed, 21 Dec 2022 20:36:27 +0800
Subject: [PATCH 0056/1167] atm: uapi: fix spelling typos in comments
Fix the typo of 'Unsuported' in atmbr2684.h
Signed-off-by: Rong Tao <rongtao@cestc.cn>
Link: https://lore.kernel.org/r/tencent_F1354BEC925C65EA357E741E91DF2044E805@qq.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
include/uapi/linux/atmbr2684.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/uapi/linux/atmbr2684.h b/include/uapi/linux/atmbr2684.h
index a9e2250cd7205..d47c47d06f110 100644
--- a/include/uapi/linux/atmbr2684.h
+++ b/include/uapi/linux/atmbr2684.h
@@ -38,7 +38,7 @@
*/
#define BR2684_ENCAPS_VC (0) /* VC-mux */
#define BR2684_ENCAPS_LLC (1)
-#define BR2684_ENCAPS_AUTODETECT (2) /* Unsuported */
+#define BR2684_ENCAPS_AUTODETECT (2) /* Unsupported */
/*
* Is this VC bridged or routed?
--
GitLab
From 09e6b30eeb254f1818a008cace3547159e908dfd Mon Sep 17 00:00:00 2001
From: Jie Wang <wangjie125@huawei.com>
Date: Thu, 22 Dec 2022 14:43:41 +0800
Subject: [PATCH 0057/1167] net: hns3: add interrupts re-initialization while
doing VF FLR
Currently keep alive message between PF and VF may be lost and the VF is
unalive in PF. So the VF will not do reset during PF FLR reset process.
This would make the allocated interrupt resources of VF invalid and VF
would't receive or respond to PF any more.
So this patch adds VF interrupts re-initialization during VF FLR for VF
recovery in above cases.
Fixes: 862d969a3a4d ("net: hns3: do VF's pci re-initialization while PF doing FLR")
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Hao Lan <lanhao@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index db6f7cdba9587..081bd2c3f2891 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2767,7 +2767,8 @@ static int hclgevf_pci_reset(struct hclgevf_dev *hdev)
struct pci_dev *pdev = hdev->pdev;
int ret = 0;
- if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+ if ((hdev->reset_type == HNAE3_VF_FULL_RESET ||
+ hdev->reset_type == HNAE3_FLR_RESET) &&
test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
hclgevf_misc_irq_uninit(hdev);
hclgevf_uninit_msi(hdev);
--
GitLab
From 7d89b53cea1a702f97117fb4361523519bb1e52c Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 22 Dec 2022 14:43:42 +0800
Subject: [PATCH 0058/1167] net: hns3: fix miss L3E checking for rx packet
For device supports RXD advanced layout, the driver will
return directly if the hardware finish the checksum
calculate. It cause missing L3E checking for ip packets.
Fixes it.
Fixes: 1ddc028ac849 ("net: hns3: refactor out RX completion checksum")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Hao Lan <lanhao@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 0ec5730b17886..b4c4fb873568c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3855,18 +3855,16 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info)
return 0;
}
-static bool hns3_checksum_complete(struct hns3_enet_ring *ring,
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
struct sk_buff *skb, u32 ptype, u16 csum)
{
if (ptype == HNS3_INVALID_PTYPE ||
hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE)
- return false;
+ return;
hns3_ring_stats_update(ring, csum_complete);
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)csum);
-
- return true;
}
static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info,
@@ -3926,8 +3924,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
HNS3_RXD_PTYPE_S);
- if (hns3_checksum_complete(ring, skb, ptype, csum))
- return;
+ hns3_checksum_complete(ring, skb, ptype, csum);
/* check if hardware has done checksum */
if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
@@ -3936,6 +3933,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
BIT(HNS3_RXD_OL3E_B) |
BIT(HNS3_RXD_OL4E_B)))) {
+ skb->ip_summed = CHECKSUM_NONE;
hns3_ring_stats_update(ring, l3l4_csum_err);
return;
--
GitLab
From 8ee57c7b8406c7aa8ca31e014440c87c6383f429 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 22 Dec 2022 14:43:43 +0800
Subject: [PATCH 0059/1167] net: hns3: fix VF promisc mode not update when mac
table full
Currently, it missed set HCLGE_VPORT_STATE_PROMISC_CHANGE
flag for VF when vport->overflow_promisc_flags changed.
So the VF won't check whether to update promisc mode in
this case. So add it.
Fixes: 1e6e76101fd9 ("net: hns3: configure promisc mode for VF asynchronously")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Hao Lan <lanhao@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../hisilicon/hns3/hns3pf/hclge_main.c | 75 +++++++++++--------
1 file changed, 43 insertions(+), 32 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 4e54f91f7a6c1..6c2742f59c777 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -12754,60 +12754,71 @@ static int hclge_gro_en(struct hnae3_handle *handle, bool enable)
return ret;
}
-static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+static int hclge_sync_vport_promisc_mode(struct hclge_vport *vport)
{
- struct hclge_vport *vport = &hdev->vport[0];
struct hnae3_handle *handle = &vport->nic;
+ struct hclge_dev *hdev = vport->back;
+ bool uc_en = false;
+ bool mc_en = false;
u8 tmp_flags;
+ bool bc_en;
int ret;
- u16 i;
if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_promisc_flags = vport->overflow_promisc_flags;
}
- if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) {
+ if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state))
+ return 0;
+
+ /* for PF */
+ if (!vport->vport_id) {
tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
tmp_flags & HNAE3_MPE);
- if (!ret) {
- clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ if (!ret)
set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
&vport->state);
- }
+ else
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state);
+ return ret;
}
- for (i = 1; i < hdev->num_alloc_vport; i++) {
- bool uc_en = false;
- bool mc_en = false;
- bool bc_en;
+ /* for VF */
+ if (vport->vf_info.trusted) {
+ uc_en = vport->vf_info.request_uc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE;
+ mc_en = vport->vf_info.request_mc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE;
+ }
+ bc_en = vport->vf_info.request_bc_en > 0;
- vport = &hdev->vport[i];
+ ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
+ mc_en, bc_en);
+ if (ret) {
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+ return ret;
+ }
+ hclge_set_vport_vlan_fltr_change(vport);
- if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state))
- continue;
+ return 0;
+}
- if (vport->vf_info.trusted) {
- uc_en = vport->vf_info.request_uc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_UPE;
- mc_en = vport->vf_info.request_mc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_MPE;
- }
- bc_en = vport->vf_info.request_bc_en > 0;
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+{
+ struct hclge_vport *vport;
+ int ret;
+ u16 i;
- ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
- mc_en, bc_en);
- if (ret) {
- set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ for (i = 0; i < hdev->num_alloc_vport; i++) {
+ vport = &hdev->vport[i];
+
+ ret = hclge_sync_vport_promisc_mode(vport);
+ if (ret)
return;
- }
- hclge_set_vport_vlan_fltr_change(vport);
}
}
--
GitLab
From fcbb408a1aaf426f88d8fb3b4c14e3625745b02f Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 22 Dec 2022 13:39:58 -0800
Subject: [PATCH 0060/1167] selftests/bpf: Add host-tools to gitignore
Shows up when cross-compiling:
HOST_SCRATCH_DIR := $(OUTPUT)/host-tools
vs
SCRATCH_DIR := $(OUTPUT)/tools
HOST_SCRATCH_DIR := $(SCRATCH_DIR)
Reported-by: John Sperbeck <jsperbeck@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20221222213958.2302320-1-sdf@google.com
---
tools/testing/selftests/bpf/.gitignore | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 07d2d0a8c5cb4..401a75844cc0e 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -36,6 +36,7 @@ test_cpp
*.lskel.h
/no_alu32
/bpf_gcc
+/host-tools
/tools
/runqslower
/bench
--
GitLab
From 523dfa96add75e60cfe6bf5a1c8f713635cd6b73 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:34:49 +0100
Subject: [PATCH 0061/1167] drm/tests: reduce drm_mm_test stack usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The check_reserve_boundaries function uses a lot of kernel stack,
and it gets inlined by clang, which makes __drm_test_mm_reserve
use even more of it, to the point of hitting the warning limit:
drivers/gpu/drm/tests/drm_mm_test.c:344:12: error: stack frame size (1048) exceeds limit (1024) in '__drm_test_mm_reserve' [-Werror,-Wframe-larger-than]
When building with gcc, this does not happen, but the structleak
plugin can similarly increase the stack usage and needs to be
disabled, as we do for all other kunit users.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: MaÃra Canal <mcanal@igalia.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: MaÃra Canal <mairacanal@riseup.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20221215163511.266214-1-arnd@kernel.org
---
drivers/gpu/drm/tests/Makefile | 2 ++
drivers/gpu/drm/tests/drm_mm_test.c | 6 +++---
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/tests/Makefile b/drivers/gpu/drm/tests/Makefile
index b29ef1085cad9..f896ef85c2f2b 100644
--- a/drivers/gpu/drm/tests/Makefile
+++ b/drivers/gpu/drm/tests/Makefile
@@ -12,3 +12,5 @@ obj-$(CONFIG_DRM_KUNIT_TEST) += \
drm_mm_test.o \
drm_plane_helper_test.o \
drm_rect_test.o
+
+CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN)
diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c
index 89f12d3b4a219..186b28dc70380 100644
--- a/drivers/gpu/drm/tests/drm_mm_test.c
+++ b/drivers/gpu/drm/tests/drm_mm_test.c
@@ -298,9 +298,9 @@ static bool expect_reserve_fail(struct kunit *test, struct drm_mm *mm, struct dr
return false;
}
-static bool check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
- unsigned int count,
- u64 size)
+static bool noinline_for_stack check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
+ unsigned int count,
+ u64 size)
{
const struct boundary {
u64 start, size;
--
GitLab
From 399ab7fe0fa0d846881685fd4e57e9a8ef7559f7 Mon Sep 17 00:00:00 2001
From: Hawkins Jiawei <yin31149@gmail.com>
Date: Thu, 22 Dec 2022 11:51:19 +0800
Subject: [PATCH 0062/1167] net: sched: fix memory leak in tcindex_set_parms
Syzkaller reports a memory leak as follows:
====================================
BUG: memory leak
unreferenced object 0xffff88810c287f00 (size 256):
comm "syz-executor105", pid 3600, jiffies 4294943292 (age 12.990s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<ffffffff814cf9f0>] kmalloc_trace+0x20/0x90 mm/slab_common.c:1046
[<ffffffff839c9e07>] kmalloc include/linux/slab.h:576 [inline]
[<ffffffff839c9e07>] kmalloc_array include/linux/slab.h:627 [inline]
[<ffffffff839c9e07>] kcalloc include/linux/slab.h:659 [inline]
[<ffffffff839c9e07>] tcf_exts_init include/net/pkt_cls.h:250 [inline]
[<ffffffff839c9e07>] tcindex_set_parms+0xa7/0xbe0 net/sched/cls_tcindex.c:342
[<ffffffff839caa1f>] tcindex_change+0xdf/0x120 net/sched/cls_tcindex.c:553
[<ffffffff8394db62>] tc_new_tfilter+0x4f2/0x1100 net/sched/cls_api.c:2147
[<ffffffff8389e91c>] rtnetlink_rcv_msg+0x4dc/0x5d0 net/core/rtnetlink.c:6082
[<ffffffff839eba67>] netlink_rcv_skb+0x87/0x1d0 net/netlink/af_netlink.c:2540
[<ffffffff839eab87>] netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
[<ffffffff839eab87>] netlink_unicast+0x397/0x4c0 net/netlink/af_netlink.c:1345
[<ffffffff839eb046>] netlink_sendmsg+0x396/0x710 net/netlink/af_netlink.c:1921
[<ffffffff8383e796>] sock_sendmsg_nosec net/socket.c:714 [inline]
[<ffffffff8383e796>] sock_sendmsg+0x56/0x80 net/socket.c:734
[<ffffffff8383eb08>] ____sys_sendmsg+0x178/0x410 net/socket.c:2482
[<ffffffff83843678>] ___sys_sendmsg+0xa8/0x110 net/socket.c:2536
[<ffffffff838439c5>] __sys_sendmmsg+0x105/0x330 net/socket.c:2622
[<ffffffff83843c14>] __do_sys_sendmmsg net/socket.c:2651 [inline]
[<ffffffff83843c14>] __se_sys_sendmmsg net/socket.c:2648 [inline]
[<ffffffff83843c14>] __x64_sys_sendmmsg+0x24/0x30 net/socket.c:2648
[<ffffffff84605fd5>] do_syscall_x64 arch/x86/entry/common.c:50 [inline]
[<ffffffff84605fd5>] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80
[<ffffffff84800087>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
====================================
Kernel uses tcindex_change() to change an existing
filter properties.
Yet the problem is that, during the process of changing,
if `old_r` is retrieved from `p->perfect`, then
kernel uses tcindex_alloc_perfect_hash() to newly
allocate filter results, uses tcindex_filter_result_init()
to clear the old filter result, without destroying
its tcf_exts structure, which triggers the above memory leak.
To be more specific, there are only two source for the `old_r`,
according to the tcindex_lookup(). `old_r` is retrieved from
`p->perfect`, or `old_r` is retrieved from `p->h`.
* If `old_r` is retrieved from `p->perfect`, kernel uses
tcindex_alloc_perfect_hash() to newly allocate the
filter results. Then `r` is assigned with `cp->perfect + handle`,
which is newly allocated. So condition `old_r && old_r != r` is
true in this situation, and kernel uses tcindex_filter_result_init()
to clear the old filter result, without destroying
its tcf_exts structure
* If `old_r` is retrieved from `p->h`, then `p->perfect` is NULL
according to the tcindex_lookup(). Considering that `cp->h`
is directly copied from `p->h` and `p->perfect` is NULL,
`r` is assigned with `tcindex_lookup(cp, handle)`, whose value
should be the same as `old_r`, so condition `old_r && old_r != r`
is false in this situation, kernel ignores using
tcindex_filter_result_init() to clear the old filter result.
So only when `old_r` is retrieved from `p->perfect` does kernel use
tcindex_filter_result_init() to clear the old filter result, which
triggers the above memory leak.
Considering that there already exists a tc_filter_wq workqueue
to destroy the old tcindex_data by tcindex_partial_destroy_work()
at the end of tcindex_set_parms(), this patch solves
this memory leak bug by removing this old filter result
clearing part and delegating it to the tc_filter_wq workqueue.
Note that this patch doesn't introduce any other issues. If
`old_r` is retrieved from `p->perfect`, this patch just
delegates old filter result clearing part to the
tc_filter_wq workqueue; If `old_r` is retrieved from `p->h`,
kernel doesn't reach the old filter result clearing part, so
removing this part has no effect.
[Thanks to the suggestion from Jakub Kicinski, Cong Wang, Paolo Abeni
and Dmitry Vyukov]
Fixes: b9a24bb76bf6 ("net_sched: properly handle failure case of tcf_exts_init()")
Link: https://lore.kernel.org/all/0000000000001de5c505ebc9ec59@google.com/
Reported-by: syzbot+232ebdbd36706c965ebf@syzkaller.appspotmail.com
Tested-by: syzbot+232ebdbd36706c965ebf@syzkaller.appspotmail.com
Cc: Cong Wang <cong.wang@bytedance.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hawkins Jiawei <yin31149@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/cls_tcindex.c | 12 ++----------
1 file changed, 2 insertions(+), 10 deletions(-)
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index eb0e9458e722e..ee2a050c887bf 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -333,7 +333,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
struct tcindex_filter_result *r, struct nlattr **tb,
struct nlattr *est, u32 flags, struct netlink_ext_ack *extack)
{
- struct tcindex_filter_result new_filter_result, *old_r = r;
+ struct tcindex_filter_result new_filter_result;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
struct tcf_result cr = {};
@@ -402,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
err = tcindex_filter_result_init(&new_filter_result, cp, net);
if (err < 0)
goto errout_alloc;
- if (old_r)
+ if (r)
cr = r->res;
err = -EBUSY;
@@ -479,14 +479,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
tcf_bind_filter(tp, &cr, base);
}
- if (old_r && old_r != r) {
- err = tcindex_filter_result_init(old_r, cp, net);
- if (err < 0) {
- kfree(f);
- goto errout_alloc;
- }
- }
-
oldp = p;
r->res = cr;
tcf_exts_change(&r->exts, &e);
--
GitLab
From 13a7c8964afcd8ca43c0b6001ebb0127baa95362 Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Thu, 22 Dec 2022 14:52:28 +0300
Subject: [PATCH 0063/1167] qlcnic: prevent ->dcb use-after-free on
qlcnic_dcb_enable() failure
adapter->dcb would get silently freed inside qlcnic_dcb_enable() in
case qlcnic_dcb_attach() would return an error, which always happens
under OOM conditions. This would lead to use-after-free because both
of the existing callers invoke qlcnic_dcb_get_info() on the obtained
pointer, which is potentially freed at that point.
Propagate errors from qlcnic_dcb_enable(), and instead free the dcb
pointer at callsite using qlcnic_dcb_free(). This also removes the now
unused qlcnic_clear_dcb_ops() helper, which was a simple wrapper around
kfree() also causing memory leaks for partially initialized dcb.
Found by Linux Verification Center (linuxtesting.org) with the SVACE
static analysis tool.
Fixes: 3c44bba1d270 ("qlcnic: Disable DCB operations from SR-IOV VFs")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 8 +++++++-
drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h | 10 ++--------
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 8 +++++++-
3 files changed, 16 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index dbb800769cb63..c95d56e56c59a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -2505,7 +2505,13 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter)
goto disable_mbx_intr;
qlcnic_83xx_clear_function_resources(adapter);
- qlcnic_dcb_enable(adapter->dcb);
+
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ goto disable_mbx_intr;
+ }
+
qlcnic_83xx_initialize_nic(adapter, 1);
qlcnic_dcb_get_info(adapter->dcb);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h
index 7519773eaca6e..22afa2be85fdb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h
@@ -41,11 +41,6 @@ struct qlcnic_dcb {
unsigned long state;
};
-static inline void qlcnic_clear_dcb_ops(struct qlcnic_dcb *dcb)
-{
- kfree(dcb);
-}
-
static inline int qlcnic_dcb_get_hw_capability(struct qlcnic_dcb *dcb)
{
if (dcb && dcb->ops->get_hw_capability)
@@ -112,9 +107,8 @@ static inline void qlcnic_dcb_init_dcbnl_ops(struct qlcnic_dcb *dcb)
dcb->ops->init_dcbnl_ops(dcb);
}
-static inline void qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
+static inline int qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
{
- if (dcb && qlcnic_dcb_attach(dcb))
- qlcnic_clear_dcb_ops(dcb);
+ return dcb ? qlcnic_dcb_attach(dcb) : 0;
}
#endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 28476b982bab6..44dac3c0908eb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2599,7 +2599,13 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
"Device does not support MSI interrupts\n");
if (qlcnic_82xx_check(adapter)) {
- qlcnic_dcb_enable(adapter->dcb);
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ dev_err(&pdev->dev, "Failed to enable DCB\n");
+ goto err_out_free_hw;
+ }
+
qlcnic_dcb_get_info(adapter->dcb);
err = qlcnic_setup_intr(adapter);
--
GitLab
From 30e725537546248bddc12eaac2fe0a258917f190 Mon Sep 17 00:00:00 2001
From: "Johnny S. Lee" <foss@jsl.io>
Date: Thu, 22 Dec 2022 22:34:05 +0800
Subject: [PATCH 0064/1167] net: dsa: mv88e6xxx: depend on PTP conditionally
PTP hardware timestamping related objects are not linked when PTP
support for MV88E6xxx (NET_DSA_MV88E6XXX_PTP) is disabled, therefore
NET_DSA_MV88E6XXX should not depend on PTP_1588_CLOCK_OPTIONAL
regardless of NET_DSA_MV88E6XXX_PTP.
Instead, condition more strictly on how NET_DSA_MV88E6XXX_PTP's
dependencies are met, making sure that it cannot be enabled when
NET_DSA_MV88E6XXX=y and PTP_1588_CLOCK=m.
In other words, this commit allows NET_DSA_MV88E6XXX to be built-in
while PTP_1588_CLOCK is a module, as long as NET_DSA_MV88E6XXX_PTP is
prevented from being enabled.
Fixes: e5f31552674e ("ethernet: fix PTP_1588_CLOCK dependencies")
Signed-off-by: Johnny S. Lee <foss@jsl.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/dsa/mv88e6xxx/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
index 7a2445a34eb77..e3181d5471dfe 100644
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -2,7 +2,6 @@
config NET_DSA_MV88E6XXX
tristate "Marvell 88E6xxx Ethernet switch fabric support"
depends on NET_DSA
- depends on PTP_1588_CLOCK_OPTIONAL
select IRQ_DOMAIN
select NET_DSA_TAG_EDSA
select NET_DSA_TAG_DSA
@@ -13,7 +12,8 @@ config NET_DSA_MV88E6XXX
config NET_DSA_MV88E6XXX_PTP
bool "PTP support for Marvell 88E6xxx"
default n
- depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
+ depends on (NET_DSA_MV88E6XXX = y && PTP_1588_CLOCK = y) || \
+ (NET_DSA_MV88E6XXX = m && PTP_1588_CLOCK)
help
Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
chips that support it.
--
GitLab
From df49908f3c52d211aea5e2a14a93bbe67a2cb3af Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Fri, 23 Dec 2022 11:37:18 +0400
Subject: [PATCH 0065/1167] nfc: Fix potential resource leaks
nfc_get_device() take reference for the device, add missing
nfc_put_device() to release it when not need anymore.
Also fix the style warnning by use error EOPNOTSUPP instead of
ENOTSUPP.
Fixes: 5ce3f32b5264 ("NFC: netlink: SE API implementation")
Fixes: 29e76924cf08 ("nfc: netlink: Add capability to reply to vendor_cmd with data")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/nfc/netlink.c | 52 ++++++++++++++++++++++++++++++++++-------------
1 file changed, 38 insertions(+), 14 deletions(-)
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 9d91087b93992..1fc339084d897 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1497,6 +1497,7 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info)
u32 dev_idx, se_idx;
u8 *apdu;
size_t apdu_len;
+ int rc;
if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
!info->attrs[NFC_ATTR_SE_INDEX] ||
@@ -1510,25 +1511,37 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info)
if (!dev)
return -ENODEV;
- if (!dev->ops || !dev->ops->se_io)
- return -ENOTSUPP;
+ if (!dev->ops || !dev->ops->se_io) {
+ rc = -EOPNOTSUPP;
+ goto put_dev;
+ }
apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]);
- if (apdu_len == 0)
- return -EINVAL;
+ if (apdu_len == 0) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]);
- if (!apdu)
- return -EINVAL;
+ if (!apdu) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
+ if (!ctx) {
+ rc = -ENOMEM;
+ goto put_dev;
+ }
ctx->dev_idx = dev_idx;
ctx->se_idx = se_idx;
- return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+ rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+
+put_dev:
+ nfc_put_device(dev);
+ return rc;
}
static int nfc_genl_vendor_cmd(struct sk_buff *skb,
@@ -1551,14 +1564,21 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb,
subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]);
dev = nfc_get_device(dev_idx);
- if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds)
+ if (!dev)
return -ENODEV;
+ if (!dev->vendor_cmds || !dev->n_vendor_cmds) {
+ err = -ENODEV;
+ goto put_dev;
+ }
+
if (info->attrs[NFC_ATTR_VENDOR_DATA]) {
data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]);
data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]);
- if (data_len == 0)
- return -EINVAL;
+ if (data_len == 0) {
+ err = -EINVAL;
+ goto put_dev;
+ }
} else {
data = NULL;
data_len = 0;
@@ -1573,10 +1593,14 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb,
dev->cur_cmd_info = info;
err = cmd->doit(dev, data, data_len);
dev->cur_cmd_info = NULL;
- return err;
+ goto put_dev;
}
- return -EOPNOTSUPP;
+ err = -EOPNOTSUPP;
+
+put_dev:
+ nfc_put_device(dev);
+ return err;
}
/* message building helper */
--
GitLab
From d3805695fe1e7383517903715cefc9bbdcffdc90 Mon Sep 17 00:00:00 2001
From: Anuradha Weeraman <anuradha@debian.org>
Date: Sun, 25 Dec 2022 23:12:22 +0530
Subject: [PATCH 0066/1167] net: ethernet: marvell: octeontx2: Fix
uninitialized variable warning
Fix for uninitialized variable warning.
Addresses-Coverity: ("Uninitialized scalar variable")
Signed-off-by: Anuradha Weeraman <anuradha@debian.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
index fa8029a940689..eb25e458266ca 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
@@ -589,7 +589,7 @@ int rvu_mbox_handler_mcs_free_resources(struct rvu *rvu,
u16 pcifunc = req->hdr.pcifunc;
struct mcs_rsrc_map *map;
struct mcs *mcs;
- int rc;
+ int rc = 0;
if (req->mcs_id >= rvu->mcs_blk_cnt)
return MCS_AF_ERR_INVALID_MCSID;
--
GitLab
From 26870c3f5b15187268bf183055c7b9f29fe66079 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 26 Dec 2022 10:11:17 -0800
Subject: [PATCH 0067/1167] xfs: don't assert if cmap covers imap after cycling
lock
In xfs_reflink_fill_cow_hole, there's a debugging assertion that trips
if (after cycling the ILOCK to get a transaction) the requeried cow
mapping overlaps the start of the area being written. IOWs, it trips if
the hole in the cow fork that it's supposed to fill has been filled.
This is trivially possible since we cycled ILOCK_EXCL. If we trip the
assertion, then we know that cmap is a delalloc extent because @found is
false. Fortunately, the bmapi_write call below will convert the
delalloc extent to a real unwritten cow fork extent, so all we need to
do here is remove the assertion.
It turns out that generic/095 trips this pretty regularly with alwayscow
mode enabled.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
fs/xfs/xfs_reflink.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index fe46bce8cae63..5535778a98f92 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -416,8 +416,6 @@ xfs_reflink_fill_cow_hole(
goto convert;
}
- ASSERT(cmap->br_startoff > imap->br_startoff);
-
/* Allocate the entire reservation as unwritten blocks. */
nimaps = 1;
error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
--
GitLab
From d4542f314507015ac0e25c6e8102b88293826a51 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 26 Dec 2022 10:11:18 -0800
Subject: [PATCH 0068/1167] xfs: make xfs_iomap_page_ops static
Shut up the sparse warnings about this variable that isn't referenced
anywhere else.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
fs/xfs/xfs_iomap.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 669c1bc5c3a77..fc1946f80a4aa 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -83,7 +83,7 @@ xfs_iomap_valid(
return true;
}
-const struct iomap_page_ops xfs_iomap_page_ops = {
+static const struct iomap_page_ops xfs_iomap_page_ops = {
.iomap_valid = xfs_iomap_valid,
};
--
GitLab
From 896c3dc21f1e84cb2f60d54572fc3377eb57e004 Mon Sep 17 00:00:00 2001
From: Gongjun Song <gongjun.song@intel.com>
Date: Mon, 26 Dec 2022 09:09:16 +0800
Subject: [PATCH 0069/1167] ASoC: Intel: soc-acpi: add configuration for
variant of 0C40 product
Support configuration with SoundWire RT1316 amplifiers on link0 and
link1, and RT711 on link2 for headphone/headset. This product does
not support local microphones.
Signed-off-by: Gongjun Song <gongjun.song@intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20221226010917.2632973-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../intel/common/soc-acpi-intel-rpl-match.c | 25 +++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
index 31b43116e3d88..c70d85bfedbf2 100644
--- a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
@@ -203,6 +203,25 @@ static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01_rt71
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01[] = {
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt711_sdca_2_adr),
+ .adr_d = rt711_sdca_2_adr,
+ },
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt1316_0_group2_adr),
+ .adr_d = rt1316_0_group2_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1316_1_group2_adr),
+ .adr_d = rt1316_1_group2_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt714_link3[] = {
{
.mask = BIT(0),
@@ -277,6 +296,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_rpl_sdw_machines[] = {
.drv_name = "sof_sdw",
.sof_tplg_filename = "sof-rpl-rt1316-l12-rt714-l0.tplg",
},
+ {
+ .link_mask = 0x7, /* rt711 on link2 & two rt1316s on link0 and link1 */
+ .links = rpl_sdw_rt711_link2_rt1316_link01,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l2-rt1316-l01.tplg",
+ },
{
.link_mask = 0x1, /* link0 required */
.links = rpl_rvp,
--
GitLab
From b25a31b463391cc47a654594eb154ebf5dd0d60a Mon Sep 17 00:00:00 2001
From: Gongjun Song <gongjun.song@intel.com>
Date: Mon, 26 Dec 2022 09:09:17 +0800
Subject: [PATCH 0070/1167] ASoC: Intel: soc-acpi: add configuration for
variant of 0C11 product
Support configuration with SoundWire RT1318 amplifiers on link1 and
link2, and RT711 on link0 for headphone/headset. This product does
not support local microphones.
Signed-off-by: Gongjun Song <gongjun.song@intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://lore.kernel.org/r/20221226010917.2632973-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../intel/common/soc-acpi-intel-rpl-match.c | 25 +++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
index c70d85bfedbf2..07f96a11ea2f9 100644
--- a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c
@@ -246,6 +246,25 @@ static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt71
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12[] = {
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt711_sdca_0_adr),
+ .adr_d = rt711_sdca_0_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1318_1_group1_adr),
+ .adr_d = rt1318_1_group1_adr,
+ },
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt1318_2_group1_adr),
+ .adr_d = rt1318_2_group1_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt1316_link12_rt714_link0[] = {
{
.mask = BIT(1),
@@ -290,6 +309,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_rpl_sdw_machines[] = {
.drv_name = "sof_sdw",
.sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12-rt714-l3.tplg",
},
+ {
+ .link_mask = 0x7, /* rt711 on link0 & two rt1318s on link1 and link2 */
+ .links = rpl_sdw_rt711_link0_rt1318_link12,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12.tplg",
+ },
{
.link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */
.links = rpl_sdw_rt1316_link12_rt714_link0,
--
GitLab
From 68506a173dd700c2bd794dcc3489edcdb8ee35c6 Mon Sep 17 00:00:00 2001
From: Wim Van Boven <wimvanboven@gmail.com>
Date: Fri, 16 Dec 2022 09:18:27 +0100
Subject: [PATCH 0071/1167] ASoC: amd: yc: Add Razer Blade 14 2022 into DMI
table
Razer Blade 14 (2022) - RZ09-0427 needs the quirk to enable the built in microphone
Signed-off-by: Wim Van Boven <wimvanboven@gmail.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20221216081828.12382-1-wimvanboven@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 1f0b5527c5949..469c5e79e0ea0 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -220,6 +220,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Razer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"),
+ }
+ },
{}
};
--
GitLab
From ba7523bb0f494fc440d3a9bb0b665cfcaa192d0c Mon Sep 17 00:00:00 2001
From: Ajye Huang <ajye_huang@compal.corp-partner.google.com>
Date: Thu, 22 Dec 2022 12:26:24 +0800
Subject: [PATCH 0072/1167] ASoC: Intel: sof_nau8825: add variant with nau8318
amplifier.
This patch adds the driver data for two nau8318 speaker amplifiers on
SSP1 and nau8825 on SSP0 for ADL platform.
The nau8315 and nau8318 are both Nuvoton Amp chips. They use the same
Amp driver nau8315.c. The acpi_device_id for nau8315 is "NVTN2010",
for nau8318 is "NVTN2012".
The nau8825 is one of Nuvoton headset codec, and its acpi_device_id is
"10508825".
Signed-off-by: Ajye Huang <ajye_huang@compal.corp-partner.google.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20221222042624.557869-1-ajye_huang@compal.corp-partner.google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/boards/Kconfig | 1 +
sound/soc/intel/boards/sof_nau8825.c | 23 +++++++++++++++++++
.../intel/common/soc-acpi-intel-adl-match.c | 12 ++++++++++
3 files changed, 36 insertions(+)
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index a472de1909f4b..3f68e9edd8534 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -554,6 +554,7 @@ config SND_SOC_INTEL_SOF_NAU8825_MACH
select SND_SOC_RT1015P
select SND_SOC_MAX98373_I2C
select SND_SOC_MAX98357A
+ select SND_SOC_NAU8315
select SND_SOC_DMIC
select SND_SOC_HDAC_HDMI
select SND_SOC_INTEL_HDA_DSP_COMMON
diff --git a/sound/soc/intel/boards/sof_nau8825.c b/sound/soc/intel/boards/sof_nau8825.c
index 27880224359d5..78d84527081a9 100644
--- a/sound/soc/intel/boards/sof_nau8825.c
+++ b/sound/soc/intel/boards/sof_nau8825.c
@@ -48,6 +48,7 @@
#define SOF_MAX98373_SPEAKER_AMP_PRESENT BIT(15)
#define SOF_MAX98360A_SPEAKER_AMP_PRESENT BIT(16)
#define SOF_RT1015P_SPEAKER_AMP_PRESENT BIT(17)
+#define SOF_NAU8318_SPEAKER_AMP_PRESENT BIT(18)
static unsigned long sof_nau8825_quirk = SOF_NAU8825_SSP_CODEC(0);
@@ -338,6 +339,13 @@ static struct snd_soc_dai_link_component rt1019p_component[] = {
}
};
+static struct snd_soc_dai_link_component nau8318_components[] = {
+ {
+ .name = "NVTN2012:00",
+ .dai_name = "nau8315-hifi",
+ }
+};
+
static struct snd_soc_dai_link_component dummy_component[] = {
{
.name = "snd-soc-dummy",
@@ -486,6 +494,11 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev,
max_98360a_dai_link(&links[id]);
} else if (sof_nau8825_quirk & SOF_RT1015P_SPEAKER_AMP_PRESENT) {
sof_rt1015p_dai_link(&links[id]);
+ } else if (sof_nau8825_quirk &
+ SOF_NAU8318_SPEAKER_AMP_PRESENT) {
+ links[id].codecs = nau8318_components;
+ links[id].num_codecs = ARRAY_SIZE(nau8318_components);
+ links[id].init = speaker_codec_init;
} else {
goto devm_err;
}
@@ -657,6 +670,16 @@ static const struct platform_device_id board_ids[] = {
SOF_BT_OFFLOAD_SSP(2) |
SOF_SSP_BT_OFFLOAD_PRESENT),
},
+ {
+ .name = "adl_nau8318_8825",
+ .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
+ SOF_SPEAKER_AMP_PRESENT |
+ SOF_NAU8318_SPEAKER_AMP_PRESENT |
+ SOF_NAU8825_SSP_AMP(1) |
+ SOF_NAU8825_NUM_HDMIDEV(4) |
+ SOF_BT_OFFLOAD_SSP(2) |
+ SOF_SSP_BT_OFFLOAD_PRESENT),
+ },
{ }
};
MODULE_DEVICE_TABLE(platform, board_ids);
diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
index 60aee56f94bd4..b1c0a89a87878 100644
--- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
@@ -450,6 +450,11 @@ static const struct snd_soc_acpi_codecs adl_lt6911_hdmi = {
.codecs = {"INTC10B0"}
};
+static const struct snd_soc_acpi_codecs adl_nau8318_amp = {
+ .num_codecs = 1,
+ .codecs = {"NVTN2012"}
+};
+
struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
{
.comp_ids = &adl_rt5682_rt5682s_hp,
@@ -507,6 +512,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
.quirk_data = &adl_rt1015p_amp,
.sof_tplg_filename = "sof-adl-rt1015-nau8825.tplg",
},
+ {
+ .id = "10508825",
+ .drv_name = "adl_nau8318_8825",
+ .machine_quirk = snd_soc_acpi_codec_list,
+ .quirk_data = &adl_nau8318_amp,
+ .sof_tplg_filename = "sof-adl-nau8318-nau8825.tplg",
+ },
{
.id = "10508825",
.drv_name = "sof_nau8825",
--
GitLab
From 63f3d99b7efe4c5404a9388c05780917099cecf4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 21 Dec 2022 14:25:48 +0100
Subject: [PATCH 0073/1167] ASoC: Intel: fix sof-nau8825 link failure
The snd-soc-sof_nau8825.ko module fails to link unless the
sof_realtek_common support is also enabled:
ERROR: modpost: "sof_rt1015p_codec_conf" [sound/soc/intel/boards/snd-soc-sof_nau8825.ko] undefined!
ERROR: modpost: "sof_rt1015p_dai_link" [sound/soc/intel/boards/snd-soc-sof_nau8825.ko] undefined!
Fixes: 8d0872f6239f ("ASoC: Intel: add sof-nau8825 machine driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20221221132559.2402341-1-arnd@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/boards/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 3f68e9edd8534..99308ed85277b 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -559,6 +559,7 @@ config SND_SOC_INTEL_SOF_NAU8825_MACH
select SND_SOC_HDAC_HDMI
select SND_SOC_INTEL_HDA_DSP_COMMON
select SND_SOC_INTEL_SOF_MAXIM_COMMON
+ select SND_SOC_INTEL_SOF_REALTEK_COMMON
help
This adds support for ASoC machine driver for SOF platforms
with nau8825 codec.
--
GitLab
From 3e78986a840d59dd27e636eae3f52dc11125c835 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 21 Dec 2022 14:24:56 +0100
Subject: [PATCH 0074/1167] ASoC: Intel: sof-nau8825: fix module alias overflow
The maximum name length for a platform_device_id entry is 20 characters
including the trailing NUL byte. The sof_nau8825.c file exceeds that,
which causes an obscure error message:
sound/soc/intel/boards/snd-soc-sof_nau8825.mod.c:35:45: error: illegal character encoding in string literal [-Werror,-Winvalid-source-encoding]
MODULE_ALIAS("platform:adl_max98373_nau8825<U+0018><AA>");
^~~~
include/linux/module.h:168:49: note: expanded from macro 'MODULE_ALIAS'
^~~~~~
include/linux/module.h:165:56: note: expanded from macro 'MODULE_INFO'
^~~~
include/linux/moduleparam.h:26:47: note: expanded from macro '__MODULE_INFO'
= __MODULE_INFO_PREFIX __stringify(tag) "=" info
I could not figure out how to make the module handling robust enough
to handle this better, but as a quick fix, using slightly shorter
names that are still unique avoids the build issue.
Fixes: 8d0872f6239f ("ASoC: Intel: add sof-nau8825 machine driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20221221132515.2363276-1-arnd@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/intel/boards/sof_nau8825.c | 8 ++++----
sound/soc/intel/common/soc-acpi-intel-adl-match.c | 8 ++++----
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/intel/boards/sof_nau8825.c b/sound/soc/intel/boards/sof_nau8825.c
index 78d84527081a9..a800854c2831a 100644
--- a/sound/soc/intel/boards/sof_nau8825.c
+++ b/sound/soc/intel/boards/sof_nau8825.c
@@ -631,7 +631,7 @@ static const struct platform_device_id board_ids[] = {
},
{
- .name = "adl_rt1019p_nau8825",
+ .name = "adl_rt1019p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1019P_SPEAKER_AMP_PRESENT |
@@ -639,7 +639,7 @@ static const struct platform_device_id board_ids[] = {
SOF_NAU8825_NUM_HDMIDEV(4)),
},
{
- .name = "adl_max98373_nau8825",
+ .name = "adl_max98373_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98373_SPEAKER_AMP_PRESENT |
@@ -650,7 +650,7 @@ static const struct platform_device_id board_ids[] = {
},
{
/* The limitation of length of char array, shorten the name */
- .name = "adl_mx98360a_nau8825",
+ .name = "adl_mx98360a_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98360A_SPEAKER_AMP_PRESENT |
@@ -661,7 +661,7 @@ static const struct platform_device_id board_ids[] = {
},
{
- .name = "adl_rt1015p_nau8825",
+ .name = "adl_rt1015p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1015P_SPEAKER_AMP_PRESENT |
diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
index b1c0a89a87878..56ee5fef66a8b 100644
--- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c
@@ -479,21 +479,21 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
},
{
.id = "10508825",
- .drv_name = "adl_rt1019p_nau8825",
+ .drv_name = "adl_rt1019p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1019p_amp,
.sof_tplg_filename = "sof-adl-rt1019-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_max98373_nau8825",
+ .drv_name = "adl_max98373_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98373_amp,
.sof_tplg_filename = "sof-adl-max98373-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_mx98360a_nau8825",
+ .drv_name = "adl_mx98360a_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98360a_amp,
.sof_tplg_filename = "sof-adl-max98360a-nau8825.tplg",
@@ -507,7 +507,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
},
{
.id = "10508825",
- .drv_name = "adl_rt1015p_nau8825",
+ .drv_name = "adl_rt1015p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1015p_amp,
.sof_tplg_filename = "sof-adl-rt1015-nau8825.tplg",
--
GitLab
From b24cded8c065d7cef8690b2c7b82b828cce57708 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Sun, 25 Dec 2022 09:37:12 +0100
Subject: [PATCH 0075/1167] spi: mediatek: Enable irq before the spi
registration
If the irq is enabled after the spi si registered, there can be a race
with the initialization of the devices on the spi bus.
Eg:
mtk-spi 1100a000.spi: spi-mem transfer timeout
spi-nor: probe of spi0.0 failed with error -110
Unable to handle kernel NULL pointer dereference at virtual address
0000000000000010
...
Call trace:
mtk_spi_can_dma+0x0/0x2c
Fixes: c6f7874687f7 ("spi: mediatek: Enable irq when pdata is ready")
Reported-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20221225-mtk-spi-fixes-v1-0-bb6c14c232f8@chromium.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-mt65xx.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 6de8360e5c2a9..9eab6c20dbc56 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -1253,6 +1253,11 @@ static int mtk_spi_probe(struct platform_device *pdev)
dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
+ IRQF_TRIGGER_NONE, dev_name(dev), master);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to register irq\n");
+
pm_runtime_enable(dev);
ret = devm_spi_register_master(dev, master);
@@ -1261,13 +1266,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
return dev_err_probe(dev, ret, "failed to register master\n");
}
- ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
- IRQF_TRIGGER_NONE, dev_name(dev), master);
- if (ret) {
- pm_runtime_disable(dev);
- return dev_err_probe(dev, ret, "failed to register irq\n");
- }
-
return 0;
}
--
GitLab
From e8bb8f19e73a1e855e54788f8673b9b49e46b5cd Mon Sep 17 00:00:00 2001
From: Witold Sadowski <wsadowski@marvell.com>
Date: Mon, 19 Dec 2022 06:42:48 -0800
Subject: [PATCH 0076/1167] spi: cadence: Fix busy cycles calculation
If xSPI is in x2/x4/x8 mode to calculate busy
cycles, busy bits count must be divided by the number
of lanes.
If opcommand is using 8 busy bits, but SPI is
in x4 mode, there will be only 2 busy cycles.
Signed-off-by: Witold Sadowski <wsadowski@marvell.com>
Reviewed-by: Chandrakala Chavva <cchavva@marvell.com>
Reviewed-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Link: https://lore.kernel.org/r/20221219144254.20883-2-wsadowski@marvell.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-cadence-xspi.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index 520b4cc69cdc9..91db3c973167b 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -177,7 +177,10 @@
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \
((op)->data.nbytes >> 16) & 0xffff) | \
- FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, (op)->dummy.nbytes * 8))
+ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \
+ (op)->dummy.buswidth != 0 ? \
+ (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \
+ 0))
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R4_BANK, chipsel) | \
--
GitLab
From 83749a2ee548f568ce2037749e19602fdc9f3ee3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:55:15 +0100
Subject: [PATCH 0077/1167] cpufreq: apple: remove duplicate intializer
When -Woverride-init is enabled, gcc notices that the .attr
field is initialized twice:
drivers/cpufreq/apple-soc-cpufreq.c:331:27: error: initialized field overwritten [-Werror=override-init]
331 | .attr = apple_soc_cpufreq_hw_attr,
| ^~~~~~~~~~~~~~~~~~~~~~~~~
Remove the first one, since this is not actually used.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Eric Curtin <ecurtin@redhat.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/apple-soc-cpufreq.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index d1801281cdd99..6f26395184c41 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -321,7 +321,6 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = {
.flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV,
.verify = cpufreq_generic_frequency_table_verify,
- .attr = cpufreq_generic_attr,
.get = apple_soc_cpufreq_get_rate,
.init = apple_soc_cpufreq_init,
.exit = apple_soc_cpufreq_exit,
--
GitLab
From f5f94b9c8b805d87ff185caf9779c3a4d07819e3 Mon Sep 17 00:00:00 2001
From: Pierre Gondois <pierre.gondois@arm.com>
Date: Tue, 20 Dec 2022 11:12:25 +0100
Subject: [PATCH 0078/1167] cpufreq: CPPC: Add u64 casts to avoid overflowing
The fields of the _CPC object are unsigned 32-bits values.
To avoid overflows while using _CPC's values, add 'u64' casts.
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/cppc_cpufreq.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 432dfb4e8027e..022e3555407c8 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -487,7 +487,8 @@ static unsigned int get_perf_level_count(struct cpufreq_policy *policy)
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
if ((min_cap == 0) || (max_cap < min_cap))
return 0;
return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
@@ -519,10 +520,10 @@ static int cppc_get_cpu_power(struct device *cpu_dev,
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu_dev->id);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf,
- perf_caps->highest_perf);
-
- perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
+ perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf,
+ max_cap);
min_step = min_cap / CPPC_EM_CAP_STEP;
max_step = max_cap / CPPC_EM_CAP_STEP;
--
GitLab
From 1a6a8b0080b09bf14a7d45abfe8020bd63306c17 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Tue, 20 Dec 2022 14:39:10 +0100
Subject: [PATCH 0079/1167] cpufreq: qcom-hw: Fix reading "reg" with
address/size-cells != 2
Commit 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during
probe") assumed that every reg variable is 4*u32 wide (as most new qcom
SoCs set #address- and #size-cells to <2>. That is not the case for all of
them though. Check the cells values dynamically to ensure the proper
region of the DTB is being read.
Fixes: 054a3ef683a1 ("cpufreq: qcom-hw: Allocate qcom_cpufreq_data during probe")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/qcom-cpufreq-hw.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 340fed35e45dd..9505a812d6a1d 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -649,9 +649,10 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
{
struct clk_hw_onecell_data *clk_data;
struct device *dev = &pdev->dev;
+ struct device_node *soc_node;
struct device *cpu_dev;
struct clk *clk;
- int ret, i, num_domains;
+ int ret, i, num_domains, reg_sz;
clk = clk_get(dev, "xo");
if (IS_ERR(clk))
@@ -679,7 +680,21 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
return ret;
/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
- num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4);
+ soc_node = of_get_parent(dev->of_node);
+ if (!soc_node)
+ return -EINVAL;
+
+ ret = of_property_read_u32(soc_node, "#address-cells", ®_sz);
+ if (ret)
+ goto of_exit;
+
+ ret = of_property_read_u32(soc_node, "#size-cells", &i);
+ if (ret)
+ goto of_exit;
+
+ reg_sz += i;
+
+ num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz);
if (num_domains <= 0)
return num_domains;
@@ -743,6 +758,9 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
else
dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
+of_exit:
+ of_node_put(soc_node);
+
return ret;
}
--
GitLab
From 01c5bb0cc2a39fbc56ff9a5ef28b79447f0c2351 Mon Sep 17 00:00:00 2001
From: Sumit Gupta <sumitg@nvidia.com>
Date: Tue, 20 Dec 2022 21:32:37 +0530
Subject: [PATCH 0080/1167] cpufreq: Add Tegra234 to cpufreq-dt-platdev
blocklist
Tegra234 platform uses the tegra194-cpufreq driver, so add it
to the blocklist in cpufreq-dt-platdev driver to avoid the cpufreq
driver registration from there.
Signed-off-by: Sumit Gupta <sumitg@nvidia.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/cpufreq-dt-platdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 8ab6728830436..e329d29d1f9d1 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -137,6 +137,7 @@ static const struct of_device_id blocklist[] __initconst = {
{ .compatible = "nvidia,tegra30", },
{ .compatible = "nvidia,tegra124", },
{ .compatible = "nvidia,tegra210", },
+ { .compatible = "nvidia,tegra234", },
{ .compatible = "qcom,apq8096", },
{ .compatible = "qcom,msm8996", },
--
GitLab
From c28f3d80383571d3630df1a0e89500d23e855924 Mon Sep 17 00:00:00 2001
From: Utkarsh Patel <utkarsh.h.patel@intel.com>
Date: Thu, 22 Dec 2022 20:22:46 -0800
Subject: [PATCH 0081/1167] thunderbolt: Do not report errors if on-board
retimers are found
Currently we return an error even if on-board retimers are found and
that's not expected. Fix this to return an error only if there was one
and 0 otherwise.
Fixes: 1e56c88adecc ("thunderbolt: Runtime resume USB4 port when retimers are scanned")
Cc: stable@vger.kernel.org
Signed-off-by: Utkarsh Patel <utkarsh.h.patel@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/thunderbolt/retimer.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index 81252e31014a1..6ebe7a2886ec7 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -471,10 +471,9 @@ int tb_retimer_scan(struct tb_port *port, bool add)
break;
}
- if (!last_idx) {
- ret = 0;
+ ret = 0;
+ if (!last_idx)
goto out;
- }
/* Add on-board retimers if they do not exist already */
for (i = 1; i <= last_idx; i++) {
--
GitLab
From 827e0920dbfb0d92416e56081d70745597403446 Mon Sep 17 00:00:00 2001
From: Benedikt Niedermayr <benedikt.niedermayr@siemens.com>
Date: Fri, 9 Dec 2022 12:28:28 +0100
Subject: [PATCH 0082/1167] memory: omap-gpmc: fix wait pin validation
This bug has been introduced after switching from -1 to UINT_MAX
for GPMC_WAITPIN_INVALID.
The bug leads to an error when the optional gpmc,wait-pin
dt-property is not used:
...
gpmc_cs_program_settings: invalid wait-pin (-1)
...
Signed-off-by: Benedikt Niedermayr <benedikt.niedermayr@siemens.com>
Fixes: 8dd7e4af5853 ("memory: omap-gpmc: fix coverity issue "Control flow issues"")
Acked-by: Roger Quadros <rogerq@kernel.org>
Tested-by: Tony Lindgren <tony@atomide.com>
Link: https://lore.kernel.org/r/20221209112828.581491-1-benedikt.niedermayr@siemens.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
drivers/memory/omap-gpmc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 57d9f91fe89bf..d78f73db37c88 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -1918,7 +1918,8 @@ int gpmc_cs_program_settings(int cs, struct gpmc_settings *p)
}
}
- if (p->wait_pin > gpmc_nr_waitpins) {
+ if (p->wait_pin != GPMC_WAITPIN_INVALID &&
+ p->wait_pin > gpmc_nr_waitpins) {
pr_err("%s: invalid wait-pin (%d)\n", __func__, p->wait_pin);
return -EINVAL;
}
--
GitLab
From ef86b2c2807f41c045e5534d8513a8b83f63bc39 Mon Sep 17 00:00:00 2001
From: Ashish Mhetre <amhetre@nvidia.com>
Date: Fri, 25 Nov 2022 09:37:52 +0530
Subject: [PATCH 0083/1167] memory: tegra: Remove clients SID override
programming
On newer Tegra releases, early boot SID override programming and SID
override programming during resume is handled by bootloader.
In the function tegra186_mc_program_sid() which is getting removed, SID
override register of all clients is written without checking if secure
firmware has allowed write on it or not. If write is disabled by secure
firmware then it can lead to errors coming from secure firmware and hang
in kernel boot.
Also, SID override is programmed on-demand during probe_finalize() call
of IOMMU which is done in tegra186_mc_client_sid_override() in this same
file. This function does it correctly by checking if write is permitted
on SID override register. It also checks if SID override register is
already written with correct value and skips re-writing it in that case.
Fixes: 393d66fd2cac ("memory: tegra: Implement SID override programming")
Signed-off-by: Ashish Mhetre <amhetre@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20221125040752.12627-1-amhetre@nvidia.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
drivers/memory/tegra/tegra186.c | 36 ---------------------------------
1 file changed, 36 deletions(-)
diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c
index 62477e592bf5f..7bb73f06fad3e 100644
--- a/drivers/memory/tegra/tegra186.c
+++ b/drivers/memory/tegra/tegra186.c
@@ -22,32 +22,6 @@
#define MC_SID_STREAMID_SECURITY_WRITE_ACCESS_DISABLED BIT(16)
#define MC_SID_STREAMID_SECURITY_OVERRIDE BIT(8)
-static void tegra186_mc_program_sid(struct tegra_mc *mc)
-{
- unsigned int i;
-
- for (i = 0; i < mc->soc->num_clients; i++) {
- const struct tegra_mc_client *client = &mc->soc->clients[i];
- u32 override, security;
-
- override = readl(mc->regs + client->regs.sid.override);
- security = readl(mc->regs + client->regs.sid.security);
-
- dev_dbg(mc->dev, "client %s: override: %x security: %x\n",
- client->name, override, security);
-
- dev_dbg(mc->dev, "setting SID %u for %s\n", client->sid,
- client->name);
- writel(client->sid, mc->regs + client->regs.sid.override);
-
- override = readl(mc->regs + client->regs.sid.override);
- security = readl(mc->regs + client->regs.sid.security);
-
- dev_dbg(mc->dev, "client %s: override: %x security: %x\n",
- client->name, override, security);
- }
-}
-
static int tegra186_mc_probe(struct tegra_mc *mc)
{
struct platform_device *pdev = to_platform_device(mc->dev);
@@ -85,8 +59,6 @@ static int tegra186_mc_probe(struct tegra_mc *mc)
if (err < 0)
return err;
- tegra186_mc_program_sid(mc);
-
return 0;
}
@@ -95,13 +67,6 @@ static void tegra186_mc_remove(struct tegra_mc *mc)
of_platform_depopulate(mc->dev);
}
-static int tegra186_mc_resume(struct tegra_mc *mc)
-{
- tegra186_mc_program_sid(mc);
-
- return 0;
-}
-
#if IS_ENABLED(CONFIG_IOMMU_API)
static void tegra186_mc_client_sid_override(struct tegra_mc *mc,
const struct tegra_mc_client *client,
@@ -173,7 +138,6 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev)
const struct tegra_mc_ops tegra186_mc_ops = {
.probe = tegra186_mc_probe,
.remove = tegra186_mc_remove,
- .resume = tegra186_mc_resume,
.probe_device = tegra186_mc_probe_device,
.handle_irq = tegra30_mc_handle_irq,
};
--
GitLab
From 340cb392a038cf70540a4cdf2e98a247c66b6df4 Mon Sep 17 00:00:00 2001
From: Gaosheng Cui <cuigaosheng1@huawei.com>
Date: Fri, 25 Nov 2022 15:37:57 +0800
Subject: [PATCH 0084/1167] memory: atmel-sdramc: Fix missing
clk_disable_unprepare in atmel_ramc_probe()
The clk_disable_unprepare() should be called in the error handling
of caps->has_mpddr_clk, fix it by replacing devm_clk_get and
clk_prepare_enable by devm_clk_get_enabled.
Fixes: e81b6abebc87 ("memory: add a driver for atmel ram controllers")
Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Link: https://lore.kernel.org/r/20221125073757.3535219-1-cuigaosheng1@huawei.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
drivers/memory/atmel-sdramc.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/memory/atmel-sdramc.c b/drivers/memory/atmel-sdramc.c
index 9c49d00c2a966..ea6e9e1eaf046 100644
--- a/drivers/memory/atmel-sdramc.c
+++ b/drivers/memory/atmel-sdramc.c
@@ -47,19 +47,17 @@ static int atmel_ramc_probe(struct platform_device *pdev)
caps = of_device_get_match_data(&pdev->dev);
if (caps->has_ddrck) {
- clk = devm_clk_get(&pdev->dev, "ddrck");
+ clk = devm_clk_get_enabled(&pdev->dev, "ddrck");
if (IS_ERR(clk))
return PTR_ERR(clk);
- clk_prepare_enable(clk);
}
if (caps->has_mpddr_clk) {
- clk = devm_clk_get(&pdev->dev, "mpddr");
+ clk = devm_clk_get_enabled(&pdev->dev, "mpddr");
if (IS_ERR(clk)) {
pr_err("AT91 RAMC: couldn't get mpddr clock\n");
return PTR_ERR(clk);
}
- clk_prepare_enable(clk);
}
return 0;
--
GitLab
From cb8fd6f75775165390ededea8799b60d93d9fe3e Mon Sep 17 00:00:00 2001
From: Gaosheng Cui <cuigaosheng1@huawei.com>
Date: Sat, 26 Nov 2022 12:49:11 +0800
Subject: [PATCH 0085/1167] memory: mvebu-devbus: Fix missing
clk_disable_unprepare in mvebu_devbus_probe()
The clk_disable_unprepare() should be called in the error handling
of devbus_get_timing_params() and of_platform_populate(), fix it by
replacing devm_clk_get and clk_prepare_enable by devm_clk_get_enabled.
Fixes: e81b6abebc87 ("memory: add a driver for atmel ram controllers")
Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Link: https://lore.kernel.org/r/20221126044911.7226-1-cuigaosheng1@huawei.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
drivers/memory/mvebu-devbus.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c
index 8450638e86700..efc6c08db2b70 100644
--- a/drivers/memory/mvebu-devbus.c
+++ b/drivers/memory/mvebu-devbus.c
@@ -280,10 +280,9 @@ static int mvebu_devbus_probe(struct platform_device *pdev)
if (IS_ERR(devbus->base))
return PTR_ERR(devbus->base);
- clk = devm_clk_get(&pdev->dev, NULL);
+ clk = devm_clk_get_enabled(&pdev->dev, NULL);
if (IS_ERR(clk))
return PTR_ERR(clk);
- clk_prepare_enable(clk);
/*
* Obtain clock period in picoseconds,
--
GitLab
From ad75bd85b1db69c97eefea07b375567821f6ef58 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 13 Dec 2022 13:29:43 +0100
Subject: [PATCH 0086/1167] platform/x86: sony-laptop: Don't turn off 0x153
keyboard backlight during probe
The 0x153 version of the kbd backlight control SNC handle has no separate
address to probe if the backlight is there.
This turns the probe call into a set keyboard backlight call with a value
of 0 turning off the keyboard backlight.
Skip probing when there is no separate probe address to avoid this.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=1583752
Fixes: 800f20170dcf ("Keyboard backlight control for some Vaio Fit models")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Mattia Dongili <malattia@linux.it>
Link: https://lore.kernel.org/r/20221213122943.11123-1-hdegoede@redhat.com
---
drivers/platform/x86/sony-laptop.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 7156ae2ad1962..537d6a2d0781b 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -1887,14 +1887,21 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd,
break;
}
- ret = sony_call_snc_handle(handle, probe_base, &result);
- if (ret)
- return ret;
+ /*
+ * Only probe if there is a separate probe_base, otherwise the probe call
+ * is equivalent to __sony_nc_kbd_backlight_mode_set(0), resulting in
+ * the keyboard backlight being turned off.
+ */
+ if (probe_base) {
+ ret = sony_call_snc_handle(handle, probe_base, &result);
+ if (ret)
+ return ret;
- if ((handle == 0x0137 && !(result & 0x02)) ||
- !(result & 0x01)) {
- dprintk("no backlight keyboard found\n");
- return 0;
+ if ((handle == 0x0137 && !(result & 0x02)) ||
+ !(result & 0x01)) {
+ dprintk("no backlight keyboard found\n");
+ return 0;
+ }
}
kbdbl_ctl = kzalloc(sizeof(*kbdbl_ctl), GFP_KERNEL);
--
GitLab
From f4b7f8febd4d9b615fbec2a06bf352b9c3729b11 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 15 Dec 2022 16:43:57 +0100
Subject: [PATCH 0087/1167] platform/x86: ideapad-laptop: Add Legion 5 15ARH05
DMI id to set_fn_lock_led_list[]
The Lenovo Legion 5 15ARH05 needs ideapad-laptop to call SALS_FNLOCK_ON /
SALS_FNLOCK_OFF on Fn-lock state change to get the LED in the Fn key to
correctly reflect the Fn-lock state.
Add a DMI match for the Legion 5 15ARH05 to the set_fn_lock_led_list[]
table for this.
Fixes: 81a5603a0f50 ("platform/x86: ideapad-laptop: Fix interrupt storm on fn-lock toggle on some Yoga laptops")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20221215154357.123876-1-hdegoede@redhat.com
---
drivers/platform/x86/ideapad-laptop.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 435d2d3d903b0..0eb5bfdd823a1 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -1621,6 +1621,12 @@ static const struct dmi_system_id set_fn_lock_led_list[] = {
DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion R7000P2020H"),
}
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion 5 15ARH05"),
+ }
+ },
{}
};
--
GitLab
From b1e9c223736b1471287f0ac46a368676c3bd7727 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Sun, 25 Dec 2022 09:37:12 +0100
Subject: [PATCH 0088/1167] spi: mediatek: Enable irq before the spi
registration
If the irq is enabled after the spi si registered, there can be a race
with the initialization of the devices on the spi bus.
Eg:
mtk-spi 1100a000.spi: spi-mem transfer timeout
spi-nor: probe of spi0.0 failed with error -110
Unable to handle kernel NULL pointer dereference at virtual address
0000000000000010
...
Call trace:
mtk_spi_can_dma+0x0/0x2c
Fixes: c6f7874687f7 ("spi: mediatek: Enable irq when pdata is ready")
Reported-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Tested-by: Daniel Golle <daniel@makrotopia.org>
Link: https://lore.kernel.org/r/20221225-mtk-spi-fixes-v1-0-bb6c14c232f8@chromium.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi-mt65xx.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 6de8360e5c2a9..9eab6c20dbc56 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -1253,6 +1253,11 @@ static int mtk_spi_probe(struct platform_device *pdev)
dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
+ IRQF_TRIGGER_NONE, dev_name(dev), master);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to register irq\n");
+
pm_runtime_enable(dev);
ret = devm_spi_register_master(dev, master);
@@ -1261,13 +1266,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
return dev_err_probe(dev, ret, "failed to register master\n");
}
- ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
- IRQF_TRIGGER_NONE, dev_name(dev), master);
- if (ret) {
- pm_runtime_disable(dev);
- return dev_err_probe(dev, ret, "failed to register irq\n");
- }
-
return 0;
}
--
GitLab
From ee4e530bdde29a69c58656a919545251a782674e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 21 Nov 2022 09:50:57 +0100
Subject: [PATCH 0089/1167] arm64: dts: qcom: sc8280xp: fix primary USB-DP PHY
reset
The vendor kernel is using the GCC_USB4_DP_PHY_PRIM_BCR and
GCC_USB4_1_DP_PHY_PRIM_BCR resets for the USB4-USB3-DP QMP PHYs.
Update the primary USB-DP PHY node to match.
Fixes: 152d1faf1e2f ("arm64: dts: qcom: add SC8280XP platform")
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221121085058.31213-15-johan+linaro@kernel.org
---
arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
index 109c9d2b684d1..ad71e68384da5 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
@@ -1689,7 +1689,7 @@ usb_0_qmpphy: phy-wrapper@88ec000 {
clock-names = "aux", "ref_clk_src", "ref", "com_aux";
resets = <&gcc GCC_USB3_PHY_PRIM_BCR>,
- <&gcc GCC_USB3_DP_PHY_PRIM_BCR>;
+ <&gcc GCC_USB4_DP_PHY_PRIM_BCR>;
reset-names = "phy", "common";
power-domains = <&gcc USB30_PRIM_GDSC>;
--
GitLab
From 721c0d68c0f882b6358102b52961ff6eb601839c Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 21 Nov 2022 09:50:58 +0100
Subject: [PATCH 0090/1167] arm64: dts: qcom: sc8280xp: fix USB-DP PHY nodes
Update the USB4-USB3-DP QMP PHY nodes to match the new binding which
specifically includes the missing register regions (e.g. DP_PHY) and
allows for supporting DisplayPort Alternate Mode.
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221121085058.31213-16-johan+linaro@kernel.org
---
arch/arm64/boot/dts/qcom/sc8280xp.dtsi | 77 ++++++++------------------
1 file changed, 23 insertions(+), 54 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
index ad71e68384da5..71cf81a8eb4da 100644
--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
@@ -10,6 +10,7 @@
#include <dt-bindings/interconnect/qcom,sc8280xp.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/mailbox/qcom-ipcc.h>
+#include <dt-bindings/phy/phy-qcom-qmp.h>
#include <dt-bindings/power/qcom-rpmpd.h>
#include <dt-bindings/soc/qcom,rpmh-rsc.h>
#include <dt-bindings/thermal/thermal.h>
@@ -762,7 +763,7 @@ gcc: clock-controller@100000 {
<0>,
<0>,
<0>,
- <&usb_0_ssphy>,
+ <&usb_0_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
<0>,
<0>,
<0>,
@@ -770,7 +771,7 @@ gcc: clock-controller@100000 {
<0>,
<0>,
<0>,
- <&usb_1_ssphy>,
+ <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>,
<0>,
<0>,
<0>,
@@ -1673,42 +1674,26 @@ IPCC_MPROC_SIGNAL_GLINK_QMP
};
};
- usb_0_qmpphy: phy-wrapper@88ec000 {
+ usb_0_qmpphy: phy@88eb000 {
compatible = "qcom,sc8280xp-qmp-usb43dp-phy";
- reg = <0 0x088ec000 0 0x1e4>,
- <0 0x088eb000 0 0x40>,
- <0 0x088ed000 0 0x1c8>;
- #address-cells = <2>;
- #size-cells = <2>;
- ranges;
+ reg = <0 0x088eb000 0 0x4000>;
clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
<&gcc GCC_USB4_EUD_CLKREF_CLK>,
- <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>;
- clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+ <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>,
+ <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
+ clock-names = "aux", "ref", "com_aux", "usb3_pipe";
+
+ power-domains = <&gcc USB30_PRIM_GDSC>;
resets = <&gcc GCC_USB3_PHY_PRIM_BCR>,
<&gcc GCC_USB4_DP_PHY_PRIM_BCR>;
reset-names = "phy", "common";
- power-domains = <&gcc USB30_PRIM_GDSC>;
+ #clock-cells = <1>;
+ #phy-cells = <1>;
status = "disabled";
-
- usb_0_ssphy: usb3-phy@88eb400 {
- reg = <0 0x088eb400 0 0x100>,
- <0 0x088eb600 0 0x3ec>,
- <0 0x088ec400 0 0x364>,
- <0 0x088eba00 0 0x100>,
- <0 0x088ebc00 0 0x3ec>,
- <0 0x088ec200 0 0x18>;
- #phy-cells = <0>;
- #clock-cells = <0>;
- clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>;
- clock-names = "pipe0";
- clock-output-names = "usb0_phy_pipe_clk_src";
- };
};
usb_1_hsphy: phy@8902000 {
@@ -1725,42 +1710,26 @@ usb_1_hsphy: phy@8902000 {
status = "disabled";
};
- usb_1_qmpphy: phy-wrapper@8904000 {
+ usb_1_qmpphy: phy@8903000 {
compatible = "qcom,sc8280xp-qmp-usb43dp-phy";
- reg = <0 0x08904000 0 0x1e4>,
- <0 0x08903000 0 0x40>,
- <0 0x08905000 0 0x1c8>;
- #address-cells = <2>;
- #size-cells = <2>;
- ranges;
+ reg = <0 0x08903000 0 0x4000>;
clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
<&gcc GCC_USB4_CLKREF_CLK>,
- <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>;
- clock-names = "aux", "ref_clk_src", "ref", "com_aux";
+ <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>,
+ <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
+ clock-names = "aux", "ref", "com_aux", "usb3_pipe";
+
+ power-domains = <&gcc USB30_SEC_GDSC>;
resets = <&gcc GCC_USB3_PHY_SEC_BCR>,
<&gcc GCC_USB4_1_DP_PHY_PRIM_BCR>;
reset-names = "phy", "common";
- power-domains = <&gcc USB30_SEC_GDSC>;
+ #clock-cells = <1>;
+ #phy-cells = <1>;
status = "disabled";
-
- usb_1_ssphy: usb3-phy@8903400 {
- reg = <0 0x08903400 0 0x100>,
- <0 0x08903600 0 0x3ec>,
- <0 0x08904400 0 0x364>,
- <0 0x08903a00 0 0x100>,
- <0 0x08903c00 0 0x3ec>,
- <0 0x08904200 0 0x18>;
- #phy-cells = <0>;
- #clock-cells = <0>;
- clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>;
- clock-names = "pipe0";
- clock-output-names = "usb1_phy_pipe_clk_src";
- };
};
pmu@9091000 {
@@ -1910,7 +1879,7 @@ usb_0_dwc3: usb@a600000 {
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>;
iommus = <&apps_smmu 0x820 0x0>;
- phys = <&usb_0_hsphy>, <&usb_0_ssphy>;
+ phys = <&usb_0_hsphy>, <&usb_0_qmpphy QMP_USB43DP_USB3_PHY>;
phy-names = "usb2-phy", "usb3-phy";
};
};
@@ -1964,7 +1933,7 @@ usb_1_dwc3: usb@a800000 {
reg = <0 0x0a800000 0 0xcd00>;
interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>;
iommus = <&apps_smmu 0x860 0x0>;
- phys = <&usb_1_hsphy>, <&usb_1_ssphy>;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
phy-names = "usb2-phy", "usb3-phy";
};
};
--
GitLab
From 9d8b5376cc2848ca22314fdec9a7a45b1bf69189 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 25 Nov 2022 16:04:01 -0800
Subject: [PATCH 0091/1167] fbdev: make offb driver tristate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Make the offb (Open Firmware frame buffer) driver tristate,
i.e., so that it can be built as a loadable module.
However, it still depends on the setting of DRM_OFDRM
so that both of these drivers cannot be builtin at the same time
nor can one be builtin and the other one a loadable module.
Build-tested successfully with all combination of DRM_OFDRM and FB_OF.
This fixes a build issue that Michal reported when FB_OF=y and
DRM_OFDRM=m:
powerpc64-linux-ld: drivers/video/fbdev/offb.o:(.data.rel.ro+0x58): undefined reference to `cfb_fillrect'
powerpc64-linux-ld: drivers/video/fbdev/offb.o:(.data.rel.ro+0x60): undefined reference to `cfb_copyarea'
powerpc64-linux-ld: drivers/video/fbdev/offb.o:(.data.rel.ro+0x68): undefined reference to `cfb_imageblit'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Michal Suchánek <msuchanek@suse.de>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Helge Deller <deller@gmx.de>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
drivers/video/fbdev/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index df6e09f7d2422..b2bed599e6c6e 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -456,8 +456,8 @@ config FB_ATARI
chipset found in Ataris.
config FB_OF
- bool "Open Firmware frame buffer device support"
- depends on (FB = y) && PPC && (!PPC_PSERIES || PCI)
+ tristate "Open Firmware frame buffer device support"
+ depends on FB && PPC && (!PPC_PSERIES || PCI)
depends on !DRM_OFDRM
select APERTURE_HELPERS
select FB_CFB_FILLRECT
--
GitLab
From 1bdeb321d1f856346fe0078af09c9e7ffbd2ca7a Mon Sep 17 00:00:00 2001
From: Yang Li <yang.lee@linux.alibaba.com>
Date: Tue, 15 Nov 2022 09:49:02 +0800
Subject: [PATCH 0092/1167] drm/msm/dpu: Fix some kernel-doc comments
Make the description of @init to @p in dpu_encoder_phys_wb_init()
and remove @wb_roi in dpu_encoder_phys_wb_setup_fb() to clear the below
warnings:
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c:139: warning: Excess function parameter 'wb_roi' description in 'dpu_encoder_phys_wb_setup_fb'
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c:699: warning: Function parameter or member 'p' not described in 'dpu_encoder_phys_wb_init'
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c:699: warning: Excess function parameter 'init' description in 'dpu_encoder_phys_wb_init'
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=3067
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Fixes: d7d0e73f7de3 ("drm/msm/dpu: introduce the dpu_encoder_phys_* for writeback")
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/511605/
Link: https://lore.kernel.org/r/20221115014902.45240-1-yang.lee@linux.alibaba.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
index 7cbcef6efe171..62f6ff6abf410 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
@@ -132,7 +132,6 @@ static void dpu_encoder_phys_wb_set_qos(struct dpu_encoder_phys *phys_enc)
* dpu_encoder_phys_wb_setup_fb - setup output framebuffer
* @phys_enc: Pointer to physical encoder
* @fb: Pointer to output framebuffer
- * @wb_roi: Pointer to output region of interest
*/
static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc,
struct drm_framebuffer *fb)
@@ -692,7 +691,7 @@ static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops)
/**
* dpu_encoder_phys_wb_init - initialize writeback encoder
- * @init: Pointer to init info structure with initialization params
+ * @p: Pointer to init info structure with initialization params
*/
struct dpu_encoder_phys *dpu_encoder_phys_wb_init(
struct dpu_enc_phys_init_params *p)
--
GitLab
From a2117773c839a8439a3771e0c040b5c505b083a7 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 30 Nov 2022 14:58:07 +0100
Subject: [PATCH 0093/1167] dt-bindings: msm/dsi: Don't require vcca-supply on
14nm PHY
On some SoCs (hello SM6115) vcca-supply is not wired to any smd-rpm
or rpmh regulator, but instead powered by the VDD_MX line, which is
voted for in the DSI ctrl node.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Fixes: 8fc939e72ff8 ("dt-bindings: msm: dsi: add yaml schemas for DSI PHY bindings")
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/513555/
Link: https://lore.kernel.org/r/20221130135807.45028-1-konrad.dybcio@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml | 1 -
1 file changed, 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml
index 819de5ce0bc91..a43e11d3b00d2 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml
@@ -39,7 +39,6 @@ required:
- compatible
- reg
- reg-names
- - vcca-supply
unevaluatedProperties: false
--
GitLab
From ef11cb7a29c0e13031c968190ea8f86104e7fb6a Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Wed, 16 Nov 2022 17:32:18 +0100
Subject: [PATCH 0094/1167] dt-bindings: msm/dsi: Don't require vdds-supply on
10nm PHY
On some SoCs (hello SM6350) vdds-supply is not wired to any smd-rpm
or rpmh regulator, but instead powered by the VDD_MX/mx.lvl line,
which is voted for in the DSI ctrl node.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
Fixes: 8fc939e72ff8 ("dt-bindings: msm: dsi: add yaml schemas for DSI PHY bindings")
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/511889/
Link: https://lore.kernel.org/r/20221116163218.42449-1-konrad.dybcio@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml | 1 -
1 file changed, 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml
index d9ad8b659f58e..3ec466c3ab38b 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml
@@ -69,7 +69,6 @@ required:
- compatible
- reg
- reg-names
- - vdds-supply
unevaluatedProperties: false
--
GitLab
From e5266ca38294c6eba48f5c9cd3d0402d619d7c05 Mon Sep 17 00:00:00 2001
From: Adam Skladowski <a39.skl@gmail.com>
Date: Wed, 30 Nov 2022 21:09:39 +0100
Subject: [PATCH 0095/1167] dt-bindings: display: msm: Rename mdss node name in
example
Follow other YAMLs and replace mdss name into display-subystem.
Signed-off-by: Adam Skladowski <a39.skl@gmail.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Fixes: b93bdff44a85 ("dt-bindings: display/msm: add support for SM6115")
Fixes: 06097b13ef97 ("dt-bindings: display/msm: split dpu-qcm2290 into DPU and MDSS parts")
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/513585/
Link: https://lore.kernel.org/r/20221130200950.144618-2-a39.skl@gmail.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
.../devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml | 2 +-
.../devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
index d6f043a4b08d2..4795e13c7b597 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml
@@ -72,7 +72,7 @@ examples:
#include <dt-bindings/interconnect/qcom,qcm2290.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,qcm2290-mdss";
diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml
index a86d7f53fa84d..886858ef67000 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml
@@ -62,7 +62,7 @@ examples:
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,sm6115-mdss";
--
GitLab
From 45dac1352b55b1d8cb17f218936b2bc2bc1fb4ee Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Wed, 7 Dec 2022 10:59:22 +0400
Subject: [PATCH 0096/1167] drm/msm/dpu: Fix memory leak in
msm_mdss_parse_data_bus_icc_path
of_icc_get() alloc resources for path1, we should release it when not
need anymore. Early return when IS_ERR_OR_NULL(path0) may leak path1.
Defer getting path1 to fix this.
Fixes: b9364eed9232 ("drm/msm/dpu: Move min BW request and full BW disable back to mdss")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/514264/
Link: https://lore.kernel.org/r/20221207065922.2086368-1-linmq006@gmail.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/msm_mdss.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 86b28add1ffff..2527afef9c199 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -47,15 +47,17 @@ struct msm_mdss {
static int msm_mdss_parse_data_bus_icc_path(struct device *dev,
struct msm_mdss *msm_mdss)
{
- struct icc_path *path0 = of_icc_get(dev, "mdp0-mem");
- struct icc_path *path1 = of_icc_get(dev, "mdp1-mem");
+ struct icc_path *path0;
+ struct icc_path *path1;
+ path0 = of_icc_get(dev, "mdp0-mem");
if (IS_ERR_OR_NULL(path0))
return PTR_ERR_OR_ZERO(path0);
msm_mdss->path[0] = path0;
msm_mdss->num_paths = 1;
+ path1 = of_icc_get(dev, "mdp1-mem");
if (!IS_ERR_OR_NULL(path1)) {
msm_mdss->path[1] = path1;
msm_mdss->num_paths++;
--
GitLab
From 4164843261d28f86910a5c2727faddce066334c5 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 13 Dec 2022 07:15:33 +0100
Subject: [PATCH 0097/1167] drm/msm/hdmi: Fix the error handling path of
msm_hdmi_dev_probe()
If an error occurs after a successful msm_hdmi_get_phy() call, it must be
undone by a corresponding msm_hdmi_put_phy(), as already done in the
remove function.
Fixes: 437365464043 ("drm/msm/hdmi: move msm_hdmi_get_phy() to msm_hdmi_dev_probe()")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/514847/
Link: https://lore.kernel.org/r/b3f9da097851e2e42a40dc61458aa98c41c88d0d.1670741386.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/hdmi/hdmi.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 4d3fdc806befd..97372bb241d89 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -532,11 +532,19 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev)
ret = devm_pm_runtime_enable(&pdev->dev);
if (ret)
- return ret;
+ goto err_put_phy;
platform_set_drvdata(pdev, hdmi);
- return component_add(&pdev->dev, &msm_hdmi_ops);
+ ret = component_add(&pdev->dev, &msm_hdmi_ops);
+ if (ret)
+ goto err_put_phy;
+
+ return 0;
+
+err_put_phy:
+ msm_hdmi_put_phy(hdmi);
+ return ret;
}
static int msm_hdmi_dev_remove(struct platform_device *pdev)
--
GitLab
From 22c7e1a0fa45cd7d028d6b4117161fd0e3427fe0 Mon Sep 17 00:00:00 2001
From: Dominik Kobinski <dominikkobinski314@gmail.com>
Date: Sun, 11 Dec 2022 11:05:01 +0100
Subject: [PATCH 0098/1167] arm64: dts: msm8992-bullhead: add memory hole
region
Add region for memory hole present on bullhead in order to
fix a reboot issue on recent kernels
Reported-by: Petr Vorel <petr.vorel@gmail.com>
Signed-off-by: Dominik Kobinski <dominikkobinski314@gmail.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Tested-by: Petr Vorel <petr.vorel@gmail.com>
Reviewed-by: Petr Vorel <petr.vorel@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221211100501.82323-1-dominikkobinski314@gmail.com
---
arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi
index 87c90e93667f7..79de9cc395c4c 100644
--- a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi
@@ -3,6 +3,7 @@
* Copyright (c) 2015, LGE Inc. All rights reserved.
* Copyright (c) 2016, The Linux Foundation. All rights reserved.
* Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com>
+ * Copyright (c) 2022, Dominik Kobinski <dominikkobinski314@gmail.com>
*/
/dts-v1/;
@@ -51,6 +52,11 @@ cont_splash_mem: memory@3400000 {
reg = <0 0x03400000 0 0x1200000>;
no-map;
};
+
+ removed_region: reserved@5000000 {
+ reg = <0 0x05000000 0 0x2200000>;
+ no-map;
+ };
};
};
--
GitLab
From 25e8ac233d24051e2c4ff64c34f60609b0988568 Mon Sep 17 00:00:00 2001
From: Vijaya Krishna Nivarthi <quic_vnivarth@quicinc.com>
Date: Fri, 16 Dec 2022 23:08:13 +0530
Subject: [PATCH 0099/1167] dmaengine: qcom: gpi: Set link_rx bit on GO TRE for
rx operation
Rx operation on SPI GSI DMA is currently not working.
As per GSI spec, link_rx bit is to be set on GO TRE on tx
channel whenever there is going to be a DMA TRE on rx
channel. This is currently set for duplex operation only.
Set the bit for rx operation as well.
This is part of changes required to bring up Rx.
Fixes: 94b8f0e58fa1 ("dmaengine: qcom: gpi: set chain and link flag for duplex")
Signed-off-by: Vijaya Krishna Nivarthi <quic_vnivarth@quicinc.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/1671212293-14767-1-git-send-email-quic_vnivarth@quicinc.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/qcom/gpi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c
index 061add8322951..59a36cbf9b5f7 100644
--- a/drivers/dma/qcom/gpi.c
+++ b/drivers/dma/qcom/gpi.c
@@ -1756,6 +1756,7 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc,
tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE);
if (spi->cmd == SPI_RX) {
tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB);
+ tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK);
} else if (spi->cmd == SPI_TX) {
tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN);
} else { /* SPI_DUPLEX */
--
GitLab
From 8d8cf163c8d8c93bccf0c70a133309693af9bf61 Mon Sep 17 00:00:00 2001
From: Xu Panda <xu.panda@zte.com.cn>
Date: Wed, 28 Dec 2022 09:40:01 +0800
Subject: [PATCH 0100/1167] fbdev: omapfb: use strscpy() to instead of
strncpy()
The implementation of strscpy() is more robust and safer.
That's now the recommended way to copy NUL-terminated strings.
Signed-off-by: Xu Panda <xu.panda@zte.com.cn>
Signed-off-by: Yang Yang <yang.yang29@zte.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
drivers/video/fbdev/omap/omapfb_main.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index 17cda57656838..1f3df2055ff0d 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1447,7 +1447,7 @@ static int fbinfo_init(struct omapfb_device *fbdev, struct fb_info *info)
info->fbops = &omapfb_ops;
info->flags = FBINFO_FLAG_DEFAULT;
- strncpy(fix->id, MODULE_NAME, sizeof(fix->id));
+ strscpy(fix->id, MODULE_NAME, sizeof(fix->id));
info->pseudo_palette = fbdev->pseudo_palette;
@@ -1573,8 +1573,7 @@ static int omapfb_find_ctrl(struct omapfb_device *fbdev)
fbdev->ctrl = NULL;
- strncpy(name, conf->lcd.ctrl_name, sizeof(name) - 1);
- name[sizeof(name) - 1] = '\0';
+ strscpy(name, conf->lcd.ctrl_name, sizeof(name));
if (strcmp(name, "internal") == 0) {
fbdev->ctrl = fbdev->int_ctrl;
--
GitLab
From 6b90032c73405cd4da29ab914df11fd1be960b99 Mon Sep 17 00:00:00 2001
From: Xu Panda <xu.panda@zte.com.cn>
Date: Wed, 28 Dec 2022 09:44:11 +0800
Subject: [PATCH 0101/1167] fbdev: atyfb: use strscpy() to instead of strncpy()
The implementation of strscpy() is more robust and safer.
That's now the recommended way to copy NUL-terminated strings.
Signed-off-by: Xu Panda <xu.panda@zte.com.cn>
Signed-off-by: Yang Yang <yang.yang29@zte.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
drivers/video/fbdev/aty/atyfb_base.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index 0ccf5d401ecbc..d59215a4992e0 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -3192,8 +3192,7 @@ static void aty_init_lcd(struct atyfb_par *par, u32 bios_base)
* which we print to the screen.
*/
id = *(u8 *)par->lcd_table;
- strncpy(model, (char *)par->lcd_table+1, 24);
- model[23] = 0;
+ strscpy(model, (char *)par->lcd_table+1, sizeof(model));
width = par->lcd_width = *(u16 *)(par->lcd_table+25);
height = par->lcd_height = *(u16 *)(par->lcd_table+27);
--
GitLab
From 0e50d999903c009b6a9cd2277c82d6798d982e31 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 24 Dec 2022 14:49:00 +0000
Subject: [PATCH 0102/1167] rxrpc: Fix a couple of potential use-after-frees
At the end of rxrpc_recvmsg(), if a call is found, the call is put and then
a trace line is emitted referencing that call in a couple of places - but
the call may have been deallocated by the time those traces happen.
Fix this by stashing the call debug_id in a variable and passing that to
the tracepoint rather than the call pointer.
Fixes: 849979051cbc ("rxrpc: Add a tracepoint to follow what recvmsg does")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/trace/events/rxrpc.h | 6 +++---
net/rxrpc/recvmsg.c | 14 ++++++++------
2 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index c6cfed00d0c6c..5f9dd73895364 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1062,10 +1062,10 @@ TRACE_EVENT(rxrpc_receive,
);
TRACE_EVENT(rxrpc_recvmsg,
- TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why,
+ TP_PROTO(unsigned int call_debug_id, enum rxrpc_recvmsg_trace why,
int ret),
- TP_ARGS(call, why, ret),
+ TP_ARGS(call_debug_id, why, ret),
TP_STRUCT__entry(
__field(unsigned int, call )
@@ -1074,7 +1074,7 @@ TRACE_EVENT(rxrpc_recvmsg,
),
TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
+ __entry->call = call_debug_id;
__entry->why = why;
__entry->ret = ret;
),
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 36b25d003cf00..6ebd6440a2b7c 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -388,13 +388,14 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct list_head *l;
+ unsigned int call_debug_id = 0;
size_t copied = 0;
long timeo;
int ret;
DEFINE_WAIT(wait);
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_enter, 0);
if (flags & (MSG_OOB | MSG_TRUNC))
return -EOPNOTSUPP;
@@ -431,7 +432,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
if (list_empty(&rx->recvmsg_q)) {
if (signal_pending(current))
goto wait_interrupted;
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0);
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(&rx->sk), &wait);
@@ -450,7 +451,8 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
rxrpc_get_call(call, rxrpc_call_get_recvmsg);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0);
+ call_debug_id = call->debug_id;
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0);
/* We're going to drop the socket lock, so we need to lock the call
* against interference by sendmsg.
@@ -531,7 +533,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
error_unlock_call:
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
error_requeue_call:
@@ -539,14 +541,14 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
write_lock(&rx->recvmsg_lock);
list_add(&call->recvmsg_link, &rx->recvmsg_q);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0);
} else {
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
}
error_no_call:
release_sock(&rx->sk);
error_trace:
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
wait_interrupted:
--
GitLab
From f4ef681115f822daf7f36f8b1892d9f1e1a26fbf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 22 Dec 2022 11:22:47 -0800
Subject: [PATCH 0103/1167] docs: netdev: reshuffle sections in prep for
de-FAQization
Subsequent changes will reformat the doc away from FAQ.
To make that more readable perform the pure section moves now.
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/process/maintainer-netdev.rst | 186 ++++++++++----------
1 file changed, 93 insertions(+), 93 deletions(-)
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 1fa5ab8754d35..8f22f8a3dcd10 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -44,17 +44,6 @@ for the future release. You can find the trees here:
- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
-How do I indicate which tree (net vs. net-next) my patch should be in?
-----------------------------------------------------------------------
-To help maintainers and CI bots you should explicitly mark which tree
-your patch is targeting. Assuming that you use git, use the prefix
-flag::
-
- git format-patch --subject-prefix='PATCH net-next' start..finish
-
-Use ``net`` instead of ``net-next`` (always lower case) in the above for
-bug-fix ``net`` content.
-
How often do changes from these trees make it to the mainline Linus tree?
-------------------------------------------------------------------------
To understand this, you need to know a bit of background information on
@@ -127,15 +116,6 @@ patch. Patches are indexed by the ``Message-ID`` header of the emails
which carried them so if you have trouble finding your patch append
the value of ``Message-ID`` to the URL above.
-How long before my patch is accepted?
--------------------------------------
-Generally speaking, the patches get triaged quickly (in less than
-48h). But be patient, if your patch is active in patchwork (i.e. it's
-listed on the project's patch list) the chances it was missed are close to zero.
-Asking the maintainer for status updates on your
-patch is a good way to ensure your patch is ignored or pushed to the
-bottom of the priority list.
-
Should I directly update patchwork state of my own patches?
-----------------------------------------------------------
It may be tempting to help the maintainers and update the state of your
@@ -145,19 +125,14 @@ it to the maintainer to figure out what is the most recent and current
version that should be applied. If there is any doubt, the maintainer
will reply and ask what should be done.
-How do I divide my work into patches?
+How long before my patch is accepted?
-------------------------------------
-
-Put yourself in the shoes of the reviewer. Each patch is read separately
-and therefore should constitute a comprehensible step towards your stated
-goal.
-
-Avoid sending series longer than 15 patches. Larger series takes longer
-to review as reviewers will defer looking at it until they find a large
-chunk of time. A small series can be reviewed in a short time, so Maintainers
-just do it. As a result, a sequence of smaller series gets merged quicker and
-with better review coverage. Re-posting large series also increases the mailing
-list traffic.
+Generally speaking, the patches get triaged quickly (in less than
+48h). But be patient, if your patch is active in patchwork (i.e. it's
+listed on the project's patch list) the chances it was missed are close to zero.
+Asking the maintainer for status updates on your
+patch is a good way to ensure your patch is ignored or pushed to the
+bottom of the priority list.
I made changes to only a few patches in a patch series should I resend only those changed?
------------------------------------------------------------------------------------------
@@ -165,17 +140,6 @@ No, please resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
that can be applied.
-I have received review feedback, when should I post a revised version of the patches?
--------------------------------------------------------------------------------------
-Allow at least 24 hours to pass between postings. This will ensure reviewers
-from all geographical locations have a chance to chime in. Do not wait
-too long (weeks) between postings either as it will make it harder for reviewers
-to recall all the context.
-
-Make sure you address all the feedback in your new posting. Do not post a new
-version of the code if the discussion about the previous version is still
-ongoing, unless directly instructed by a reviewer.
-
I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
----------------------------------------------------------------------------------------------------------------------------------------
There is no revert possible, once it is pushed out, it stays like that.
@@ -191,6 +155,82 @@ the case today. Please follow the standard stable rules in
:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
and make sure you include appropriate Fixes tags!
+I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
+---------------------------------------------------------------------------------------------------------------------------
+No. The current netdev maintainer has consistently requested that
+people use the mailing lists and not reach out directly. If you aren't
+OK with that, then perhaps consider mailing security@kernel.org or
+reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
+as possible alternative mechanisms.
+
+How do I post corresponding changes to user space components?
+-------------------------------------------------------------
+User space code exercising kernel features should be posted
+alongside kernel patches. This gives reviewers a chance to see
+how any new interface is used and how well it works.
+
+When user space tools reside in the kernel repo itself all changes
+should generally come as one series. If series becomes too large
+or the user space project is not reviewed on netdev include a link
+to a public repo where user space patches can be seen.
+
+In case user space tooling lives in a separate repository but is
+reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
+user space patches should form separate series (threads) when posted
+to the mailing list, e.g.::
+
+ [PATCH net-next 0/3] net: some feature cover letter
+ └─ [PATCH net-next 1/3] net: some feature prep
+ └─ [PATCH net-next 2/3] net: some feature do it
+ └─ [PATCH net-next 3/3] selftest: net: some feature
+
+ [PATCH iproute2-next] ip: add support for some feature
+
+Posting as one thread is discouraged because it confuses patchwork
+(as of patchwork 2.2.2).
+
+Any other tips to help ensure my net/net-next patch gets OK'd?
+--------------------------------------------------------------
+Attention to detail. Re-read your own work as if you were the
+reviewer. You can start with using ``checkpatch.pl``, perhaps even with
+the ``--strict`` flag. But do not be mindlessly robotic in doing so.
+If your change is a bug fix, make sure your commit log indicates the
+end-user visible symptom, the underlying reason as to why it happens,
+and then if necessary, explain why the fix proposed is the best way to
+get things done. Don't mangle whitespace, and as is common, don't
+mis-indent function arguments that span multiple lines. If it is your
+first patch, mail it to yourself so you can test apply it to an
+unpatched tree to confirm infrastructure didn't mangle it.
+
+Finally, go back and read
+:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
+to be sure you are not repeating some common mistake documented there.
+
+How do I indicate which tree (net vs. net-next) my patch should be in?
+----------------------------------------------------------------------
+To help maintainers and CI bots you should explicitly mark which tree
+your patch is targeting. Assuming that you use git, use the prefix
+flag::
+
+ git format-patch --subject-prefix='PATCH net-next' start..finish
+
+Use ``net`` instead of ``net-next`` (always lower case) in the above for
+bug-fix ``net`` content.
+
+How do I divide my work into patches?
+-------------------------------------
+
+Put yourself in the shoes of the reviewer. Each patch is read separately
+and therefore should constitute a comprehensible step towards your stated
+goal.
+
+Avoid sending series longer than 15 patches. Larger series takes longer
+to review as reviewers will defer looking at it until they find a large
+chunk of time. A small series can be reviewed in a short time, so Maintainers
+just do it. As a result, a sequence of smaller series gets merged quicker and
+with better review coverage. Re-posting large series also increases the mailing
+list traffic.
+
Is the comment style convention different for the networking content?
---------------------------------------------------------------------
Yes, in a largely trivial way. Instead of this::
@@ -224,13 +264,16 @@ I am working in existing code which uses non-standard formatting. Which formatti
Make your code follow the most recent guidelines, so that eventually all code
in the domain of netdev is in the preferred format.
-I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
----------------------------------------------------------------------------------------------------------------------------
-No. The current netdev maintainer has consistently requested that
-people use the mailing lists and not reach out directly. If you aren't
-OK with that, then perhaps consider mailing security@kernel.org or
-reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
-as possible alternative mechanisms.
+I have received review feedback, when should I post a revised version of the patches?
+-------------------------------------------------------------------------------------
+Allow at least 24 hours to pass between postings. This will ensure reviewers
+from all geographical locations have a chance to chime in. Do not wait
+too long (weeks) between postings either as it will make it harder for reviewers
+to recall all the context.
+
+Make sure you address all the feedback in your new posting. Do not post a new
+version of the code if the discussion about the previous version is still
+ongoing, unless directly instructed by a reviewer.
What level of testing is expected before I submit my change?
------------------------------------------------------------
@@ -244,32 +287,6 @@ and the patch series contains a set of kernel selftest for
You are expected to test your changes on top of the relevant networking
tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
-How do I post corresponding changes to user space components?
--------------------------------------------------------------
-User space code exercising kernel features should be posted
-alongside kernel patches. This gives reviewers a chance to see
-how any new interface is used and how well it works.
-
-When user space tools reside in the kernel repo itself all changes
-should generally come as one series. If series becomes too large
-or the user space project is not reviewed on netdev include a link
-to a public repo where user space patches can be seen.
-
-In case user space tooling lives in a separate repository but is
-reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
-user space patches should form separate series (threads) when posted
-to the mailing list, e.g.::
-
- [PATCH net-next 0/3] net: some feature cover letter
- └─ [PATCH net-next 1/3] net: some feature prep
- └─ [PATCH net-next 2/3] net: some feature do it
- └─ [PATCH net-next 3/3] selftest: net: some feature
-
- [PATCH iproute2-next] ip: add support for some feature
-
-Posting as one thread is discouraged because it confuses patchwork
-(as of patchwork 2.2.2).
-
Can I reproduce the checks from patchwork on my local machine?
--------------------------------------------------------------
@@ -303,23 +320,6 @@ it has a real, in-tree user. Mock-ups and tests based on ``netdevsim`` are
strongly encouraged when adding new APIs, but ``netdevsim`` in itself
is **not** considered a use case/user.
-Any other tips to help ensure my net/net-next patch gets OK'd?
---------------------------------------------------------------
-Attention to detail. Re-read your own work as if you were the
-reviewer. You can start with using ``checkpatch.pl``, perhaps even with
-the ``--strict`` flag. But do not be mindlessly robotic in doing so.
-If your change is a bug fix, make sure your commit log indicates the
-end-user visible symptom, the underlying reason as to why it happens,
-and then if necessary, explain why the fix proposed is the best way to
-get things done. Don't mangle whitespace, and as is common, don't
-mis-indent function arguments that span multiple lines. If it is your
-first patch, mail it to yourself so you can test apply it to an
-unpatched tree to confirm infrastructure didn't mangle it.
-
-Finally, go back and read
-:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
-to be sure you are not repeating some common mistake documented there.
-
My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
---------------------------------------------------------------------------------------------------------
--
GitLab
From ff249be5cca9f982e58936847ba6c30104abbcad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 22 Dec 2022 11:22:48 -0800
Subject: [PATCH 0104/1167] docs: netdev: convert to a non-FAQ document
The netdev-FAQ document has grown over the years to the point
where finding information in it is somewhat challenging.
The length of the questions prevents readers from locating
content that's relevant at a glance.
Convert to a more standard documentation format with sections
and sub-sections rather than questions and answers.
The content edits are limited to what's necessary to change
the format, and very minor clarifications.
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
Documentation/process/maintainer-netdev.rst | 221 +++++++++++---------
1 file changed, 125 insertions(+), 96 deletions(-)
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 8f22f8a3dcd10..4a75686d35ab4 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -2,9 +2,9 @@
.. _netdev-FAQ:
-==========
-netdev FAQ
-==========
+=============================
+Networking subsystem (netdev)
+=============================
tl;dr
-----
@@ -15,14 +15,15 @@ tl;dr
- don't repost your patches within one 24h period
- reverse xmas tree
-What is netdev?
----------------
-It is a mailing list for all network-related Linux stuff. This
+netdev
+------
+
+netdev is a mailing list for all network-related Linux stuff. This
includes anything found under net/ (i.e. core code like IPv6) and
drivers/net (i.e. hardware specific drivers) in the Linux source tree.
Note that some subsystems (e.g. wireless drivers) which have a high
-volume of traffic have their own specific mailing lists.
+volume of traffic have their own specific mailing lists and trees.
The netdev list is managed (like many other Linux mailing lists) through
VGER (http://vger.kernel.org/) with archives available at
@@ -32,21 +33,10 @@ Aside from subsystems like those mentioned above, all network-related
Linux development (i.e. RFC, review, comments, etc.) takes place on
netdev.
-How do the changes posted to netdev make their way into Linux?
---------------------------------------------------------------
-There are always two trees (git repositories) in play. Both are
-driven by David Miller, the main network maintainer. There is the
-``net`` tree, and the ``net-next`` tree. As you can probably guess from
-the names, the ``net`` tree is for fixes to existing code already in the
-mainline tree from Linus, and ``net-next`` is where the new code goes
-for the future release. You can find the trees here:
-
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
+Development cycle
+-----------------
-How often do changes from these trees make it to the mainline Linus tree?
--------------------------------------------------------------------------
-To understand this, you need to know a bit of background information on
+Here is a bit of background information on
the cadence of Linux development. Each new release starts off with a
two week "merge window" where the main maintainers feed their new stuff
to Linus for merging into the mainline tree. After the two weeks, the
@@ -58,9 +48,33 @@ rc2 is released. This repeats on a roughly weekly basis until rc7
state of churn), and a week after the last vX.Y-rcN was done, the
official vX.Y is released.
-Relating that to netdev: At the beginning of the 2-week merge window,
-the ``net-next`` tree will be closed - no new changes/features. The
-accumulated new content of the past ~10 weeks will be passed onto
+To find out where we are now in the cycle - load the mainline (Linus)
+page here:
+
+ https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+and note the top of the "tags" section. If it is rc1, it is early in
+the dev cycle. If it was tagged rc7 a week ago, then a release is
+probably imminent. If the most recent tag is a final release tag
+(without an ``-rcN`` suffix) - we are most likely in a merge window
+and ``net-next`` is closed.
+
+git trees and patch flow
+------------------------
+
+There are two networking trees (git repositories) in play. Both are
+driven by David Miller, the main network maintainer. There is the
+``net`` tree, and the ``net-next`` tree. As you can probably guess from
+the names, the ``net`` tree is for fixes to existing code already in the
+mainline tree from Linus, and ``net-next`` is where the new code goes
+for the future release. You can find the trees here:
+
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
+
+Relating that to kernel development: At the beginning of the 2-week
+merge window, the ``net-next`` tree will be closed - no new changes/features.
+The accumulated new content of the past ~10 weeks will be passed onto
mainline/Linus via a pull request for vX.Y -- at the same time, the
``net`` tree will start accumulating fixes for this pulled content
relating to vX.Y
@@ -92,22 +106,14 @@ focus for ``net`` is on stabilization and bug fixes.
Finally, the vX.Y gets released, and the whole cycle starts over.
-So where are we now in this cycle?
-----------------------------------
+netdev patch review
+-------------------
-Load the mainline (Linus) page here:
+Patch status
+~~~~~~~~~~~~
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-and note the top of the "tags" section. If it is rc1, it is early in
-the dev cycle. If it was tagged rc7 a week ago, then a release is
-probably imminent. If the most recent tag is a final release tag
-(without an ``-rcN`` suffix) - we are most likely in a merge window
-and ``net-next`` is closed.
-
-How can I tell the status of a patch I've sent?
------------------------------------------------
-Start by looking at the main patchworks queue for netdev:
+Status of a patch can be checked by looking at the main patchwork
+queue for netdev:
https://patchwork.kernel.org/project/netdevbpf/list/
@@ -116,17 +122,20 @@ patch. Patches are indexed by the ``Message-ID`` header of the emails
which carried them so if you have trouble finding your patch append
the value of ``Message-ID`` to the URL above.
-Should I directly update patchwork state of my own patches?
------------------------------------------------------------
+Updating patch status
+~~~~~~~~~~~~~~~~~~~~~
+
It may be tempting to help the maintainers and update the state of your
-own patches when you post a new version or spot a bug. Please do not do that.
+own patches when you post a new version or spot a bug. Please **do not**
+do that.
Interfering with the patch status on patchwork will only cause confusion. Leave
it to the maintainer to figure out what is the most recent and current
version that should be applied. If there is any doubt, the maintainer
will reply and ask what should be done.
-How long before my patch is accepted?
--------------------------------------
+Review timelines
+~~~~~~~~~~~~~~~~
+
Generally speaking, the patches get triaged quickly (in less than
48h). But be patient, if your patch is active in patchwork (i.e. it's
listed on the project's patch list) the chances it was missed are close to zero.
@@ -134,37 +143,47 @@ Asking the maintainer for status updates on your
patch is a good way to ensure your patch is ignored or pushed to the
bottom of the priority list.
-I made changes to only a few patches in a patch series should I resend only those changed?
-------------------------------------------------------------------------------------------
-No, please resend the entire patch series and make sure you do number your
+Partial resends
+~~~~~~~~~~~~~~~
+
+Please always resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
-that can be applied.
+that can be applied. Do not try to resend just the patches which changed.
+
+Handling misapplied patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
-I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
-----------------------------------------------------------------------------------------------------------------------------------------
+Occasionally a patch series gets applied before receiving critical feedback,
+or the wrong version of a series gets applied.
There is no revert possible, once it is pushed out, it stays like that.
Please send incremental versions on top of what has been merged in order to fix
the patches the way they would look like if your latest patch series was to be
merged.
-Are there special rules regarding stable submissions on netdev?
----------------------------------------------------------------
+Stable tree
+~~~~~~~~~~~
+
While it used to be the case that netdev submissions were not supposed
to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
the case today. Please follow the standard stable rules in
:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
and make sure you include appropriate Fixes tags!
-I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
----------------------------------------------------------------------------------------------------------------------------
-No. The current netdev maintainer has consistently requested that
+Security fixes
+~~~~~~~~~~~~~~
+
+Do not email netdev maintainers directly if you think you discovered
+a bug that might have possible security implications.
+The current netdev maintainer has consistently requested that
people use the mailing lists and not reach out directly. If you aren't
OK with that, then perhaps consider mailing security@kernel.org or
reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
as possible alternative mechanisms.
-How do I post corresponding changes to user space components?
--------------------------------------------------------------
+
+Co-posting changes to user space components
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
User space code exercising kernel features should be posted
alongside kernel patches. This gives reviewers a chance to see
how any new interface is used and how well it works.
@@ -189,9 +208,10 @@ to the mailing list, e.g.::
Posting as one thread is discouraged because it confuses patchwork
(as of patchwork 2.2.2).
-Any other tips to help ensure my net/net-next patch gets OK'd?
---------------------------------------------------------------
-Attention to detail. Re-read your own work as if you were the
+Preparing changes
+-----------------
+
+Attention to detail is important. Re-read your own work as if you were the
reviewer. You can start with using ``checkpatch.pl``, perhaps even with
the ``--strict`` flag. But do not be mindlessly robotic in doing so.
If your change is a bug fix, make sure your commit log indicates the
@@ -206,8 +226,9 @@ Finally, go back and read
:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
to be sure you are not repeating some common mistake documented there.
-How do I indicate which tree (net vs. net-next) my patch should be in?
-----------------------------------------------------------------------
+Indicating target tree
+~~~~~~~~~~~~~~~~~~~~~~
+
To help maintainers and CI bots you should explicitly mark which tree
your patch is targeting. Assuming that you use git, use the prefix
flag::
@@ -217,8 +238,8 @@ flag::
Use ``net`` instead of ``net-next`` (always lower case) in the above for
bug-fix ``net`` content.
-How do I divide my work into patches?
--------------------------------------
+Dividing work into patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~
Put yourself in the shoes of the reviewer. Each patch is read separately
and therefore should constitute a comprehensible step towards your stated
@@ -231,9 +252,11 @@ just do it. As a result, a sequence of smaller series gets merged quicker and
with better review coverage. Re-posting large series also increases the mailing
list traffic.
-Is the comment style convention different for the networking content?
----------------------------------------------------------------------
-Yes, in a largely trivial way. Instead of this::
+Multi-line comments
+~~~~~~~~~~~~~~~~~~~
+
+Comment style convention is slightly different for networking and most of
+the tree. Instead of this::
/*
* foobar blah blah blah
@@ -246,8 +269,8 @@ it is requested that you make it look like this::
* another line of text
*/
-What is "reverse xmas tree"?
-----------------------------
+Local variable ordering ("reverse xmas tree", "RCS")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Netdev has a convention for ordering local variables in functions.
Order the variable declaration lines longest to shortest, e.g.::
@@ -259,13 +282,16 @@ Order the variable declaration lines longest to shortest, e.g.::
If there are dependencies between the variables preventing the ordering
move the initialization out of line.
-I am working in existing code which uses non-standard formatting. Which formatting should I use?
-------------------------------------------------------------------------------------------------
-Make your code follow the most recent guidelines, so that eventually all code
+Format precedence
+~~~~~~~~~~~~~~~~~
+
+When working in existing code which uses nonstandard formatting make
+your code follow the most recent guidelines, so that eventually all code
in the domain of netdev is in the preferred format.
-I have received review feedback, when should I post a revised version of the patches?
--------------------------------------------------------------------------------------
+Resending after review
+~~~~~~~~~~~~~~~~~~~~~~
+
Allow at least 24 hours to pass between postings. This will ensure reviewers
from all geographical locations have a chance to chime in. Do not wait
too long (weeks) between postings either as it will make it harder for reviewers
@@ -275,8 +301,12 @@ Make sure you address all the feedback in your new posting. Do not post a new
version of the code if the discussion about the previous version is still
ongoing, unless directly instructed by a reviewer.
-What level of testing is expected before I submit my change?
-------------------------------------------------------------
+Testing
+-------
+
+Expected level of testing
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
At the very minimum your changes must survive an ``allyesconfig`` and an
``allmodconfig`` build with ``W=1`` set without new warnings or failures.
@@ -287,43 +317,42 @@ and the patch series contains a set of kernel selftest for
You are expected to test your changes on top of the relevant networking
tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
-Can I reproduce the checks from patchwork on my local machine?
---------------------------------------------------------------
+patchwork checks
+~~~~~~~~~~~~~~~~
Checks in patchwork are mostly simple wrappers around existing kernel
scripts, the sources are available at:
https://github.com/kuba-moo/nipa/tree/master/tests
-Running all the builds and checks locally is a pain, can I post my patches and have the patchwork bot validate them?
---------------------------------------------------------------------------------------------------------------------
-
-No, you must ensure that your patches are ready by testing them locally
+**Do not** post your patches just to run them through the checks.
+You must ensure that your patches are ready by testing them locally
before posting to the mailing list. The patchwork build bot instance
gets overloaded very easily and netdev@vger really doesn't need more
traffic if we can help it.
-netdevsim is great, can I extend it for my out-of-tree tests?
--------------------------------------------------------------
+netdevsim
+~~~~~~~~~
-No, ``netdevsim`` is a test vehicle solely for upstream tests.
-(Please add your tests under ``tools/testing/selftests/``.)
+``netdevsim`` is a test driver which can be used to exercise driver
+configuration APIs without requiring capable hardware.
+Mock-ups and tests based on ``netdevsim`` are strongly encouraged when
+adding new APIs, but ``netdevsim`` in itself is **not** considered
+a use case/user. You must also implement the new APIs in a real driver.
-We also give no guarantees that ``netdevsim`` won't change in the future
+We give no guarantees that ``netdevsim`` won't change in the future
in a way which would break what would normally be considered uAPI.
-Is netdevsim considered a "user" of an API?
--------------------------------------------
-
-Linux kernel has a long standing rule that no API should be added unless
-it has a real, in-tree user. Mock-ups and tests based on ``netdevsim`` are
-strongly encouraged when adding new APIs, but ``netdevsim`` in itself
-is **not** considered a use case/user.
+``netdevsim`` is reserved for use by upstream tests only, so any
+new ``netdevsim`` features must be accompanied by selftests under
+``tools/testing/selftests/``.
-My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
----------------------------------------------------------------------------------------------------------
+Testimonials / feedback
+-----------------------
-Yes, especially if you spend significant amount of time reviewing code
+Some companies use peer feedback in employee performance reviews.
+Please feel free to request feedback from netdev maintainers,
+especially if you spend significant amount of time reviewing code
and go out of your way to improve shared infrastructure.
The feedback must be requested by you, the contributor, and will always
--
GitLab
From b9e05399d9273c8c066e73db1e6e85364003030c Mon Sep 17 00:00:00 2001
From: Si-Wei Liu <si-wei.liu@oracle.com>
Date: Mon, 10 Oct 2022 10:27:03 -0700
Subject: [PATCH 0105/1167] vdpa: merge functionally duplicated dev_features
attributes
We can merge VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES with
VDPA_ATTR_DEV_FEATURES which is functionally equivalent.
While at it, tweak the comment in header file to make
user provioned device features distinguished from those
supported by the parent mgmtdev device: the former of
which can be inherited as a whole from the latter, or
can be a subset of the latter if explicitly specified.
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Message-Id: <1665422823-18364-1-git-send-email-si-wei.liu@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vdpa/vdpa.c | 2 +-
include/uapi/linux/vdpa.h | 4 +---
2 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index febdc99b51a7b..41ed56362992b 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -855,7 +855,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms
features_device = vdev->config->get_device_features(vdev);
- if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
+ if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device,
VDPA_ATTR_PAD))
return -EMSGSIZE;
diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h
index 9bd79235c875f..54b649ab0f22b 100644
--- a/include/uapi/linux/vdpa.h
+++ b/include/uapi/linux/vdpa.h
@@ -53,11 +53,9 @@ enum vdpa_attr {
VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */
VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */
+ /* virtio features that are provisioned to the vDPA device */
VDPA_ATTR_DEV_FEATURES, /* u64 */
- /* virtio features that are supported by the vDPA device */
- VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */
-
/* new attributes must be added above here */
VDPA_ATTR_MAX,
};
--
GitLab
From c262f75cb6bb5a63828e72ce3b8fe808e5029479 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo?= <ricardo.canuelo@collabora.com>
Date: Wed, 12 Oct 2022 08:29:49 +0200
Subject: [PATCH 0106/1167] tools/virtio: initialize spinlocks in vring_test.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The virtio_device vqs_list spinlocks must be initialized before use to
prevent functions that manipulate the device virtualqueues, such as
vring_new_virtqueue(), from blocking indefinitely.
Signed-off-by: Ricardo Cañuelo <ricardo.canuelo@collabora.com>
Message-Id: <20221012062949.1526176-1-ricardo.canuelo@collabora.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
tools/virtio/vringh_test.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/virtio/vringh_test.c b/tools/virtio/vringh_test.c
index fa87b58bd5fa5..98ff808d6f0c2 100644
--- a/tools/virtio/vringh_test.c
+++ b/tools/virtio/vringh_test.c
@@ -308,6 +308,7 @@ static int parallel_test(u64 features,
gvdev.vdev.features = features;
INIT_LIST_HEAD(&gvdev.vdev.vqs);
+ spin_lock_init(&gvdev.vdev.vqs_list_lock);
gvdev.to_host_fd = to_host[1];
gvdev.notifies = 0;
@@ -455,6 +456,7 @@ int main(int argc, char *argv[])
getrange = getrange_iov;
vdev.features = 0;
INIT_LIST_HEAD(&vdev.vqs);
+ spin_lock_init(&vdev.vqs_list_lock);
while (argv[1]) {
if (strcmp(argv[1], "--indirect") == 0)
--
GitLab
From 258896fcc786b4e7db238eba26f6dd080e0ff41e Mon Sep 17 00:00:00 2001
From: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Date: Sat, 15 Oct 2022 23:41:26 -0400
Subject: [PATCH 0107/1167] virtio-blk: use a helper to handle request queuing
errors
Define a new helper function, virtblk_fail_to_queue(), to
clean up the error handling code in virtio_queue_rq().
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Message-Id: <20221016034127.330942-2-dmitry.fomichev@wdc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/block/virtio_blk.c | 29 ++++++++++++++++-------------
1 file changed, 16 insertions(+), 13 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 68bd2f7961b3f..271a9878fa8b3 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -315,6 +315,19 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
virtqueue_notify(vq->vq);
}
+static blk_status_t virtblk_fail_to_queue(struct request *req, int rc)
+{
+ virtblk_cleanup_cmd(req);
+ switch (rc) {
+ case -ENOSPC:
+ return BLK_STS_DEV_RESOURCE;
+ case -ENOMEM:
+ return BLK_STS_RESOURCE;
+ default:
+ return BLK_STS_IOERR;
+ }
+}
+
static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
struct virtio_blk *vblk,
struct request *req,
@@ -327,10 +340,8 @@ static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
return status;
vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
- if (unlikely(vbr->sg_table.nents < 0)) {
- virtblk_cleanup_cmd(req);
- return BLK_STS_RESOURCE;
- }
+ if (unlikely(vbr->sg_table.nents < 0))
+ return virtblk_fail_to_queue(req, -ENOMEM);
blk_mq_start_request(req);
@@ -364,15 +375,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
virtblk_unmap_data(req, vbr);
- virtblk_cleanup_cmd(req);
- switch (err) {
- case -ENOSPC:
- return BLK_STS_DEV_RESOURCE;
- case -ENOMEM:
- return BLK_STS_RESOURCE;
- default:
- return BLK_STS_IOERR;
- }
+ return virtblk_fail_to_queue(req, err);
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
--
GitLab
From 8e6a8d7a3dd93e93645be061692cb4ee6702dff0 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 26 Dec 2022 16:13:27 +0900
Subject: [PATCH 0108/1167] net: ethernet: renesas: rswitch: Fix error path in
renesas_eth_sw_probe()
If rswitch_init() returns non-zero and this driver is re-probed,
the following error happens:
renesas_eth_sw e6880000.ethernet: Unbalanced pm_runtime_enable!
So, fix error path in renesas_eth_sw_probe().
Fixes: 3590918b5d07 ("net: ethernet: renesas: Add support for "Ethernet Switch"")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/renesas/rswitch.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index e42ceaa0099fd..473d86bdf97d6 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1786,6 +1786,11 @@ static int renesas_eth_sw_probe(struct platform_device *pdev)
pm_runtime_get_sync(&pdev->dev);
ret = rswitch_init(priv);
+ if (ret < 0) {
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+ return ret;
+ }
device_set_wakeup_capable(&pdev->dev, 1);
--
GitLab
From bd2adfe3b3b863c883309bcc915f13c831ca88da Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 26 Dec 2022 16:13:28 +0900
Subject: [PATCH 0109/1167] net: ethernet: renesas: rswitch: Fix getting mac
address from device tree
To get mac address from device tree which is from each ethernet-port,
fix the first argument of of_get_ethdev_address().
Fixes: 3590918b5d07 ("net: ethernet: renesas: Add support for "Ethernet Switch"")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/renesas/rswitch.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 473d86bdf97d6..6441892636dba 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1578,6 +1578,7 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index)
{
struct platform_device *pdev = priv->pdev;
struct rswitch_device *rdev;
+ struct device_node *port;
struct net_device *ndev;
int err;
@@ -1606,7 +1607,9 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index)
netif_napi_add(ndev, &rdev->napi, rswitch_poll);
- err = of_get_ethdev_address(pdev->dev.of_node, ndev);
+ port = rswitch_get_port_node(rdev);
+ err = of_get_ethdev_address(port, ndev);
+ of_node_put(port);
if (err) {
if (is_valid_ether_addr(rdev->etha->mac_addr))
eth_hw_addr_set(ndev, rdev->etha->mac_addr);
--
GitLab
From 0020ae2a4aa81becd182231bf48acd66c86c86dd Mon Sep 17 00:00:00 2001
From: Vikas Gupta <vikas.gupta@broadcom.com>
Date: Mon, 26 Dec 2022 22:19:36 -0500
Subject: [PATCH 0110/1167] bnxt_en: fix devlink port registration to netdev
We don't register a devlink port in case of a VF so
avoid setting the devlink pointer to netdev.
Also, SET_NETDEV_DEVLINK_PORT has to be moved
so that we determine whether the device is PF/VF first.
This fixes the NULL pointer dereference of devlink_port->devlink
when creating VFs:
BUG: kernel NULL pointer dereference, address: 0000000000000160
PGD 0
Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 14 PID: 388 Comm: kworker/14:1 Kdump: loaded Not tainted 6.1.0-rc8 #5
Hardware name: Dell Inc. PowerEdge R750/06V45N, BIOS 1.3.8 08/31/2021
Workqueue: events work_for_cpu_fn
RIP: 0010:devlink_nl_port_handle_size+0xb/0x50
Code: 83 c4 10 5b 5d c3 cc cc cc cc b8 a6 ff ff ff eb de e8 c9 59 21 00 66 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 53 48 8b 47 20 <48> 8b a8 60 01 00 00 48 8b 45 60 48 8b 38 e8 92 90 1a 00 48 8b 7d
RSP: 0018:ff4fe5394846fcd8 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000794 RCX: 0000000000000000
RDX: ff1f129683a30a40 RSI: 0000000000000008 RDI: ff1f1296bb496188
RBP: 0000000000000334 R08: 0000000000000cc0 R09: 0000000000000000
R10: ff1f1296bb494298 R11: ffffffffffffffc0 R12: 0000000000000000
R13: 0000000000000000 R14: ff1f1296bb494000 R15: 0000000000000000
FS: 0000000000000000(0000) GS:ff1f129e5fa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000160 CR3: 000000131f610006 CR4: 0000000000771ee0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
<TASK>
if_nlmsg_size+0x14a/0x220
rtmsg_ifinfo_build_skb+0x3c/0x100
rtmsg_ifinfo+0x9c/0xc0
register_netdevice+0x59d/0x670
register_netdev+0x1c/0x40
bnxt_init_one+0x674/0xa60 [bnxt_en]
local_pci_probe+0x42/0x80
work_for_cpu_fn+0x13/0x20
process_one_work+0x1e2/0x3b0
? rescuer_thread+0x390/0x390
worker_thread+0x1c4/0x3a0
? rescuer_thread+0x390/0x390
kthread+0xd6/0x100
? kthread_complete_and_exit+0x20/0x20
Fixes: ac73d4bf2cda ("net: make drivers to use SET_NETDEV_DEVLINK_PORT to set devlink_port")
Cc: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Kalesh Anakkur Purayil <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 4c7d07c684c49..93d32b333007f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13591,7 +13591,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
return -ENOMEM;
bp = netdev_priv(dev);
- SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
bp->board_idx = ent->driver_data;
bp->msg_enable = BNXT_DEF_MSG_ENABLE;
bnxt_set_max_func_irqs(bp, max_irqs);
@@ -13599,6 +13598,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (bnxt_vf_pciid(bp->board_idx))
bp->flags |= BNXT_FLAG_VF;
+ /* No devlink port registration in case of a VF */
+ if (BNXT_PF(bp))
+ SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
+
if (pdev->msix_cap)
bp->flags |= BNXT_FLAG_MSIX_CAP;
--
GitLab
From bbfc17e50ba2ed18dfef46b1c433d50a58566bf1 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 26 Dec 2022 22:19:37 -0500
Subject: [PATCH 0111/1167] bnxt_en: Simplify bnxt_xdp_buff_init()
bnxt_xdp_buff_init() does not modify the data_ptr or the len parameters,
so no need to pass in the addresses of these parameters.
Fixes: b231c3f3414c ("bnxt: refactor bnxt_rx_xdp to separate xdp_init_buff/xdp_prepare_buff")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 6 +++---
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h | 2 +-
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 93d32b333007f..b8639b7e6b2b3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1925,7 +1925,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
dma_addr = rx_buf->mapping;
if (bnxt_xdp_attached(bp, rxr)) {
- bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp);
+ bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
if (agg_bufs) {
u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
cp_cons, agg_bufs,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index c3065ec0a4798..1847f191577d1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -177,7 +177,7 @@ bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
}
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp)
{
struct bnxt_sw_rx_bd *rx_buf;
@@ -191,13 +191,13 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
offset = bp->rx_offset;
mapping = rx_buf->mapping - bp->rx_dma_offset;
- dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
+ dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
if (bp->xdp_has_frags)
buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
- xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
+ xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
}
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 505911ae095d3..2bbdb8e7c506b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -27,7 +27,7 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr);
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp);
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
struct xdp_buff *xdp);
--
GitLab
From 9b3e607871ea5ee90f10f5be3965fc07f2aa3ef7 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 26 Dec 2022 22:19:38 -0500
Subject: [PATCH 0112/1167] bnxt_en: Fix XDP RX path
The XDP program can change the starting address of the RX data buffer and
this information needs to be passed back from bnxt_rx_xdp() to
bnxt_rx_pkt() for the XDP_PASS case so that the SKB can point correctly
to the modified buffer address. Add back the data_ptr parameter to
bnxt_rx_xdp() to make this work.
Fixes: b231c3f3414c ("bnxt: refactor bnxt_rx_xdp to separate xdp_init_buff/xdp_prepare_buff")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 7 +++++--
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h | 4 ++--
3 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b8639b7e6b2b3..1acabfe26db18 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1940,7 +1940,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
}
if (xdp_active) {
- if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) {
+ if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &data_ptr, &len, event)) {
rc = 1;
goto next_rx;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 1847f191577d1..2ceeaa818c1c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -222,7 +222,8 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
* false - packet should be passed to the stack.
*/
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event)
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event)
{
struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
struct bnxt_tx_ring_info *txr;
@@ -255,8 +256,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
*event &= ~BNXT_RX_EVENT;
*len = xdp.data_end - xdp.data;
- if (orig_data != xdp.data)
+ if (orig_data != xdp.data) {
offset = xdp.data - xdp.data_hard_start;
+ *data_ptr = xdp.data_hard_start + offset;
+ }
switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 2bbdb8e7c506b..ea430d6961df3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -18,8 +18,8 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp,
struct xdp_buff *xdp);
void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len,
- u8 *event);
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event);
int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
struct xdp_frame **frames, u32 flags);
--
GitLab
From 1abeacc1979fa4a756695f5030791d8f0fa934b9 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 26 Dec 2022 22:19:39 -0500
Subject: [PATCH 0113/1167] bnxt_en: Fix first buffer size calculations for XDP
multi-buffer
The size of the first buffer is always page size, and the useable
space is the page size minus the offset and the skb_shared_info size.
Make sure SKB and XDP buf sizes match so that the skb_shared_info
is at the same offset seen from the SKB and XDP_BUF.
build_skb() should be passed PAGE_SIZE. xdp_init_buff() should
be passed PAGE_SIZE as well. xdp_get_shared_info_from_buff() will
automatically deduct the skb_shared_info size if the XDP buffer
has frags. There is no need to keep bp->xdp_has_frags.
Change BNXT_PAGE_MODE_BUF_SIZE to BNXT_MAX_PAGE_MODE_MTU_SBUF
since this constant is really the MTU with ethernet header size
subtracted.
Also fix the BNXT_MAX_PAGE_MODE_MTU macro with proper parentheses.
Fixes: 32861236190b ("bnxt: change receive ring space parameters")
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 +++++----
drivers/net/ethernet/broadcom/bnxt/bnxt.h | 15 +++++++++++----
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 7 +------
3 files changed, 17 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1acabfe26db18..a21c6829e301e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -991,8 +991,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
dma_addr -= bp->rx_dma_offset;
dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
DMA_ATTR_WEAK_ORDERING);
- skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE +
- bp->rx_dma_offset);
+ skb = build_skb(page_address(page), PAGE_SIZE);
if (!skb) {
__free_page(page);
return NULL;
@@ -3969,8 +3968,10 @@ void bnxt_set_ring_params(struct bnxt *bp)
bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1;
if (BNXT_RX_PAGE_MODE(bp)) {
- rx_space = BNXT_PAGE_MODE_BUF_SIZE;
- rx_size = BNXT_MAX_PAGE_MODE_MTU;
+ rx_space = PAGE_SIZE;
+ rx_size = PAGE_SIZE -
+ ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
} else {
rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
rx_space = rx_size + NET_SKB_PAD +
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 41c6dd0ae447e..5163ef4a49ea3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -591,12 +591,20 @@ struct nqe_cn {
#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
#define BNXT_MAX_MTU 9500
-#define BNXT_PAGE_MODE_BUF_SIZE \
+
+/* First RX buffer page in XDP multi-buf mode
+ *
+ * +-------------------------------------------------------------------------+
+ * | XDP_PACKET_HEADROOM | bp->rx_buf_use_size | skb_shared_info|
+ * | (bp->rx_dma_offset) | | |
+ * +-------------------------------------------------------------------------+
+ */
+#define BNXT_MAX_PAGE_MODE_MTU_SBUF \
((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \
XDP_PACKET_HEADROOM)
#define BNXT_MAX_PAGE_MODE_MTU \
- BNXT_PAGE_MODE_BUF_SIZE - \
- SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))
+ (BNXT_MAX_PAGE_MODE_MTU_SBUF - \
+ SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
#define BNXT_MIN_PKT_SIZE 52
@@ -2134,7 +2142,6 @@ struct bnxt {
#define BNXT_DUMP_CRASH 1
struct bpf_prog *xdp_prog;
- u8 xdp_has_frags;
struct bnxt_ptp_cfg *ptp_cfg;
u8 ptp_all_rx_tstamp;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 2ceeaa818c1c6..36d5202c0aeec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -193,9 +193,6 @@ void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
mapping = rx_buf->mapping - bp->rx_dma_offset;
dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
- if (bp->xdp_has_frags)
- buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
-
xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
}
@@ -404,10 +401,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
return -EOPNOTSUPP;
}
- if (prog) {
+ if (prog)
tx_xdp = bp->rx_nr_rings;
- bp->xdp_has_frags = prog->aux->xdp_has_frags;
- }
tc = netdev_get_num_tc(dev);
if (!tc)
--
GitLab
From a056ebcc30e2f78451d66f615d2f6bdada3e6438 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 26 Dec 2022 22:19:40 -0500
Subject: [PATCH 0114/1167] bnxt_en: Fix HDS and jumbo thresholds for RX
packets
The recent XDP multi-buffer feature has introduced regressions in the
setting of HDS and jumbo thresholds. HDS was accidentally disabled in
the nornmal mode without XDP. This patch restores jumbo HDS placement
when not in XDP mode. In XDP multi-buffer mode, HDS should be disabled
and the jumbo threshold should be set to the usable page size in the
first page buffer.
Fixes: 32861236190b ("bnxt: change receive ring space parameters")
Reviewed-by: Mohammad Shuab Siddique <mohammad-shuab.siddique@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index a21c6829e301e..16ce7a90610c5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5399,15 +5399,16 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
- if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) {
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
+ } else {
req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
req->enables |=
cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+ req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
+ req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
}
- /* thresholds not implemented in firmware yet */
- req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
- req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
return hwrm_req_send(bp, req);
}
--
GitLab
From b659b613cea2ae39746ca8bd2b69d1985dd9d770 Mon Sep 17 00:00:00 2001
From: Ferry Toth <ftoth@exalondelft.nl>
Date: Thu, 22 Dec 2022 21:53:02 +0100
Subject: [PATCH 0115/1167] Revert "usb: ulpi: defer ulpi_register on
ulpi_read_id timeout"
This reverts commit 8a7b31d545d3a15f0e6f5984ae16f0ca4fd76aac.
This patch results in some qemu test failures, specifically xilinx-zynq-a9
machine and zynq-zc702 as well as zynq-zed devicetree files, when trying
to boot from USB drive.
Link: https://lore.kernel.org/lkml/20221220194334.GA942039@roeck-us.net/
Fixes: 8a7b31d545d3 ("usb: ulpi: defer ulpi_register on ulpi_read_id timeout")
Cc: stable@vger.kernel.org
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Ferry Toth <ftoth@exalondelft.nl>
Link: https://lore.kernel.org/r/20221222205302.45761-1-ftoth@exalondelft.nl
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/common/ulpi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 60e8174686a17..d7c8461976ce0 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -207,7 +207,7 @@ static int ulpi_read_id(struct ulpi *ulpi)
/* Test the interface */
ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa);
if (ret < 0)
- return ret;
+ goto err;
ret = ulpi_read(ulpi, ULPI_SCRATCH);
if (ret < 0)
--
GitLab
From 2de5bba5890f6604a997c75e754df8082386c9f7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:57:20 +0100
Subject: [PATCH 0116/1167] usb: fotg210: fix OTG-only build
The fotg210 module combines the HCD and OTG drivers, which then
fails to build when only the USB gadget support is enabled
in the kernel but host support is not:
aarch64-linux-ld: drivers/usb/fotg210/fotg210-core.o: in function `fotg210_init':
fotg210-core.c:(.init.text+0xc): undefined reference to `usb_disabled'
Move the check for usb_disabled() after the check for the HCD module,
and let the OTG driver still be probed in this configuration.
A nicer approach might be to have the common portion built as a
library module, with the two platform other files registering
their own platform_driver instances separately.
Fixes: ddacd6ef44ca ("usb: fotg210: Fix Kconfig for USB host modules")
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20221215165728.2062984-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/fotg210/fotg210-core.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/usb/fotg210/fotg210-core.c b/drivers/usb/fotg210/fotg210-core.c
index 8a54edf921ac2..ee740a6da463f 100644
--- a/drivers/usb/fotg210/fotg210-core.c
+++ b/drivers/usb/fotg210/fotg210-core.c
@@ -144,10 +144,7 @@ static struct platform_driver fotg210_driver = {
static int __init fotg210_init(void)
{
- if (usb_disabled())
- return -ENODEV;
-
- if (IS_ENABLED(CONFIG_USB_FOTG210_HCD))
+ if (IS_ENABLED(CONFIG_USB_FOTG210_HCD) && !usb_disabled())
fotg210_hcd_init();
return platform_driver_register(&fotg210_driver);
}
--
GitLab
From a6ce72c0fb6041f9871f880b2d02b294f7f49cb4 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 14 Nov 2022 15:17:52 +0200
Subject: [PATCH 0117/1167] vdpa/mlx5: Fix rule forwarding VLAN to TIR
Set the VLAN id to the header values field instead of overwriting the
headers criteria field.
Before this fix, VLAN filtering would not really work and tagged packets
would be forwarded unfiltered to the TIR.
Fixes: baf2ad3f6a98 ("vdpa/mlx5: Add RX MAC VLAN filter support")
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20221114131759.57883-2-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 90913365def43..3fb06dcee9436 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1468,11 +1468,13 @@ static int mlx5_vdpa_add_mac_vlan_rules(struct mlx5_vdpa_net *ndev, u8 *mac,
dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
eth_broadcast_addr(dmac_c);
ether_addr_copy(dmac_v, mac);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
+ }
if (tagged) {
MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
- MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid);
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
--
GitLab
From 5aec804936bbff182081f1cdc271fcb76af1a4ff Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 14 Nov 2022 15:17:53 +0200
Subject: [PATCH 0118/1167] vdpa/mlx5: Return error on vlan ctrl commands if
not supported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Check if VIRTIO_NET_F_CTRL_VLAN is negotiated and return error if
control VQ command is received.
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20221114131759.57883-3-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 3fb06dcee9436..01da229d22da3 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1823,6 +1823,9 @@ static virtio_net_ctrl_ack handle_ctrl_vlan(struct mlx5_vdpa_dev *mvdev, u8 cmd)
size_t read;
u16 id;
+ if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)))
+ return status;
+
switch (cmd) {
case VIRTIO_NET_CTRL_VLAN_ADD:
read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &vlan, sizeof(vlan));
--
GitLab
From 1ab53760d322c82fb4cb5e81b5817065801e3ec4 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 14 Nov 2022 15:17:54 +0200
Subject: [PATCH 0119/1167] vdpa/mlx5: Fix wrong mac address deletion
Delete the old MAC from the table and not the new one which is not there
yet.
Fixes: baf2ad3f6a98 ("vdpa/mlx5: Add RX MAC VLAN filter support")
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20221114131759.57883-4-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 01da229d22da3..b06260a376800 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1686,7 +1686,7 @@ static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd)
/* Need recreate the flow table entry, so that the packet could forward back
*/
- mac_vlan_del(ndev, ndev->config.mac, 0, false);
+ mac_vlan_del(ndev, mac_back, 0, false);
if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) {
mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n");
--
GitLab
From 0dbc1b4ae07d003b2e88ba9d4142846320f8e349 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 14 Nov 2022 15:17:55 +0200
Subject: [PATCH 0120/1167] vdpa/mlx5: Avoid using reslock in event_handler
event_handler runs under atomic context and may not acquire reslock. We
can still guarantee that the handler won't be called after suspend by
clearing nb_registered, unregistering the handler and flushing the
workqueue.
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20221114131759.57883-5-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 16 ++++------------
1 file changed, 4 insertions(+), 12 deletions(-)
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index b06260a376800..98dd8ce8af265 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2845,8 +2845,8 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev)
int i;
down_write(&ndev->reslock);
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
flush_workqueue(ndev->mvdev.wq);
for (i = 0; i < ndev->cur_num_vqs; i++) {
mvq = &ndev->vqs[i];
@@ -3024,7 +3024,7 @@ static void update_carrier(struct work_struct *work)
else
ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
- if (ndev->config_cb.callback)
+ if (ndev->nb_registered && ndev->config_cb.callback)
ndev->config_cb.callback(ndev->config_cb.private);
kfree(wqent);
@@ -3041,21 +3041,13 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p
switch (eqe->sub_type) {
case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
- down_read(&ndev->reslock);
- if (!ndev->nb_registered) {
- up_read(&ndev->reslock);
- return NOTIFY_DONE;
- }
wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
- if (!wqent) {
- up_read(&ndev->reslock);
+ if (!wqent)
return NOTIFY_DONE;
- }
wqent->mvdev = &ndev->mvdev;
INIT_WORK(&wqent->work, update_carrier);
queue_work(ndev->mvdev.wq, &wqent->work);
- up_read(&ndev->reslock);
ret = NOTIFY_OK;
break;
default:
@@ -3242,8 +3234,8 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *
struct workqueue_struct *wq;
if (ndev->nb_registered) {
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
}
wq = mvdev->wq;
mvdev->wq = NULL;
--
GitLab
From 38fc462f57ef4e5dc722bab6824854b105de8aa2 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Mon, 14 Nov 2022 15:17:56 +0200
Subject: [PATCH 0121/1167] vdpa/mlx5: Avoid overwriting CVQ iotlb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When qemu uses different address spaces for data and control virtqueues,
the current code would overwrite the control virtqueue iotlb through the
dup_iotlb call. Fix this by referring to the address space identifier
and the group to asid mapping to determine which mapping needs to be
updated. We also move the address space logic from mlx5 net to core
directory.
Reported-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Eli Cohen <elic@nvidia.com>
Message-Id: <20221114131759.57883-6-elic@nvidia.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
---
drivers/vdpa/mlx5/core/mlx5_vdpa.h | 5 +--
drivers/vdpa/mlx5/core/mr.c | 44 ++++++++++++++++-----------
drivers/vdpa/mlx5/net/mlx5_vnet.c | 49 ++++++------------------------
3 files changed, 39 insertions(+), 59 deletions(-)
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 6af9fdbb86b7a..058fbe28107e9 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -116,8 +116,9 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in,
int inlen);
int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map);
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+ bool *change_map, unsigned int asid);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid);
void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
#define mlx5_vdpa_warn(__dev, format, ...) \
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index a639b9208d414..a4d7ee2339fa5 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -511,7 +511,8 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
mutex_unlock(&mr->mkey_mtx);
}
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err;
@@ -519,42 +520,49 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
if (mr->initialized)
return 0;
- if (iotlb)
- err = create_user_mr(mvdev, iotlb);
- else
- err = create_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ err = create_user_mr(mvdev, iotlb);
+ else
+ err = create_dma_mr(mvdev, mr);
- if (err)
- return err;
+ if (err)
+ return err;
+ }
- err = dup_iotlb(mvdev, iotlb);
- if (err)
- goto out_err;
+ if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+ err = dup_iotlb(mvdev, iotlb);
+ if (err)
+ goto out_err;
+ }
mr->initialized = true;
return 0;
out_err:
- if (iotlb)
- destroy_user_mr(mvdev, mr);
- else
- destroy_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ destroy_user_mr(mvdev, mr);
+ else
+ destroy_dma_mr(mvdev, mr);
+ }
return err;
}
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
int err;
mutex_lock(&mvdev->mr.mkey_mtx);
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mvdev->mr.mkey_mtx);
return err;
}
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map)
+ bool *change_map, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err = 0;
@@ -566,7 +574,7 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io
*change_map = true;
}
if (!*change_map)
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mr->mkey_mtx);
return err;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 98dd8ce8af265..3a6dbbc6440d4 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2394,7 +2394,8 @@ static void restore_channels_info(struct mlx5_vdpa_net *ndev)
}
}
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
int err;
@@ -2406,7 +2407,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
teardown_driver(ndev);
mlx5_vdpa_destroy_mr(mvdev);
- err = mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
if (err)
goto err_mr;
@@ -2587,7 +2588,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
++mvdev->generation;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- if (mlx5_vdpa_create_mr(mvdev, NULL))
+ if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
mlx5_vdpa_warn(mvdev, "create MR failed\n");
}
up_write(&ndev->reslock);
@@ -2623,41 +2624,20 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
return mvdev->generation;
}
-static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
-{
- u64 start = 0ULL, last = 0ULL - 1;
- struct vhost_iotlb_map *map;
- int err = 0;
-
- spin_lock(&mvdev->cvq.iommu_lock);
- vhost_iotlb_reset(mvdev->cvq.iotlb);
-
- for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
- map = vhost_iotlb_itree_next(map, start, last)) {
- err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start,
- map->last, map->addr, map->perm);
- if (err)
- goto out;
- }
-
-out:
- spin_unlock(&mvdev->cvq.iommu_lock);
- return err;
-}
-
-static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
bool change_map;
int err;
- err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+ err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid);
if (err) {
mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
return err;
}
if (change_map)
- err = mlx5_vdpa_change_map(mvdev, iotlb);
+ err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
return err;
}
@@ -2670,16 +2650,7 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
int err = -EINVAL;
down_write(&ndev->reslock);
- if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
- err = set_map_data(mvdev, iotlb);
- if (err)
- goto out;
- }
-
- if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
- err = set_map_control(mvdev, iotlb);
-
-out:
+ err = set_map_data(mvdev, iotlb, asid);
up_write(&ndev->reslock);
return err;
}
@@ -3182,7 +3153,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
goto err_mpfs;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- err = mlx5_vdpa_create_mr(mvdev, NULL);
+ err = mlx5_vdpa_create_mr(mvdev, NULL, 0);
if (err)
goto err_res;
}
--
GitLab
From 344686136d73501a18a9621de690ff7824a3d129 Mon Sep 17 00:00:00 2001
From: Shaoqin Huang <shaoqin.huang@intel.com>
Date: Thu, 20 Oct 2022 23:27:33 -0700
Subject: [PATCH 0122/1167] virtio_pci: use helper function is_power_of_2()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Use helper function is_power_of_2() to check if num is power of two.
Minor readability improvement.
Signed-off-by: Shaoqin Huang <shaoqin.huang@intel.com>
Message-Id: <20221021062734.228881-2-shaoqin.huang@intel.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
drivers/virtio/virtio_pci_modern.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index c3b9f27618497..207294bd7b9d6 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -310,7 +310,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
if (!num || vp_modern_get_queue_enable(mdev, index))
return ERR_PTR(-ENOENT);
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
return ERR_PTR(-EINVAL);
}
--
GitLab
From b9d978a89296c57fbbbd8ea647c303ce4d37028f Mon Sep 17 00:00:00 2001
From: Shaoqin Huang <shaoqin.huang@intel.com>
Date: Thu, 20 Oct 2022 23:27:34 -0700
Subject: [PATCH 0123/1167] virtio_ring: use helper function is_power_of_2()
Use helper function is_power_of_2() to check if num is power of two.
Minor readability improvement.
Signed-off-by: Shaoqin Huang <shaoqin.huang@intel.com>
Message-Id: <20221021062734.228881-3-shaoqin.huang@intel.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
drivers/virtio/virtio_ring.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 2e7689bb933b8..723c4e29e1d3b 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1052,7 +1052,7 @@ static int vring_alloc_queue_split(struct vring_virtqueue_split *vring_split,
dma_addr_t dma_addr;
/* We assume num is a power of 2. */
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
return -EINVAL;
}
--
GitLab
From a9f0a19ff7700cc8a30db2496f40d18490dcb9df Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 24 Oct 2022 14:37:56 +0100
Subject: [PATCH 0124/1167] RDMA/mlx5: remove variable i
Variable i is just being incremented and it's never used
anywhere else. The variable and the increment are redundant so
remove it.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Message-Id: <20221024133756.2158497-1-colin.i.king@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vdpa/mlx5/core/mr.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index a4d7ee2339fa5..0a1e0b0dc37e3 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -311,7 +311,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8
u64 st;
u64 sz;
int err;
- int i = 0;
st = start;
while (size) {
@@ -336,7 +335,6 @@ static int add_direct_chain(struct mlx5_vdpa_dev *mvdev, u64 start, u64 size, u8
mr->num_directs++;
mr->num_klms++;
st += sz;
- i++;
}
list_splice_tail(&tmp, &mr->head);
return 0;
--
GitLab
From b66ead2d0ecac00c3a06a6218af5411cb5fcb5d5 Mon Sep 17 00:00:00 2001
From: Angus Chen <angus.chen@jaguarmicro.com>
Date: Tue, 1 Nov 2022 19:16:54 +0800
Subject: [PATCH 0125/1167] virtio_pci: modify ENOENT to EINVAL
Virtio_crypto use max_data_queues+1 to setup vqs,
we use vp_modern_get_num_queues to protect the vq range in setup_vq.
We could enter index >= vp_modern_get_num_queues(mdev) in setup_vq
if common->num_queues is not set well,and it return -ENOENT.
It is better to use -EINVAL instead.
Signed-off-by: Angus Chen <angus.chen@jaguarmicro.com>
Message-Id: <20221101111655.1947-1-angus.chen@jaguarmicro.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/virtio/virtio_pci_modern.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 207294bd7b9d6..9e496e288cfad 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -303,7 +303,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
int err;
if (index >= vp_modern_get_num_queues(mdev))
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(-EINVAL);
/* Check if queue is either not available or already active. */
num = vp_modern_get_queue_size(mdev, index);
--
GitLab
From 75e4ab9735a5a70612dd06461ca372b897bf371c Mon Sep 17 00:00:00 2001
From: Shaomin Deng <dengshaomin@cdjrlc.com>
Date: Sat, 5 Nov 2022 11:51:51 -0400
Subject: [PATCH 0126/1167] tools: Delete the unneeded semicolon after curly
braces
Unneeded semicolon after curly braces, so delete it.
Signed-off-by: Shaomin Deng <dengshaomin@cdjrlc.com>
Message-Id: <20221105155151.12155-1-dengshaomin@cdjrlc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
tools/virtio/virtio-trace/trace-agent-ctl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/virtio/virtio-trace/trace-agent-ctl.c b/tools/virtio/virtio-trace/trace-agent-ctl.c
index 73d253d4b559a..39860be6e2d86 100644
--- a/tools/virtio/virtio-trace/trace-agent-ctl.c
+++ b/tools/virtio/virtio-trace/trace-agent-ctl.c
@@ -75,7 +75,7 @@ static int wait_order(int ctl_fd)
if (ret)
break;
- };
+ }
return ret;
--
GitLab
From aeca7ff254843d49a8739f07f7dab1341450111d Mon Sep 17 00:00:00 2001
From: ruanjinjie <ruanjinjie@huawei.com>
Date: Thu, 10 Nov 2022 16:23:48 +0800
Subject: [PATCH 0127/1167] vdpa_sim: fix possible memory leak in
vdpasim_net_init() and vdpasim_blk_init()
Inject fault while probing module, if device_register() fails in
vdpasim_net_init() or vdpasim_blk_init(), but the refcount of kobject is
not decreased to 0, the name allocated in dev_set_name() is leaked.
Fix this by calling put_device(), so that name can be freed in
callback function kobject_cleanup().
(vdpa_sim_net)
unreferenced object 0xffff88807eebc370 (size 16):
comm "modprobe", pid 3848, jiffies 4362982860 (age 18.153s)
hex dump (first 16 bytes):
76 64 70 61 73 69 6d 5f 6e 65 74 00 6b 6b 6b a5 vdpasim_net.kkk.
backtrace:
[<ffffffff8174f19e>] __kmalloc_node_track_caller+0x4e/0x150
[<ffffffff81731d53>] kstrdup+0x33/0x60
[<ffffffff83a5d421>] kobject_set_name_vargs+0x41/0x110
[<ffffffff82d87aab>] dev_set_name+0xab/0xe0
[<ffffffff82d91a23>] device_add+0xe3/0x1a80
[<ffffffffa0270013>] 0xffffffffa0270013
[<ffffffff81001c27>] do_one_initcall+0x87/0x2e0
[<ffffffff813739cb>] do_init_module+0x1ab/0x640
[<ffffffff81379d20>] load_module+0x5d00/0x77f0
[<ffffffff8137bc40>] __do_sys_finit_module+0x110/0x1b0
[<ffffffff83c4d505>] do_syscall_64+0x35/0x80
[<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0
(vdpa_sim_blk)
unreferenced object 0xffff8881070c1250 (size 16):
comm "modprobe", pid 6844, jiffies 4364069319 (age 17.572s)
hex dump (first 16 bytes):
76 64 70 61 73 69 6d 5f 62 6c 6b 00 6b 6b 6b a5 vdpasim_blk.kkk.
backtrace:
[<ffffffff8174f19e>] __kmalloc_node_track_caller+0x4e/0x150
[<ffffffff81731d53>] kstrdup+0x33/0x60
[<ffffffff83a5d421>] kobject_set_name_vargs+0x41/0x110
[<ffffffff82d87aab>] dev_set_name+0xab/0xe0
[<ffffffff82d91a23>] device_add+0xe3/0x1a80
[<ffffffffa0220013>] 0xffffffffa0220013
[<ffffffff81001c27>] do_one_initcall+0x87/0x2e0
[<ffffffff813739cb>] do_init_module+0x1ab/0x640
[<ffffffff81379d20>] load_module+0x5d00/0x77f0
[<ffffffff8137bc40>] __do_sys_finit_module+0x110/0x1b0
[<ffffffff83c4d505>] do_syscall_64+0x35/0x80
[<ffffffff83e0006a>] entry_SYSCALL_64_after_hwframe+0x46/0xb0
Fixes: 899c4d187f6a ("vdpa_sim_blk: add support for vdpa management tool")
Fixes: a3c06ae158dd ("vdpa_sim_net: Add support for user supported devices")
Signed-off-by: ruanjinjie <ruanjinjie@huawei.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20221110082348.4105476-1-ruanjinjie@huawei.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 4 +++-
drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 4 +++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index c6db1a1baf768..f745926237a88 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -427,8 +427,10 @@ static int __init vdpasim_blk_init(void)
int ret;
ret = device_register(&vdpasim_blk_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_blk_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index c3cb225ea4693..11f5a121df243 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -305,8 +305,10 @@ static int __init vdpasim_net_init(void)
int ret;
ret = device_register(&vdpasim_net_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_net_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
--
GitLab
From 7a4efe182ca61fb3e5307e69b261c57cbf434cd4 Mon Sep 17 00:00:00 2001
From: Yuan Can <yuancan@huawei.com>
Date: Tue, 8 Nov 2022 10:17:05 +0000
Subject: [PATCH 0128/1167] vhost/vsock: Fix error handling in
vhost_vsock_init()
A problem about modprobe vhost_vsock failed is triggered with the
following log given:
modprobe: ERROR: could not insert 'vhost_vsock': Device or resource busy
The reason is that vhost_vsock_init() returns misc_register() directly
without checking its return value, if misc_register() failed, it returns
without calling vsock_core_unregister() on vhost_transport, resulting the
vhost_vsock can never be installed later.
A simple call graph is shown as below:
vhost_vsock_init()
vsock_core_register() # register vhost_transport
misc_register()
device_create_with_groups()
device_create_groups_vargs()
dev = kzalloc(...) # OOM happened
# return without unregister vhost_transport
Fix by calling vsock_core_unregister() when misc_register() returns error.
Fixes: 433fc58e6bf2 ("VSOCK: Introduce vhost_vsock.ko")
Signed-off-by: Yuan Can <yuancan@huawei.com>
Message-Id: <20221108101705.45981-1-yuancan@huawei.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/vsock.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index cd6f7776013ac..a2b3743723639 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -959,7 +959,14 @@ static int __init vhost_vsock_init(void)
VSOCK_TRANSPORT_F_H2G);
if (ret < 0)
return ret;
- return misc_register(&vhost_vsock_misc);
+
+ ret = misc_register(&vhost_vsock_misc);
+ if (ret) {
+ vsock_core_unregister(&vhost_transport.transport);
+ return ret;
+ }
+
+ return 0;
};
static void __exit vhost_vsock_exit(void)
--
GitLab
From f85efa9b0f5381874f727bd98f56787840313f0b Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 9 Nov 2022 11:25:02 +0100
Subject: [PATCH 0129/1167] vringh: fix range used in iotlb_translate()
vhost_iotlb_itree_first() requires `start` and `last` parameters
to search for a mapping that overlaps the range.
In iotlb_translate() we cyclically call vhost_iotlb_itree_first(),
incrementing `addr` by the amount already translated, so rightly
we move the `start` parameter passed to vhost_iotlb_itree_first(),
but we should hold the `last` parameter constant.
Let's fix it by saving the `last` parameter value before incrementing
`addr` in the loop.
Fixes: 9ad9c49cfe97 ("vringh: IOTLB support")
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20221109102503.18816-2-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vhost/vringh.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index c9f5c8ea3afbd..33eb941fcf154 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -1102,7 +1102,7 @@ static int iotlb_translate(const struct vringh *vrh,
struct vhost_iotlb_map *map;
struct vhost_iotlb *iotlb = vrh->iotlb;
int ret = 0;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
spin_lock(vrh->iotlb_lock);
@@ -1114,8 +1114,7 @@ static int iotlb_translate(const struct vringh *vrh,
break;
}
- map = vhost_iotlb_itree_first(iotlb, addr,
- addr + len - 1);
+ map = vhost_iotlb_itree_first(iotlb, addr, last);
if (!map || map->start > addr) {
ret = -EINVAL;
break;
--
GitLab
From 98047313cdb46828093894d0ac8b1183b8b317f9 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 9 Nov 2022 11:25:03 +0100
Subject: [PATCH 0130/1167] vhost: fix range used in translate_desc()
vhost_iotlb_itree_first() requires `start` and `last` parameters
to search for a mapping that overlaps the range.
In translate_desc() we cyclically call vhost_iotlb_itree_first(),
incrementing `addr` by the amount already translated, so rightly
we move the `start` parameter passed to vhost_iotlb_itree_first(),
but we should hold the `last` parameter constant.
Let's fix it by saving the `last` parameter value before incrementing
`addr` in the loop.
Fixes: a9709d6874d5 ("vhost: convert pre sorted vhost memory array to interval tree")
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20221109102503.18816-3-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vhost/vhost.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5c9fe3c9c3646..cbe72bfd2f1fa 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2053,7 +2053,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
struct vhost_dev *dev = vq->dev;
struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
struct iovec *_iov;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
int ret = 0;
while ((u64)len > s) {
@@ -2063,7 +2063,7 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
break;
}
- map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+ map = vhost_iotlb_itree_first(umem, addr, last);
if (map == NULL || map->start > addr) {
if (umem != dev->iotlb) {
ret = -EFAULT;
--
GitLab
From c070c1912a83432530cbb4271d5b9b11fa36b67a Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Wed, 9 Nov 2022 16:42:13 +0100
Subject: [PATCH 0131/1167] vhost-vdpa: fix an iotlb memory leak
Before commit 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB")
we called vhost_vdpa_iotlb_unmap(v, iotlb, 0ULL, 0ULL - 1) during
release to free all the resources allocated when processing user IOTLB
messages through vhost_vdpa_process_iotlb_update().
That commit changed the handling of IOTLB a bit, and we accidentally
removed some code called during the release.
We partially fixed this with commit 037d4305569a ("vhost-vdpa: call
vhost_vdpa_cleanup during the release") but a potential memory leak is
still there as showed by kmemleak if the application does not send
VHOST_IOTLB_INVALIDATE or crashes:
unreferenced object 0xffff888007fbaa30 (size 16):
comm "blkio-bench", pid 914, jiffies 4294993521 (age 885.500s)
hex dump (first 16 bytes):
40 73 41 07 80 88 ff ff 00 00 00 00 00 00 00 00 @sA.............
backtrace:
[<0000000087736d2a>] kmem_cache_alloc_trace+0x142/0x1c0
[<0000000060740f50>] vhost_vdpa_process_iotlb_msg+0x68c/0x901 [vhost_vdpa]
[<0000000083e8e205>] vhost_chr_write_iter+0xc0/0x4a0 [vhost]
[<000000008f2f414a>] vhost_vdpa_chr_write_iter+0x18/0x20 [vhost_vdpa]
[<00000000de1cd4a0>] vfs_write+0x216/0x4b0
[<00000000a2850200>] ksys_write+0x71/0xf0
[<00000000de8e720b>] __x64_sys_write+0x19/0x20
[<0000000018b12cbb>] do_syscall_64+0x3f/0x90
[<00000000986ec465>] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Let's fix this calling vhost_vdpa_iotlb_unmap() on the whole range in
vhost_vdpa_remove_as(). We move that call before vhost_dev_cleanup()
since we need a valid v->vdev.mm in vhost_vdpa_pa_unmap().
vhost_iotlb_reset() call can be removed, since vhost_vdpa_iotlb_unmap()
on the whole range removes all the entries.
The kmemleak log reported was observed with a vDPA device that has `use_va`
set to true (e.g. VDUSE). This patch has been tested with both types of
devices.
Fixes: 037d4305569a ("vhost-vdpa: call vhost_vdpa_cleanup during the release")
Fixes: 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20221109154213.146789-1-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/vdpa.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 166044642fd5c..b08e07fc7d1ff 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -65,6 +65,10 @@ static DEFINE_IDA(vhost_vdpa_ida);
static dev_t vhost_vdpa_major;
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb *iotlb,
+ u64 start, u64 last);
+
static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
{
struct vhost_vdpa_as *as = container_of(iotlb, struct
@@ -135,7 +139,7 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)
return -EINVAL;
hlist_del(&as->hash_link);
- vhost_iotlb_reset(&as->iotlb);
+ vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1);
kfree(as);
return 0;
@@ -1162,14 +1166,14 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v)
struct vhost_vdpa_as *as;
u32 asid;
- vhost_dev_cleanup(&v->vdev);
- kfree(v->vdev.vqs);
-
for (asid = 0; asid < v->vdpa->nas; asid++) {
as = asid_to_as(v, asid);
if (as)
vhost_vdpa_remove_as(v, asid);
}
+
+ vhost_dev_cleanup(&v->vdev);
+ kfree(v->vdev.vqs);
}
static int vhost_vdpa_open(struct inode *inode, struct file *filep)
--
GitLab
From f4e468f708386ce5fa6878a7ef43a9818ceeaecf Mon Sep 17 00:00:00 2001
From: Angus Chen <angus.chen@jaguarmicro.com>
Date: Thu, 10 Nov 2022 11:01:23 +0800
Subject: [PATCH 0132/1167] virtio_blk: use UINT_MAX instead of -1U
We use UINT_MAX to limit max_discard_sectors in virtblk_probe,
we can use UINT_MAX to limit max_hw_sectors for consistencies.
No functional change intended.
Signed-off-by: Angus Chen <angus.chen@jaguarmicro.com>
Message-Id: <20221110030124.1986-1-angus.chen@jaguarmicro.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
drivers/block/virtio_blk.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 271a9878fa8b3..dcbf86cd2155e 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -994,7 +994,7 @@ static int virtblk_probe(struct virtio_device *vdev)
blk_queue_max_segments(q, sg_elems);
/* No real sector limit. */
- blk_queue_max_hw_sectors(q, -1U);
+ blk_queue_max_hw_sectors(q, UINT_MAX);
max_size = virtio_max_dma_size(vdev);
--
GitLab
From 794ec498c9fa79e6bfd71b931410d5897a9c00d4 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 10 Nov 2022 15:13:35 +0100
Subject: [PATCH 0133/1167] vdpa_sim: fix vringh initialization in
vdpasim_queue_ready()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When we initialize vringh, we should pass the features and the
number of elements in the virtqueue negotiated with the driver,
otherwise operations with vringh may fail.
This was discovered in a case where the driver sets a number of
elements in the virtqueue different from the value returned by
.get_vq_num_max().
In vdpasim_vq_reset() is safe to initialize the vringh with
default values, since the virtqueue will not be used until
vdpasim_queue_ready() is called again.
Fixes: 2c53d0f64c06 ("vdpasim: vDPA device simulator")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20221110141335.62171-1-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
---
drivers/vdpa/vdpa_sim/vdpa_sim.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index b071f0d842fba..b20689f8fe89c 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -67,8 +67,7 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
{
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
- vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
- VDPASIM_QUEUE_MAX, false,
+ vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false,
(struct vring_desc *)(uintptr_t)vq->desc_addr,
(struct vring_avail *)
(uintptr_t)vq->driver_addr,
--
GitLab
From a4722f64f924a9992efc08d141c21b2da02b70f3 Mon Sep 17 00:00:00 2001
From: wangjianli <wangjianli@cdjrlc.com>
Date: Sun, 13 Nov 2022 15:07:42 +0800
Subject: [PATCH 0134/1167] tools/virtio: Variable type completion
Replace "unsigned" with "unsigned int"
Signed-off-by: wangjianli <wangjianli@cdjrlc.com>
Message-Id: <20221113070742.48271-1-wangjianli@cdjrlc.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
tools/virtio/virtio_test.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index 86a410ddcedde..120062f94590c 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -173,7 +173,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
long started = 0, completed = 0, next_reset = reset_n;
long completed_before, started_before;
int r, test = 1;
- unsigned len;
+ unsigned int len;
long long spurious = 0;
const bool random_batch = batch == RANDOM_BATCH;
--
GitLab
From b1d65f717cd6305a396a8738e022c6f7c65cfbe8 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 14 Nov 2022 11:07:40 +0000
Subject: [PATCH 0135/1167] virtio-crypto: fix memory leak in
virtio_crypto_alg_skcipher_close_session()
'vc_ctrl_req' is alloced in virtio_crypto_alg_skcipher_close_session(),
and should be freed in the invalid ctrl_status->status error handling
case. Otherwise there is a memory leak.
Fixes: 0756ad15b1fe ("virtio-crypto: use private buffer for control request")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Message-Id: <20221114110740.537276-1-weiyongjun@huaweicloud.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Gonglei <arei.gonglei@huawei.com>
Acked-by: zhenwei pi<pizhenwei@bytedance.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/crypto/virtio/virtio_crypto_skcipher_algs.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c
index e553ccadbcbc8..e5876286828b8 100644
--- a/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_skcipher_algs.c
@@ -239,7 +239,8 @@ static int virtio_crypto_alg_skcipher_close_session(
pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n",
ctrl_status->status, destroy_session->session_id);
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
err = 0;
--
GitLab
From c8e82e3877028381969779a86972d9a4f57a9ea0 Mon Sep 17 00:00:00 2001
From: Dawei Li <set_pte_at@outlook.com>
Date: Fri, 25 Nov 2022 00:12:14 +0800
Subject: [PATCH 0136/1167] virtio: Implementing attribute show with sysfs_emit
Replace sprintf with sysfs_emit or its variants for their
built-in PAGE_SIZE awareness.
Signed-off-by: Dawei Li <set_pte_at@outlook.com>
Message-Id: <TYCP286MB23232A999FE7DBDF50BA0FAACA0F9@TYCP286MB2323.JPNP286.PROD.OUTLOOK.COM>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/virtio/virtio.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 828ced0607423..b9a80aedee1b7 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -15,7 +15,7 @@ static ssize_t device_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.device);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.device);
}
static DEVICE_ATTR_RO(device);
@@ -23,7 +23,7 @@ static ssize_t vendor_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
}
static DEVICE_ATTR_RO(vendor);
@@ -31,7 +31,7 @@ static ssize_t status_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+ return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
}
static DEVICE_ATTR_RO(status);
@@ -39,7 +39,7 @@ static ssize_t modalias_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "virtio:d%08Xv%08X\n",
+ return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
dev->id.device, dev->id.vendor);
}
static DEVICE_ATTR_RO(modalias);
@@ -54,9 +54,9 @@ static ssize_t features_show(struct device *_d,
/* We actually represent this as a bitstring, as it could be
* arbitrary length in future. */
for (i = 0; i < sizeof(dev->features)*8; i++)
- len += sprintf(buf+len, "%c",
+ len += sysfs_emit_at(buf, len, "%c",
__virtio_test_bit(dev, i) ? '1' : '0');
- len += sprintf(buf+len, "\n");
+ len += sysfs_emit_at(buf, len, "\n");
return len;
}
static DEVICE_ATTR_RO(features);
--
GitLab
From e794070af224ade46db368271896b2685ff4f96b Mon Sep 17 00:00:00 2001
From: Cindy Lu <lulu@redhat.com>
Date: Mon, 19 Dec 2022 15:33:31 +0800
Subject: [PATCH 0137/1167] vhost_vdpa: fix the crash in unmap a large memory
While testing in vIOMMU, sometimes Guest will unmap very large memory,
which will cause the crash. To fix this, add a new function
vhost_vdpa_general_unmap(). This function will only unmap the memory
that saved in iotlb.
Call Trace:
[ 647.820144] ------------[ cut here ]------------
[ 647.820848] kernel BUG at drivers/iommu/intel/iommu.c:1174!
[ 647.821486] invalid opcode: 0000 [#1] PREEMPT SMP PTI
[ 647.822082] CPU: 10 PID: 1181 Comm: qemu-system-x86 Not tainted 6.0.0-rc1home_lulu_2452_lulu7_vhost+ #62
[ 647.823139] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.15.0-29-g6a62e0cb0dfe-prebuilt.qem4
[ 647.824365] RIP: 0010:domain_unmap+0x48/0x110
[ 647.825424] Code: 48 89 fb 8d 4c f6 1e 39 c1 0f 4f c8 83 e9 0c 83 f9 3f 7f 18 48 89 e8 48 d3 e8 48 85 c0 75 59
[ 647.828064] RSP: 0018:ffffae5340c0bbf0 EFLAGS: 00010202
[ 647.828973] RAX: 0000000000000001 RBX: ffff921793d10540 RCX: 000000000000001b
[ 647.830083] RDX: 00000000080000ff RSI: 0000000000000001 RDI: ffff921793d10540
[ 647.831214] RBP: 0000000007fc0100 R08: ffffae5340c0bcd0 R09: 0000000000000003
[ 647.832388] R10: 0000007fc0100000 R11: 0000000000100000 R12: 00000000080000ff
[ 647.833668] R13: ffffae5340c0bcd0 R14: ffff921793d10590 R15: 0000008000100000
[ 647.834782] FS: 00007f772ec90640(0000) GS:ffff921ce7a80000(0000) knlGS:0000000000000000
[ 647.836004] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 647.836990] CR2: 00007f02c27a3a20 CR3: 0000000101b0c006 CR4: 0000000000372ee0
[ 647.838107] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 647.839283] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 647.840666] Call Trace:
[ 647.841437] <TASK>
[ 647.842107] intel_iommu_unmap_pages+0x93/0x140
[ 647.843112] __iommu_unmap+0x91/0x1b0
[ 647.844003] iommu_unmap+0x6a/0x95
[ 647.844885] vhost_vdpa_unmap+0x1de/0x1f0 [vhost_vdpa]
[ 647.845985] vhost_vdpa_process_iotlb_msg+0xf0/0x90b [vhost_vdpa]
[ 647.847235] ? _raw_spin_unlock+0x15/0x30
[ 647.848181] ? _copy_from_iter+0x8c/0x580
[ 647.849137] vhost_chr_write_iter+0xb3/0x430 [vhost]
[ 647.850126] vfs_write+0x1e4/0x3a0
[ 647.850897] ksys_write+0x53/0xd0
[ 647.851688] do_syscall_64+0x3a/0x90
[ 647.852508] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 647.853457] RIP: 0033:0x7f7734ef9f4f
[ 647.854408] Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 29 76 f8 ff 48 8b 54 24 18 48 8b 74 24 10 41 89 c8
[ 647.857217] RSP: 002b:00007f772ec8f040 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
[ 647.858486] RAX: ffffffffffffffda RBX: 00000000fef00000 RCX: 00007f7734ef9f4f
[ 647.859713] RDX: 0000000000000048 RSI: 00007f772ec8f090 RDI: 0000000000000010
[ 647.860942] RBP: 00007f772ec8f1a0 R08: 0000000000000000 R09: 0000000000000000
[ 647.862206] R10: 0000000000000001 R11: 0000000000000293 R12: 0000000000000010
[ 647.863446] R13: 0000000000000002 R14: 0000000000000000 R15: ffffffff01100000
[ 647.864692] </TASK>
[ 647.865458] Modules linked in: rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs v]
[ 647.874688] ---[ end trace 0000000000000000 ]---
Cc: stable@vger.kernel.org
Fixes: 4c8cf31885f6 ("vhost: introduce vDPA-based backend")
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20221219073331.556140-1-lulu@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vhost/vdpa.c | 46 +++++++++++++++++++++++++-------------------
1 file changed, 26 insertions(+), 20 deletions(-)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index b08e07fc7d1ff..ec32f785dfdec 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -66,8 +66,8 @@ static DEFINE_IDA(vhost_vdpa_ida);
static dev_t vhost_vdpa_major;
static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last);
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid);
static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
{
@@ -139,7 +139,7 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)
return -EINVAL;
hlist_del(&as->hash_link);
- vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1);
+ vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
kfree(as);
return 0;
@@ -687,10 +687,20 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
mutex_unlock(&d->mutex);
return r;
}
+static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb_map *map, u32 asid)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+ if (ops->dma_map) {
+ ops->dma_unmap(vdpa, asid, map->start, map->size);
+ } else if (ops->set_map == NULL) {
+ iommu_unmap(v->domain, map->start, map->size);
+ }
+}
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb_map *map;
@@ -707,13 +717,13 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
unpin_user_page(page);
}
atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_iotlb_map *map;
struct vdpa_map_file *map_file;
@@ -722,20 +732,21 @@ static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
map_file = (struct vdpa_map_file *)map->opaque;
fput(map_file->file);
kfree(map_file);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid)
{
struct vdpa_device *vdpa = v->vdpa;
if (vdpa->use_va)
- return vhost_vdpa_va_unmap(v, iotlb, start, last);
+ return vhost_vdpa_va_unmap(v, iotlb, start, last, asid);
- return vhost_vdpa_pa_unmap(v, iotlb, start, last);
+ return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid);
}
static int perm_to_iommu_flags(u32 perm)
@@ -802,17 +813,12 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,
const struct vdpa_config_ops *ops = vdpa->config;
u32 asid = iotlb_to_asid(iotlb);
- vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
+ vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid);
- if (ops->dma_map) {
- ops->dma_unmap(vdpa, asid, iova, size);
- } else if (ops->set_map) {
+ if (ops->set_map) {
if (!v->in_batch)
ops->set_map(vdpa, asid, iotlb);
- } else {
- iommu_unmap(v->domain, iova, size);
}
-
/* If we are in the middle of batch processing, delay the free
* of AS until BATCH_END.
*/
--
GitLab
From 8aeac42d60936046a00e67cdf7d27b061df2962f Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Sun, 27 Nov 2022 19:43:46 -0800
Subject: [PATCH 0138/1167] tools/virtio: remove stray characters
__read_once_size() is not a macro, remove those '/'s.
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Message-Id: <20221128034347.990-2-dave@stgolabs.net>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
tools/virtio/ringtest/main.h | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 6d1fccd3d86ce..9ed09caa659e7 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -149,16 +149,16 @@ static inline void busy_wait(void)
static __always_inline
void __read_once_size(const volatile void *p, void *res, int size)
{
- switch (size) { \
- case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break; \
- case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break; \
- case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break; \
- case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break; \
- default: \
- barrier(); \
- __builtin_memcpy((void *)res, (const void *)p, size); \
- barrier(); \
- } \
+ switch (size) {
+ case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;
+ case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;
+ case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;
+ case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)res, (const void *)p, size);
+ barrier();
+ }
}
static __always_inline void __write_once_size(volatile void *p, void *res, int size)
--
GitLab
From 81931012bd7dc52fadf2b720605fce8a7148d4a7 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Sun, 27 Nov 2022 19:43:47 -0800
Subject: [PATCH 0139/1167] tools/virtio: remove smp_read_barrier_depends()
This gets rid of the last references to smp_read_barrier_depends()
which for the kernel side was removed in v5.9. The serialization
required for Alpha is done inside READ_ONCE() instead of having
users deal with it. Simply use a full barrier, the architecture
does not have rmb in the first place.
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Message-Id: <20221128034347.990-3-dave@stgolabs.net>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
tools/virtio/ringtest/main.h | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 9ed09caa659e7..b68920d527503 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -140,12 +140,6 @@ static inline void busy_wait(void)
#define smp_wmb() smp_release()
#endif
-#ifdef __alpha__
-#define smp_read_barrier_depends() smp_acquire()
-#else
-#define smp_read_barrier_depends() do {} while(0)
-#endif
-
static __always_inline
void __read_once_size(const volatile void *p, void *res, int size)
{
@@ -175,13 +169,22 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
}
}
+#ifdef __alpha__
#define READ_ONCE(x) \
({ \
union { typeof(x) __val; char __c[1]; } __u; \
__read_once_size(&(x), __u.__c, sizeof(x)); \
- smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
+ smp_mb(); /* Enforce dependency ordering from x */ \
__u.__val; \
})
+#else
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
+ __u.__val; \
+})
+#endif
#define WRITE_ONCE(x, val) \
({ \
--
GitLab
From 937c783aa3d8d77963ec91918d3298edb45b9161 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 28 Nov 2022 07:57:15 -0800
Subject: [PATCH 0140/1167] vduse: Validate vq_num in vduse_validate_config()
Add a limit to 'config->vq_num' which is user controlled data which
comes from an vduse_ioctl to prevent large memory allocations.
Micheal says - This limit is somewhat arbitrary.
However, currently virtio pci and ccw are limited to a 16 bit vq number.
While MMIO isn't it is also isn't used with lots of VQs due to
current lack of support for per-vq interrupts.
Thus, the 0xffff limit on number of VQs corresponding
to a 16-bit VQ number seems sufficient for now.
This is found using static analysis with smatch.
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Message-Id: <20221128155717.2579992-1-harshit.m.mogalapalli@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vdpa/vdpa_user/vduse_dev.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 0dd3c1f291da3..0c3b48616a9f3 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1440,6 +1440,9 @@ static bool vduse_validate_config(struct vduse_dev_config *config)
if (config->config_size > PAGE_SIZE)
return false;
+ if (config->vq_num > 0xffff)
+ return false;
+
if (!device_is_allowed(config->device_id))
return false;
--
GitLab
From ed843d6ed7310a27cf7c8ee0a82a482eed0cb4a6 Mon Sep 17 00:00:00 2001
From: Rong Wang <wangrong68@huawei.com>
Date: Wed, 7 Dec 2022 20:08:13 +0800
Subject: [PATCH 0141/1167] vdpa/vp_vdpa: fix kfree a wrong pointer in
vp_vdpa_remove
In vp_vdpa_remove(), the code kfree(&vp_vdpa_mgtdev->mgtdev.id_table) uses
a reference of pointer as the argument of kfree, which is the wrong pointer
and then may hit crash like this:
Unable to handle kernel paging request at virtual address 00ffff003363e30c
Internal error: Oops: 96000004 [#1] SMP
Call trace:
rb_next+0x20/0x5c
ext4_readdir+0x494/0x5c4 [ext4]
iterate_dir+0x168/0x1b4
__se_sys_getdents64+0x68/0x170
__arm64_sys_getdents64+0x24/0x30
el0_svc_common.constprop.0+0x7c/0x1bc
do_el0_svc+0x2c/0x94
el0_svc+0x20/0x30
el0_sync_handler+0xb0/0xb4
el0_sync+0x160/0x180
Code: 54000220 f9400441 b4000161 aa0103e0 (f9400821)
SMP: stopping secondary CPUs
Starting crashdump kernel...
Fixes: ffbda8e9df10 ("vdpa/vp_vdpa : add vdpa tool support in vp_vdpa")
Signed-off-by: Rong Wang <wangrong68@huawei.com>
Signed-off-by: Nanyong Sun <sunnanyong@huawei.com>
Message-Id: <20221207120813.2837529-1-sunnanyong@huawei.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cindy Lu <lulu@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vdpa/virtio_pci/vp_vdpa.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index d448db0c4de3f..8fe267ca3e76f 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -647,7 +647,7 @@ static void vp_vdpa_remove(struct pci_dev *pdev)
mdev = vp_vdpa_mgtdev->mdev;
vp_modern_remove(mdev);
vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
- kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+ kfree(vp_vdpa_mgtdev->mgtdev.id_table);
kfree(mdev);
kfree(vp_vdpa_mgtdev);
}
--
GitLab
From 1c96d5457f7251d1c62aacc04921557d56fc049a Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 7 Sep 2022 14:01:10 +0800
Subject: [PATCH 0142/1167] vdpa: conditionally fill max max queue pair for
stats
For the device without multiqueue feature, we will read 0 as
max_virtqueue_pairs from the config. So if we fill
VDPA_ATTR_DEV_NET_CFG_MAX_VQP with the value we read from the config
we will confuse the user.
Fixing this by only filling the value when multiqueue is offered by
the device so userspace can assume 1 when the attr is not provided.
Fixes: 13b00b135665c("vdpa: Add support for querying vendor statistics")
Cc: Eli Cohen <elic@nvidia.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20220907060110.4511-1-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Eli Cohen <elic@nvidia.com>
---
drivers/vdpa/vdpa.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 41ed56362992b..8ef7aa1365cc5 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -935,7 +935,6 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
{
struct virtio_net_config config = {};
u64 features;
- u16 max_vqp;
u8 status;
int err;
@@ -946,15 +945,15 @@ static int vdpa_fill_stats_rec(struct vdpa_device *vdev, struct sk_buff *msg,
}
vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
- max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs);
- if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
- return -EMSGSIZE;
-
features = vdev->config->get_driver_features(vdev);
if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
features, VDPA_ATTR_PAD))
return -EMSGSIZE;
+ err = vdpa_dev_net_mq_config_fill(msg, features, &config);
+ if (err)
+ return err;
+
if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
return -EMSGSIZE;
--
GitLab
From 0b7a04a30eef20e6b24926a45c0ce7906ae85bd6 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 13 Dec 2022 17:07:17 +0800
Subject: [PATCH 0143/1167] vdpasim: fix memory leak when freeing IOTLBs
After commit bda324fd037a ("vdpasim: control virtqueue support"),
vdpasim->iommu became an array of IOTLB, so we should clean the
mappings of each free one by one instead of just deleting the ranges
in the first IOTLB which may leak maps.
Fixes: bda324fd037a ("vdpasim: control virtqueue support")
Cc: Gautam Dawar <gautam.dawar@xilinx.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20221213090717.61529-1-jasowang@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Gautam Dawar <gautam.dawar@amd.com>
---
drivers/vdpa/vdpa_sim/vdpa_sim.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index b20689f8fe89c..cb88891b44a8c 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -689,7 +689,9 @@ static void vdpasim_free(struct vdpa_device *vdpa)
}
kvfree(vdpasim->buffer);
- vhost_iotlb_free(vdpasim->iommu);
+ for (i = 0; i < vdpasim->dev_attr.nas; i++)
+ vhost_iotlb_reset(&vdpasim->iommu[i]);
+ kfree(vdpasim->iommu);
kfree(vdpasim->vqs);
kfree(vdpasim->config);
}
--
GitLab
From 72455a1142527e607e1d69439f3ffa2ef6d09e26 Mon Sep 17 00:00:00 2001
From: Cindy Lu <lulu@redhat.com>
Date: Wed, 14 Dec 2022 13:43:06 +0800
Subject: [PATCH 0144/1167] vdpa_sim_net: should not drop the
multicast/broadcast packet
In the receive_filter(), should not drop the packet with the
broadcast/multicast address. Add the check for this
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20221214054306.24145-1-lulu@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index 11f5a121df243..584b975a98a7e 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -62,6 +62,9 @@ static bool receive_filter(struct vdpasim *vdpasim, size_t len)
if (len < ETH_ALEN + hdr_len)
return false;
+ if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
+ is_multicast_ether_addr(vdpasim->buffer + hdr_len))
+ return true;
if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
return true;
--
GitLab
From a26116c1e74028914f281851488546c91cbae57d Mon Sep 17 00:00:00 2001
From: Rafael Mendonca <rafaelmendsr@gmail.com>
Date: Fri, 21 Oct 2022 17:41:26 -0300
Subject: [PATCH 0145/1167] virtio_blk: Fix signedness bug in virtblk_prep_rq()
The virtblk_map_data() function returns negative error codes, however, the
'nents' field of vbr->sg_table is an unsigned int, which causes the error
handling not to work correctly.
Cc: stable@vger.kernel.org
Fixes: 0e9911fa768f ("virtio-blk: support mq_ops->queue_rqs()")
Signed-off-by: Rafael Mendonca <rafaelmendsr@gmail.com>
Message-Id: <20221021204126.927603-1-rafaelmendsr@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Suwan Kim <suwan.kim027@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
drivers/block/virtio_blk.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index dcbf86cd2155e..6a77fa9174288 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -334,14 +334,16 @@ static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
struct virtblk_req *vbr)
{
blk_status_t status;
+ int num;
status = virtblk_setup_cmd(vblk->vdev, req, vbr);
if (unlikely(status))
return status;
- vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
- if (unlikely(vbr->sg_table.nents < 0))
+ num = virtblk_map_data(hctx, req, vbr);
+ if (unlikely(num < 0))
return virtblk_fail_to_queue(req, -ENOMEM);
+ vbr->sg_table.nents = num;
blk_mq_start_request(req);
--
GitLab
From b51b75f0604f17c0f6f3b6f68f1a521a5cc6b04f Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Wed, 7 Dec 2022 14:52:20 -0800
Subject: [PATCH 0146/1167] dmaengine: idxd: Let probe fail when workqueue
cannot be enabled
The workqueue is enabled when the appropriate driver is loaded and
disabled when the driver is removed. When the driver is removed it
assumes that the workqueue was enabled successfully and proceeds to
free allocations made during workqueue enabling.
Failure during workqueue enabling does not prevent the driver from
being loaded. This is because the error path within drv_enable_wq()
returns success unless a second failure is encountered
during the error path. By returning success it is possible to load
the driver even if the workqueue cannot be enabled and
allocations that do not exist are attempted to be freed during
driver remove.
Some examples of problematic flows:
(a)
idxd_dmaengine_drv_probe() -> drv_enable_wq() -> idxd_wq_request_irq():
In above flow, if idxd_wq_request_irq() fails then
idxd_wq_unmap_portal() is called on error exit path, but
drv_enable_wq() returns 0 because idxd_wq_disable() succeeds. The
driver is thus loaded successfully.
idxd_dmaengine_drv_remove()->drv_disable_wq()->idxd_wq_unmap_portal()
Above flow on driver unload triggers the WARN in devm_iounmap() because
the device resource has already been removed during error path of
drv_enable_wq().
(b)
idxd_dmaengine_drv_probe() -> drv_enable_wq() -> idxd_wq_request_irq():
In above flow, if idxd_wq_request_irq() fails then
idxd_wq_init_percpu_ref() is never called to initialize the percpu
counter, yet the driver loads successfully because drv_enable_wq()
returns 0.
idxd_dmaengine_drv_remove()->__idxd_wq_quiesce()->percpu_ref_kill():
Above flow on driver unload triggers a BUG when attempting to drop the
initial ref of the uninitialized percpu ref:
BUG: kernel NULL pointer dereference, address: 0000000000000010
Fix the drv_enable_wq() error path by returning the original error that
indicates failure of workqueue enabling. This ensures that the probe
fails when an error is encountered and the driver remove paths are only
attempted when the workqueue was enabled successfully.
Fixes: 1f2bb40337f0 ("dmaengine: idxd: move wq_enable() to device.c")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/e8d8116e5efa0fd14fadc5adae6ffd319f0e5ff1.1670452419.git.reinette.chatre@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/idxd/device.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 06f5d3783d771..c5523ced2e3a4 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1390,8 +1390,7 @@ int drv_enable_wq(struct idxd_wq *wq)
err_irq:
idxd_wq_unmap_portal(wq);
err_map_portal:
- rc = idxd_wq_disable(wq, false);
- if (rc < 0)
+ if (idxd_wq_disable(wq, false))
dev_dbg(dev, "wq %s disable failed\n", dev_name(wq_confdev(wq)));
err:
return rc;
--
GitLab
From 1beeec45f9ac31eba52478379f70a5fa9c2ad005 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Wed, 7 Dec 2022 14:52:21 -0800
Subject: [PATCH 0147/1167] dmaengine: idxd: Prevent use after free on
completion memory
On driver unload any pending descriptors are flushed at the
time the interrupt is freed:
idxd_dmaengine_drv_remove() ->
drv_disable_wq() ->
idxd_wq_free_irq() ->
idxd_flush_pending_descs().
If there are any descriptors present that need to be flushed this
flow triggers a "not present" page fault as below:
BUG: unable to handle page fault for address: ff391c97c70c9040
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
The address that triggers the fault is the address of the
descriptor that was freed moments earlier via:
drv_disable_wq()->idxd_wq_free_resources()
Fix the use after free by freeing the descriptors after any possible
usage. This is done after idxd_wq_reset() to ensure that the memory
remains accessible during possible completion writes by the device.
Fixes: 63c14ae6c161 ("dmaengine: idxd: refactor wq driver enable/disable operations")
Suggested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/6c4657d9cff0a0a00501a7b928297ac966e9ec9d.1670452419.git.reinette.chatre@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/idxd/device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index c5523ced2e3a4..cd792f3f9873f 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1407,11 +1407,11 @@ void drv_disable_wq(struct idxd_wq *wq)
dev_warn(dev, "Clients has claim on wq %d: %d\n",
wq->id, idxd_wq_refcount(wq));
- idxd_wq_free_resources(wq);
idxd_wq_unmap_portal(wq);
idxd_wq_drain(wq);
idxd_wq_free_irq(wq);
idxd_wq_reset(wq);
+ idxd_wq_free_resources(wq);
percpu_ref_exit(&wq->wq_active);
wq->type = IDXD_WQT_NONE;
wq->client_count = 0;
--
GitLab
From 6744a030d81e456883bfbb627ac1f30465c1a989 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Wed, 7 Dec 2022 14:52:22 -0800
Subject: [PATCH 0148/1167] dmaengine: idxd: Do not call DMX TX callbacks
during workqueue disable
On driver unload any pending descriptors are flushed and pending
DMA descriptors are explicitly completed:
idxd_dmaengine_drv_remove() ->
drv_disable_wq() ->
idxd_wq_free_irq() ->
idxd_flush_pending_descs() ->
idxd_dma_complete_txd()
With this done during driver unload any remaining descriptor is
likely stuck and can be dropped. Even so, the descriptor may still
have a callback set that could no longer be accessible. An
example of such a problem is when the dmatest fails and the dmatest
module is unloaded. The failure of dmatest leaves descriptors with
dma_async_tx_descriptor::callback pointing to code that no longer
exist. This causes a page fault as below at the time the IDXD driver
is unloaded when it attempts to run the callback:
BUG: unable to handle page fault for address: ffffffffc0665190
#PF: supervisor instruction fetch in kernel mode
#PF: error_code(0x0010) - not-present page
Fix this by clearing the callback pointers on the transmit
descriptors only when workqueue is disabled.
Fixes: 403a2e236538 ("dmaengine: idxd: change MSIX allocation based on per wq activation")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/37d06b772aa7f8863ca50f90930ea2fd80b38fc3.1670452419.git.reinette.chatre@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/idxd/device.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index cd792f3f9873f..29dbb0f52e186 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -1172,8 +1172,19 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
spin_unlock(&ie->list_lock);
list_for_each_entry_safe(desc, itr, &flist, list) {
+ struct dma_async_tx_descriptor *tx;
+
list_del(&desc->list);
ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
+ /*
+ * wq is being disabled. Any remaining descriptors are
+ * likely to be stuck and can be dropped. callback could
+ * point to code that is no longer accessible, for example
+ * if dmatest module has been unloaded.
+ */
+ tx = &desc->txd;
+ tx->callback = NULL;
+ tx->callback_result = NULL;
idxd_dma_complete_txd(desc, ctype, true);
}
}
--
GitLab
From efab25894a41a920d9581183741e7fadba00719c Mon Sep 17 00:00:00 2001
From: Jayesh Choudhary <j-choudhary@ti.com>
Date: Mon, 28 Nov 2022 14:20:05 +0530
Subject: [PATCH 0149/1167] dmaengine: ti: k3-udma: Do conditional decrement of
UDMA_CHAN_RT_PEER_BCNT_REG
PSIL_EP_NATIVE endpoints may not have PEER registers for BCNT and thus
udma_decrement_byte_counters() should not try to decrement these counters.
This fixes the issue of crypto IPERF testing where the client side (EVM)
hangs without transfer of packets to the server side, seen since this
function was added.
Fixes: 7c94dcfa8fcf ("dmaengine: ti: k3-udma: Reset UDMA_CHAN_RT byte counters to prevent overflow")
Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
Acked-by: Peter Ujfalusi <peter.ujfalusi@gmail.com>
Link: https://lore.kernel.org/r/20221128085005.489964-1-j-choudhary@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/ti/k3-udma.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index ce8b80bb34d7d..4c62274e0b332 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -762,11 +762,12 @@ static void udma_decrement_byte_counters(struct udma_chan *uc, u32 val)
if (uc->desc->dir == DMA_DEV_TO_MEM) {
udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
- udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
+ if (uc->config.ep_type != PSIL_EP_NATIVE)
+ udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
} else {
udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val);
udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val);
- if (!uc->bchan)
+ if (!uc->bchan && uc->config.ep_type != PSIL_EP_NATIVE)
udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val);
}
}
--
GitLab
From f96a483f8e131de50ebf30589ffba1a4f6bd12f7 Mon Sep 17 00:00:00 2001
From: Jie Hai <haijie1@huawei.com>
Date: Sat, 26 Nov 2022 14:49:38 +0800
Subject: [PATCH 0150/1167] MAINTAINERS: update Jie Hai's email address
Signed-off-by: Jie Hai <haijie1@huawei.com>
Link: https://lore.kernel.org/r/20221126064938.50685-1-haijie1@huawei.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index f61eb221415bd..ef4d96db17c16 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9299,7 +9299,7 @@ F: net/dsa/tag_hellcreek.c
HISILICON DMA DRIVER
M: Zhou Wang <wangzhou1@hisilicon.com>
-M: Jie Hai <haijie1@hisilicon.com>
+M: Jie Hai <haijie1@huawei.com>
L: dmaengine@vger.kernel.org
S: Maintained
F: drivers/dma/hisi_dma.c
--
GitLab
From 9deb1e9fb88b1120a908676fa33bdf9e2eeaefce Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Mon, 26 Dec 2022 14:48:23 +0300
Subject: [PATCH 0151/1167] net/ethtool/ioctl: return -EOPNOTSUPP if we have no
phy stats
It's not very useful to copy back an empty ethtool_stats struct and
return 0 if we didn't actually have any stats. This also allows for
further simplification of this function in the future commits.
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ethtool/ioctl.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index c2f1a542e6fa9..932fa8225b2f3 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2099,7 +2099,8 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
return n_stats;
if (n_stats > S32_MAX / sizeof(u64))
return -ENOMEM;
- WARN_ON_ONCE(!n_stats);
+ if (WARN_ON_ONCE(!n_stats))
+ return -EOPNOTSUPP;
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
--
GitLab
From fd4778581d61d8848b532f8cdc9b325138748437 Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Mon, 26 Dec 2022 14:48:24 +0300
Subject: [PATCH 0152/1167] net/ethtool/ioctl: remove if n_stats checks from
ethtool_get_phy_stats
Now that we always early return if we don't have any stats we can remove
these checks as they're no longer necessary.
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ethtool/ioctl.c | 24 ++++++++++--------------
1 file changed, 10 insertions(+), 14 deletions(-)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 932fa8225b2f3..85f0cffdcec8a 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2107,28 +2107,24 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
stats.n_stats = n_stats;
- if (n_stats) {
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (!data)
- return -ENOMEM;
+ data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!data)
+ return -ENOMEM;
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_stats) {
- ret = phy_ops->get_stats(phydev, &stats, data);
- if (ret < 0)
- goto out;
- } else {
- ops->get_ethtool_phy_stats(dev, &stats, data);
- }
+ if (phydev && !ops->get_ethtool_phy_stats &&
+ phy_ops && phy_ops->get_stats) {
+ ret = phy_ops->get_stats(phydev, &stats, data);
+ if (ret < 0)
+ goto out;
} else {
- data = NULL;
+ ops->get_ethtool_phy_stats(dev, &stats, data);
}
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
goto out;
useraddr += sizeof(stats);
- if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
+ if (copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
goto out;
ret = 0;
--
GitLab
From 201ed315f9676809cd5b20a39206e964106d4f27 Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Mon, 26 Dec 2022 14:48:25 +0300
Subject: [PATCH 0153/1167] net/ethtool/ioctl: split ethtool_get_phy_stats into
multiple helpers
So that it's easier to follow and make sense of the branching and
various conditions.
Stats retrieval has been split into two separate functions
ethtool_get_phy_stats_phydev & ethtool_get_phy_stats_ethtool.
The former attempts to retrieve the stats using phydev & phy_ops, while
the latter uses ethtool_ops.
Actual n_stats validation & array allocation has been moved into a new
ethtool_vzalloc_stats_array helper.
This also fixes a potential NULL dereference of
ops->get_ethtool_phy_stats where it was getting called in an else branch
unconditionally without making sure it was actually present.
Found by Linux Verification Center (linuxtesting.org) with the SVACE
static analysis tool.
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ethtool/ioctl.c | 102 ++++++++++++++++++++++++++++++--------------
1 file changed, 69 insertions(+), 33 deletions(-)
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 85f0cffdcec8a..646b3e490c71a 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2078,23 +2078,8 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
return ret;
}
-static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+static int ethtool_vzalloc_stats_array(int n_stats, u64 **data)
{
- const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
- const struct ethtool_ops *ops = dev->ethtool_ops;
- struct phy_device *phydev = dev->phydev;
- struct ethtool_stats stats;
- u64 *data;
- int ret, n_stats;
-
- if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
- return -EOPNOTSUPP;
-
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_sset_count)
- n_stats = phy_ops->get_sset_count(phydev);
- else
- n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
if (n_stats < 0)
return n_stats;
if (n_stats > S32_MAX / sizeof(u64))
@@ -2102,31 +2087,82 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
if (WARN_ON_ONCE(!n_stats))
return -EOPNOTSUPP;
+ *data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!*data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
+ struct ethtool_stats *stats,
+ u64 **data)
+ {
+ const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
+ int n_stats, ret;
+
+ if (!phy_ops || !phy_ops->get_sset_count || !phy_ops->get_stats)
+ return -EOPNOTSUPP;
+
+ n_stats = phy_ops->get_sset_count(phydev);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ return phy_ops->get_stats(phydev, stats, *data);
+}
+
+static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 **data)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ int n_stats, ret;
+
+ if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
+ return -EOPNOTSUPP;
+
+ n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ ops->get_ethtool_phy_stats(dev, stats, *data);
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+{
+ struct phy_device *phydev = dev->phydev;
+ struct ethtool_stats stats;
+ u64 *data = NULL;
+ int ret = -EOPNOTSUPP;
+
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
- stats.n_stats = n_stats;
+ if (phydev)
+ ret = ethtool_get_phy_stats_phydev(phydev, &stats, &data);
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (!data)
- return -ENOMEM;
+ if (ret == -EOPNOTSUPP)
+ ret = ethtool_get_phy_stats_ethtool(dev, &stats, &data);
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_stats) {
- ret = phy_ops->get_stats(phydev, &stats, data);
- if (ret < 0)
- goto out;
- } else {
- ops->get_ethtool_phy_stats(dev, &stats, data);
- }
+ if (ret)
+ goto out;
- ret = -EFAULT;
- if (copy_to_user(useraddr, &stats, sizeof(stats)))
+ if (copy_to_user(useraddr, &stats, sizeof(stats))) {
+ ret = -EFAULT;
goto out;
+ }
+
useraddr += sizeof(stats);
- if (copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
- goto out;
- ret = 0;
+ if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
+ ret = -EFAULT;
out:
vfree(data);
--
GitLab
From ad425666a1f05d9b215a84cf010c3789b2ea8206 Mon Sep 17 00:00:00 2001
From: Chunhao Lin <hau@realtek.com>
Date: Mon, 26 Dec 2022 20:31:52 +0800
Subject: [PATCH 0154/1167] r8169: move rtl_wol_enable_rx() and
rtl_prepare_power_down()
There is no functional change. Moving these two functions for following
patch "r8169: fix dmar pte write access is not set error".
Signed-off-by: Chunhao Lin <hau@realtek.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/realtek/r8169_main.c | 44 +++++++++++------------
1 file changed, 22 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index a9dcc98b6af18..acc2500342cab 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2210,28 +2210,6 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
return 0;
}
-static void rtl_wol_enable_rx(struct rtl8169_private *tp)
-{
- if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
- RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
- AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
-}
-
-static void rtl_prepare_power_down(struct rtl8169_private *tp)
-{
- if (tp->dash_type != RTL_DASH_NONE)
- return;
-
- if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
- tp->mac_version == RTL_GIGA_MAC_VER_33)
- rtl_ephy_write(tp, 0x19, 0xff64);
-
- if (device_may_wakeup(tp_to_dev(tp))) {
- phy_speed_down(tp->phydev, false);
- rtl_wol_enable_rx(tp);
- }
-}
-
static void rtl_init_rxcfg(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
@@ -2455,6 +2433,28 @@ static void rtl_enable_rxdvgate(struct rtl8169_private *tp)
rtl_wait_txrx_fifo_empty(tp);
}
+static void rtl_wol_enable_rx(struct rtl8169_private *tp)
+{
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
+ RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
+ AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
+}
+
+static void rtl_prepare_power_down(struct rtl8169_private *tp)
+{
+ if (tp->dash_type != RTL_DASH_NONE)
+ return;
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_33)
+ rtl_ephy_write(tp, 0x19, 0xff64);
+
+ if (device_may_wakeup(tp_to_dev(tp))) {
+ phy_speed_down(tp->phydev, false);
+ rtl_wol_enable_rx(tp);
+ }
+}
+
static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
{
u32 val = TX_DMA_BURST << TxDMAShift |
--
GitLab
From bb41c13c05c23d9bc46b4e37d8914078c6a40e3a Mon Sep 17 00:00:00 2001
From: Chunhao Lin <hau@realtek.com>
Date: Mon, 26 Dec 2022 20:31:53 +0800
Subject: [PATCH 0155/1167] r8169: fix dmar pte write access is not set error
When close device, if wol is enabled, rx will be enabled. When open
device it will cause rx packet to be dma to the wrong memory address
after pci_set_master() and system log will show blow messages.
DMAR: DRHD: handling fault status reg 3
DMAR: [DMA Write] Request device [02:00.0] PASID ffffffff fault addr
ffdd4000 [fault reason 05] PTE Write access is not set
In this patch, driver disable tx/rx when close device. If wol is
enabled, only enable rx filter and disable rxdv_gate(if support) to
let hardware only receive packet to fifo but not to dma it.
Signed-off-by: Chunhao Lin <hau@realtek.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/realtek/r8169_main.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index acc2500342cab..24592d9725230 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2438,6 +2438,9 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp)
if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
+
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_40)
+ rtl_disable_rxdvgate(tp);
}
static void rtl_prepare_power_down(struct rtl8169_private *tp)
@@ -3872,7 +3875,7 @@ static void rtl8169_tx_clear(struct rtl8169_private *tp)
netdev_reset_queue(tp->dev);
}
-static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
+static void rtl8169_cleanup(struct rtl8169_private *tp)
{
napi_disable(&tp->napi);
@@ -3884,9 +3887,6 @@ static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
rtl_rx_close(tp);
- if (going_down && tp->dev->wol_enabled)
- goto no_reset;
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_28:
case RTL_GIGA_MAC_VER_31:
@@ -3907,7 +3907,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
}
rtl_hw_reset(tp);
-no_reset:
+
rtl8169_tx_clear(tp);
rtl8169_init_ring_indexes(tp);
}
@@ -3918,7 +3918,7 @@ static void rtl_reset_work(struct rtl8169_private *tp)
netif_stop_queue(tp->dev);
- rtl8169_cleanup(tp, false);
+ rtl8169_cleanup(tp);
for (i = 0; i < NUM_RX_DESC; i++)
rtl8169_mark_to_asic(tp->RxDescArray + i);
@@ -4605,7 +4605,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
pci_clear_master(tp->pci_dev);
rtl_pci_commit(tp);
- rtl8169_cleanup(tp, true);
+ rtl8169_cleanup(tp);
rtl_disable_exit_l1(tp);
rtl_prepare_power_down(tp);
}
--
GitLab
From c2052189f19bd98c80b5d46dc6e42330d2b3b35d Mon Sep 17 00:00:00 2001
From: Xuezhi Zhang <zhangxuezhi1@coolpad.com>
Date: Tue, 27 Dec 2022 19:03:52 +0800
Subject: [PATCH 0156/1167] s390/qeth: convert sysfs snprintf to sysfs_emit
Follow the advice of the Documentation/filesystems/sysfs.rst
and show() should only use sysfs_emit() or sysfs_emit_at()
when formatting the value to be returned to user space.
Signed-off-by: Xuezhi Zhang <zhangxuezhi1@coolpad.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/s390/net/qeth_core_sys.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 406be169173ce..d1adc4b831936 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -410,13 +410,13 @@ static ssize_t qeth_dev_isolation_show(struct device *dev,
switch (card->options.isolation) {
case ISOLATION_MODE_NONE:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_NONE);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_NONE);
case ISOLATION_MODE_FWD:
- return snprintf(buf, 9, "%s\n", ATTR_QETH_ISOLATION_FWD);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_FWD);
case ISOLATION_MODE_DROP:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_DROP);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_DROP);
default:
- return snprintf(buf, 5, "%s\n", "N/A");
+ return sysfs_emit(buf, "%s\n", "N/A");
}
}
@@ -500,9 +500,9 @@ static ssize_t qeth_hw_trap_show(struct device *dev,
struct qeth_card *card = dev_get_drvdata(dev);
if (card->info.hwtrap)
- return snprintf(buf, 5, "arm\n");
+ return sysfs_emit(buf, "arm\n");
else
- return snprintf(buf, 8, "disarm\n");
+ return sysfs_emit(buf, "disarm\n");
}
static ssize_t qeth_hw_trap_store(struct device *dev,
--
GitLab
From 40cab44b9089a41f71bbd0eff753eb91d5dafd68 Mon Sep 17 00:00:00 2001
From: Pedro Tammela <pctammela@mojatatu.com>
Date: Tue, 27 Dec 2022 11:04:59 -0300
Subject: [PATCH 0157/1167] net/sched: fix retpoline wrapper compilation on
configs without tc filters
Rudi reports a compilation failure on x86_64 when CONFIG_NET_CLS or
CONFIG_NET_CLS_ACT is not set but CONFIG_RETPOLINE is set.
A misplaced '#endif' was causing the issue.
Fixes: 7f0e810220e2 ("net/sched: add retpoline wrapper for tc")
Tested-by: Rudi Heitbaum <rudi@heitbaum.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/tc_wrapper.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h
index ceed2fc089ffa..d323fffb839aa 100644
--- a/include/net/tc_wrapper.h
+++ b/include/net/tc_wrapper.h
@@ -216,6 +216,8 @@ static inline int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
return tp->classify(skb, tp, res);
}
+#endif /* CONFIG_NET_CLS */
+
static inline void tc_wrapper_init(void)
{
#ifdef CONFIG_X86
@@ -224,8 +226,6 @@ static inline void tc_wrapper_init(void)
#endif
}
-#endif /* CONFIG_NET_CLS */
-
#else
#define TC_INDIRECT_SCOPE static
--
GitLab
From 0154252a3b87f77db1e44516d1ed2e82e2d29c30 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 4 Dec 2022 09:46:14 +0100
Subject: [PATCH 0158/1167] ARM: dts: qcom: apq8084-ifc6540: fix overriding
SDHCI
While changing node names of APQ8084 SDHCI, the ones in IFC6540 board
were not updated leading to disabled and misconfigured SDHCI.
Cc: <stable@vger.kernel.org>
Fixes: 2477d81901a2 ("ARM: dts: qcom: Fix sdhci node names - use 'mmc@'")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221204084614.12193-1-krzysztof.kozlowski@linaro.org
---
arch/arm/boot/dts/qcom-apq8084-ifc6540.dts | 20 ++++++++++----------
arch/arm/boot/dts/qcom-apq8084.dtsi | 4 ++--
2 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts
index 44cd72f1b1be4..116e59a3b76d0 100644
--- a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts
+++ b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts
@@ -19,16 +19,16 @@ soc {
serial@f995e000 {
status = "okay";
};
+ };
+};
- sdhci@f9824900 {
- bus-width = <8>;
- non-removable;
- status = "okay";
- };
+&sdhc_1 {
+ bus-width = <8>;
+ non-removable;
+ status = "okay";
+};
- sdhci@f98a4900 {
- cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>;
- bus-width = <4>;
- };
- };
+&sdhc_2 {
+ cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>;
+ bus-width = <4>;
};
diff --git a/arch/arm/boot/dts/qcom-apq8084.dtsi b/arch/arm/boot/dts/qcom-apq8084.dtsi
index fe30abfff90a7..4b0d2b4f4b6a9 100644
--- a/arch/arm/boot/dts/qcom-apq8084.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8084.dtsi
@@ -421,7 +421,7 @@ blsp2_uart2: serial@f995e000 {
status = "disabled";
};
- mmc@f9824900 {
+ sdhc_1: mmc@f9824900 {
compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4";
reg = <0xf9824900 0x11c>, <0xf9824000 0x800>;
reg-names = "hc", "core";
@@ -434,7 +434,7 @@ mmc@f9824900 {
status = "disabled";
};
- mmc@f98a4900 {
+ sdhc_2: mmc@f98a4900 {
compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4";
reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>;
reg-names = "hc", "core";
--
GitLab
From 6c82b94d583a116faf99858379ee34844df963a1 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 22 Nov 2022 13:37:13 +0100
Subject: [PATCH 0159/1167] Revert "arm64: dts: qcom: sm8250: Disable the not
yet supported cluster idle state"
Due to recent improvements of the cluster idle state support for Qcom based
platforms, we are now able to support the deepest cluster idle state. Let's
therefore revert the earlier workaround.
This reverts commit cadaa773bcf1 ("arm64: dts: qcom: sm8250: Disable the
not yet supported cluster idle state"), which is available from v6.1-rc6.
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221122123713.65631-1-ulf.hansson@linaro.org
---
arch/arm64/boot/dts/qcom/sm8250.dtsi | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index dab5579946f35..927032863e2f1 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -334,7 +334,6 @@ CLUSTER_SLEEP_0: cluster-sleep-0 {
exit-latency-us = <6562>;
min-residency-us = <9987>;
local-timer-stop;
- status = "disabled";
};
};
};
--
GitLab
From 1f0ae22ab470946143485a02cc1cd7e05c0f9120 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 12 Dec 2022 10:42:15 +0200
Subject: [PATCH 0160/1167] net/mlx5: E-Switch, properly handle ingress tagged
packets on VST
Fix SRIOV VST mode behavior to insert cvlan when a guest tag is already
present in the frame. Previous VST mode behavior was to drop packets or
override existing tag, depending on the device version.
In this patch we fix this behavior by correctly building the HW steering
rule with a push vlan action, or for older devices we ask the FW to stack
the vlan when a vlan is already present.
Fixes: 07bab9502641 ("net/mlx5: E-Switch, Refactor eswitch ingress acl codes")
Fixes: dfcb1ed3c331 ("net/mlx5: E-Switch, Vport ingress/egress ACLs rules for VST mode")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../mellanox/mlx5/core/esw/acl/egress_lgcy.c | 7 +++-
.../mellanox/mlx5/core/esw/acl/ingress_lgcy.c | 33 ++++++++++++++++---
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 30 ++++++++++++-----
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 6 ++++
include/linux/mlx5/device.h | 5 +++
include/linux/mlx5/mlx5_ifc.h | 3 +-
6 files changed, 68 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 60a73990017c2..6b4c9ffad95b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -67,6 +67,7 @@ static void esw_acl_egress_lgcy_groups_destroy(struct mlx5_vport *vport)
int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_fc *drop_counter = NULL;
@@ -77,6 +78,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
*/
int table_size = 2;
int dest_num = 0;
+ int actions_flag;
int err = 0;
if (vport->egress.legacy.drop_counter) {
@@ -119,8 +121,11 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
vport->vport, vport->info.vlan, vport->info.qos);
/* Allowed vlan rule */
+ actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_mode_steering)
+ actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+ actions_flag);
if (err)
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
index b1a5199260f69..093ed86a0acd8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
@@ -139,11 +139,14 @@ static void esw_acl_ingress_lgcy_groups_destroy(struct mlx5_vport *vport)
int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_flow_act flow_act = {};
struct mlx5_flow_spec *spec = NULL;
struct mlx5_fc *counter = NULL;
+ bool vst_check_cvlan = false;
+ bool vst_push_cvlan = false;
/* The ingress acl table contains 4 groups
* (2 active rules at the same time -
* 1 allow rule from one of the first 3 groups.
@@ -203,7 +206,26 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
goto out;
}
- if (vport->info.vlan || vport->info.qos)
+ if ((vport->info.vlan || vport->info.qos)) {
+ if (vst_mode_steering)
+ vst_push_cvlan = true;
+ else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always))
+ vst_check_cvlan = true;
+ }
+
+ if (vst_check_cvlan || vport->info.spoofchk)
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+ /* Create ingress allow rule */
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_push_cvlan) {
+ flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ flow_act.vlan[0].prio = vport->info.qos;
+ flow_act.vlan[0].vid = vport->info.vlan;
+ flow_act.vlan[0].ethtype = ETH_P_8021Q;
+ }
+
+ if (vst_check_cvlan)
MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
outer_headers.cvlan_tag);
@@ -218,9 +240,6 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
ether_addr_copy(smac_v, vport->info.mac);
}
- /* Create ingress allow rule */
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
&flow_act, NULL, 0);
if (IS_ERR(vport->ingress.allow_rule)) {
@@ -232,6 +251,9 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
goto out;
}
+ if (!vst_check_cvlan && !vport->info.spoofchk)
+ goto out;
+
memset(&flow_act, 0, sizeof(flow_act));
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
/* Attach drop flow counter */
@@ -257,7 +279,8 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
return 0;
out:
- esw_acl_ingress_lgcy_cleanup(esw, vport);
+ if (err)
+ esw_acl_ingress_lgcy_cleanup(esw, vport);
kvfree(spec);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 527e4bffda8d4..0dfd5742c6fe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -161,10 +161,17 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
esw_vport_context.vport_cvlan_strip, 1);
if (set_flags & SET_VLAN_INSERT) {
- /* insert only if no vlan in packet */
- MLX5_SET(modify_esw_vport_context_in, in,
- esw_vport_context.vport_cvlan_insert, 1);
-
+ if (MLX5_CAP_ESW(dev, vport_cvlan_insert_always)) {
+ /* insert either if vlan exist in packet or not */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS);
+ } else {
+ /* insert only if no vlan in packet */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN);
+ }
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.cvlan_pcp, qos);
MLX5_SET(modify_esw_vport_context_in, in,
@@ -809,6 +816,7 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
u16 vport_num = vport->vport;
int flags;
int err;
@@ -839,8 +847,9 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
flags = (vport->info.vlan || vport->info.qos) ?
SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
- modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
- vport->info.qos, flags);
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering)
+ modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+ vport->info.qos, flags);
return 0;
@@ -1848,6 +1857,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
u16 vport, u16 vlan, u8 qos, u8 set_flags)
{
struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
int err = 0;
if (IS_ERR(evport))
@@ -1855,9 +1865,11 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
if (vlan > 4095 || qos > 7)
return -EINVAL;
- err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
- if (err)
- return err;
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering) {
+ err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
+ if (err)
+ return err;
+ }
evport->info.vlan = vlan;
evport->info.qos = qos;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 5a85a5d32be7e..92644fbb50816 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -527,6 +527,12 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
u16 vport, u16 vlan, u8 qos, u8 set_flags);
+static inline bool esw_vst_mode_is_steering(struct mlx5_eswitch *esw)
+{
+ return (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, pop_vlan) &&
+ MLX5_CAP_ESW_INGRESS_ACL(esw->dev, push_vlan));
+}
+
static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
u8 vlan_depth)
{
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5fe5d198b57ad..29d4b201c7b26 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1090,6 +1090,11 @@ enum {
MLX5_VPORT_ADMIN_STATE_AUTO = 0x2,
};
+enum {
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN = 0x1,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS = 0x3,
+};
+
enum {
MLX5_L3_PROT_TYPE_IPV4 = 0,
MLX5_L3_PROT_TYPE_IPV6 = 1,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f3d1c62c98ddc..a9ee7bc59c901 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -913,7 +913,8 @@ struct mlx5_ifc_e_switch_cap_bits {
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x2];
+ u8 reserved_at_5[0x1];
+ u8 vport_cvlan_insert_always[0x1];
u8 esw_shared_ingress_acl[0x1];
u8 esw_uplink_ingress_acl[0x1];
u8 root_ft_on_other_esw[0x1];
--
GitLab
From 2a35b2c2e6a252eda2134aae6a756861d9299531 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Tue, 18 Oct 2022 12:51:52 +0200
Subject: [PATCH 0161/1167] net/mlx5: Add forgotten cleanup calls into
mlx5_init_once() error path
There are two cleanup calls missing in mlx5_init_once() error path.
Add them making the error path flow to be the same as
mlx5_cleanup_once().
Fixes: 52ec462eca9b ("net/mlx5: Add reserved-gids support")
Fixes: 7c39afb394c7 ("net/mlx5: PTP code migration to driver core section")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7f5db13e3550c..ec5652f31dda1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1050,6 +1050,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
err_tables_cleanup:
mlx5_geneve_destroy(dev->geneve);
mlx5_vxlan_destroy(dev->vxlan);
+ mlx5_cleanup_clock(dev);
+ mlx5_cleanup_reserved_gids(dev);
mlx5_cq_debugfs_cleanup(dev);
mlx5_fw_reset_cleanup(dev);
err_events_cleanup:
--
GitLab
From 44aee8ea15ac205490a41b00cbafcccbf9f7f82b Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Sun, 18 Dec 2022 12:42:14 +0200
Subject: [PATCH 0162/1167] net/mlx5: Fix io_eq_size and event_eq_size params
validation
io_eq_size and event_eq_size params are of param type
DEVLINK_PARAM_TYPE_U32. But, the validation callback is addressing them
as DEVLINK_PARAM_TYPE_U16.
This cause mismatch in validation in big-endian systems, in which
values in range were rejected while 268500991 was accepted.
Fix it by checking the U32 value in the validation callback.
Fixes: 0844fa5f7b89 ("net/mlx5: Let user configure io_eq_size param")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index ddb197970c22c..be59bb35d795c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -563,7 +563,7 @@ static int mlx5_devlink_eq_depth_validate(struct devlink *devlink, u32 id,
union devlink_param_value val,
struct netlink_ext_ack *extack)
{
- return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+ return (val.vu32 >= 64 && val.vu32 <= 4096) ? 0 : -EINVAL;
}
static const struct devlink_param mlx5_devlink_params[] = {
--
GitLab
From 9078e843efec530f279a155f262793c58b0746bd Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 24 Nov 2022 13:34:12 +0200
Subject: [PATCH 0163/1167] net/mlx5: Avoid recovery in probe flows
Currently, recovery is done without considering whether the device is
still in probe flow.
This may lead to recovery before device have finished probed
successfully. e.g.: while mlx5_init_one() is running. Recovery flow is
using functionality that is loaded only by mlx5_init_one(), and there
is no point in running recovery without mlx5_init_one() finished
successfully.
Fix it by waiting for probe flow to finish and checking whether the
device is probed before trying to perform recovery.
Fixes: 51d138c2610a ("net/mlx5: Fix health error state handling")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/health.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 86ed87d704f7d..96417c5feed76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -674,6 +674,12 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
dev = container_of(priv, struct mlx5_core_dev, priv);
devlink = priv_to_devlink(dev);
+ mutex_lock(&dev->intf_state_mutex);
+ if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
+ mlx5_core_err(dev, "health works are not permitted at this stage\n");
+ return;
+ }
+ mutex_unlock(&dev->intf_state_mutex);
enter_error_state(dev, false);
if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
devl_lock(devlink);
--
GitLab
From c4ad5f2bdad56265b23d3635494ecdb205431807 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 9 Nov 2022 14:42:59 +0200
Subject: [PATCH 0164/1167] net/mlx5: Fix RoCE setting at HCA level
mlx5 PF can disable RoCE for its VFs and SFs. In such case RoCE is
marked as unsupported on those VFs/SFs.
The cited patch added an option for disable (and enable) RoCE at HCA
level. However, that commit didn't check whether RoCE is supported on
the HCA and enabled user to try and set RoCE to on.
Fix it by checking whether the HCA supports RoCE.
Fixes: fbfa97b4d79f ("net/mlx5: Disable roce at HCA level")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index be59bb35d795c..5bd83c0275f82 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -468,7 +468,7 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
bool new_state = val.vbool;
if (new_state && !MLX5_CAP_GEN(dev, roce) &&
- !MLX5_CAP_GEN(dev, roce_rw_supported)) {
+ !(MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))) {
NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec5652f31dda1..df134f6d32dc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -613,7 +613,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
- if (MLX5_CAP_GEN(dev, roce_rw_supported))
+ if (MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))
MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
mlx5_is_roce_on(dev));
--
GitLab
From b12d581e83e3ae1080c32ab83f123005bd89a840 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 28 Nov 2022 15:24:21 +0200
Subject: [PATCH 0165/1167] net/mlx5e: IPoIB, Don't allow CQE compression to be
turned on by default
mlx5e_build_nic_params will turn CQE compression on if the hardware
capability is enabled and the slow_pci_heuristic condition is detected.
As IPoIB doesn't support CQE compression, make sure to disable the
feature in the IPoIB profile init.
Please note that the feature is not exposed to the user for IPoIB
interfaces, so it can't be subsequently turned on.
Fixes: b797a684b0dd ("net/mlx5e: Enable CQE compression when PCI is slower than link")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 7c5c500fd215e..2c73c8445e630 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -71,6 +71,10 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
params->tunneled_offload_en = false;
+
+ /* CQE compression is not supported for IPoIB */
+ params->rx_cqe_compress_def = false;
+ MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
}
/* Called directly after IPoIB netdevice was created to initialize SW structs */
--
GitLab
From f8c18a5749cf917096f75dd59885b7a0fe9298ba Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Sun, 27 Nov 2022 09:21:28 +0200
Subject: [PATCH 0166/1167] net/mlx5e: Fix RX reporter for XSK RQs
RX reporter mistakenly reads from the regular (inactive) RQ
when XSK RQ is active. Fix it here.
Fixes: 3db4c85cde7a ("net/mlx5e: xsk: Use queue indices starting from 0 for XSK queues")
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 5f6f95ad6888c..1ae15b8536a85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -459,7 +459,11 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
goto unlock;
for (i = 0; i < priv->channels.num; i++) {
- struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+ struct mlx5e_channel *c = priv->channels.c[i];
+ struct mlx5e_rq *rq;
+
+ rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ?
+ &c->xskrq : &c->rq;
err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
if (err)
--
GitLab
From 849190e3e4ccf452fbe2240eace30a9ca83fb8d2 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Mon, 28 Nov 2022 13:54:29 +0800
Subject: [PATCH 0167/1167] net/mlx5e: CT: Fix ct debugfs folder name
Need to use sprintf to build a string instead of sscanf. Otherwise
dirname is null and both "ct_nic" and "ct_fdb" won't be created.
But its redundant anyway as driver could be in switchdev mode but
still add nic rules. So use "ct" as folder name.
Fixes: 77422a8f6f61 ("net/mlx5e: CT: Add ct driver counters")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 7 +------
1 file changed, 1 insertion(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index a69849e0deed7..313df8232db70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -2103,14 +2103,9 @@ mlx5_tc_ct_init_check_support(struct mlx5e_priv *priv,
static void
mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
{
- bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
- char dirname[16] = {};
- if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
- return;
-
- ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
+ ct_dbgfs->root = debugfs_create_dir("ct", mlx5_debugfs_get_dev_root(ct_priv->dev));
debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
&ct_dbgfs->stats.offloaded);
debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,
--
GitLab
From 2951b2e142ecf6e0115df785ba91e91b6da74602 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Mon, 5 Dec 2022 09:22:50 +0800
Subject: [PATCH 0168/1167] net/mlx5e: Always clear dest encap in
neigh-update-del
The cited commit introduced a bug for multiple encapsulations flow.
If one dest encap becomes invalid, the flow is set slow path flag.
But when other dests encap become invalid, they are not cleared due
to slow path flag of the flow. When neigh-update-add is running, it
will use invalid encap.
Fix it by checking slow path flag after clearing dest encap.
Fixes: 9a5f9cc794e1 ("net/mlx5e: Fix possible use-after-free deleting fdb rule")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index ff73d25bc6eb8..2aaf8ab857b8f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -222,7 +222,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
int err;
list_for_each_entry(flow, flow_list, tmp_list) {
- if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
+ if (!mlx5e_is_offloaded_flow(flow))
continue;
attr = mlx5e_tc_get_encap_attr(flow);
@@ -231,6 +231,13 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL;
+ /* Clear pkt_reformat before checking slow path flag. Because
+ * in next iteration, the same flow is already set slow path
+ * flag, but still need to clear the pkt_reformat.
+ */
+ if (flow_flag_test(flow, SLOW))
+ continue;
+
/* update from encap rule to slow path rule */
spec = &flow->attr->parse_attr->spec;
rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);
--
GitLab
From 1e267ab88dc44c48f556218f7b7f14c76f7aa066 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Wed, 14 Dec 2022 16:02:57 +0200
Subject: [PATCH 0169/1167] net/mlx5e: Fix hw mtu initializing at XDP SQ
allocation
Current xdp xmit functions logic (mlx5e_xmit_xdp_frame_mpwqe or
mlx5e_xmit_xdp_frame), validates xdp packet length by comparing it to
hw mtu (configured at xdp sq allocation) before xmiting it. This check
does not account for ethernet fcs length (calculated and filled by the
nic). Hence, when we try sending packets with length > (hw-mtu -
ethernet-fcs-size), the device port drops it and tx_errors_phy is
incremented. Desired behavior is to catch these packets and drop them
by the driver.
Fix this behavior in XDP SQ allocation function (mlx5e_alloc_xdpsq) by
subtracting ethernet FCS header size (4 Bytes) from current hw mtu
value, since ethernet FCS is calculated and written to ethernet frames
by the nic.
Fixes: d8bec2b29a82 ("net/mlx5e: Support bpf_xdp_adjust_head()")
Signed-off-by: Adham Faris <afaris@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 8d36e2de53a99..cff5f2e29e1e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1305,7 +1305,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
- sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
sq->xsk_pool = xsk_pool;
sq->stats = sq->xsk_pool ?
--
GitLab
From e54638a8380bd9c146a883035fffd0a821813682 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Sun, 1 Aug 2021 14:45:17 +0300
Subject: [PATCH 0170/1167] net/mlx5e: Set geneve_tlv_option_0_exist when
matching on geneve option
The cited patch added support of matching on geneve option by setting
geneve_tlv_option_0_data mask and key but didn't set geneve_tlv_option_0_exist
bit which is required on some HWs when matching geneve_tlv_option_0_data parameter,
this may cause in some cases for packets to wrongly match on rules with different
geneve option.
Example of such case is packet with geneve_tlv_object class=789 and data=456
will wrongly match on rule with match geneve_tlv_object class=123 and data=456.
Fix it by setting geneve_tlv_option_0_exist bit when supported by the HW when matching
on geneve_tlv_option_0_data parameter.
Fixes: 9272e3df3023 ("net/mlx5e: Geneve, Add support for encap/decap flows offload")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
index f5b26f5a7de46..054d80c4e65cf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -273,6 +273,11 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
MLX5_SET(fte_match_set_misc3, misc_3_c,
geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+ ft_field_support.geneve_tlv_option_0_exist)) {
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_tlv_option_0_exist);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_v, geneve_tlv_option_0_exist);
+ }
spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
--
GitLab
From 4d1c1379d71777ddeda3e54f8fc26e9ecbfd1009 Mon Sep 17 00:00:00 2001
From: Eli Cohen <elic@nvidia.com>
Date: Thu, 15 Dec 2022 14:28:34 +0200
Subject: [PATCH 0171/1167] net/mlx5: Lag, fix failure to cancel delayed bond
work
Commit 0d4e8ed139d8 ("net/mlx5: Lag, avoid lockdep warnings")
accidentally removed a call to cancel delayed bond work thus it may
cause queued delay to expire and fall on an already destroyed work
queue.
Fix by restoring the call cancel_delayed_work_sync() before
destroying the workqueue.
This prevents call trace such as this:
[ 329.230417] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 329.231444] #PF: supervisor write access in kernel mode
[ 329.232233] #PF: error_code(0x0002) - not-present page
[ 329.233007] PGD 0 P4D 0
[ 329.233476] Oops: 0002 [#1] SMP
[ 329.234012] CPU: 5 PID: 145 Comm: kworker/u20:4 Tainted: G OE 6.0.0-rc5_mlnx #1
[ 329.235282] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 329.236868] Workqueue: mlx5_cmd_0000:08:00.1 cmd_work_handler [mlx5_core]
[ 329.237886] RIP: 0010:_raw_spin_lock+0xc/0x20
[ 329.238585] Code: f0 0f b1 17 75 02 f3 c3 89 c6 e9 6f 3c 5f ff 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 0f 1f 44 00 00 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 02 f3 c3 89 c6 e9 45 3c 5f ff 0f 1f 44 00 00 0f 1f
[ 329.241156] RSP: 0018:ffffc900001b0e98 EFLAGS: 00010046
[ 329.241940] RAX: 0000000000000000 RBX: ffffffff82374ae0 RCX: 0000000000000000
[ 329.242954] RDX: 0000000000000001 RSI: 0000000000000014 RDI: 0000000000000000
[ 329.243974] RBP: ffff888106ccf000 R08: ffff8881004000c8 R09: ffff888100400000
[ 329.244990] R10: 0000000000000000 R11: ffffffff826669f8 R12: 0000000000002000
[ 329.246009] R13: 0000000000000005 R14: ffff888100aa7ce0 R15: ffff88852ca80000
[ 329.247030] FS: 0000000000000000(0000) GS:ffff88852ca80000(0000) knlGS:0000000000000000
[ 329.248260] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 329.249111] CR2: 0000000000000000 CR3: 000000016d675001 CR4: 0000000000770ee0
[ 329.250133] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 329.251152] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 329.252176] PKRU: 55555554
Fixes: 0d4e8ed139d8 ("net/mlx5: Lag, avoid lockdep warnings")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 32c3e0a649a75..ad32b80e85018 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -228,6 +228,7 @@ static void mlx5_ldev_free(struct kref *ref)
if (ldev->nb.notifier_call)
unregister_netdevice_notifier_net(&init_net, &ldev->nb);
mlx5_lag_mp_cleanup(ldev);
+ cancel_delayed_work_sync(&ldev->bond_work);
destroy_workqueue(ldev->wq);
mlx5_lag_mpesw_cleanup(ldev);
mutex_destroy(&ldev->lock);
--
GitLab
From 9ed1d9aeef5842ecacb660fce933613b58af1e00 Mon Sep 17 00:00:00 2001
From: Chuang Wang <nashuiliang@gmail.com>
Date: Sat, 24 Dec 2022 21:31:46 +0800
Subject: [PATCH 0172/1167] bpf: Fix panic due to wrong pageattr of im->image
In the scenario where livepatch and kretfunc coexist, the pageattr of
im->image is rox after arch_prepare_bpf_trampoline in
bpf_trampoline_update, and then modify_fentry or register_fentry returns
-EAGAIN from bpf_tramp_ftrace_ops_func, the BPF_TRAMP_F_ORIG_STACK flag
will be configured, and arch_prepare_bpf_trampoline will be re-executed.
At this time, because the pageattr of im->image is rox,
arch_prepare_bpf_trampoline will read and write im->image, which causes
a fault. as follows:
insmod livepatch-sample.ko # samples/livepatch/livepatch-sample.c
bpftrace -e 'kretfunc:cmdline_proc_show {}'
BUG: unable to handle page fault for address: ffffffffa0206000
PGD 322d067 P4D 322d067 PUD 322e063 PMD 1297e067 PTE d428061
Oops: 0003 [#1] PREEMPT SMP PTI
CPU: 2 PID: 270 Comm: bpftrace Tainted: G E K 6.1.0 #5
RIP: 0010:arch_prepare_bpf_trampoline+0xed/0x8c0
RSP: 0018:ffffc90001083ad8 EFLAGS: 00010202
RAX: ffffffffa0206000 RBX: 0000000000000020 RCX: 0000000000000000
RDX: ffffffffa0206001 RSI: ffffffffa0206000 RDI: 0000000000000030
RBP: ffffc90001083b70 R08: 0000000000000066 R09: ffff88800f51b400
R10: 000000002e72c6e5 R11: 00000000d0a15080 R12: ffff8880110a68c8
R13: 0000000000000000 R14: ffff88800f51b400 R15: ffffffff814fec10
FS: 00007f87bc0dc780(0000) GS:ffff88803e600000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffa0206000 CR3: 0000000010b70000 CR4: 00000000000006e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
bpf_trampoline_update+0x25a/0x6b0
__bpf_trampoline_link_prog+0x101/0x240
bpf_trampoline_link_prog+0x2d/0x50
bpf_tracing_prog_attach+0x24c/0x530
bpf_raw_tp_link_attach+0x73/0x1d0
__sys_bpf+0x100e/0x2570
__x64_sys_bpf+0x1c/0x30
do_syscall_64+0x5b/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
With this patch, when modify_fentry or register_fentry returns -EAGAIN
from bpf_tramp_ftrace_ops_func, the pageattr of im->image will be reset
to nx+rw.
Cc: stable@vger.kernel.org
Fixes: 00963a2e75a8 ("bpf: Support bpf_trampoline on functions with IPMODIFY (e.g. livepatch)")
Signed-off-by: Chuang Wang <nashuiliang@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20221224133146.780578-1-nashuiliang@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/trampoline.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 11f5ec0b80165..d0ed7d6f5eec5 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -488,6 +488,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut
/* reset fops->func and fops->trampoline for re-register */
tr->fops->func = NULL;
tr->fops->trampoline = 0;
+
+ /* reset im->image memory attr for arch_prepare_bpf_trampoline */
+ set_memory_nx((long)im->image, 1);
+ set_memory_rw((long)im->image, 1);
goto again;
}
#endif
--
GitLab
From 8f161ca1105a6af6614333f13aa7be4aab8b633a Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Wed, 28 Dec 2022 13:55:57 -0800
Subject: [PATCH 0173/1167] selftests/bpf: Temporarily disable part of
btf_dump:var_data test.
Commit 7443b296e699 ("x86/percpu: Move cpu_number next to current_task")
moved global per_cpu variable 'cpu_number' into pcpu_hot structure.
Therefore this part of var_data test is no longer valid.
Disable it until better solution is found.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/bpf/prog_tests/btf_dump.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 0ba2e8b9c6ace..e9ea38aa8248b 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -801,7 +801,7 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
char *str)
{
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if 0
TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
"int cpu_number = (int)100", 100);
#endif
--
GitLab
From 7ff94f276f8ea05df82eb115225e9b26f47a3347 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <kuifeng@meta.com>
Date: Fri, 16 Dec 2022 14:18:54 -0800
Subject: [PATCH 0174/1167] bpf: keep a reference to the mm, in case the task
is dead.
Fix the system crash that happens when a task iterator travel through
vma of tasks.
In task iterators, we used to access mm by following the pointer on
the task_struct; however, the death of a task will clear the pointer,
even though we still hold the task_struct. That can cause an
unexpected crash for a null pointer when an iterator is visiting a
task that dies during the visit. Keeping a reference of mm on the
iterator ensures we always have a valid pointer to mm.
Co-developed-by: Song Liu <song@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Reported-by: Nathan Slingerland <slinger@meta.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221216221855.4122288-2-kuifeng@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/task_iter.c | 39 +++++++++++++++++++++++++++------------
1 file changed, 27 insertions(+), 12 deletions(-)
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index c2a2182ce5702..c4ab9d6cdbe9c 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -438,6 +438,7 @@ struct bpf_iter_seq_task_vma_info {
*/
struct bpf_iter_seq_task_common common;
struct task_struct *task;
+ struct mm_struct *mm;
struct vm_area_struct *vma;
u32 tid;
unsigned long prev_vm_start;
@@ -456,16 +457,19 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
enum bpf_task_vma_iter_find_op op;
struct vm_area_struct *curr_vma;
struct task_struct *curr_task;
+ struct mm_struct *curr_mm;
u32 saved_tid = info->tid;
/* If this function returns a non-NULL vma, it holds a reference to
- * the task_struct, and holds read lock on vma->mm->mmap_lock.
+ * the task_struct, holds a refcount on mm->mm_users, and holds
+ * read lock on vma->mm->mmap_lock.
* If this function returns NULL, it does not hold any reference or
* lock.
*/
if (info->task) {
curr_task = info->task;
curr_vma = info->vma;
+ curr_mm = info->mm;
/* In case of lock contention, drop mmap_lock to unblock
* the writer.
*
@@ -504,13 +508,15 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
* 4.2) VMA2 and VMA2' covers different ranges, process
* VMA2'.
*/
- if (mmap_lock_is_contended(curr_task->mm)) {
+ if (mmap_lock_is_contended(curr_mm)) {
info->prev_vm_start = curr_vma->vm_start;
info->prev_vm_end = curr_vma->vm_end;
op = task_vma_iter_find_vma;
- mmap_read_unlock(curr_task->mm);
- if (mmap_read_lock_killable(curr_task->mm))
+ mmap_read_unlock(curr_mm);
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
} else {
op = task_vma_iter_next_vma;
}
@@ -535,42 +541,47 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
op = task_vma_iter_find_vma;
}
- if (!curr_task->mm)
+ curr_mm = get_task_mm(curr_task);
+ if (!curr_mm)
goto next_task;
- if (mmap_read_lock_killable(curr_task->mm))
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
}
switch (op) {
case task_vma_iter_first_vma:
- curr_vma = find_vma(curr_task->mm, 0);
+ curr_vma = find_vma(curr_mm, 0);
break;
case task_vma_iter_next_vma:
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
case task_vma_iter_find_vma:
/* We dropped mmap_lock so it is necessary to use find_vma
* to find the next vma. This is similar to the mechanism
* in show_smaps_rollup().
*/
- curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+ curr_vma = find_vma(curr_mm, info->prev_vm_end - 1);
/* case 1) and 4.2) above just use curr_vma */
/* check for case 2) or case 4.1) above */
if (curr_vma &&
curr_vma->vm_start == info->prev_vm_start &&
curr_vma->vm_end == info->prev_vm_end)
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
}
if (!curr_vma) {
/* case 3) above, or case 2) 4.1) with vma->next == NULL */
- mmap_read_unlock(curr_task->mm);
+ mmap_read_unlock(curr_mm);
+ mmput(curr_mm);
goto next_task;
}
info->task = curr_task;
info->vma = curr_vma;
+ info->mm = curr_mm;
return curr_vma;
next_task:
@@ -579,6 +590,7 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
put_task_struct(curr_task);
info->task = NULL;
+ info->mm = NULL;
info->tid++;
goto again;
@@ -587,6 +599,7 @@ task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
put_task_struct(curr_task);
info->task = NULL;
info->vma = NULL;
+ info->mm = NULL;
return NULL;
}
@@ -658,7 +671,9 @@ static void task_vma_seq_stop(struct seq_file *seq, void *v)
*/
info->prev_vm_start = ~0UL;
info->prev_vm_end = info->vma->vm_end;
- mmap_read_unlock(info->task->mm);
+ mmap_read_unlock(info->mm);
+ mmput(info->mm);
+ info->mm = NULL;
put_task_struct(info->task);
info->task = NULL;
}
--
GitLab
From b7793c8db7d9beb903bb42f52872b5b46abdcb88 Mon Sep 17 00:00:00 2001
From: Kui-Feng Lee <kuifeng@meta.com>
Date: Fri, 16 Dec 2022 14:18:55 -0800
Subject: [PATCH 0175/1167] selftests/bpf: add a test for iter/task_vma for
short-lived processes
When a task iterator traverses vma(s), it is possible task->mm might
become invalid in the middle of traversal and this may cause kernel
misbehave (e.g., crash)
This test case creates iterators repeatedly and forks short-lived
processes in the background to detect this bug. The test will last
for 3 seconds to get the chance to trigger the issue.
Signed-off-by: Kui-Feng Lee <kuifeng@meta.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221216221855.4122288-3-kuifeng@meta.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
.../selftests/bpf/prog_tests/bpf_iter.c | 73 +++++++++++++++++++
1 file changed, 73 insertions(+)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 6f8ed61fc4b4a..3af6450763e9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -1465,6 +1465,77 @@ static void test_task_vma_common(struct bpf_iter_attach_opts *opts)
bpf_iter_task_vma__destroy(skel);
}
+static void test_task_vma_dead_task(void)
+{
+ struct bpf_iter_task_vma *skel;
+ int wstatus, child_pid = -1;
+ time_t start_tm, cur_tm;
+ int err, iter_fd = -1;
+ int wait_sec = 3;
+
+ skel = bpf_iter_task_vma__open();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ err = bpf_iter_task_vma__load(skel);
+ if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+ goto out;
+
+ skel->links.proc_maps = bpf_program__attach_iter(
+ skel->progs.proc_maps, NULL);
+
+ if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
+ skel->links.proc_maps = NULL;
+ goto out;
+ }
+
+ start_tm = time(NULL);
+ cur_tm = start_tm;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ /* Fork short-lived processes in the background. */
+ while (cur_tm < start_tm + wait_sec) {
+ system("echo > /dev/null");
+ cur_tm = time(NULL);
+ }
+ exit(0);
+ }
+
+ if (!ASSERT_GE(child_pid, 0, "fork_child"))
+ goto out;
+
+ while (cur_tm < start_tm + wait_sec) {
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.proc_maps));
+ if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+ goto out;
+
+ /* Drain all data from iter_fd. */
+ while (cur_tm < start_tm + wait_sec) {
+ err = read_fd_into_buffer(iter_fd, task_vma_output, CMP_BUFFER_SIZE);
+ if (!ASSERT_GE(err, 0, "read_iter_fd"))
+ goto out;
+
+ cur_tm = time(NULL);
+
+ if (err == 0)
+ break;
+ }
+
+ close(iter_fd);
+ iter_fd = -1;
+ }
+
+ check_bpf_link_info(skel->progs.proc_maps);
+
+out:
+ waitpid(child_pid, &wstatus, 0);
+ close(iter_fd);
+ bpf_iter_task_vma__destroy(skel);
+}
+
void test_bpf_sockmap_map_iter_fd(void)
{
struct bpf_iter_sockmap *skel;
@@ -1586,6 +1657,8 @@ void test_bpf_iter(void)
test_task_file();
if (test__start_subtest("task_vma"))
test_task_vma();
+ if (test__start_subtest("task_vma_dead_task"))
+ test_task_vma_dead_task();
if (test__start_subtest("task_btf"))
test_task_btf();
if (test__start_subtest("tcp4"))
--
GitLab
From 45435d8da71f9f3e6860e6e6ea9667b6ec17ec64 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 23 Dec 2022 10:28:44 -0800
Subject: [PATCH 0176/1167] bpf: Always use maximal size for copy_array()
Instead of counting on prior allocations to have sized allocations to
the next kmalloc bucket size, always perform a krealloc that is at least
ksize(dst) in size (which is a no-op), so the size can be correctly
tracked by all the various allocation size trackers (KASAN,
__alloc_size, etc).
Reported-by: Hyunwoo Kim <v4bel@theori.io>
Link: https://lore.kernel.org/bpf/20221223094551.GA1439509@ubuntu
Fixes: ceb35b666d42 ("bpf/verifier: Use kmalloc_size_roundup() to match ksize() usage")
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Song Liu <song@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: bpf@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221223182836.never.866-kees@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/verifier.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 243d06ce68426..85f96c1e9f62f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1054,6 +1054,8 @@ static void print_insn_state(struct bpf_verifier_env *env,
*/
static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
{
+ size_t alloc_bytes;
+ void *orig = dst;
size_t bytes;
if (ZERO_OR_NULL_PTR(src))
@@ -1062,11 +1064,11 @@ static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
- if (ksize(dst) < ksize(src)) {
- kfree(dst);
- dst = kmalloc_track_caller(kmalloc_size_roundup(bytes), flags);
- if (!dst)
- return NULL;
+ alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
+ dst = krealloc(orig, alloc_bytes, flags);
+ if (!dst) {
+ kfree(orig);
+ return NULL;
}
memcpy(dst, src, bytes);
--
GitLab
From 5626af8fc4322a972b59c7b1a6760767f7b58d4f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:38:10 +0100
Subject: [PATCH 0177/1167] pinctrl: sp7021: fix unused function warning
sppctl_gpio_inv_get is only used from the debugfs code inside
of an #ifdef, so we get a warning without that:
drivers/pinctrl/sunplus/sppctl.c:393:12: error: 'sppctl_gpio_inv_get' defined but not used [-Werror=unused-function]
393 | static int sppctl_gpio_inv_get(struct gpio_chip *chip, unsigned int offset)
| ^~~~~~~~~~~~~~~~~~~
Replace the #ifdef with an IS_ENABLED() check that avoids the warning.
Fixes: aa74c44be19c ("pinctrl: Add driver for Sunplus SP7021")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20221215163822.542622-1-arnd@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/pinctrl/sunplus/sppctl.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/pinctrl/sunplus/sppctl.c b/drivers/pinctrl/sunplus/sppctl.c
index 2b3335ab56c66..25101293268f6 100644
--- a/drivers/pinctrl/sunplus/sppctl.c
+++ b/drivers/pinctrl/sunplus/sppctl.c
@@ -499,7 +499,6 @@ static int sppctl_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
return 0;
}
-#ifdef CONFIG_DEBUG_FS
static void sppctl_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
{
const char *label;
@@ -521,7 +520,6 @@ static void sppctl_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip)
seq_puts(s, "\n");
}
}
-#endif
static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pctl)
{
@@ -550,9 +548,8 @@ static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pc
gchip->get = sppctl_gpio_get;
gchip->set = sppctl_gpio_set;
gchip->set_config = sppctl_gpio_set_config;
-#ifdef CONFIG_DEBUG_FS
- gchip->dbg_show = sppctl_gpio_dbg_show;
-#endif
+ gchip->dbg_show = IS_ENABLED(CONFIG_DEBUG_FS) ?
+ sppctl_gpio_dbg_show : NULL;
gchip->base = -1;
gchip->ngpio = sppctl_gpio_list_sz;
gchip->names = sppctl_gpio_list_s;
--
GitLab
From 56c5dab20a6391604df9521f812c01d1e3fe1bd0 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Mon, 12 Dec 2022 13:04:11 +0100
Subject: [PATCH 0178/1167] RDMA/srp: Move large values to a new enum for gcc13
Since gcc13, each member of an enum has the same type as the enum [1]. And
that is inherited from its members. Provided these two:
SRP_TAG_NO_REQ = ~0U,
SRP_TAG_TSK_MGMT = 1U << 31
all other members are unsigned ints.
Esp. with SRP_MAX_SGE and SRP_TSK_MGMT_SQ_SIZE and their use in min(),
this results in the following warnings:
include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast
drivers/infiniband/ulp/srp/ib_srp.c:563:42: note: in expansion of macro 'min'
include/linux/minmax.h:20:35: error: comparison of distinct pointer types lacks a cast
drivers/infiniband/ulp/srp/ib_srp.c:2369:27: note: in expansion of macro 'min'
So move the large values away to a separate enum, so that they don't
affect other members.
[1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=36113
Link: https://lore.kernel.org/r/20221212120411.13750-1-jirislaby@kernel.org
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/ulp/srp/ib_srp.h | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 00b0068fda208..5d94db453df32 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -62,9 +62,6 @@ enum {
SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE -
SRP_TSK_MGMT_SQ_SIZE,
- SRP_TAG_NO_REQ = ~0U,
- SRP_TAG_TSK_MGMT = 1U << 31,
-
SRP_MAX_PAGES_PER_MR = 512,
SRP_MAX_ADD_CDB_LEN = 16,
@@ -79,6 +76,11 @@ enum {
sizeof(struct srp_imm_buf),
};
+enum {
+ SRP_TAG_NO_REQ = ~0U,
+ SRP_TAG_TSK_MGMT = BIT(31),
+};
+
enum srp_target_state {
SRP_TARGET_SCANNING,
SRP_TARGET_LIVE,
--
GitLab
From 6e1dbf694d7cd1737ee14866e9e05016ccc9ac40 Mon Sep 17 00:00:00 2001
From: tongjian <tongjian@huaqin.corp-partner.google.com>
Date: Wed, 28 Dec 2022 20:22:29 +0800
Subject: [PATCH 0179/1167] ASoC: mediatek: mt8186: support rt5682s_max98360
Add support for using the rt5682s codec together with max98360a on
MT8186-MT6366-RT1019-RT5682S machines.
Signed-off-by: tongjian <tongjian@huaqin.corp-partner.google.com>
Link: https://lore.kernel.org/r/20221228122230.3818533-2-tongjian@huaqin.corp-partner.google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../mt8186/mt8186-mt6366-rt1019-rt5682s.c | 22 ++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
index 8f77a0bc1dc8d..af44e331dae82 100644
--- a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
+++ b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c
@@ -1083,6 +1083,21 @@ static struct snd_soc_card mt8186_mt6366_rt1019_rt5682s_soc_card = {
.num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
};
+static struct snd_soc_card mt8186_mt6366_rt5682s_max98360_soc_card = {
+ .name = "mt8186_rt5682s_max98360",
+ .owner = THIS_MODULE,
+ .dai_link = mt8186_mt6366_rt1019_rt5682s_dai_links,
+ .num_links = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_dai_links),
+ .controls = mt8186_mt6366_rt1019_rt5682s_controls,
+ .num_controls = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_controls),
+ .dapm_widgets = mt8186_mt6366_rt1019_rt5682s_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_widgets),
+ .dapm_routes = mt8186_mt6366_rt1019_rt5682s_routes,
+ .num_dapm_routes = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_routes),
+ .codec_conf = mt8186_mt6366_rt1019_rt5682s_codec_conf,
+ .num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
+};
+
static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
{
struct snd_soc_card *card;
@@ -1232,9 +1247,14 @@ static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
#if IS_ENABLED(CONFIG_OF)
static const struct of_device_id mt8186_mt6366_rt1019_rt5682s_dt_match[] = {
- { .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
.data = &mt8186_mt6366_rt1019_rt5682s_soc_card,
},
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt5682s-max98360-sound",
+ .data = &mt8186_mt6366_rt5682s_max98360_soc_card,
+ },
{}
};
MODULE_DEVICE_TABLE(of, mt8186_mt6366_rt1019_rt5682s_dt_match);
--
GitLab
From 2d3dd559751ce19ba84f9690c6c7c5a4b39129df Mon Sep 17 00:00:00 2001
From: tongjian <tongjian@huaqin.corp-partner.google.com>
Date: Wed, 28 Dec 2022 20:22:30 +0800
Subject: [PATCH 0180/1167] ASoC: dt-bindings: mt8186-mt6366: add new
compatible for max98360a
Adds new compatible string "mt8186-mt6366-rt5682s-max98360-sound" for machines
with max98360a and rt5682s.
Signed-off-by: tongjian <tongjian@huaqin.corp-partner.google.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20221228122230.3818533-3-tongjian@huaqin.corp-partner.google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml | 1 +
1 file changed, 1 insertion(+)
diff --git a/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml b/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml
index 9d31399902374..aa23b0024c461 100644
--- a/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml
+++ b/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml
@@ -16,6 +16,7 @@ properties:
compatible:
enum:
- mediatek,mt8186-mt6366-rt1019-rt5682s-sound
+ - mediatek,mt8186-mt6366-rt5682s-max98360-sound
mediatek,platform:
$ref: "/schemas/types.yaml#/definitions/phandle"
--
GitLab
From 8a54f666db581bbf07494cca44a0124acbced581 Mon Sep 17 00:00:00 2001
From: Allen-KH Cheng <allen-kh.cheng@mediatek.com>
Date: Wed, 28 Dec 2022 19:57:56 +0800
Subject: [PATCH 0181/1167] ASoC: mediatek: mt8186: Add machine support for
max98357a
Add support for mt8186 with mt6366 and max98357a.
Signed-off-by: Allen-KH Cheng <allen-kh.cheng@mediatek.com>
Link: https://lore.kernel.org/r/20221228115756.28014-1-allen-kh.cheng@mediatek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/mediatek/Kconfig | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 363fa4d476800..7bdb0ded831c4 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -182,9 +182,10 @@ config SND_SOC_MT8186_MT6366_DA7219_MAX98357
If unsure select "N".
config SND_SOC_MT8186_MT6366_RT1019_RT5682S
- tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S codec"
+ tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S MAX98357A/MAX98360 codec"
depends on I2C && GPIOLIB
depends on SND_SOC_MT8186 && MTK_PMIC_WRAP
+ select SND_SOC_MAX98357A
select SND_SOC_MT6358
select SND_SOC_RT1015P
select SND_SOC_RT5682S
--
GitLab
From 7161bd540eebebae2bbe8c79de25d8caf12dbf78 Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Thu, 29 Dec 2022 16:03:53 +0800
Subject: [PATCH 0182/1167] ASoC: rt9120: Make dev PM runtime bind AsoC
component PM
RT9120 uses PM runtime autosuspend to decrease the frequently on/off
spent time. This exists one case, when pcm is closed and dev PM is
waiting for autosuspend time expired to enter runtime suspend state.
At the mean time, system is going to enter suspend, dev PM runtime
suspend won't be called. It makes the rt9120 suspend consumption
current not as expected.
This patch can fix the rt9120 dev PM issue during runtime autosuspend
and system suspend by binding dev PM runtime and ASoC component PM.
Fixes: 80b949f332e3 ("ASoC: rt9120: Use pm_runtime and regcache to optimize 'pwdnn' logic")
Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Link: https://lore.kernel.org/r/1672301033-3675-1-git-send-email-u0084500@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/rt9120.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c
index 644300e88b4c5..fcf4fbaed3c76 100644
--- a/sound/soc/codecs/rt9120.c
+++ b/sound/soc/codecs/rt9120.c
@@ -177,8 +177,20 @@ static int rt9120_codec_probe(struct snd_soc_component *comp)
return 0;
}
+static int rt9120_codec_suspend(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_suspend(comp->dev);
+}
+
+static int rt9120_codec_resume(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_resume(comp->dev);
+}
+
static const struct snd_soc_component_driver rt9120_component_driver = {
.probe = rt9120_codec_probe,
+ .suspend = rt9120_codec_suspend,
+ .resume = rt9120_codec_resume,
.controls = rt9120_snd_controls,
.num_controls = ARRAY_SIZE(rt9120_snd_controls),
.dapm_widgets = rt9120_dapm_widgets,
--
GitLab
From a0dd7fcab5cd221fa960f594c586e1f9f16c02c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aniol=20Mart=C3=AD?= <aniol@aniolmarti.cat>
Date: Tue, 27 Dec 2022 23:49:32 +0100
Subject: [PATCH 0183/1167] ASoC: amd: yc: Add ASUS M5402RA into DMI table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
ASUS VivoBook 13 OLED (M5402RA) needs this quirk to get the built-in microphone working properly.
Signed-off-by: Aniol Martà <aniol@aniolmarti.cat>
Link: https://lore.kernel.org/r/20221227224932.9771-1-aniol@aniolmarti.cat
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 469c5e79e0ea0..0d283e41f66dc 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -206,6 +206,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"),
+ }
+ },
{
.driver_data = &acp6x_card,
.matches = {
--
GitLab
From 810948f45d99c46b60852ef2a5a2777c12d6bb3e Mon Sep 17 00:00:00 2001
From: Mars Chen <chenxiangrui@huaqin.corp-partner.google.com>
Date: Wed, 28 Dec 2022 18:38:12 +0800
Subject: [PATCH 0184/1167] ASoC: support machine driver with max98360
Signed-off-by: Mars Chen <chenxiangrui@huaqin.corp-partner.google.com>
Link: https://lore.kernel.org/r/20221228103812.450956-1-chenxiangrui@huaqin.corp-partner.google.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/mediatek/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig
index 7bdb0ded831c4..b027fba8233df 100644
--- a/sound/soc/mediatek/Kconfig
+++ b/sound/soc/mediatek/Kconfig
@@ -187,6 +187,7 @@ config SND_SOC_MT8186_MT6366_RT1019_RT5682S
depends on SND_SOC_MT8186 && MTK_PMIC_WRAP
select SND_SOC_MAX98357A
select SND_SOC_MT6358
+ select SND_SOC_MAX98357A
select SND_SOC_RT1015P
select SND_SOC_RT5682S
select SND_SOC_BT_SCO
--
GitLab
From 74b91a1bdb994dfaed0074154ca7d493aeb735a6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 24 Dec 2022 22:43:51 +0100
Subject: [PATCH 0185/1167] arm64: dts: qcom: sm8350: correct SDHCI
interconnect arguments
The interconnect providers accept only one argument (cells == 1), so fix
a copy&paste from SM8450:
sm8350-hdk.dtb: mmc@8804000: interconnects: [[74, 9, 0], [75, 1, 0], [76, 2, 0], [77, 36, 0]] is too long
Fixes: 60477435e4de ("arm64: dts: qcom: sm8350: Add SDHCI2")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221224214351.18215-1-krzysztof.kozlowski@linaro.org
---
arch/arm64/boot/dts/qcom/sm8350.dtsi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
index 245dce24ec599..fb3cd20a82b5e 100644
--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
@@ -2382,8 +2382,8 @@ sdhc_2: sdhci@8804000 {
<&rpmhcc RPMH_CXO_CLK>;
clock-names = "iface", "core", "xo";
resets = <&gcc GCC_SDCC2_BCR>;
- interconnects = <&aggre2_noc MASTER_SDCC_2 0 &mc_virt SLAVE_EBI1 0>,
- <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_SDCC_2 0>;
+ interconnects = <&aggre2_noc MASTER_SDCC_2 &mc_virt SLAVE_EBI1>,
+ <&gem_noc MASTER_APPSS_PROC &config_noc SLAVE_SDCC_2>;
interconnect-names = "sdhc-ddr","cpu-sdhc";
iommus = <&apps_smmu 0x4a0 0x0>;
power-domains = <&rpmhpd SM8350_CX>;
--
GitLab
From 472a6309c6467af89dbf660a8310369cc9cb041f Mon Sep 17 00:00:00 2001
From: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Date: Fri, 23 Dec 2022 09:02:47 +0100
Subject: [PATCH 0186/1167] ASoC: wm8904: fix wrong outputs volume after power
reactivation
Restore volume after charge pump and PGA activation to ensure
that volume settings are correctly applied when re-enabling codec
from SND_SOC_BIAS_OFF state.
CLASS_W, CHARGE_PUMP and POWER_MANAGEMENT_2 register configuration
affect how the volume register are applied and must be configured first.
Fixes: a91eb199e4dc ("ASoC: Initial WM8904 CODEC driver")
Link: https://lore.kernel.org/all/c7864c35-738c-a867-a6a6-ddf9f98df7e7@gmail.com/
Signed-off-by: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20221223080247.7258-1-francesco@dolcini.it
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/codecs/wm8904.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index ca6a01a230af4..791d8738d1c0e 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -697,6 +697,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
int dcs_mask;
int dcs_l, dcs_r;
int dcs_l_reg, dcs_r_reg;
+ int an_out_reg;
int timeout;
int pwr_reg;
@@ -712,6 +713,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
dcs_mask = WM8904_DCS_ENA_CHAN_0 | WM8904_DCS_ENA_CHAN_1;
dcs_r_reg = WM8904_DC_SERVO_8;
dcs_l_reg = WM8904_DC_SERVO_9;
+ an_out_reg = WM8904_ANALOGUE_OUT1_LEFT;
dcs_l = 0;
dcs_r = 1;
break;
@@ -720,6 +722,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
dcs_mask = WM8904_DCS_ENA_CHAN_2 | WM8904_DCS_ENA_CHAN_3;
dcs_r_reg = WM8904_DC_SERVO_6;
dcs_l_reg = WM8904_DC_SERVO_7;
+ an_out_reg = WM8904_ANALOGUE_OUT2_LEFT;
dcs_l = 2;
dcs_r = 3;
break;
@@ -792,6 +795,10 @@ static int out_pga_event(struct snd_soc_dapm_widget *w,
snd_soc_component_update_bits(component, reg,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP);
+
+ /* Update volume, requires PGA to be powered */
+ val = snd_soc_component_read(component, an_out_reg);
+ snd_soc_component_write(component, an_out_reg, val);
break;
case SND_SOC_DAPM_POST_PMU:
--
GitLab
From 936a192f974018b4f6040f6f77b1cc1e75bd8666 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 26 Dec 2022 22:27:52 +0900
Subject: [PATCH 0187/1167] tcp: Add TIME_WAIT sockets in bhash2.
Jiri Slaby reported regression of bind() with a simple repro. [0]
The repro creates a TIME_WAIT socket and tries to bind() a new socket
with the same local address and port. Before commit 28044fc1d495 ("net:
Add a bhash2 table hashed by port and address"), the bind() failed with
-EADDRINUSE, but now it succeeds.
The cited commit should have put TIME_WAIT sockets into bhash2; otherwise,
inet_bhash2_conflict() misses TIME_WAIT sockets when validating bind()
requests if the address is not a wildcard one.
The straight option is to move sk_bind2_node from struct sock to struct
sock_common to add twsk to bhash2 as implemented as RFC. [1] However, the
binary layout change in the struct sock could affect performances moving
hot fields on different cachelines.
To avoid that, we add another TIME_WAIT list in inet_bind2_bucket and check
it while validating bind().
[0]: https://lore.kernel.org/netdev/6b971a4e-c7d8-411e-1f92-fda29b5b2fb9@kernel.org/
[1]: https://lore.kernel.org/netdev/20221221151258.25748-2-kuniyu@amazon.com/
Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address")
Reported-by: Jiri Slaby <jirislaby@kernel.org>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/inet_hashtables.h | 4 ++++
include/net/inet_timewait_sock.h | 5 +++++
net/ipv4/inet_connection_sock.c | 26 ++++++++++++++++++++++----
net/ipv4/inet_hashtables.c | 8 +++++---
net/ipv4/inet_timewait_sock.c | 31 +++++++++++++++++++++++++++++--
5 files changed, 65 insertions(+), 9 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 69174093078f0..99bd823e97f62 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -108,6 +108,10 @@ struct inet_bind2_bucket {
struct hlist_node node;
/* List of sockets hashed to this bucket */
struct hlist_head owners;
+ /* bhash has twsk in owners, but bhash2 has twsk in
+ * deathrow not to add a member in struct sock_common.
+ */
+ struct hlist_head deathrow;
};
static inline struct net *ib_net(const struct inet_bind_bucket *ib)
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index 5b47545f22d39..4a8e578405cb3 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -73,9 +73,14 @@ struct inet_timewait_sock {
u32 tw_priority;
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
+ struct inet_bind2_bucket *tw_tb2;
+ struct hlist_node tw_bind2_node;
};
#define tw_tclass tw_tos
+#define twsk_for_each_bound_bhash2(__tw, list) \
+ hlist_for_each_entry(__tw, list, tw_bind2_node)
+
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
{
return (struct inet_timewait_sock *)sk;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b366ab9148f2d..848ffc3e0239c 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -173,22 +173,40 @@ static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
return false;
}
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+ kuid_t sk_uid, bool relax,
+ bool reuseport_cb_ok, bool reuseport_ok)
+{
+ if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+ return false;
+
+ return inet_bind_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok);
+}
+
static bool inet_bhash2_conflict(const struct sock *sk,
const struct inet_bind2_bucket *tb2,
kuid_t sk_uid,
bool relax, bool reuseport_cb_ok,
bool reuseport_ok)
{
+ struct inet_timewait_sock *tw2;
struct sock *sk2;
sk_for_each_bound_bhash2(sk2, &tb2->owners) {
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- continue;
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
+ return true;
+ }
- if (inet_bind_conflict(sk, sk2, sk_uid, relax,
- reuseport_cb_ok, reuseport_ok))
+ twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+ sk2 = (struct sock *)tw2;
+
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
return true;
}
+
return false;
}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d039b4e732a31..24a38b56fab9e 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -116,6 +116,7 @@ static void inet_bind2_bucket_init(struct inet_bind2_bucket *tb,
#endif
tb->rcv_saddr = sk->sk_rcv_saddr;
INIT_HLIST_HEAD(&tb->owners);
+ INIT_HLIST_HEAD(&tb->deathrow);
hlist_add_head(&tb->node, &head->chain);
}
@@ -137,7 +138,7 @@ struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep,
/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
- if (hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
@@ -1103,15 +1104,16 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, tb2, port);
- spin_unlock(&head2->lock);
-
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
+
+ spin_unlock(&head2->lock);
spin_unlock(&head->lock);
+
if (tw)
inet_twsk_deschedule_put(tw);
local_bh_enable();
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 66fc940f9521a..1d77d992e6e77 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -29,6 +29,7 @@
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
+ struct inet_bind2_bucket *tb2 = tw->tw_tb2;
struct inet_bind_bucket *tb = tw->tw_tb;
if (!tb)
@@ -37,6 +38,11 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
__hlist_del(&tw->tw_bind_node);
tw->tw_tb = NULL;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+
+ __hlist_del(&tw->tw_bind2_node);
+ tw->tw_tb2 = NULL;
+ inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+
__sock_put((struct sock *)tw);
}
@@ -45,7 +51,7 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
spin_lock(lock);
sk_nulls_del_node_init_rcu((struct sock *)tw);
@@ -54,9 +60,13 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw,
+ twsk_net(tw), tw->tw_num);
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
inet_twsk_bind_unhash(tw, hashinfo);
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
refcount_dec(&tw->tw_dr->tw_refcount);
@@ -93,6 +103,12 @@ static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
hlist_add_head(&tw->tw_bind_node, list);
}
+static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
+ struct hlist_head *list)
+{
+ hlist_add_head(&tw->tw_bind2_node, list);
+}
+
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
@@ -105,17 +121,28 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
+
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
+
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
+
+ tw->tw_tb2 = icsk->icsk_bind2_hash;
+ WARN_ON(!icsk->icsk_bind2_hash);
+ inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
spin_lock(lock);
--
GitLab
From 2c042e8e54efb2b8e25ed0cb28224e79948dc8ce Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 26 Dec 2022 22:27:53 +0900
Subject: [PATCH 0188/1167] tcp: Add selftest for bind() and TIME_WAIT.
bhash2 split the bind() validation logic into wildcard and non-wildcard
cases. Let's add a test to catch future regression.
Before the previous patch:
# ./bind_timewait
TAP version 13
1..2
# Starting 2 tests from 3 test cases.
# RUN bind_timewait.localhost.1 ...
# bind_timewait.c:87:1:Expected ret (0) == -1 (-1)
# 1: Test terminated by assertion
# FAIL bind_timewait.localhost.1
not ok 1 bind_timewait.localhost.1
# RUN bind_timewait.addrany.1 ...
# OK bind_timewait.addrany.1
ok 2 bind_timewait.addrany.1
# FAILED: 1 / 2 tests passed.
# Totals: pass:1 fail:1 xfail:0 xpass:0 skip:0 error:0
After:
# ./bind_timewait
TAP version 13
1..2
# Starting 2 tests from 3 test cases.
# RUN bind_timewait.localhost.1 ...
# OK bind_timewait.localhost.1
ok 1 bind_timewait.localhost.1
# RUN bind_timewait.addrany.1 ...
# OK bind_timewait.addrany.1
ok 2 bind_timewait.addrany.1
# PASSED: 2 / 2 tests passed.
# Totals: pass:2 fail:0 xfail:0 xpass:0 skip:0 error:0
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/bind_timewait.c | 92 +++++++++++++++++++++
2 files changed, 93 insertions(+)
create mode 100644 tools/testing/selftests/net/bind_timewait.c
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 9cc84114741d3..a6911cae368c7 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
bind_bhash
+bind_timewait
csum
cmsg_sender
diag_uid
diff --git a/tools/testing/selftests/net/bind_timewait.c b/tools/testing/selftests/net/bind_timewait.c
new file mode 100644
index 0000000000000..cb9fdf51ea59f
--- /dev/null
+++ b/tools/testing/selftests/net/bind_timewait.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "../kselftest_harness.h"
+
+FIXTURE(bind_timewait)
+{
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+};
+
+FIXTURE_VARIANT(bind_timewait)
+{
+ __u32 addr_const;
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, localhost)
+{
+ .addr_const = INADDR_LOOPBACK
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, addrany)
+{
+ .addr_const = INADDR_ANY
+};
+
+FIXTURE_SETUP(bind_timewait)
+{
+ self->addr.sin_family = AF_INET;
+ self->addr.sin_port = 0;
+ self->addr.sin_addr.s_addr = htonl(variant->addr_const);
+ self->addrlen = sizeof(self->addr);
+}
+
+FIXTURE_TEARDOWN(bind_timewait)
+{
+}
+
+void create_timewait_socket(struct __test_metadata *_metadata,
+ FIXTURE_DATA(bind_timewait) *self)
+{
+ int server_fd, client_fd, child_fd, ret;
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+
+ server_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(server_fd, 0);
+
+ ret = bind(server_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ ret = listen(server_fd, 1);
+ ASSERT_EQ(ret, 0);
+
+ ret = getsockname(server_fd, (struct sockaddr *)&self->addr, &self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ client_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(client_fd, 0);
+
+ ret = connect(client_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ addrlen = sizeof(addr);
+ child_fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+ ASSERT_GT(child_fd, 0);
+
+ close(child_fd);
+ close(client_fd);
+ close(server_fd);
+}
+
+TEST_F(bind_timewait, 1)
+{
+ int fd, ret;
+
+ create_timewait_socket(_metadata, self);
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(fd, 0);
+
+ ret = bind(fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EADDRINUSE);
+
+ close(fd);
+}
+
+TEST_HARNESS_MAIN
--
GitLab
From 6b57bffa5f675a01c7981ed271e8521e87441abd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 27 Dec 2022 22:45:07 +0100
Subject: [PATCH 0189/1167] net: ethernet: broadcom: bcm63xx_enet: Drop empty
platform remove function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A remove callback just returning 0 is equivalent to no remove callback
at all. So drop the useless function.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bcm63xx_enet.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index d91fdb0c2649d..2cf96892e5650 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -2784,17 +2784,11 @@ static int bcm_enet_shared_probe(struct platform_device *pdev)
return 0;
}
-static int bcm_enet_shared_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
/* this "shared" driver is needed because both macs share a single
* address space
*/
struct platform_driver bcm63xx_enet_shared_driver = {
.probe = bcm_enet_shared_probe,
- .remove = bcm_enet_shared_remove,
.driver = {
.name = "bcm63xx_enet_shared",
.owner = THIS_MODULE,
--
GitLab
From af691c94d022440476b76560d310d6fea790cc60 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@pengutronix.de>
Date: Tue, 27 Dec 2022 22:45:08 +0100
Subject: [PATCH 0190/1167] net: ethernet: freescale: enetc: Drop empty
platform remove function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A remove callback just returning 0 is equivalent to no remove callback
at all. So drop the useless function.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/freescale/enetc/enetc_ierb.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
index 91f02c5050285..b307bef4dc298 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c
@@ -127,11 +127,6 @@ static int enetc_ierb_probe(struct platform_device *pdev)
return 0;
}
-static int enetc_ierb_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
static const struct of_device_id enetc_ierb_match[] = {
{ .compatible = "fsl,ls1028a-enetc-ierb", },
{},
@@ -144,7 +139,6 @@ static struct platform_driver enetc_ierb_driver = {
.of_match_table = enetc_ierb_match,
},
.probe = enetc_ierb_probe,
- .remove = enetc_ierb_remove,
};
module_platform_driver(enetc_ierb_driver);
--
GitLab
From fec7352117fa301bfbc31bacc14bb9a579376b36 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Wed, 28 Dec 2022 14:27:49 +0800
Subject: [PATCH 0191/1167] net: hns3: refine the handling for VF heartbeat
Currently, the PF check the VF alive by the KEEP_ALVE
mailbox from VF. VF keep sending the mailbox per 2
seconds. Once PF lost the mailbox for more than 8
seconds, it will regards the VF is abnormal, and stop
notifying the state change to VF, include link state,
vf mac, reset, even though it receives the KEEP_ALIVE
mailbox again. It's inreasonable.
This patch fixes it. PF will record the state change which
need to notify VF when lost the VF's KEEP_ALIVE mailbox.
And notify VF when receive the mailbox again. Introduce a
new flag HCLGE_VPORT_STATE_INITED, used to distinguish the
case whether VF driver loaded or not. For VF will query
these states when initializing, so it's unnecessary to
notify it in this case.
Fixes: aa5c4f175be6 ("net: hns3: add reset handling for VF when doing PF reset")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Hao Lan <lanhao@huawei.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../hisilicon/hns3/hns3pf/hclge_main.c | 57 +++++++++++----
.../hisilicon/hns3/hns3pf/hclge_main.h | 7 ++
.../hisilicon/hns3/hns3pf/hclge_mbx.c | 71 ++++++++++++++++---
3 files changed, 112 insertions(+), 23 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 6c2742f59c777..07ad5f35219e2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3910,9 +3910,17 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
return ret;
}
- if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ if (!reset ||
+ !test_bit(HCLGE_VPORT_STATE_INITED, &vport->state))
continue;
+ if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state) &&
+ hdev->reset_type == HNAE3_FUNC_RESET) {
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_RESET,
+ &vport->need_notify);
+ continue;
+ }
+
/* Inform VF to process the reset.
* hclge_inform_reset_assert_to_vf may fail if VF
* driver is not loaded.
@@ -4609,18 +4617,25 @@ static void hclge_reset_service_task(struct hclge_dev *hdev)
static void hclge_update_vport_alive(struct hclge_dev *hdev)
{
+#define HCLGE_ALIVE_SECONDS_NORMAL 8
+
+ unsigned long alive_time = HCLGE_ALIVE_SECONDS_NORMAL * HZ;
int i;
/* start from vport 1 for PF is always alive */
for (i = 1; i < hdev->num_alloc_vport; i++) {
struct hclge_vport *vport = &hdev->vport[i];
- if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+ if (!test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) ||
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ continue;
+ if (time_after(jiffies, vport->last_active_jiffies +
+ alive_time)) {
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
-
- /* If vf is not alive, set to default value */
- if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+ dev_warn(&hdev->pdev->dev,
+ "VF %u heartbeat timeout\n",
+ i - HCLGE_VF_VPORT_START_NUM);
+ }
}
}
@@ -8064,9 +8079,11 @@ int hclge_vport_start(struct hclge_vport *vport)
{
struct hclge_dev *hdev = vport->back;
+ set_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_active_jiffies = jiffies;
+ vport->need_notify = 0;
if (test_bit(vport->vport_id, hdev->vport_config_block)) {
if (vport->vport_id) {
@@ -8084,7 +8101,9 @@ int hclge_vport_start(struct hclge_vport *vport)
void hclge_vport_stop(struct hclge_vport *vport)
{
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
}
static int hclge_client_start(struct hnae3_handle *handle)
@@ -9208,7 +9227,8 @@ static int hclge_set_vf_mac(struct hnae3_handle *handle, int vf,
return 0;
}
- dev_info(&hdev->pdev->dev, "MAC of VF %d has been set to %s\n",
+ dev_info(&hdev->pdev->dev,
+ "MAC of VF %d has been set to %s, will be active after VF reset\n",
vf, format_mac_addr);
return 0;
}
@@ -10465,12 +10485,16 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid,
* for DEVICE_VERSION_V3, vf doesn't need to know about the port based
* VLAN state.
*/
- if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
- test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
- vport->vport_id,
- state, &vlan_info);
-
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+ if (test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ state,
+ &vlan_info);
+ else
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+ &vport->need_notify);
+ }
return 0;
}
@@ -11941,7 +11965,7 @@ static void hclge_reset_vport_state(struct hclge_dev *hdev)
int i;
for (i = 0; i < hdev->num_alloc_vport; i++) {
- hclge_vport_stop(vport);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
vport++;
}
}
@@ -12955,6 +12979,11 @@ static void hclge_clear_vport_vf_info(struct hclge_vport *vport, int vfid)
struct hclge_vlan_info vlan_info;
int ret;
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
+ vport->mps = 0;
+
/* after disable sriov, clean VF rate configured by PF */
ret = hclge_tm_qs_shaper_cfg(vport, 0);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 495b639b0dc24..13f23d606e77b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -995,9 +995,15 @@ enum HCLGE_VPORT_STATE {
HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
HCLGE_VPORT_STATE_PROMISC_CHANGE,
HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+ HCLGE_VPORT_STATE_INITED,
HCLGE_VPORT_STATE_MAX
};
+enum HCLGE_VPORT_NEED_NOTIFY {
+ HCLGE_VPORT_NEED_NOTIFY_RESET,
+ HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+};
+
struct hclge_vlan_info {
u16 vlan_proto; /* so far support 802.1Q only */
u16 qos;
@@ -1044,6 +1050,7 @@ struct hclge_vport {
struct hnae3_handle roce;
unsigned long state;
+ unsigned long need_notify;
unsigned long last_active_jiffies;
u32 mps; /* Max packet size */
struct hclge_vf_info vf_info;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index a7b06c63143cc..04ff9bf121853 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -124,17 +124,26 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
return status;
}
+static int hclge_inform_vf_reset(struct hclge_vport *vport, u16 reset_type)
+{
+ __le16 msg_data;
+ u8 dest_vfid;
+
+ dest_vfid = (u8)vport->vport_id;
+ msg_data = cpu_to_le16(reset_type);
+
+ /* send this requested info to VF */
+ return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
+ HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+}
+
int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
{
struct hclge_dev *hdev = vport->back;
- __le16 msg_data;
u16 reset_type;
- u8 dest_vfid;
BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX);
- dest_vfid = (u8)vport->vport_id;
-
if (hdev->reset_type == HNAE3_FUNC_RESET)
reset_type = HNAE3_VF_PF_FUNC_RESET;
else if (hdev->reset_type == HNAE3_FLR_RESET)
@@ -142,11 +151,7 @@ int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
else
reset_type = HNAE3_VF_FUNC_RESET;
- msg_data = cpu_to_le16(reset_type);
-
- /* send this requested info to VF */
- return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
- HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+ return hclge_inform_vf_reset(vport, reset_type);
}
static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
@@ -652,9 +657,56 @@ static int hclge_reset_vf(struct hclge_vport *vport)
return hclge_func_reset_cmd(hdev, vport->vport_id);
}
+static void hclge_notify_vf_config(struct hclge_vport *vport)
+{
+ struct hclge_dev *hdev = vport->back;
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ struct hclge_port_base_vlan_config *vlan_cfg;
+ int ret;
+
+ hclge_push_vf_link_status(vport);
+ if (test_bit(HCLGE_VPORT_NEED_NOTIFY_RESET, &vport->need_notify)) {
+ ret = hclge_inform_vf_reset(vport, HNAE3_VF_PF_FUNC_RESET);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u reset!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ vport->need_notify = 0;
+ return;
+ }
+
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
+ test_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify)) {
+ vlan_cfg = &vport->port_base_vlan_cfg;
+ ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ vlan_cfg->state,
+ &vlan_cfg->vlan_info);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u port base vlan!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ clear_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify);
+ }
+}
+
static void hclge_vf_keep_alive(struct hclge_vport *vport)
{
+ struct hclge_dev *hdev = vport->back;
+
vport->last_active_jiffies = jiffies;
+
+ if (test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) &&
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+ set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ dev_info(&hdev->pdev->dev, "VF %u is alive!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ hclge_notify_vf_config(vport);
+ }
}
static int hclge_set_vf_mtu(struct hclge_vport *vport,
@@ -954,6 +1006,7 @@ static int hclge_mbx_vf_uninit_handler(struct hclge_mbx_ops_param *param)
hclge_rm_vport_all_mac_table(param->vport, true,
HCLGE_MAC_ADDR_MC);
hclge_rm_vport_all_vlan_table(param->vport, true);
+ param->vport->mps = 0;
return 0;
}
--
GitLab
From d530ece70f16f912e1d1bfeea694246ab78b0a4b Mon Sep 17 00:00:00 2001
From: Jiguang Xiao <jiguang.xiao@windriver.com>
Date: Wed, 28 Dec 2022 16:14:47 +0800
Subject: [PATCH 0192/1167] net: amd-xgbe: add missed tasklet_kill
The driver does not call tasklet_kill in several places.
Add the calls to fix it.
Fixes: 85b85c853401 ("amd-xgbe: Re-issue interrupt if interrupt status not cleared")
Signed-off-by: Jiguang Xiao <jiguang.xiao@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 3 +++
drivers/net/ethernet/amd/xgbe/xgbe-i2c.c | 4 +++-
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 4 +++-
3 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7b666106feee9..614c0278419bc 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1064,6 +1064,9 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata)
devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+ tasklet_kill(&pdata->tasklet_dev);
+ tasklet_kill(&pdata->tasklet_ecc);
+
if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index 22d4fc547a0a3..a9ccc4258ee50 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -447,8 +447,10 @@ static void xgbe_i2c_stop(struct xgbe_prv_data *pdata)
xgbe_i2c_disable(pdata);
xgbe_i2c_clear_all_interrupts(pdata);
- if (pdata->dev_irq != pdata->i2c_irq)
+ if (pdata->dev_irq != pdata->i2c_irq) {
devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
+ tasklet_kill(&pdata->tasklet_i2c);
+ }
}
static int xgbe_i2c_start(struct xgbe_prv_data *pdata)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4e97b48695220..0c5c1b1556830 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1390,8 +1390,10 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
/* Disable auto-negotiation */
xgbe_an_disable_all(pdata);
- if (pdata->dev_irq != pdata->an_irq)
+ if (pdata->dev_irq != pdata->an_irq) {
devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+ tasklet_kill(&pdata->tasklet_an);
+ }
pdata->phy_if.phy_impl.stop(pdata);
--
GitLab
From 1573c6882018f69991aead951d09423ce978adac Mon Sep 17 00:00:00 2001
From: Po-Hsu Lin <po-hsu.lin@canonical.com>
Date: Thu, 29 Dec 2022 13:41:06 +0800
Subject: [PATCH 0193/1167] selftests: net: fix cmsg_so_mark.sh test hang
This cmsg_so_mark.sh test will hang on non-amd64 systems because of the
infinity loop for argument parsing in cmsg_sender.
Variable "o" in cs_parse_args() for taking getopt() should be an int,
otherwise it will be 255 when getopt() returns -1 on non-amd64 system
and thus causing infinity loop.
Link: https://lore.kernel.org/lkml/CA+G9fYsM2k7mrF7W4V_TrZ-qDauWM394=8yEJ=-t1oUg8_40YA@mail.gmail.com/t/
Signed-off-by: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/cmsg_sender.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 75dd83e39207b..24b21b15ed3fb 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -110,7 +110,7 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
static void cs_parse_args(int argc, char *argv[])
{
- char o;
+ int o;
while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) {
switch (o) {
--
GitLab
From 332b49ff637d6c1a75b971022a8b992cf3c57db1 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:05 +0000
Subject: [PATCH 0194/1167] net: ena: Fix toeplitz initial hash value
On driver initialization, RSS hash initial value is set to zero,
instead of the default value. This happens because we pass NULL as
the RSS key parameter, which caused us to never initialize
the RSS hash value.
This patch fixes it by making sure the initial value is set, no matter
what the value of the RSS key is.
Fixes: 91a65b7d3ed8 ("net: ena: fix potential crash when rxfh key is NULL")
Signed-off-by: Nati Koler <nkoler@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_com.c | 29 +++++++----------------
1 file changed, 9 insertions(+), 20 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 8c8b4c88c7dea..451c3a1b62553 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2400,29 +2400,18 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
return -EOPNOTSUPP;
}
- switch (func) {
- case ENA_ADMIN_TOEPLITZ:
- if (key) {
- if (key_len != sizeof(hash_key->key)) {
- netdev_err(ena_dev->net_device,
- "key len (%u) doesn't equal the supported size (%zu)\n",
- key_len, sizeof(hash_key->key));
- return -EINVAL;
- }
- memcpy(hash_key->key, key, key_len);
- rss->hash_init_val = init_val;
- hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
+ if ((func == ENA_ADMIN_TOEPLITZ) && key) {
+ if (key_len != sizeof(hash_key->key)) {
+ netdev_err(ena_dev->net_device,
+ "key len (%u) doesn't equal the supported size (%zu)\n",
+ key_len, sizeof(hash_key->key));
+ return -EINVAL;
}
- break;
- case ENA_ADMIN_CRC32:
- rss->hash_init_val = init_val;
- break;
- default:
- netdev_err(ena_dev->net_device, "Invalid hash function (%d)\n",
- func);
- return -EINVAL;
+ memcpy(hash_key->key, key, key_len);
+ hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
}
+ rss->hash_init_val = init_val;
old_func = rss->hash_func;
rss->hash_func = func;
rc = ena_com_set_hash_function(ena_dev);
--
GitLab
From 9c9e539956fa67efb8a65e32b72a853740b33445 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:06 +0000
Subject: [PATCH 0195/1167] net: ena: Don't register memory info on XDP
exchange
Since the queues aren't destroyed when we only exchange XDP programs,
there's no need to re-register them again.
Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a95529a69cbb6..6ba9b06719a08 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -512,16 +512,18 @@ static void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter,
struct bpf_prog *prog,
int first, int count)
{
+ struct bpf_prog *old_bpf_prog;
struct ena_ring *rx_ring;
int i = 0;
for (i = first; i < count; i++) {
rx_ring = &adapter->rx_ring[i];
- xchg(&rx_ring->xdp_bpf_prog, prog);
- if (prog) {
+ old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
+
+ if (!old_bpf_prog && prog) {
ena_xdp_register_rxq_info(rx_ring);
rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
- } else {
+ } else if (old_bpf_prog && !prog) {
ena_xdp_unregister_rxq_info(rx_ring);
rx_ring->rx_headroom = NET_SKB_PAD;
}
--
GitLab
From c7f5e34d906320fdc996afa616676161c029cc02 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:07 +0000
Subject: [PATCH 0196/1167] net: ena: Account for the number of processed bytes
in XDP
The size of packets that were forwarded or dropped by XDP wasn't added
to the total processed bytes statistic.
Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6ba9b06719a08..9ae86bd3d457b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1719,6 +1719,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
}
if (xdp_verdict != XDP_PASS) {
xdp_flags |= xdp_verdict;
+ total_len += ena_rx_ctx.ena_bufs[0].len;
res_budget--;
continue;
}
--
GitLab
From 59811faa2c54dbcf44d575b5a8f6e7077da88dc2 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:08 +0000
Subject: [PATCH 0197/1167] net: ena: Use bitmask to indicate packet
redirection
Redirecting packets with XDP Redirect is done in two phases:
1. A packet is passed by the driver to the kernel using
xdp_do_redirect().
2. After finishing polling for new packets the driver lets the kernel
know that it can now process the redirected packet using
xdp_do_flush_map().
The packets' redirection is handled in the napi context of the
queue that called xdp_do_redirect()
To avoid calling xdp_do_flush_map() each time the driver first checks
whether any packets were redirected, using
xdp_flags |= xdp_verdict;
and
if (xdp_flags & XDP_REDIRECT)
xdp_do_flush_map()
essentially treating XDP instructions as a bitmask, which isn't the case:
enum xdp_action {
XDP_ABORTED = 0,
XDP_DROP,
XDP_PASS,
XDP_TX,
XDP_REDIRECT,
};
Given the current possible values of xdp_action, the current design
doesn't have a bug (since XDP_REDIRECT = 100b), but it is still
flawed.
This patch makes the driver use a bitmask instead, to avoid future
issues.
Fixes: a318c70ad152 ("net: ena: introduce XDP redirect implementation")
Signed-off-by: Shay Agroskin <shayagr@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 26 ++++++++++++--------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 9 +++++++
2 files changed, 25 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 9ae86bd3d457b..a67f55e5f7554 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -374,9 +374,9 @@ static int ena_xdp_xmit(struct net_device *dev, int n,
static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
{
+ u32 verdict = ENA_XDP_PASS;
struct bpf_prog *xdp_prog;
struct ena_ring *xdp_ring;
- u32 verdict = XDP_PASS;
struct xdp_frame *xdpf;
u64 *xdp_stat;
@@ -393,7 +393,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
if (unlikely(!xdpf)) {
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
}
@@ -409,29 +409,35 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
spin_unlock(&xdp_ring->xdp_tx_lock);
xdp_stat = &rx_ring->rx_stats.xdp_tx;
+ verdict = ENA_XDP_TX;
break;
case XDP_REDIRECT:
if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
xdp_stat = &rx_ring->rx_stats.xdp_redirect;
+ verdict = ENA_XDP_REDIRECT;
break;
}
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
case XDP_ABORTED:
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+ verdict = ENA_XDP_DROP;
break;
case XDP_DROP:
xdp_stat = &rx_ring->rx_stats.xdp_drop;
+ verdict = ENA_XDP_DROP;
break;
case XDP_PASS:
xdp_stat = &rx_ring->rx_stats.xdp_pass;
+ verdict = ENA_XDP_PASS;
break;
default:
bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_invalid;
+ verdict = ENA_XDP_DROP;
}
ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
@@ -1621,12 +1627,12 @@ static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp)
* we expect, then we simply drop it
*/
if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
- return XDP_DROP;
+ return ENA_XDP_DROP;
ret = ena_xdp_execute(rx_ring, xdp);
/* The xdp program might expand the headers */
- if (ret == XDP_PASS) {
+ if (ret == ENA_XDP_PASS) {
rx_info->page_offset = xdp->data - xdp->data_hard_start;
rx_ring->ena_bufs[0].len = xdp->data_end - xdp->data;
}
@@ -1665,7 +1671,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
xdp_init_buff(&xdp, ENA_PAGE_SIZE, &rx_ring->xdp_rxq);
do {
- xdp_verdict = XDP_PASS;
+ xdp_verdict = ENA_XDP_PASS;
skb = NULL;
ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
ena_rx_ctx.max_bufs = rx_ring->sgl_size;
@@ -1693,7 +1699,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
/* allocate skb and fill it */
- if (xdp_verdict == XDP_PASS)
+ if (xdp_verdict == ENA_XDP_PASS)
skb = ena_rx_skb(rx_ring,
rx_ring->ena_bufs,
ena_rx_ctx.descs,
@@ -1711,13 +1717,13 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
/* Packets was passed for transmission, unmap it
* from RX side.
*/
- if (xdp_verdict == XDP_TX || xdp_verdict == XDP_REDIRECT) {
+ if (xdp_verdict & ENA_XDP_FORWARDED) {
ena_unmap_rx_buff(rx_ring,
&rx_ring->rx_buffer_info[req_id]);
rx_ring->rx_buffer_info[req_id].page = NULL;
}
}
- if (xdp_verdict != XDP_PASS) {
+ if (xdp_verdict != ENA_XDP_PASS) {
xdp_flags |= xdp_verdict;
total_len += ena_rx_ctx.ena_bufs[0].len;
res_budget--;
@@ -1763,7 +1769,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
ena_refill_rx_bufs(rx_ring, refill_required);
}
- if (xdp_flags & XDP_REDIRECT)
+ if (xdp_flags & ENA_XDP_REDIRECT)
xdp_do_flush_map();
return work_done;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 1bdce99bf6888..290ae9bf47ee4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -409,6 +409,15 @@ enum ena_xdp_errors_t {
ENA_XDP_NO_ENOUGH_QUEUES,
};
+enum ENA_XDP_ACTIONS {
+ ENA_XDP_PASS = 0,
+ ENA_XDP_TX = BIT(0),
+ ENA_XDP_REDIRECT = BIT(1),
+ ENA_XDP_DROP = BIT(2)
+};
+
+#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
+
static inline bool ena_xdp_present(struct ena_adapter *adapter)
{
return !!adapter->xdp_bpf_prog;
--
GitLab
From c7062aaee099f2f43d6f07a71744b44b94b94b34 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:09 +0000
Subject: [PATCH 0198/1167] net: ena: Fix rx_copybreak value update
Make the upper bound on rx_copybreak tighter, by
making sure it is smaller than the minimum of mtu and
ENA_PAGE_SIZE. With the current upper bound of mtu,
rx_copybreak can be larger than a page. Such large
rx_copybreak will not bring any performance benefit to
the user and therefore makes no sense.
In addition, the value update was only reflected in
the adapter structure, but not applied for each ring,
causing it to not take effect.
Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: Osama Abboud <osamaabb@amazon.com>
Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 6 +-----
drivers/net/ethernet/amazon/ena/ena_netdev.c | 18 ++++++++++++++++++
drivers/net/ethernet/amazon/ena/ena_netdev.h | 2 ++
3 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 48ae6d810f8f9..8da79eedc057c 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -887,11 +887,7 @@ static int ena_set_tunable(struct net_device *netdev,
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
len = *(u32 *)data;
- if (len > adapter->netdev->mtu) {
- ret = -EINVAL;
- break;
- }
- adapter->rx_copybreak = len;
+ ret = ena_set_rx_copybreak(adapter, len);
break;
default:
ret = -EINVAL;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a67f55e5f7554..80a726932e810 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2814,6 +2814,24 @@ int ena_update_queue_sizes(struct ena_adapter *adapter,
return dev_was_up ? ena_up(adapter) : 0;
}
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak)
+{
+ struct ena_ring *rx_ring;
+ int i;
+
+ if (rx_copybreak > min_t(u16, adapter->netdev->mtu, ENA_PAGE_SIZE))
+ return -EINVAL;
+
+ adapter->rx_copybreak = rx_copybreak;
+
+ for (i = 0; i < adapter->num_io_queues; i++) {
+ rx_ring = &adapter->rx_ring[i];
+ rx_ring->rx_copybreak = rx_copybreak;
+ }
+
+ return 0;
+}
+
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count)
{
struct ena_com_dev *ena_dev = adapter->ena_dev;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 290ae9bf47ee4..f9d862b630fad 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -392,6 +392,8 @@ int ena_update_queue_sizes(struct ena_adapter *adapter,
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count);
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak);
+
int ena_get_sset_count(struct net_device *netdev, int sset);
static inline void ena_reset_device(struct ena_adapter *adapter,
--
GitLab
From e712f3e4920b3a1a5e6b536827d118e14862896c Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:10 +0000
Subject: [PATCH 0199/1167] net: ena: Set default value for RX interrupt
moderation
RX ring can be NULL in XDP use cases where only TX queues
are configured. In this scenario, the RX interrupt moderation
value sent to the device remains in its default value of 0.
In this change, setting the default value of the RX interrupt
moderation to be the same as of the TX.
Fixes: 548c4940b9f1 ("net: ena: Implement XDP_TX action")
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 80a726932e810..99f80c2d560a5 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1823,8 +1823,9 @@ static void ena_adjust_adaptive_rx_intr_moderation(struct ena_napi *ena_napi)
static void ena_unmask_interrupt(struct ena_ring *tx_ring,
struct ena_ring *rx_ring)
{
+ u32 rx_interval = tx_ring->smoothed_interval;
struct ena_eth_io_intr_reg intr_reg;
- u32 rx_interval = 0;
+
/* Rx ring can be NULL when for XDP tx queues which don't have an
* accompanying rx_ring pair.
*/
--
GitLab
From a8ee104f986e720cea52133885cc822d459398c7 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Thu, 29 Dec 2022 07:30:11 +0000
Subject: [PATCH 0200/1167] net: ena: Update NUMA TPH hint register upon NUMA
node update
The device supports a PCIe optimization hint, which indicates on
which NUMA the queue is currently processed. This hint is utilized
by PCIe in order to reduce its access time by accessing the
correct NUMA resources and maintaining cache coherence.
The driver calls the register update for the hint (called TPH -
TLP Processing Hint) during the NAPI loop.
Though the update is expected upon a NUMA change (when a queue
is moved from one NUMA to the other), the current logic performs
a register update when the queue is moved to a different CPU,
but the CPU is not necessarily in a different NUMA.
The changes include:
1. Performing the TPH update only when the queue has switched
a NUMA node.
2. Moving the TPH update call to be triggered only when NAPI was
scheduled from interrupt context, as opposed to a busy-polling loop.
This is due to the fact that during busy-polling, the frequency
of CPU switches for a particular queue is significantly higher,
thus, the likelihood to switch NUMA is much higher. Therefore,
providing the frequent updates to the device upon a NUMA update
are unlikely to be beneficial.
Fixes: 1738cd3ed342 ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)")
Signed-off-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 27 +++++++++++++-------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 6 +++--
2 files changed, 22 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 99f80c2d560a5..e8ad5ea31affe 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -680,6 +680,7 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter,
ring->ena_dev = adapter->ena_dev;
ring->per_napi_packets = 0;
ring->cpu = 0;
+ ring->numa_node = 0;
ring->no_interrupt_event_cnt = 0;
u64_stats_init(&ring->syncp);
}
@@ -783,6 +784,7 @@ static int ena_setup_tx_resources(struct ena_adapter *adapter, int qid)
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
tx_ring->cpu = ena_irq->cpu;
+ tx_ring->numa_node = node;
return 0;
err_push_buf_intermediate_buf:
@@ -915,6 +917,7 @@ static int ena_setup_rx_resources(struct ena_adapter *adapter,
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
rx_ring->cpu = ena_irq->cpu;
+ rx_ring->numa_node = node;
return 0;
}
@@ -1863,20 +1866,27 @@ static void ena_update_ring_numa_node(struct ena_ring *tx_ring,
if (likely(tx_ring->cpu == cpu))
goto out;
+ tx_ring->cpu = cpu;
+ if (rx_ring)
+ rx_ring->cpu = cpu;
+
numa_node = cpu_to_node(cpu);
+
+ if (likely(tx_ring->numa_node == numa_node))
+ goto out;
+
put_cpu();
if (numa_node != NUMA_NO_NODE) {
ena_com_update_numa_node(tx_ring->ena_com_io_cq, numa_node);
- if (rx_ring)
+ tx_ring->numa_node = numa_node;
+ if (rx_ring) {
+ rx_ring->numa_node = numa_node;
ena_com_update_numa_node(rx_ring->ena_com_io_cq,
numa_node);
+ }
}
- tx_ring->cpu = cpu;
- if (rx_ring)
- rx_ring->cpu = cpu;
-
return;
out:
put_cpu();
@@ -1997,11 +2007,10 @@ static int ena_io_poll(struct napi_struct *napi, int budget)
if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
ena_adjust_adaptive_rx_intr_moderation(ena_napi);
+ ena_update_ring_numa_node(tx_ring, rx_ring);
ena_unmask_interrupt(tx_ring, rx_ring);
}
- ena_update_ring_numa_node(tx_ring, rx_ring);
-
ret = rx_work_done;
} else {
ret = budget;
@@ -2386,7 +2395,7 @@ static int ena_create_io_tx_queue(struct ena_adapter *adapter, int qid)
ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
ctx.msix_vector = msix_vector;
ctx.queue_size = tx_ring->ring_size;
- ctx.numa_node = cpu_to_node(tx_ring->cpu);
+ ctx.numa_node = tx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
@@ -2454,7 +2463,7 @@ static int ena_create_io_rx_queue(struct ena_adapter *adapter, int qid)
ctx.mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
ctx.msix_vector = msix_vector;
ctx.queue_size = rx_ring->ring_size;
- ctx.numa_node = cpu_to_node(rx_ring->cpu);
+ ctx.numa_node = rx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index f9d862b630fad..2cb141079474c 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -262,9 +262,11 @@ struct ena_ring {
bool disable_meta_caching;
u16 no_interrupt_event_cnt;
- /* cpu for TPH */
+ /* cpu and NUMA for TPH */
int cpu;
- /* number of tx/rx_buffer_info's entries */
+ int numa_node;
+
+ /* number of tx/rx_buffer_info's entries */
int ring_size;
enum ena_admin_placement_policy_type tx_mem_queue_type;
--
GitLab
From d039535850ee47079d59527e96be18d8e0daa84b Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 29 Dec 2022 10:29:25 +0400
Subject: [PATCH 0201/1167] net: phy: xgmiitorgmii: Fix refcount leak in
xgmiitorgmii_probe
of_phy_find_device() return device node with refcount incremented.
Call put_device() to relese it when not needed anymore.
Fixes: ab4e6ee578e8 ("net: phy: xgmiitorgmii: Check phy_driver ready before accessing")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/phy/xilinx_gmii2rgmii.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 8dcb49ed1f3d9..7fd9fe6a602bc 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -105,6 +105,7 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
if (!priv->phy_dev->drv) {
dev_info(dev, "Attached phy not ready\n");
+ put_device(&priv->phy_dev->mdio.dev);
return -EPROBE_DEFER;
}
--
GitLab
From a23529989a8f56d23680c4f2d14011bc9c9457c9 Mon Sep 17 00:00:00 2001
From: Nikolaus Voss <nikolaus.voss@haag-streit.com>
Date: Tue, 20 Dec 2022 09:17:50 +0100
Subject: [PATCH 0202/1167] crypto: caam - fix CAAM io mem access in blob_gen
IO memory access has to be done with accessors defined in caam/regs.h
as there are little-endian architectures with a big-endian CAAM unit.
Fixes: 6a83830f649a ("crypto: caam - warn if blob_gen key is insecure")
Signed-off-by: Nikolaus Voss <nikolaus.voss@haag-streit.com>
Reviewed-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
drivers/crypto/caam/blob_gen.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/caam/blob_gen.c b/drivers/crypto/caam/blob_gen.c
index 1f65df4898478..f46b161d2cda6 100644
--- a/drivers/crypto/caam/blob_gen.c
+++ b/drivers/crypto/caam/blob_gen.c
@@ -104,7 +104,7 @@ int caam_process_blob(struct caam_blob_priv *priv,
}
ctrlpriv = dev_get_drvdata(jrdev->parent);
- moo = FIELD_GET(CSTA_MOO, ioread32(&ctrlpriv->ctrl->perfmon.status));
+ moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status));
if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED)
dev_warn(jrdev,
"using insecure test key, enable HAB to use unique device key!\n");
--
GitLab
From 736f88689c6912f05d0116917910603a7ba97de7 Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Wed, 21 Dec 2022 15:32:32 +0800
Subject: [PATCH 0203/1167] crypto: arm64/sm4 - fix possible crash with CFI
enabled
The SM4 CCM/GCM assembly functions for encryption and decryption is
called via indirect function calls. Therefore they need to use
SYM_TYPED_FUNC_START instead of SYM_FUNC_START to cause its type hash
to be emitted when the kernel is built with CONFIG_CFI_CLANG=y.
Otherwise, the code crashes with a CFI failure (if the compiler didn't
happen to optimize out the indirect call).
Fixes: 67fa3a7fdf80 ("crypto: arm64/sm4 - add CE implementation for CCM mode")
Fixes: ae1b83c7d572 ("crypto: arm64/sm4 - add CE implementation for GCM mode")
Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
arch/arm64/crypto/sm4-ce-ccm-core.S | 5 +++--
arch/arm64/crypto/sm4-ce-gcm-core.S | 5 +++--
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/crypto/sm4-ce-ccm-core.S b/arch/arm64/crypto/sm4-ce-ccm-core.S
index 028207c4afd0f..fa85856f33cee 100644
--- a/arch/arm64/crypto/sm4-ce-ccm-core.S
+++ b/arch/arm64/crypto/sm4-ce-ccm-core.S
@@ -8,6 +8,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
@@ -104,7 +105,7 @@ SYM_FUNC_START(sm4_ce_ccm_final)
SYM_FUNC_END(sm4_ce_ccm_final)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
@@ -216,7 +217,7 @@ SYM_FUNC_START(sm4_ce_ccm_enc)
SYM_FUNC_END(sm4_ce_ccm_enc)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
diff --git a/arch/arm64/crypto/sm4-ce-gcm-core.S b/arch/arm64/crypto/sm4-ce-gcm-core.S
index 7aa3ec18a2891..347f25d757279 100644
--- a/arch/arm64/crypto/sm4-ce-gcm-core.S
+++ b/arch/arm64/crypto/sm4-ce-gcm-core.S
@@ -9,6 +9,7 @@
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
@@ -370,7 +371,7 @@ SYM_FUNC_START(pmull_ghash_update)
SYM_FUNC_END(pmull_ghash_update)
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
@@ -581,7 +582,7 @@ SYM_FUNC_END(sm4_ce_pmull_gcm_enc)
#define RH3 v20
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
--
GitLab
From ba2dc1cb5491712a6946d0595cf11ba463f50e64 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 29 Dec 2022 17:45:01 +0100
Subject: [PATCH 0204/1167] gpiolib: Fix using uninitialized lookup-flags on
ACPI platforms
Commit 8eb1f71e7acc ("gpiolib: consolidate GPIO lookups") refactors
fwnode_get_named_gpiod() and gpiod_get_index() into a unified
gpiod_find_and_request() helper.
The old functions both initialized their local lookupflags variable to
GPIO_LOOKUP_FLAGS_DEFAULT, but the new code leaves it uninitialized.
This is a problem for at least ACPI platforms, where acpi_find_gpio()
only does a bunch of *lookupflags |= GPIO_* statements and thus relies
on the variable being initialized.
The variable not being initialized leads to:
1. Potentially the wrong flags getting used
2. The check for conflicting lookup flags in gpiod_configure_flags():
"multiple pull-up, pull-down or pull-disable enabled, invalid config"
sometimes triggering, making the GPIO unavailable
Restore the initialization of lookupflags to GPIO_LOOKUP_FLAGS_DEFAULT
to fix this.
Fixes: 8eb1f71e7acc ("gpiolib: consolidate GPIO lookups")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpiolib.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5a66d9616d7cc..939c776b94881 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3905,8 +3905,8 @@ static struct gpio_desc *gpiod_find_and_request(struct device *consumer,
const char *label,
bool platform_lookup_allowed)
{
+ unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
struct gpio_desc *desc = ERR_PTR(-ENOENT);
- unsigned long lookupflags;
int ret;
if (!IS_ERR_OR_NULL(fwnode))
--
GitLab
From 90fee3dd5bfc1b9f4c8c0ba6cd2a35c9d79ca4de Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Sun, 11 Dec 2022 00:05:58 +0200
Subject: [PATCH 0205/1167] gpio: pca953x: avoid to use uninitialized value
pinctrl
There is a variable pinctrl declared without initializer. And then
has the case (switch operation chose the default case) to directly
use this uninitialized value, this is not a safe behavior. So here
initialize the pinctrl as 0 to avoid this issue.
This is reported by Coverity.
Fixes: 13c5d4ce8060 ("gpio: pca953x: Add support for PCAL6534")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-pca953x.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index a59d61cd44b2e..5299e5bb76d6e 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -474,6 +474,9 @@ static u8 pcal6534_recalc_addr(struct pca953x_chip *chip, int reg, int off)
case PCAL6524_DEBOUNCE:
pinctrl = ((reg & PCAL_PINCTRL_MASK) >> 1) + 0x1c;
break;
+ default:
+ pinctrl = 0;
+ break;
}
return pinctrl + addr + (off / BANK_SZ);
--
GitLab
From e84077437902ec99eba0a6b516df772653f142c7 Mon Sep 17 00:00:00 2001
From: Eliav Farber <farbere@amazon.com>
Date: Thu, 20 Oct 2022 12:44:58 +0000
Subject: [PATCH 0206/1167] EDAC/device: Fix period calculation in
edac_device_reset_delay_period()
Fix period calculation in case user sets a value of 1000. The input of
round_jiffies_relative() should be in jiffies and not in milli-seconds.
[ bp: Use the same code pattern as in edac_device_workq_setup() for
clarity. ]
Fixes: c4cf3b454eca ("EDAC: Rework workqueue handling")
Signed-off-by: Eliav Farber <farbere@amazon.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20221020124458.22153-1-farbere@amazon.com
---
drivers/edac/edac_device.c | 17 ++++++++---------
drivers/edac/edac_module.h | 2 +-
2 files changed, 9 insertions(+), 10 deletions(-)
diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 19522c568aa5d..878deb4880cdb 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -394,17 +394,16 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev)
* Then restart the workq on the new delay
*/
void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev,
- unsigned long value)
+ unsigned long msec)
{
- unsigned long jiffs = msecs_to_jiffies(value);
-
- if (value == 1000)
- jiffs = round_jiffies_relative(value);
-
- edac_dev->poll_msec = value;
- edac_dev->delay = jiffs;
+ edac_dev->poll_msec = msec;
+ edac_dev->delay = msecs_to_jiffies(msec);
- edac_mod_work(&edac_dev->work, jiffs);
+ /* See comment in edac_device_workq_setup() above */
+ if (edac_dev->poll_msec == 1000)
+ edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
+ else
+ edac_mod_work(&edac_dev->work, edac_dev->delay);
}
int edac_device_alloc_index(void)
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 763c076d96f21..47593afdc2348 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -53,7 +53,7 @@ bool edac_stop_work(struct delayed_work *work);
bool edac_mod_work(struct delayed_work *work, unsigned long delay);
extern void edac_device_reset_delay_period(struct edac_device_ctl_info
- *edac_dev, unsigned long value);
+ *edac_dev, unsigned long msec);
extern void edac_mc_reset_delay_period(unsigned long value);
/*
--
GitLab
From 2788938b794633fc1865c805764bed196e01f97e Mon Sep 17 00:00:00 2001
From: Cixi Geng <cixi.geng1@unisoc.com>
Date: Thu, 29 Dec 2022 22:55:43 +0800
Subject: [PATCH 0207/1167] gpio: eic-sprd: Make the irqchip immutable
Remove the irq_chip from pmic_eic structure,
use the various calls by defining the statically
irq_chip structure.
Signed-off-by: Cixi Geng <cixi.geng1@unisoc.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-eic-sprd.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index 8d722e026e9c9..84352a6f4973b 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -91,7 +91,6 @@ enum sprd_eic_type {
struct sprd_eic {
struct gpio_chip chip;
- struct irq_chip intc;
void __iomem *base[SPRD_EIC_MAX_BANK];
enum sprd_eic_type type;
spinlock_t lock;
@@ -255,6 +254,8 @@ static void sprd_eic_irq_mask(struct irq_data *data)
default:
dev_err(chip->parent, "Unsupported EIC type.\n");
}
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_eic_irq_unmask(struct irq_data *data)
@@ -263,6 +264,8 @@ static void sprd_eic_irq_unmask(struct irq_data *data)
struct sprd_eic *sprd_eic = gpiochip_get_data(chip);
u32 offset = irqd_to_hwirq(data);
+ gpiochip_enable_irq(chip, offset);
+
switch (sprd_eic->type) {
case SPRD_EIC_DEBOUNCE:
sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IE, 1);
@@ -564,6 +567,15 @@ static void sprd_eic_irq_handler(struct irq_desc *desc)
chained_irq_exit(ic, desc);
}
+static const struct irq_chip sprd_eic_irq = {
+ .name = "sprd-eic",
+ .irq_ack = sprd_eic_irq_ack,
+ .irq_mask = sprd_eic_irq_mask,
+ .irq_unmask = sprd_eic_irq_unmask,
+ .irq_set_type = sprd_eic_irq_set_type,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
static int sprd_eic_probe(struct platform_device *pdev)
{
const struct sprd_eic_variant_data *pdata;
@@ -626,15 +638,8 @@ static int sprd_eic_probe(struct platform_device *pdev)
break;
}
- sprd_eic->intc.name = dev_name(&pdev->dev);
- sprd_eic->intc.irq_ack = sprd_eic_irq_ack;
- sprd_eic->intc.irq_mask = sprd_eic_irq_mask;
- sprd_eic->intc.irq_unmask = sprd_eic_irq_unmask;
- sprd_eic->intc.irq_set_type = sprd_eic_irq_set_type;
- sprd_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &sprd_eic->chip.irq;
- irq->chip = &sprd_eic->intc;
+ gpio_irq_chip_set_chip(irq, &sprd_eic_irq);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_eic_irq_handler;
--
GitLab
From be43eea7de5a3977ac3d13fbfb9e505fab475e97 Mon Sep 17 00:00:00 2001
From: Cixi Geng <cixi.geng1@unisoc.com>
Date: Thu, 29 Dec 2022 22:55:44 +0800
Subject: [PATCH 0208/1167] gpio: pmic-eic-sprd: Make the irqchip immutable
Remove the irq_chip from pmic_eic structure,
use the various calls by defining the statically
irq_chip structure.
Signed-off-by: Cixi Geng <cixi.geng1@unisoc.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-pmic-eic-sprd.c | 29 ++++++++++++++++++-----------
1 file changed, 18 insertions(+), 11 deletions(-)
diff --git a/drivers/gpio/gpio-pmic-eic-sprd.c b/drivers/gpio/gpio-pmic-eic-sprd.c
index e518490c4b681..c3e4d90f6b183 100644
--- a/drivers/gpio/gpio-pmic-eic-sprd.c
+++ b/drivers/gpio/gpio-pmic-eic-sprd.c
@@ -47,7 +47,6 @@ enum {
/**
* struct sprd_pmic_eic - PMIC EIC controller
* @chip: the gpio_chip structure.
- * @intc: the irq_chip structure.
* @map: the regmap from the parent device.
* @offset: the EIC controller's offset address of the PMIC.
* @reg: the array to cache the EIC registers.
@@ -56,7 +55,6 @@ enum {
*/
struct sprd_pmic_eic {
struct gpio_chip chip;
- struct irq_chip intc;
struct regmap *map;
u32 offset;
u8 reg[CACHE_NR_REGS];
@@ -151,15 +149,21 @@ static void sprd_pmic_eic_irq_mask(struct irq_data *data)
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
pmic_eic->reg[REG_IE] = 0;
pmic_eic->reg[REG_TRIG] = 0;
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_pmic_eic_irq_unmask(struct irq_data *data)
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
+
+ gpiochip_enable_irq(chip, offset);
pmic_eic->reg[REG_IE] = 1;
pmic_eic->reg[REG_TRIG] = 1;
@@ -292,6 +296,17 @@ static irqreturn_t sprd_pmic_eic_irq_handler(int irq, void *data)
return IRQ_HANDLED;
}
+static const struct irq_chip pmic_eic_irq_chip = {
+ .name = "sprd-pmic-eic",
+ .irq_mask = sprd_pmic_eic_irq_mask,
+ .irq_unmask = sprd_pmic_eic_irq_unmask,
+ .irq_set_type = sprd_pmic_eic_irq_set_type,
+ .irq_bus_lock = sprd_pmic_eic_bus_lock,
+ .irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static int sprd_pmic_eic_probe(struct platform_device *pdev)
{
struct gpio_irq_chip *irq;
@@ -338,16 +353,8 @@ static int sprd_pmic_eic_probe(struct platform_device *pdev)
pmic_eic->chip.set = sprd_pmic_eic_set;
pmic_eic->chip.get = sprd_pmic_eic_get;
- pmic_eic->intc.name = dev_name(&pdev->dev);
- pmic_eic->intc.irq_mask = sprd_pmic_eic_irq_mask;
- pmic_eic->intc.irq_unmask = sprd_pmic_eic_irq_unmask;
- pmic_eic->intc.irq_set_type = sprd_pmic_eic_irq_set_type;
- pmic_eic->intc.irq_bus_lock = sprd_pmic_eic_bus_lock;
- pmic_eic->intc.irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock;
- pmic_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &pmic_eic->chip.irq;
- irq->chip = &pmic_eic->intc;
+ gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip);
irq->threaded = true;
ret = devm_gpiochip_add_data(&pdev->dev, &pmic_eic->chip, pmic_eic);
--
GitLab
From 9883ddf9d68db5332f08dfc7283db69f69f8d6d2 Mon Sep 17 00:00:00 2001
From: Cixi Geng <cixi.geng1@unisoc.com>
Date: Thu, 29 Dec 2022 22:55:45 +0800
Subject: [PATCH 0209/1167] gpio: sprd: Make the irqchip immutable
Make the struct irq_chip const, flag it as IRQCHIP_IMMUTABLE, add the
new helper functions, and call the appropriate gpiolib functions.
Signed-off-by: Cixi Geng <cixi.geng1@unisoc.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-sprd.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c
index 9bff63990eee4..072b4e6532164 100644
--- a/drivers/gpio/gpio-sprd.c
+++ b/drivers/gpio/gpio-sprd.c
@@ -120,6 +120,7 @@ static void sprd_gpio_irq_mask(struct irq_data *data)
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 0);
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_gpio_irq_ack(struct irq_data *data)
@@ -136,6 +137,7 @@ static void sprd_gpio_irq_unmask(struct irq_data *data)
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 1);
+ gpiochip_enable_irq(chip, offset);
}
static int sprd_gpio_irq_set_type(struct irq_data *data,
@@ -205,13 +207,14 @@ static void sprd_gpio_irq_handler(struct irq_desc *desc)
chained_irq_exit(ic, desc);
}
-static struct irq_chip sprd_gpio_irqchip = {
+static const struct irq_chip sprd_gpio_irqchip = {
.name = "sprd-gpio",
.irq_ack = sprd_gpio_irq_ack,
.irq_mask = sprd_gpio_irq_mask,
.irq_unmask = sprd_gpio_irq_unmask,
.irq_set_type = sprd_gpio_irq_set_type,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
};
static int sprd_gpio_probe(struct platform_device *pdev)
@@ -245,7 +248,7 @@ static int sprd_gpio_probe(struct platform_device *pdev)
sprd_gpio->chip.direction_output = sprd_gpio_direction_output;
irq = &sprd_gpio->chip.irq;
- irq->chip = &sprd_gpio_irqchip;
+ gpio_irq_chip_set_chip(irq, &sprd_gpio_irqchip);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_gpio_irq_handler;
--
GitLab
From b878d3ba9bb41cddb73ba4b56e5552f0a638daca Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 27 Dec 2022 16:10:05 -0800
Subject: [PATCH 0210/1167] thermal: int340x: Add missing attribute for data
rate base
Commit 473be51142ad ("thermal: int340x: processor_thermal: Add RFIM
driver")' added rfi_restriction_data_rate_base string, mmio details and
documentation, but missed adding attribute to sysfs.
Add missing sysfs attribute.
Fixes: 473be51142ad ("thermal: int340x: processor_thermal: Add RFIM driver")
Cc: 5.11+ <stable@vger.kernel.org> # v5.11+
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
.../thermal/intel/int340x_thermal/processor_thermal_rfim.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
index 8c42e76620333..92ed1213fe379 100644
--- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c
@@ -172,6 +172,7 @@ static const struct attribute_group fivr_attribute_group = {
RFIM_SHOW(rfi_restriction_run_busy, 1)
RFIM_SHOW(rfi_restriction_err_code, 1)
RFIM_SHOW(rfi_restriction_data_rate, 1)
+RFIM_SHOW(rfi_restriction_data_rate_base, 1)
RFIM_SHOW(ddr_data_rate_point_0, 1)
RFIM_SHOW(ddr_data_rate_point_1, 1)
RFIM_SHOW(ddr_data_rate_point_2, 1)
@@ -181,11 +182,13 @@ RFIM_SHOW(rfi_disable, 1)
RFIM_STORE(rfi_restriction_run_busy, 1)
RFIM_STORE(rfi_restriction_err_code, 1)
RFIM_STORE(rfi_restriction_data_rate, 1)
+RFIM_STORE(rfi_restriction_data_rate_base, 1)
RFIM_STORE(rfi_disable, 1)
static DEVICE_ATTR_RW(rfi_restriction_run_busy);
static DEVICE_ATTR_RW(rfi_restriction_err_code);
static DEVICE_ATTR_RW(rfi_restriction_data_rate);
+static DEVICE_ATTR_RW(rfi_restriction_data_rate_base);
static DEVICE_ATTR_RO(ddr_data_rate_point_0);
static DEVICE_ATTR_RO(ddr_data_rate_point_1);
static DEVICE_ATTR_RO(ddr_data_rate_point_2);
@@ -248,6 +251,7 @@ static struct attribute *dvfs_attrs[] = {
&dev_attr_rfi_restriction_run_busy.attr,
&dev_attr_rfi_restriction_err_code.attr,
&dev_attr_rfi_restriction_data_rate.attr,
+ &dev_attr_rfi_restriction_data_rate_base.attr,
&dev_attr_ddr_data_rate_point_0.attr,
&dev_attr_ddr_data_rate_point_1.attr,
&dev_attr_ddr_data_rate_point_2.attr,
--
GitLab
From b814eda949c324791580003303aa608761cfde3f Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Sat, 31 Dec 2022 13:40:25 +0800
Subject: [PATCH 0211/1167] soc: imx: imx8mp-blk-ctrl: enable global pixclk
with HDMI_TX_PHY PD
NXP internal information shows that the PHY refclk is gated by the
GLOBAL_TX_PIX_CLK_EN bit, so to allow the PHY PLL to lock without the
LCDIF being already active, tie this bit to the HDMI_TX_PHY power
domain.
Fixes: e3442022f543 ("soc: imx: add i.MX8MP HDMI blk-ctrl")
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
drivers/soc/imx/imx8mp-blk-ctrl.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/soc/imx/imx8mp-blk-ctrl.c b/drivers/soc/imx/imx8mp-blk-ctrl.c
index 0e3b6ba22f943..9852714eb2a41 100644
--- a/drivers/soc/imx/imx8mp-blk-ctrl.c
+++ b/drivers/soc/imx/imx8mp-blk-ctrl.c
@@ -212,7 +212,7 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc,
break;
case IMX8MP_HDMIBLK_PD_LCDIF:
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0,
- BIT(7) | BIT(16) | BIT(17) | BIT(18) |
+ BIT(16) | BIT(17) | BIT(18) |
BIT(19) | BIT(20));
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11));
regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0,
@@ -241,6 +241,7 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc,
regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(1));
break;
case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY:
+ regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7));
regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24));
regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12));
regmap_clear_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3));
@@ -270,7 +271,7 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc,
BIT(4) | BIT(5) | BIT(6));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0,
- BIT(7) | BIT(16) | BIT(17) | BIT(18) |
+ BIT(16) | BIT(17) | BIT(18) |
BIT(19) | BIT(20));
break;
case IMX8MP_HDMIBLK_PD_PAI:
@@ -298,6 +299,7 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc,
case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY:
regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3));
regmap_clear_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12));
+ regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7));
regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24));
break;
case IMX8MP_HDMIBLK_PD_HDCP:
--
GitLab
From 8a1ed98fe0f2e7669f0409de0f46f317b275f8be Mon Sep 17 00:00:00 2001
From: Li Jun <jun.li@nxp.com>
Date: Fri, 30 Sep 2022 22:54:23 +0800
Subject: [PATCH 0212/1167] arm64: dts: imx8mp: correct usb clocks
After commit cf7f3f4fa9e5 ("clk: imx8mp: fix usb_root_clk parent"),
usb_root_clk is no longer for suspend clock so update dts accordingly
to use right bus clock and suspend clock.
Fixes: fb8587a2c165 ("arm64: dtsi: imx8mp: add usb nodes")
Cc: stable@vger.kernel.org # ed1f4ccfe947: clk: imx: imx8mp: add shared clk gate for usb suspend clk
Cc: stable@vger.kernel.org # v5.19+
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Tested-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Li Jun <jun.li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mp.dtsi | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 7a6e6221f4219..6a04d81c69e65 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1297,7 +1297,7 @@ usb3_0: usb@32f10100 {
reg = <0x32f10100 0x8>,
<0x381f0000 0x20>;
clocks = <&clk IMX8MP_CLK_HSIO_ROOT>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "hsio", "suspend";
interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>;
@@ -1310,9 +1310,9 @@ usb3_0: usb@32f10100 {
usb_dwc3_0: usb@38100000 {
compatible = "snps,dwc3";
reg = <0x38100000 0x10000>;
- clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
+ clocks = <&clk IMX8MP_CLK_USB_ROOT>,
<&clk IMX8MP_CLK_USB_CORE_REF>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "bus_early", "ref", "suspend";
interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usb3_phy0>, <&usb3_phy0>;
@@ -1339,7 +1339,7 @@ usb3_1: usb@32f10108 {
reg = <0x32f10108 0x8>,
<0x382f0000 0x20>;
clocks = <&clk IMX8MP_CLK_HSIO_ROOT>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "hsio", "suspend";
interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>;
@@ -1352,9 +1352,9 @@ usb3_1: usb@32f10108 {
usb_dwc3_1: usb@38200000 {
compatible = "snps,dwc3";
reg = <0x38200000 0x10000>;
- clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
+ clocks = <&clk IMX8MP_CLK_USB_ROOT>,
<&clk IMX8MP_CLK_USB_CORE_REF>,
- <&clk IMX8MP_CLK_USB_ROOT>;
+ <&clk IMX8MP_CLK_USB_SUSP>;
clock-names = "bus_early", "ref", "suspend";
interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>;
phys = <&usb3_phy1>, <&usb3_phy1>;
--
GitLab
From cfd04dd1c4b6c33afc2a934b957d71cf8ddd1539 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 21 Nov 2022 13:29:11 -0300
Subject: [PATCH 0213/1167] arm64: dts: imx8mp-phycore-som: Remove invalid PMIC
property
'regulator-compatible' is not a valid property according to
nxp,pca9450-regulator.yaml and causes the following warning:
DTC_CHK arch/arm64/boot/dts/freescale/imx8mp-dhcom-pdk2.dtb
...
pmic@25: regulators:LDO1: Unevaluated properties are not allowed ('regulator-compatible' was unexpected)
Remove the invalid 'regulator-compatible' property.
Cc: Teresa Remmet <t.remmet@phytec.de>
Fixes: 88f7f6bcca37 ("arm64: dts: freescale: Add support for phyBOARD-Pollux-i.MX8MP")
Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Teresa Remmet <t.remmet@phytec.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
index 79b290a002c19..ecc4bce6db97c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi
@@ -99,7 +99,6 @@ pmic: pmic@25 {
regulators {
buck1: BUCK1 {
- regulator-compatible = "BUCK1";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <2187500>;
regulator-boot-on;
@@ -108,7 +107,6 @@ buck1: BUCK1 {
};
buck2: BUCK2 {
- regulator-compatible = "BUCK2";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <2187500>;
regulator-boot-on;
@@ -119,7 +117,6 @@ buck2: BUCK2 {
};
buck4: BUCK4 {
- regulator-compatible = "BUCK4";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
@@ -127,7 +124,6 @@ buck4: BUCK4 {
};
buck5: BUCK5 {
- regulator-compatible = "BUCK5";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
@@ -135,7 +131,6 @@ buck5: BUCK5 {
};
buck6: BUCK6 {
- regulator-compatible = "BUCK6";
regulator-min-microvolt = <600000>;
regulator-max-microvolt = <3400000>;
regulator-boot-on;
@@ -143,7 +138,6 @@ buck6: BUCK6 {
};
ldo1: LDO1 {
- regulator-compatible = "LDO1";
regulator-min-microvolt = <1600000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
@@ -151,7 +145,6 @@ ldo1: LDO1 {
};
ldo2: LDO2 {
- regulator-compatible = "LDO2";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <1150000>;
regulator-boot-on;
@@ -159,7 +152,6 @@ ldo2: LDO2 {
};
ldo3: LDO3 {
- regulator-compatible = "LDO3";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
@@ -167,13 +159,11 @@ ldo3: LDO3 {
};
ldo4: LDO4 {
- regulator-compatible = "LDO4";
regulator-min-microvolt = <800000>;
regulator-max-microvolt = <3300000>;
};
ldo5: LDO5 {
- regulator-compatible = "LDO5";
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <3300000>;
regulator-boot-on;
--
GitLab
From 94e2cf1e0db5b06c7a6ae0878c5cbec925819a8a Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 21 Nov 2022 13:31:23 -0300
Subject: [PATCH 0214/1167] ARM: dts: imx6ul-pico-dwarf: Use 'clock-frequency'
'clock_frequency' is not a valid property.
Use the correct 'clock-frequency' instead.
Fixes: 47246fafef84 ("ARM: dts: imx6ul-pico: Add support for the dwarf baseboard")
Signed-off-by: Fabio Estevam <festevam@denx.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/boot/dts/imx6ul-pico-dwarf.dts | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts
index 162dc259edc8c..5a74c7f68eb62 100644
--- a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts
+++ b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts
@@ -32,7 +32,7 @@ sys_mclk: clock-sys-mclk {
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
--
GitLab
From f4dd0845c4f1f5371f1e06fef0e4a1734a2db964 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 21 Nov 2022 13:31:24 -0300
Subject: [PATCH 0215/1167] ARM: dts: imx7d-pico: Use 'clock-frequency'
'clock_frequency' is not a valid property.
Use the correct 'clock-frequency' instead.
Fixes: 8b646cfb84c3 ("ARM: dts: imx7d-pico: Add support for the dwarf baseboard")
Fixes: 6418fd92417f ("ARM: dts: imx7d-pico: Add support for the nymph baseboard")
Signed-off-by: Fabio Estevam <festevam@denx.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/boot/dts/imx7d-pico-dwarf.dts | 4 ++--
arch/arm/boot/dts/imx7d-pico-nymph.dts | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/arm/boot/dts/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/imx7d-pico-dwarf.dts
index 5162fe227d1ea..fdc10563f1473 100644
--- a/arch/arm/boot/dts/imx7d-pico-dwarf.dts
+++ b/arch/arm/boot/dts/imx7d-pico-dwarf.dts
@@ -32,7 +32,7 @@ sys_mclk: clock-sys-mclk {
};
&i2c1 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
@@ -52,7 +52,7 @@ pressure-sensor@60 {
};
&i2c4 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
diff --git a/arch/arm/boot/dts/imx7d-pico-nymph.dts b/arch/arm/boot/dts/imx7d-pico-nymph.dts
index 104a85254adbb..5afb1674e0125 100644
--- a/arch/arm/boot/dts/imx7d-pico-nymph.dts
+++ b/arch/arm/boot/dts/imx7d-pico-nymph.dts
@@ -43,7 +43,7 @@ sys_mclk: clock-sys-mclk {
};
&i2c1 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
@@ -64,7 +64,7 @@ adc@52 {
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
--
GitLab
From 9dfbc72256b5de608ad10989bcbafdbbd1ac8d4e Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 21 Nov 2022 17:22:59 -0300
Subject: [PATCH 0216/1167] ARM: dts: imx6qdl-gw560x: Remove incorrect
'uart-has-rtscts'
The following build warning is seen when running:
make dtbs_check DT_SCHEMA_FILES=fsl-imx-uart.yaml
arch/arm/boot/dts/imx6dl-gw560x.dtb: serial@2020000: rts-gpios: False schema does not allow [[20, 1, 0]]
From schema: Documentation/devicetree/bindings/serial/fsl-imx-uart.yaml
The imx6qdl-gw560x board does not expose the UART RTS and CTS
as native UART pins, so 'uart-has-rtscts' should not be used.
Using 'uart-has-rtscts' with 'rts-gpios' is an invalid combination
detected by serial.yaml.
Fix the problem by removing the incorrect 'uart-has-rtscts' property.
Fixes: b8a559feffb2 ("ARM: dts: imx: add Gateworks Ventana GW5600 support")
Signed-off-by: Fabio Estevam <festevam@denx.de>
Acked-by: Tim Harvey <tharvey@gateworks.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/boot/dts/imx6qdl-gw560x.dtsi | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi
index 4bc4371e6bae5..4b81a975c979d 100644
--- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi
@@ -632,7 +632,6 @@ &ssi1 {
&uart1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_uart1>;
- uart-has-rtscts;
rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
status = "okay";
};
--
GitLab
From 0d1d030f00f3f3eea04017cbd50ffe44a2842ebc Mon Sep 17 00:00:00 2001
From: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Date: Thu, 1 Dec 2022 13:55:48 +0100
Subject: [PATCH 0217/1167] arm64: dts: verdin-imx8mm: fix dahlia audio
playback
Set optional `simple-audio-card,mclk-fs` parameter to ensure a proper
clock to the wm8904 audio codec. Without this change with an audio
stream rate of 44.1 kHz the playback is completely distorted.
Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini")
Signed-off-by: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
index c2a5c2f7b204b..7c3f5c54f0400 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
@@ -9,6 +9,7 @@ sound_card: sound-card {
simple-audio-card,bitclock-master = <&dailink_master>;
simple-audio-card,format = "i2s";
simple-audio-card,frame-master = <&dailink_master>;
+ simple-audio-card,mclk-fs = <256>;
simple-audio-card,name = "imx8mm-wm8904";
simple-audio-card,routing =
"Headphone Jack", "HPOUTL",
--
GitLab
From f78985f9f58380eec37f82c8a2c765aa7670fc29 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 2 Dec 2022 17:49:18 +0100
Subject: [PATCH 0218/1167] ARM: dts: imx: Fix pca9547 i2c-mux node name
"make dtbs_check":
arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: $nodename:0: 'i2c-switch@70' does not match '^(i2c-?)?mux'
From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
arch/arm/boot/dts/imx53-ppd.dtb: i2c-switch@70: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@0', 'i2c@1', 'i2c@2', 'i2c@3', 'i2c@4', 'i2c@5', 'i2c@6', 'i2c@7' were unexpected)
From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
Fix this by renaming the PCA9547 node to "i2c-mux", to match the I2C bus
multiplexer/switch DT bindings and the Generic Names Recommendation in
the Devicetree Specification.
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/boot/dts/imx53-ppd.dts | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts
index 37d0cffea99c5..70c4a4852256c 100644
--- a/arch/arm/boot/dts/imx53-ppd.dts
+++ b/arch/arm/boot/dts/imx53-ppd.dts
@@ -488,7 +488,7 @@ &i2c1 {
scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
status = "okay";
- i2c-switch@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9547";
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From 42825d1f269355d63554ab3c3762611e4d8053e9 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 2 Dec 2022 17:49:21 +0100
Subject: [PATCH 0219/1167] ARM: dts: vf610: Fix pca9548 i2c-mux node names
"make dtbs_check":
arch/arm/boot/dts/vf610-zii-dev-rev-b.dtb: tca9548@70: $nodename:0: 'tca9548@70' does not match '^(i2c-?)?mux'
From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
arch/arm/boot/dts/vf610-zii-dev-rev-b.dtb: tca9548@70: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@0', 'i2c@1', 'i2c@2', 'i2c@3', 'i2c@4' were unexpected)
From schema: /scratch/geert/linux/linux-renesas/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
...
Fix this by renaming PCA9548 nodes to "i2c-mux", to match the I2C bus
multiplexer/switch DT bindings and the Generic Names Recommendation in
the Devicetree Specification.
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/boot/dts/vf610-zii-dev-rev-b.dts | 2 +-
arch/arm/boot/dts/vf610-zii-dev-rev-c.dts | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
index 42ed4a04a12e2..6280c5e86a124 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts
@@ -345,7 +345,7 @@ gpio6: io-expander@22 {
};
&i2c2 {
- tca9548@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9548";
pinctrl-0 = <&pinctrl_i2c_mux_reset>;
pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
index f892977da9e4e..c00d39562a10b 100644
--- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
+++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts
@@ -340,7 +340,7 @@ eeprom@50 {
};
&i2c2 {
- tca9548@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9548";
pinctrl-0 = <&pinctrl_i2c_mux_reset>;
pinctrl-names = "default";
--
GitLab
From b025b4f5c288e29bbea421613a5b4eacf9261fbb Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 2 Dec 2022 17:49:22 +0100
Subject: [PATCH 0220/1167] arm64: dts: freescale: Fix pca954x i2c-mux node
names
"make dtbs_check":
arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dtb: pca9547@77: $nodename:0: 'pca9547@77' does not match '^(i2c-?)?mux'
From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dtb: pca9547@77: Unevaluated properties are not allowed ('#address-cells', '#size-cells', 'i2c@4' were unexpected)
From schema: Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.yaml
...
Fix this by renaming PCA954x nodes to "i2c-mux", to match the I2C bus
multiplexer/switch DT bindings and the Generic Names Recommendation in
the Devicetree Specification.
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi | 2 +-
arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi | 2 +-
arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi | 2 +-
arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts | 2 +-
arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts | 4 ++--
arch/arm64/boot/dts/freescale/imx8qxp-mek.dts | 2 +-
12 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts
index 5a8d85a7d1612..bbdf989058ff7 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts
@@ -110,7 +110,7 @@ &esdhc1 {
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts
index 9b726c2a48426..dda27ed7aaf2b 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts
@@ -89,7 +89,7 @@ fpga: board-control@2,0 {
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts
index b2fcbba60d3ac..3b0ed9305f2bd 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts
@@ -88,7 +88,7 @@ &duart1 {
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts
index 41d8b15f25a54..aa52ff73ff9e0 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts
@@ -53,7 +53,7 @@ flash@2 {
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
index 1bfbce69cc8b7..ee8e932628d17 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts
@@ -136,7 +136,7 @@ mdio2_aquantia_phy: ethernet-phy@0 {
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
index ef6c8967533ef..d4867d6cf47cd 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts
@@ -245,7 +245,7 @@ rx8035: rtc@32 {
&i2c3 {
status = "okay";
- i2c-switch@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9540";
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi
index f598669e742fc..52c5a43b30a0f 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi
@@ -103,7 +103,7 @@ mdio0_phy15: mdio-phy3@1f {
&i2c0 {
status = "okay";
- pca9547@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
reg = <0x77>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
index 3d9647b3da147..537cecb13dd08 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi
@@ -44,7 +44,7 @@ cpld@3,0 {
&i2c0 {
status = "okay";
- pca9547@75 {
+ i2c-mux@75 {
compatible = "nxp,pca9547";
reg = <0x75>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi
index afb455210bd07..d32a52ab00a42 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi
@@ -54,7 +54,7 @@ &esdhc1 {
&i2c0 {
status = "okay";
- i2c-switch@77 {
+ i2c-mux@77 {
compatible = "nxp,pca9547";
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
index 74c09891600f2..6357078185edd 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts
@@ -214,7 +214,7 @@ &i2c3 {
pinctrl-0 = <&pinctrl_i2c3>;
status = "okay";
- i2cmux@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9540";
reg = <0x70>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts
index 9dda2a1554c32..8614c18b5998c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts
@@ -133,7 +133,7 @@ &i2c1 {
pinctrl-0 = <&pinctrl_i2c1>;
status = "okay";
- i2cmux@70 {
+ i2c-mux@70 {
compatible = "nxp,pca9546";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c1_pca9546>;
@@ -216,7 +216,7 @@ &i2c4 {
pinctrl-0 = <&pinctrl_i2c4>;
status = "okay";
- pca9546: i2cmux@70 {
+ pca9546: i2c-mux@70 {
compatible = "nxp,pca9546";
reg = <0x70>;
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
index 07d8dd8160f68..afa883389456c 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
@@ -61,7 +61,7 @@ &i2c1 {
pinctrl-0 = <&pinctrl_lpi2c1 &pinctrl_ioexp_rst>;
status = "okay";
- i2c-switch@71 {
+ i2c-mux@71 {
compatible = "nxp,pca9646", "nxp,pca9546";
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From 5225ba9db112ec4ed67da5e4d8b72e618573955e Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Fri, 2 Dec 2022 13:10:37 -0600
Subject: [PATCH 0221/1167] arm64: dts: imx8mm-beacon: Fix ecspi2 pinmux
Early hardware did not support hardware handshaking on the UART, but
final production hardware did. When the hardware was updated the chip
select was changed to facilitate hardware handshaking on UART3. Fix the
ecspi2 pin mux to eliminate a pin conflict with UART3 and allow the
EEPROM to operate again.
Fixes: 4ce01ce36d77 ("arm64: dts: imx8mm-beacon: Enable RTS-CTS on UART3")
Signed-off-by: Adam Ford <aford173@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi
index 03266bd90a06b..169f047fbca50 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi
@@ -120,7 +120,7 @@ &csi {
&ecspi2 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_espi2>;
- cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>;
+ cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>;
status = "okay";
eeprom@0 {
@@ -316,7 +316,7 @@ pinctrl_espi2: espi2grp {
MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x82
MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x82
MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x82
- MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x41
+ MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x41
>;
};
--
GitLab
From ef10d57936ead5e817ef7cea6a87531085e77773 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 4 Dec 2022 10:44:17 +0100
Subject: [PATCH 0222/1167] arm64: dts: imx8mq-thor96: fix no-mmc property for
SDHCI
There is no "no-emmc" property, so intention for SD/SDIO only nodes was
to use "no-mmc".
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mq-thor96.dts | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts
index 5d5aa6537225f..6e6182709d220 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts
@@ -339,7 +339,7 @@ &usdhc1 {
bus-width = <4>;
non-removable;
no-sd;
- no-emmc;
+ no-mmc;
status = "okay";
brcmf: wifi@1 {
@@ -359,7 +359,7 @@ &usdhc2 {
cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
bus-width = <4>;
no-sdio;
- no-emmc;
+ no-mmc;
disable-wp;
status = "okay";
};
--
GitLab
From 6c620a30515c494b5eeb3dc0e40d3220ea04c53b Mon Sep 17 00:00:00 2001
From: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Date: Wed, 7 Dec 2022 11:27:49 +0100
Subject: [PATCH 0223/1167] arm64: dts: verdin-imx8mm: fix dev board audio
playback
Set optional `simple-audio-card,mclk-fs` parameter to ensure a proper
clock to the nau8822 audio codec. Without this change with an audio
stream rate of 44.1 kHz the playback is faster.
Set the MCLK at the right frequency, codec can properly use it to
generate 44.1 kHz I2S-FS.
Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini")
Signed-off-by: Emanuele Ghidoli <emanuele.ghidoli@toradex.com>
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi
index 73cc3fafa0180..b2bcd22821702 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi
@@ -11,6 +11,7 @@ sound_card: sound-card {
simple-audio-card,bitclock-master = <&dailink_master>;
simple-audio-card,format = "i2s";
simple-audio-card,frame-master = <&dailink_master>;
+ simple-audio-card,mclk-fs = <256>;
simple-audio-card,name = "imx8mm-nau8822";
simple-audio-card,routing =
"Headphones", "LHP",
--
GitLab
From 62f0147fd4d86620853bee027800f988d3013656 Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Thu, 8 Dec 2022 17:06:58 +0800
Subject: [PATCH 0224/1167] arm64: dts: imx93-11x11-evk: correct clock and
strobe pad setting
For clock and strobe pad of usdhc, need to config as pull down.
Current pad config set these pad as both pull up and pull down,
this is wrong, so fix it here.
Find this issue when enable HS400ES mode on one Micron eMMC chip,
CMD8 always meet CRC error in HS400ES/HS400 mode.
Fixes: e37907bd8294 ("arm64: dts: freescale: add i.MX93 11x11 EVK basic support")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
index 69786c326db00..27f9a9f331346 100644
--- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts
@@ -74,7 +74,7 @@ MX93_PAD_UART1_TXD__LPUART1_TX 0x31e
pinctrl_usdhc1: usdhc1grp {
fsl,pins = <
- MX93_PAD_SD1_CLK__USDHC1_CLK 0x17fe
+ MX93_PAD_SD1_CLK__USDHC1_CLK 0x15fe
MX93_PAD_SD1_CMD__USDHC1_CMD 0x13fe
MX93_PAD_SD1_DATA0__USDHC1_DATA0 0x13fe
MX93_PAD_SD1_DATA1__USDHC1_DATA1 0x13fe
@@ -84,7 +84,7 @@ MX93_PAD_SD1_DATA4__USDHC1_DATA4 0x13fe
MX93_PAD_SD1_DATA5__USDHC1_DATA5 0x13fe
MX93_PAD_SD1_DATA6__USDHC1_DATA6 0x13fe
MX93_PAD_SD1_DATA7__USDHC1_DATA7 0x13fe
- MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x17fe
+ MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x15fe
>;
};
@@ -102,7 +102,7 @@ MX93_PAD_SD2_CD_B__GPIO3_IO00 0x31e
pinctrl_usdhc2: usdhc2grp {
fsl,pins = <
- MX93_PAD_SD2_CLK__USDHC2_CLK 0x17fe
+ MX93_PAD_SD2_CLK__USDHC2_CLK 0x15fe
MX93_PAD_SD2_CMD__USDHC2_CMD 0x13fe
MX93_PAD_SD2_DATA0__USDHC2_DATA0 0x13fe
MX93_PAD_SD2_DATA1__USDHC2_DATA1 0x13fe
--
GitLab
From 87b30c4b0efb6a194a7b8eac2568a3da520d905f Mon Sep 17 00:00:00 2001
From: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Date: Thu, 8 Dec 2022 17:54:03 +0100
Subject: [PATCH 0225/1167] ARM: imx: add missing of_node_put()
Calling of_find_compatible_node() returns a node pointer with refcount
incremented. Use of_node_put() on it when done.
The patch fixes the same problem on different i.MX platforms.
Fixes: 8b88f7ef31dde ("ARM: mx25: Retrieve IIM base from dt")
Fixes: 94b2bec1b0e05 ("ARM: imx27: Retrieve the SYSCTRL base address from devicetree")
Fixes: 3172225d45bd9 ("ARM: imx31: Retrieve the IIM base address from devicetree")
Fixes: f68ea682d1da7 ("ARM: imx35: Retrieve the IIM base address from devicetree")
Fixes: ee18a7154ee08 ("ARM: imx5: retrieve iim base from device tree")
Signed-off-by: Dario Binacchi <dario.binacchi@amarulasolutions.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Reviewed-by: Martin Kaiser <martin@kaiser.cx>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm/mach-imx/cpu-imx25.c | 1 +
arch/arm/mach-imx/cpu-imx27.c | 1 +
arch/arm/mach-imx/cpu-imx31.c | 1 +
arch/arm/mach-imx/cpu-imx35.c | 1 +
arch/arm/mach-imx/cpu-imx5.c | 1 +
5 files changed, 5 insertions(+)
diff --git a/arch/arm/mach-imx/cpu-imx25.c b/arch/arm/mach-imx/cpu-imx25.c
index 3e63445cde062..cc86977d0a340 100644
--- a/arch/arm/mach-imx/cpu-imx25.c
+++ b/arch/arm/mach-imx/cpu-imx25.c
@@ -23,6 +23,7 @@ static int mx25_read_cpu_rev(void)
np = of_find_compatible_node(NULL, NULL, "fsl,imx25-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
rev = readl(iim_base + MXC_IIMSREV);
iounmap(iim_base);
diff --git a/arch/arm/mach-imx/cpu-imx27.c b/arch/arm/mach-imx/cpu-imx27.c
index bf70e13bbe9ee..1d28939083683 100644
--- a/arch/arm/mach-imx/cpu-imx27.c
+++ b/arch/arm/mach-imx/cpu-imx27.c
@@ -28,6 +28,7 @@ static int mx27_read_cpu_rev(void)
np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm");
ccm_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!ccm_base);
/*
* now we have access to the IO registers. As we need
diff --git a/arch/arm/mach-imx/cpu-imx31.c b/arch/arm/mach-imx/cpu-imx31.c
index b9c24b851d1ab..35c544924e509 100644
--- a/arch/arm/mach-imx/cpu-imx31.c
+++ b/arch/arm/mach-imx/cpu-imx31.c
@@ -39,6 +39,7 @@ static int mx31_read_cpu_rev(void)
np = of_find_compatible_node(NULL, NULL, "fsl,imx31-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
/* read SREV register from IIM module */
diff --git a/arch/arm/mach-imx/cpu-imx35.c b/arch/arm/mach-imx/cpu-imx35.c
index 80e7d8ab9f1bb..1fe75b39c2d99 100644
--- a/arch/arm/mach-imx/cpu-imx35.c
+++ b/arch/arm/mach-imx/cpu-imx35.c
@@ -21,6 +21,7 @@ static int mx35_read_cpu_rev(void)
np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim");
iim_base = of_iomap(np, 0);
+ of_node_put(np);
BUG_ON(!iim_base);
rev = imx_readl(iim_base + MXC_IIMSREV);
diff --git a/arch/arm/mach-imx/cpu-imx5.c b/arch/arm/mach-imx/cpu-imx5.c
index ad56263778f93..a67c89bf155dd 100644
--- a/arch/arm/mach-imx/cpu-imx5.c
+++ b/arch/arm/mach-imx/cpu-imx5.c
@@ -28,6 +28,7 @@ static u32 imx5_read_srev_reg(const char *compat)
np = of_find_compatible_node(NULL, NULL, compat);
iim_base = of_iomap(np, 0);
+ of_node_put(np);
WARN_ON(!iim_base);
srev = readl(iim_base + IIM_SREV) & 0xff;
--
GitLab
From c10a5855488bbd9912ddae3ad2d1f2e4b1a3c275 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Fri, 16 Dec 2022 01:05:26 +0100
Subject: [PATCH 0226/1167] arm64: dts: imx8mm: Drop xtal clock specifier from
eDM SBC
The clk_xtal32k have clock-cells = <0>, drop the bogus specifier.
Fixes: 9509593f327a ("arm64: dts: imx8mm: Model PMIC to SNVS RTC clock path on Data Modul i.MX8M Mini eDM SBC")
Signed-off-by: Marek Vasut <marex@denx.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts
index 24f61db33eba2..752f409a30b16 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts
@@ -275,7 +275,7 @@ pmic: pmic@4b {
compatible = "rohm,bd71847";
reg = <0x4b>;
#clock-cells = <0>;
- clocks = <&clk_xtal32k 0>;
+ clocks = <&clk_xtal32k>;
clock-output-names = "clk-32k-out";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_pmic>;
--
GitLab
From 21b84ebeee79d91e405f87f051e9489ef30ecad6 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Fri, 26 Aug 2022 21:13:03 +0200
Subject: [PATCH 0227/1167] soc: imx: imx8mp-blk-ctrl: don't set power device
name
Setting the device name after it has been registered confuses the sysfs
cleanup paths. This has already been fixed for the imx8m-blk-ctrl driver in
b64b46fbaa1d ("Revert "soc: imx: imx8m-blk-ctrl: set power device name""),
but the same problem exists in imx8mp-blk-ctrl.
Fixes: 556f5cf9568a ("soc: imx: add i.MX8MP HSIO blk-ctrl")
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
drivers/soc/imx/imx8mp-blk-ctrl.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/soc/imx/imx8mp-blk-ctrl.c b/drivers/soc/imx/imx8mp-blk-ctrl.c
index 9852714eb2a41..0f13853901dfe 100644
--- a/drivers/soc/imx/imx8mp-blk-ctrl.c
+++ b/drivers/soc/imx/imx8mp-blk-ctrl.c
@@ -592,7 +592,6 @@ static int imx8mp_blk_ctrl_probe(struct platform_device *pdev)
ret = PTR_ERR(domain->power_dev);
goto cleanup_pds;
}
- dev_set_name(domain->power_dev, "%s", data->name);
domain->genpd.name = data->name;
domain->genpd.power_on = imx8mp_blk_ctrl_power_on;
--
GitLab
From b3b75ace2085aca623c57e04ea7218ae690090fb Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 17 Dec 2022 12:08:48 -0600
Subject: [PATCH 0228/1167] arm64: dts: imx8mp: Fix missing GPC Interrupt
The GPC node references an interrupt parent, but it doesn't
state the interrupt itself. According to the TRM, this IRQ
is 87. This also eliminate an error detected from dt_binding_check
Fixes: fc0f05124621 ("arm64: dts: imx8mp: add GPC node with GPU power domains")
Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mp.dtsi | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 6a04d81c69e65..f26b1b26f4a33 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -524,6 +524,7 @@ gpc: gpc@303a0000 {
compatible = "fsl,imx8mp-gpc";
reg = <0x303a0000 0x1000>;
interrupt-parent = <&gic>;
+ interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>;
interrupt-controller;
#interrupt-cells = <3>;
--
GitLab
From 10e2f328bd900787fd2db24e474f87e1d525ccc4 Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sat, 17 Dec 2022 12:08:49 -0600
Subject: [PATCH 0229/1167] arm64: dts: imx8mp: Fix power-domain typo
dt_binding_check detects an issue with the pgc_hsiomix power
domain:
pgc: 'power-domains@17' does not match any of the regexes
This is because 'power-domains' should be 'power-domain'
Fixes: 2ae42e0c0b67 ("arm64: dts: imx8mp: add HSIO power-domains")
Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mp.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index f26b1b26f4a33..03034b439c1f7 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -591,7 +591,7 @@ pgc_mipi_phy2: power-domain@16 {
reg = <IMX8MP_POWER_DOMAIN_MIPI_PHY2>;
};
- pgc_hsiomix: power-domains@17 {
+ pgc_hsiomix: power-domain@17 {
#power-domain-cells = <0>;
reg = <IMX8MP_POWER_DOMAIN_HSIOMIX>;
clocks = <&clk IMX8MP_CLK_HSIO_AXI>,
--
GitLab
From 9a65c759e4666476a6642ad87b4db8a67cb957d0 Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Sun, 1 Jan 2023 12:50:42 +0800
Subject: [PATCH 0230/1167] arm64: dts: imx8mp-evk: pcie0-refclk cosmetic
cleanup
Use the correct indention.
Fixes: d50650500064 ("arm64: dts: imx8mp-evk: Add PCIe support")
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mp-evk.dts | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
index d4c7ca16abd05..f2d93437084be 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts
@@ -36,8 +36,8 @@ memory@40000000 {
pcie0_refclk: pcie0-refclk {
compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <100000000>;
+ #clock-cells = <0>;
+ clock-frequency = <100000000>;
};
reg_can1_stby: regulator-can1-stby {
--
GitLab
From 38b50aa44495d5eb4218f0b82fc2da76505cec53 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 28 Dec 2022 14:56:09 +0200
Subject: [PATCH 0231/1167] RDMA/mlx5: Fix mlx5_ib_get_hw_stats when used for
device
Currently, when mlx5_ib_get_hw_stats() is used for device (port_num = 0),
there is a special handling in order to use the correct counters, but,
port_num is being passed down the stack without any change. Also, some
functions assume that port_num >=1. As a result, the following oops can
occur.
BUG: unable to handle page fault for address: ffff89510294f1a8
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 0 P4D 0
Oops: 0002 [#1] SMP
CPU: 8 PID: 1382 Comm: devlink Tainted: G W 6.1.0-rc4_for_upstream_base_2022_11_10_16_12 #1
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:_raw_spin_lock+0xc/0x20
Call Trace:
<TASK>
mlx5_ib_get_native_port_mdev+0x73/0xe0 [mlx5_ib]
do_get_hw_stats.constprop.0+0x109/0x160 [mlx5_ib]
mlx5_ib_get_hw_stats+0xad/0x180 [mlx5_ib]
ib_setup_device_attrs+0xf0/0x290 [ib_core]
ib_register_device+0x3bb/0x510 [ib_core]
? atomic_notifier_chain_register+0x67/0x80
__mlx5_ib_add+0x2b/0x80 [mlx5_ib]
mlx5r_probe+0xb8/0x150 [mlx5_ib]
? auxiliary_match_id+0x6a/0x90
auxiliary_bus_probe+0x3c/0x70
? driver_sysfs_add+0x6b/0x90
really_probe+0xcd/0x380
__driver_probe_device+0x80/0x170
driver_probe_device+0x1e/0x90
__device_attach_driver+0x7d/0x100
? driver_allows_async_probing+0x60/0x60
? driver_allows_async_probing+0x60/0x60
bus_for_each_drv+0x7b/0xc0
__device_attach+0xbc/0x200
bus_probe_device+0x87/0xa0
device_add+0x404/0x940
? dev_set_name+0x53/0x70
__auxiliary_device_add+0x43/0x60
add_adev+0x99/0xe0 [mlx5_core]
mlx5_attach_device+0xc8/0x120 [mlx5_core]
mlx5_load_one_devl_locked+0xb2/0xe0 [mlx5_core]
devlink_reload+0x133/0x250
devlink_nl_cmd_reload+0x480/0x570
? devlink_nl_pre_doit+0x44/0x2b0
genl_family_rcv_msg_doit.isra.0+0xc2/0x110
genl_rcv_msg+0x180/0x2b0
? devlink_nl_cmd_region_read_dumpit+0x540/0x540
? devlink_reload+0x250/0x250
? devlink_put+0x50/0x50
? genl_family_rcv_msg_doit.isra.0+0x110/0x110
netlink_rcv_skb+0x54/0x100
genl_rcv+0x24/0x40
netlink_unicast+0x1f6/0x2c0
netlink_sendmsg+0x237/0x490
sock_sendmsg+0x33/0x40
__sys_sendto+0x103/0x160
? handle_mm_fault+0x10e/0x290
? do_user_addr_fault+0x1c0/0x5f0
__x64_sys_sendto+0x25/0x30
do_syscall_64+0x3d/0x90
entry_SYSCALL_64_after_hwframe+0x46/0xb0
Fix it by setting port_num to 1 in order to get device status and remove
unused variable.
Fixes: aac4492ef23a ("IB/mlx5: Update counter implementation for dual port RoCE")
Link: https://lore.kernel.org/r/98b82994c3cd3fa593b8a75ed3f3901e208beb0f.1672231736.git.leonro@nvidia.com
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/mlx5/counters.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 945758f395236..3e1272695d993 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -278,7 +278,6 @@ static int do_get_hw_stats(struct ib_device *ibdev,
const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1);
struct mlx5_core_dev *mdev;
int ret, num_counters;
- u32 mdev_port_num;
if (!stats)
return -EINVAL;
@@ -299,8 +298,9 @@ static int do_get_hw_stats(struct ib_device *ibdev,
}
if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
- mdev = mlx5_ib_get_native_port_mdev(dev, port_num,
- &mdev_port_num);
+ if (!port_num)
+ port_num = 1;
+ mdev = mlx5_ib_get_native_port_mdev(dev, port_num, NULL);
if (!mdev) {
/* If port is not affiliated yet, its in down state
* which doesn't have any counters yet, so it would be
--
GitLab
From 8de8482fe5732fbef4f5af82bc0c0362c804cd1f Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Wed, 28 Dec 2022 14:56:10 +0200
Subject: [PATCH 0232/1167] RDMA/mlx5: Fix validation of max_rd_atomic caps for
DC
Currently, when modifying DC, we validate max_rd_atomic user attribute
against the RC cap, validate against DC. RC and DC QP types have different
device limitations.
This can cause userspace created DC QPs to malfunction.
Fixes: c32a4f296e1d ("IB/mlx5: Add support for DC Initiator QP")
Link: https://lore.kernel.org/r/0c5aee72cea188c3bb770f4207cce7abc9b6fc74.1672231736.git.leonro@nvidia.com
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/mlx5/qp.c | 49 +++++++++++++++++++++++----------
1 file changed, 35 insertions(+), 14 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 40d9410ec3033..cf953d23d18da 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4502,6 +4502,40 @@ static bool mlx5_ib_modify_qp_allowed(struct mlx5_ib_dev *dev,
return false;
}
+static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr,
+ int attr_mask, enum ib_qp_type qp_type)
+{
+ int log_max_ra_res;
+ int log_max_ra_req;
+
+ if (qp_type == MLX5_IB_QPT_DCI) {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_dc);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_dc);
+ } else {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_qp);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_qp);
+ }
+
+ if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
+ attr->max_rd_atomic > log_max_ra_res) {
+ mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
+ attr->max_rd_atomic);
+ return false;
+ }
+
+ if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
+ attr->max_dest_rd_atomic > log_max_ra_req) {
+ mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
+ attr->max_dest_rd_atomic);
+ return false;
+ }
+ return true;
+}
+
int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
int attr_mask, struct ib_udata *udata)
{
@@ -4589,21 +4623,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
goto out;
}
- if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
- attr->max_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) {
- mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
- attr->max_rd_atomic);
- goto out;
- }
-
- if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
- attr->max_dest_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) {
- mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
- attr->max_dest_rd_atomic);
+ if (!validate_rd_atomic(dev, attr, attr_mask, qp_type))
goto out;
- }
if (cur_state == new_state && cur_state == IB_QPS_RESET) {
err = 0;
--
GitLab
From 9807ae69746196ee4bbffe7d22d22ab2b61c6ed0 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Thu, 29 Dec 2022 17:33:32 +0100
Subject: [PATCH 0233/1167] net: dsa: qca8k: fix wrong length value for mgmt
eth packet
The assumption that Documentation was right about how this value work was
wrong. It was discovered that the length value of the mgmt header is in
step of word size.
As an example to process 4 byte of data the correct length to set is 2.
To process 8 byte 4, 12 byte 6, 16 byte 8...
Odd values will always return the next size on the ack packet.
(length of 3 (6 byte) will always return 8 bytes of data)
This means that a value of 15 (0xf) actually means reading/writing 32 bytes
of data instead of 16 bytes. This behaviour is totally absent and not
documented in the switch Documentation.
In fact from Documentation the max value that mgmt eth can process is
16 byte of data while in reality it can process 32 bytes at once.
To handle this we always round up the length after deviding it for word
size. We check if the result is odd and we round another time to align
to what the switch will provide in the ack packet.
The workaround for the length limit of 15 is still needed as the length
reg max value is 0xf(15)
Reported-by: Ronald Wahl <ronald.wahl@raritan.com>
Tested-by: Ronald Wahl <ronald.wahl@raritan.com>
Fixes: 90386223f44e ("net: dsa: qca8k: add support for larger read/write size with mgmt Ethernet")
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Cc: stable@vger.kernel.org # v5.18+
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/dsa/qca/qca8k-8xxx.c | 45 +++++++++++++++++++++++++-------
1 file changed, 35 insertions(+), 10 deletions(-)
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index c5c3b4e92f28b..46151320b2a8f 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -146,7 +146,16 @@ static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb)
command = get_unaligned_le32(&mgmt_ethhdr->command);
cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command);
+
len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command);
+ /* Special case for len of 15 as this is the max value for len and needs to
+ * be increased before converting it from word to dword.
+ */
+ if (len == 15)
+ len++;
+
+ /* We can ignore odd value, we always round up them in the alloc function. */
+ len *= sizeof(u16);
/* Make sure the seq match the requested packet */
if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq)
@@ -193,17 +202,33 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 *
if (!skb)
return NULL;
- /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte
- * Actually for some reason the steps are:
- * 0: nothing
- * 1-4: first 4 byte
- * 5-6: first 12 byte
- * 7-15: all 16 byte
+ /* Hdr mgmt length value is in step of word size.
+ * As an example to process 4 byte of data the correct length to set is 2.
+ * To process 8 byte 4, 12 byte 6, 16 byte 8...
+ *
+ * Odd values will always return the next size on the ack packet.
+ * (length of 3 (6 byte) will always return 8 bytes of data)
+ *
+ * This means that a value of 15 (0xf) actually means reading/writing 32 bytes
+ * of data.
+ *
+ * To correctly calculate the length we devide the requested len by word and
+ * round up.
+ * On the ack function we can skip the odd check as we already handle the
+ * case here.
+ */
+ real_len = DIV_ROUND_UP(len, sizeof(u16));
+
+ /* We check if the result len is odd and we round up another time to
+ * the next size. (length of 3 will be increased to 4 as switch will always
+ * return 8 bytes)
*/
- if (len == 16)
- real_len = 15;
- else
- real_len = len;
+ if (real_len % sizeof(u16) != 0)
+ real_len++;
+
+ /* Max reg value is 0xf(15) but switch will always return the next size (32 byte) */
+ if (real_len == 16)
+ real_len--;
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->len);
--
GitLab
From d9dba91be71f03cc75bcf39fc0d5d99ff33f1ae0 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Thu, 29 Dec 2022 17:33:33 +0100
Subject: [PATCH 0234/1167] net: dsa: tag_qca: fix wrong MGMT_DATA2 size
It was discovered that MGMT_DATA2 can contain up to 28 bytes of data
instead of the 12 bytes written in the Documentation by accounting the
limit of 16 bytes declared in Documentation subtracting the first 4 byte
in the packet header.
Update the define with the real world value.
Tested-by: Ronald Wahl <ronald.wahl@raritan.com>
Fixes: c2ee8181fddb ("net: dsa: tag_qca: add define for handling mgmt Ethernet packet")
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Cc: stable@vger.kernel.org # v5.18+
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/dsa/tag_qca.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h
index b1b5720d89a59..ee657452f122a 100644
--- a/include/linux/dsa/tag_qca.h
+++ b/include/linux/dsa/tag_qca.h
@@ -45,8 +45,8 @@ struct sk_buff;
QCA_HDR_MGMT_COMMAND_LEN + \
QCA_HDR_MGMT_DATA1_LEN)
-#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */
-#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */
+#define QCA_HDR_MGMT_DATA2_LEN 28 /* Other 28 byte for the mdio data */
+#define QCA_HDR_MGMT_PADDING_LEN 18 /* Padding to reach the min Ethernet packet */
#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \
QCA_HDR_LEN + \
--
GitLab
From 03cb9e6d0b32b768e3d9d473c5c4ca1100877664 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Thu, 29 Dec 2022 17:33:34 +0100
Subject: [PATCH 0235/1167] Revert "net: dsa: qca8k: cache lo and hi for mdio
write"
This reverts commit 2481d206fae7884cd07014fd1318e63af35e99eb.
The Documentation is very confusing about the topic.
The cache logic for hi and lo is wrong and actually miss some regs to be
actually written.
What the Documentation actually intended was that it's possible to skip
writing hi OR lo if half of the reg is not needed to be written or read.
Revert the change in favor of a better and correct implementation.
Reported-by: Ronald Wahl <ronald.wahl@raritan.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Cc: stable@vger.kernel.org # v5.18+
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/dsa/qca/qca8k-8xxx.c | 61 +++++++-------------------------
drivers/net/dsa/qca/qca8k.h | 5 ---
2 files changed, 12 insertions(+), 54 deletions(-)
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 46151320b2a8f..fbcd5c2b13aeb 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -36,44 +36,6 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page)
*page = regaddr & 0x3ff;
}
-static int
-qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo)
-{
- u16 *cached_lo = &priv->mdio_cache.lo;
- struct mii_bus *bus = priv->bus;
- int ret;
-
- if (lo == *cached_lo)
- return 0;
-
- ret = bus->write(bus, phy_id, regnum, lo);
- if (ret < 0)
- dev_err_ratelimited(&bus->dev,
- "failed to write qca8k 32bit lo register\n");
-
- *cached_lo = lo;
- return 0;
-}
-
-static int
-qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi)
-{
- u16 *cached_hi = &priv->mdio_cache.hi;
- struct mii_bus *bus = priv->bus;
- int ret;
-
- if (hi == *cached_hi)
- return 0;
-
- ret = bus->write(bus, phy_id, regnum, hi);
- if (ret < 0)
- dev_err_ratelimited(&bus->dev,
- "failed to write qca8k 32bit hi register\n");
-
- *cached_hi = hi;
- return 0;
-}
-
static int
qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
@@ -97,7 +59,7 @@ qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
}
static void
-qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
+qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
u16 lo, hi;
int ret;
@@ -105,9 +67,12 @@ qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
lo = val & 0xffff;
hi = (u16)(val >> 16);
- ret = qca8k_set_lo(priv, phy_id, regnum, lo);
+ ret = bus->write(bus, phy_id, regnum, lo);
if (ret >= 0)
- ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi);
+ ret = bus->write(bus, phy_id, regnum + 1, hi);
+ if (ret < 0)
+ dev_err_ratelimited(&bus->dev,
+ "failed to write qca8k 32bit register\n");
}
static int
@@ -442,7 +407,7 @@ qca8k_regmap_write(void *ctx, uint32_t reg, uint32_t val)
if (ret < 0)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
@@ -475,7 +440,7 @@ qca8k_regmap_update_bits(void *ctx, uint32_t reg, uint32_t mask, uint32_t write_
val &= ~mask;
val |= write_val;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
@@ -750,14 +715,14 @@ qca8k_mdio_write(struct qca8k_priv *priv, int phy, int regnum, u16 data)
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
mutex_unlock(&bus->mdio_lock);
@@ -787,7 +752,7 @@ qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum)
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
@@ -798,7 +763,7 @@ qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum)
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
mutex_unlock(&bus->mdio_lock);
@@ -1968,8 +1933,6 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
}
priv->mdio_cache.page = 0xffff;
- priv->mdio_cache.lo = 0xffff;
- priv->mdio_cache.hi = 0xffff;
/* Check the detected switch id */
ret = qca8k_read_switch_id(priv);
diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h
index 0b7a5cb123216..03514f7a20bec 100644
--- a/drivers/net/dsa/qca/qca8k.h
+++ b/drivers/net/dsa/qca/qca8k.h
@@ -375,11 +375,6 @@ struct qca8k_mdio_cache {
* mdio writes
*/
u16 page;
-/* lo and hi can also be cached and from Documentation we can skip one
- * extra mdio write if lo or hi is didn't change.
- */
- u16 lo;
- u16 hi;
};
struct qca8k_pcs {
--
GitLab
From cfbd6de588ef659c198083205dc954a6d3ed2aec Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Thu, 29 Dec 2022 17:33:35 +0100
Subject: [PATCH 0236/1167] net: dsa: qca8k: introduce single mii read/write
lo/hi
It may be useful to read/write just the lo or hi half of a reg.
This is especially useful for phy poll with the use of mdio master.
The mdio master reg is composed by the first 16 bit related to setup and
the other half with the returned data or data to write.
Refactor the mii function to permit single mii read/write of lo or hi
half of the reg.
Tested-by: Ronald Wahl <ronald.wahl@raritan.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/dsa/qca/qca8k-8xxx.c | 106 ++++++++++++++++++++++++-------
1 file changed, 84 insertions(+), 22 deletions(-)
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index fbcd5c2b13aeb..92c4bfef7c974 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -37,42 +37,104 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page)
}
static int
-qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+qca8k_mii_write_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
int ret;
+ u16 lo;
- ret = bus->read(bus, phy_id, regnum);
- if (ret >= 0) {
- *val = ret;
- ret = bus->read(bus, phy_id, regnum + 1);
- *val |= ret << 16;
- }
+ lo = val & 0xffff;
+ ret = bus->write(bus, phy_id, regnum, lo);
+ if (ret < 0)
+ dev_err_ratelimited(&bus->dev,
+ "failed to write qca8k 32bit lo register\n");
- if (ret < 0) {
+ return ret;
+}
+
+static int
+qca8k_mii_write_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+{
+ int ret;
+ u16 hi;
+
+ hi = (u16)(val >> 16);
+ ret = bus->write(bus, phy_id, regnum, hi);
+ if (ret < 0)
dev_err_ratelimited(&bus->dev,
- "failed to read qca8k 32bit register\n");
- *val = 0;
- return ret;
- }
+ "failed to write qca8k 32bit hi register\n");
+
+ return ret;
+}
+
+static int
+qca8k_mii_read_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+ int ret;
+
+ ret = bus->read(bus, phy_id, regnum);
+ if (ret < 0)
+ goto err;
+ *val = ret & 0xffff;
return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit lo register\n");
+ *val = 0;
+
+ return ret;
}
-static void
-qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+static int
+qca8k_mii_read_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
- u16 lo, hi;
int ret;
- lo = val & 0xffff;
- hi = (u16)(val >> 16);
+ ret = bus->read(bus, phy_id, regnum);
+ if (ret < 0)
+ goto err;
- ret = bus->write(bus, phy_id, regnum, lo);
- if (ret >= 0)
- ret = bus->write(bus, phy_id, regnum + 1, hi);
+ *val = ret << 16;
+ return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit hi register\n");
+ *val = 0;
+
+ return ret;
+}
+
+static int
+qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+ u32 hi, lo;
+ int ret;
+
+ *val = 0;
+
+ ret = qca8k_mii_read_lo(bus, phy_id, regnum, &lo);
if (ret < 0)
- dev_err_ratelimited(&bus->dev,
- "failed to write qca8k 32bit register\n");
+ goto err;
+
+ ret = qca8k_mii_read_hi(bus, phy_id, regnum + 1, &hi);
+ if (ret < 0)
+ goto err;
+
+ *val = lo | hi;
+
+err:
+ return ret;
+}
+
+static void
+qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+{
+ if (qca8k_mii_write_lo(bus, phy_id, regnum, val) < 0)
+ return;
+
+ qca8k_mii_write_hi(bus, phy_id, regnum + 1, val);
}
static int
--
GitLab
From a4165830ca237f2b3318faf62562bce8ce12a389 Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Thu, 29 Dec 2022 17:33:36 +0100
Subject: [PATCH 0237/1167] net: dsa: qca8k: improve mdio master read/write by
using single lo/hi
Improve mdio master read/write by using singe mii read/write lo/hi.
In a read and write we need to poll the mdio master regs in a busy loop
to check for a specific bit present in the upper half of the reg. We can
ignore the other half since it won't contain useful data. This will save
an additional useless read for each read and write operation.
In a read operation the returned data is present in the mdio master reg
lower half. We can ignore the other half since it won't contain useful
data. This will save an additional useless read for each read operation.
In a read operation it's needed to just set the hi half of the mdio
master reg as the lo half will be replaced by the result. This will save
an additional useless write for each read operation.
Tested-by: Ronald Wahl <ronald.wahl@raritan.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/dsa/qca/qca8k-8xxx.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 92c4bfef7c974..2f224b166bbb3 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -740,9 +740,9 @@ qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask)
qca8k_split_addr(reg, &r1, &r2, &page);
- ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0,
+ ret = read_poll_timeout(qca8k_mii_read_hi, ret1, !(val & mask), 0,
QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
- bus, 0x10 | r2, r1, &val);
+ bus, 0x10 | r2, r1 + 1, &val);
/* Check if qca8k_read has failed for a different reason
* before returnting -ETIMEDOUT
@@ -784,7 +784,7 @@ qca8k_mdio_write(struct qca8k_priv *priv, int phy, int regnum, u16 data)
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
@@ -814,18 +814,18 @@ qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum)
if (ret)
goto exit;
- qca8k_mii_write32(bus, 0x10 | r2, r1, val);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
if (ret)
goto exit;
- ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+ ret = qca8k_mii_read_lo(bus, 0x10 | r2, r1, &val);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
--
GitLab
From 6d4cfcf97986cc67635630a2bc1f8d5c92ecdbba Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@seco.com>
Date: Thu, 29 Dec 2022 15:21:20 -0500
Subject: [PATCH 0238/1167] net: phy: Update documentation for
get_rate_matching
Now that phylink no longer calls phy_get_rate_matching with
PHY_INTERFACE_MODE_NA, phys no longer need to support it. Remove the
documentation mandating support.
Fixes: 7642cc28fd37 ("net: phylink: fix PHY validation with rate adaption")
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/linux/phy.h | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 71eeb4e3b1fde..6378c997ded56 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -826,10 +826,7 @@ struct phy_driver {
* whether to advertise lower-speed modes for that interface. It is
* assumed that if a rate matching mode is supported on an interface,
* then that interface's rate can be adapted to all slower link speeds
- * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy
- * supports any kind of rate matching for any interface, then it must
- * return that rate matching mode (preferring %RATE_MATCH_PAUSE to
- * %RATE_MATCH_CRS). If the interface is not supported, this should
+ * supported by the phy. If the interface is not supported, this should
* return %RATE_MATCH_NONE.
*/
int (*get_rate_matching)(struct phy_device *phydev,
--
GitLab
From 9c4d7f45d60745a1cea0e841fa5e3444c398d2f1 Mon Sep 17 00:00:00 2001
From: Po-Hsu Lin <po-hsu.lin@canonical.com>
Date: Fri, 30 Dec 2022 17:18:28 +0800
Subject: [PATCH 0239/1167] selftests: net: fix cleanup_v6() for
arp_ndisc_evict_nocarrier
The cleanup_v6() will cause the arp_ndisc_evict_nocarrier script exit
with 255 (No such file or directory), even the tests are good:
# selftests: net: arp_ndisc_evict_nocarrier.sh
# run arp_evict_nocarrier=1 test
# RTNETLINK answers: File exists
# ok
# run arp_evict_nocarrier=0 test
# RTNETLINK answers: File exists
# ok
# run all.arp_evict_nocarrier=0 test
# RTNETLINK answers: File exists
# ok
# run ndisc_evict_nocarrier=1 test
# ok
# run ndisc_evict_nocarrier=0 test
# ok
# run all.ndisc_evict_nocarrier=0 test
# ok
not ok 1 selftests: net: arp_ndisc_evict_nocarrier.sh # exit=255
This is because it's trying to modify the parameter for ipv4 instead.
Also, tests for ipv6 (run_ndisc_evict_nocarrier_enabled() and
run_ndisc_evict_nocarrier_disabled() are working on veth1, reflect
this fact in cleanup_v6().
Fixes: f86ca07eb531 ("selftests: net: add arp_ndisc_evict_nocarrier")
Signed-off-by: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
index b5af08af85595..b4ec1eeee6c90 100755
--- a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
+++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
@@ -24,8 +24,8 @@ cleanup_v6()
ip netns del me
ip netns del peer
- sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
- sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.veth1.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
}
create_ns()
--
GitLab
From 1856628baa17032531916984808d1bdfd62700d4 Mon Sep 17 00:00:00 2001
From: Po-Hsu Lin <po-hsu.lin@canonical.com>
Date: Fri, 30 Dec 2022 17:18:29 +0800
Subject: [PATCH 0240/1167] selftests: net: return non-zero for failures
reported in arp_ndisc_evict_nocarrier
Return non-zero return value if there is any failure reported in this
script during the test. Otherwise it can only reflect the status of
the last command.
Fixes: f86ca07eb531 ("selftests: net: add arp_ndisc_evict_nocarrier")
Signed-off-by: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../selftests/net/arp_ndisc_evict_nocarrier.sh | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
index b4ec1eeee6c90..4a110bb01e53e 100755
--- a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
+++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
@@ -18,6 +18,7 @@ readonly V4_ADDR1=10.0.10.2
readonly V6_ADDR0=2001:db8:91::1
readonly V6_ADDR1=2001:db8:91::2
nsid=100
+ret=0
cleanup_v6()
{
@@ -61,7 +62,7 @@ setup_v6() {
if [ $? -ne 0 ]; then
cleanup_v6
echo "failed"
- exit
+ exit 1
fi
# Set veth2 down, which will put veth1 in NOCARRIER state
@@ -88,7 +89,7 @@ setup_v4() {
if [ $? -ne 0 ]; then
cleanup_v4
echo "failed"
- exit
+ exit 1
fi
# Set veth1 down, which will put veth0 in NOCARRIER state
@@ -115,6 +116,7 @@ run_arp_evict_nocarrier_enabled() {
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
@@ -134,6 +136,7 @@ run_arp_evict_nocarrier_disabled() {
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v4
@@ -164,6 +167,7 @@ run_ndisc_evict_nocarrier_enabled() {
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
@@ -182,6 +186,7 @@ run_ndisc_evict_nocarrier_disabled() {
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
@@ -198,6 +203,7 @@ run_ndisc_evict_nocarrier_disabled_all() {
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
@@ -218,3 +224,4 @@ if [ "$(id -u)" -ne 0 ];then
fi
run_all_tests
+exit $ret
--
GitLab
From d9d71a89f28d27ac772c429b37d52668d011df7a Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Fri, 30 Dec 2022 16:33:04 -0600
Subject: [PATCH 0241/1167] net: ipa: use proper endpoint mask for suspend
It is now possible for a system to have more than 32 endpoints. As
a result, registers related to endpoint suspend are parameterized,
with 32 endpoints represented in one more registers.
In ipa_interrupt_suspend_control(), the IPA_SUSPEND_EN register
offset is determined properly, but the bit mask used still assumes
the number of enpoints won't exceed 32. This is a bug. Fix it.
Fixes: f298ba785e2d ("net: ipa: add a parameter to suspend registers")
Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ipa/ipa_interrupt.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c
index a49f66efacb87..d458a35839cce 100644
--- a/drivers/net/ipa/ipa_interrupt.c
+++ b/drivers/net/ipa/ipa_interrupt.c
@@ -132,10 +132,10 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt,
u32 endpoint_id, bool enable)
{
struct ipa *ipa = interrupt->ipa;
+ u32 mask = BIT(endpoint_id % 32);
u32 unit = endpoint_id / 32;
const struct ipa_reg *reg;
u32 offset;
- u32 mask;
u32 val;
WARN_ON(!test_bit(endpoint_id, ipa->available));
@@ -148,7 +148,6 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt,
offset = ipa_reg_n_offset(reg, unit);
val = ioread32(ipa->reg_virt + offset);
- mask = BIT(endpoint_id);
if (enable)
val |= mask;
else
--
GitLab
From a3542b0ccd58f9fd42f34afa9daea435279a7c1c Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel@sholland.org>
Date: Sat, 31 Dec 2022 16:05:46 -0600
Subject: [PATCH 0242/1167] dt-bindings: net: sun8i-emac: Add phy-supply
property
This property has always been supported by the Linux driver; see
commit 9f93ac8d4085 ("net-next: stmmac: Add dwmac-sun8i"). In fact, the
original driver submission includes the phy-supply code but no mention
of it in the binding, so the omission appears to be accidental. In
addition, the property is documented in the binding for the previous
hardware generation, allwinner,sun7i-a20-gmac.
Document phy-supply in the binding to fix devicetree validation for the
25+ boards that already use this property.
Fixes: 0441bde003be ("dt-bindings: net-next: Add DT bindings documentation for Allwinner dwmac-sun8i")
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Samuel Holland <samuel@sholland.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml | 3 +++
1 file changed, 3 insertions(+)
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
index 1432fda3b603f..47bc2057e6292 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
+++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
@@ -40,6 +40,9 @@ properties:
clock-names:
const: stmmaceth
+ phy-supply:
+ description: PHY regulator
+
syscon:
$ref: /schemas/types.yaml#/definitions/phandle
description:
--
GitLab
From 91e2286160edd29d3fea8efff2dcda7df321878d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Grzelak?= <mig@semihalf.com>
Date: Thu, 29 Dec 2022 15:22:19 +0100
Subject: [PATCH 0243/1167] dt-bindings: net: marvell,orion-mdio: Fix examples
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
As stated in marvell-orion-mdio.txt deleted in commit 0781434af811f
("dt-bindings: net: orion-mdio: Convert to JSON schema") if
'interrupts' property is present, width of 'reg' should be 0x84.
Otherwise, width of 'reg' should be 0x4. Fix 'examples:' and add
constraints checking whether 'interrupts' property is present
and validate it against fixed values in reg.
Signed-off-by: Michał Grzelak <mig@semihalf.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../bindings/net/marvell,orion-mdio.yaml | 30 ++++++++++++++++---
1 file changed, 26 insertions(+), 4 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
index d2906b4a0f595..e35da8b01dc25 100644
--- a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml
@@ -16,9 +16,6 @@ description: |
8k has a second unit which provides an interface with the xMDIO bus. This
driver handles these interfaces.
-allOf:
- - $ref: "mdio.yaml#"
-
properties:
compatible:
enum:
@@ -39,13 +36,38 @@ required:
- compatible
- reg
+allOf:
+ - $ref: mdio.yaml#
+
+ - if:
+ required:
+ - interrupts
+
+ then:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - const: 0x84
+
+ else:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - enum:
+ - 0x4
+ - 0x10
+
unevaluatedProperties: false
examples:
- |
mdio@d0072004 {
compatible = "marvell,orion-mdio";
- reg = <0xd0072004 0x4>;
+ reg = <0xd0072004 0x84>;
#address-cells = <1>;
#size-cells = <0>;
interrupts = <30>;
--
GitLab
From 000bca8d706d1bf7cca01af75787247c5a2fdedf Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Fri, 30 Dec 2022 22:15:45 -0800
Subject: [PATCH 0244/1167] ASoC: qcom: lpass-cpu: Fix fallback SD line index
handling
These indices should reference the ID placed within the dai_driver
array, not the indices of the array itself.
This fixes commit 4ff028f6c108 ("ASoC: qcom: lpass-cpu: Make I2S SD
lines configurable"), which among others, broke IPQ8064 audio
(sound/soc/qcom/lpass-ipq806x.c) because it uses ID 4 but we'd stop
initializing the mi2s_playback_sd_mode and mi2s_capture_sd_mode arrays
at ID 0.
Fixes: 4ff028f6c108 ("ASoC: qcom: lpass-cpu: Make I2S SD lines configurable")
Cc: <stable@vger.kernel.org>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Reviewed-by: Stephan Gerhold <stephan@gerhold.net>
Link: https://lore.kernel.org/r/20221231061545.2110253-1-computersforpeace@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/qcom/lpass-cpu.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 54353842dc07f..dbdaaa85ce481 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -1037,10 +1037,11 @@ static void of_lpass_cpu_parse_dai_data(struct device *dev,
struct lpass_data *data)
{
struct device_node *node;
- int ret, id;
+ int ret, i, id;
/* Allow all channels by default for backwards compatibility */
- for (id = 0; id < data->variant->num_dai; id++) {
+ for (i = 0; i < data->variant->num_dai; i++) {
+ id = data->variant->dai_driver[i].id;
data->mi2s_playback_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
data->mi2s_capture_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
}
--
GitLab
From 029085b8949f5d269ae2bbd14915407dd0c7f902 Mon Sep 17 00:00:00 2001
From: Chengen Du <chengen.du@canonical.com>
Date: Fri, 30 Dec 2022 11:04:32 +0800
Subject: [PATCH 0245/1167] NFS: Judge the file access cache's timestamp in rcu
path
If the user's login time is newer than the cache's timestamp,
we expect the cache may be stale and need to clear.
The stale cache will remain in the list's tail if no other
users operate on that inode.
Once the user accesses the inode, the stale cache will be
returned in rcu path.
Signed-off-by: Chengen Du <chengen.du@canonical.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
fs/nfs/dir.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ea1ceffa1d3aa..d490d64a9ebd0 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -3023,6 +3023,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
* but do it without locking.
*/
struct nfs_inode *nfsi = NFS_I(inode);
+ u64 login_time = nfs_access_login_time(current, cred);
struct nfs_access_entry *cache;
int err = -ECHILD;
struct list_head *lh;
@@ -3037,6 +3038,8 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
cache = NULL;
if (cache == NULL)
goto out;
+ if ((s64)(login_time - cache->timestamp) > 0)
+ goto out;
if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
goto out;
*mask = cache->mask;
--
GitLab
From 5e9a7b9c2ea18551759833146a181b14835bfe39 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sun, 1 Jan 2023 20:17:23 -0500
Subject: [PATCH 0246/1167] NFS: Fix up a sparse warning
sparse is warning about an incorrect RCU dereference.
fs/nfs/dir.c:2965:56: warning: incorrect type in argument 1 (different address spaces)
fs/nfs/dir.c:2965:56: expected struct cred const *
fs/nfs/dir.c:2965:56: got struct cred const [noderef] __rcu *const cred
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
fs/nfs/dir.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index d490d64a9ebd0..f7e4a88d5d929 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2957,12 +2957,14 @@ static u64 nfs_access_login_time(const struct task_struct *task,
const struct cred *cred)
{
const struct task_struct *parent;
+ const struct cred *pcred;
u64 ret;
rcu_read_lock();
for (;;) {
parent = rcu_dereference(task->real_parent);
- if (parent == task || cred_fscmp(parent->cred, cred) != 0)
+ pcred = rcu_dereference(parent->cred);
+ if (parent == task || cred_fscmp(pcred, cred) != 0)
break;
task = parent;
}
--
GitLab
From cdfb2fef522d0c3f9cf293db51de88e9b3d46846 Mon Sep 17 00:00:00 2001
From: Marios Makassikis <mmakassikis@freebox.fr>
Date: Fri, 23 Dec 2022 11:59:31 +0100
Subject: [PATCH 0247/1167] ksmbd: send proper error response in
smb2_tree_connect()
Currently, smb2_tree_connect doesn't send an error response packet on
error.
This causes libsmb2 to skip the specific error code and fail with the
following:
smb2_service failed with : Failed to parse fixed part of command
payload. Unexpected size of Error reply. Expected 9, got 8
Signed-off-by: Marios Makassikis <mmakassikis@freebox.fr>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/smb2pdu.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 14d7f3599c639..38fbda52e06fe 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -1928,13 +1928,13 @@ int smb2_tree_connect(struct ksmbd_work *work)
if (conn->posix_ext_supported)
status.tree_conn->posix_extensions = true;
-out_err1:
rsp->StructureSize = cpu_to_le16(16);
+ inc_rfc1001_len(work->response_buf, 16);
+out_err1:
rsp->Capabilities = 0;
rsp->Reserved = 0;
/* default manual caching */
rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING;
- inc_rfc1001_len(work->response_buf, 16);
if (!IS_ERR(treename))
kfree(treename);
@@ -1967,6 +1967,9 @@ int smb2_tree_connect(struct ksmbd_work *work)
rsp->hdr.Status = STATUS_ACCESS_DENIED;
}
+ if (status.ret != KSMBD_TREE_CONN_STATUS_OK)
+ smb2_set_err_rsp(work);
+
return rc;
}
--
GitLab
From 797805d81baa814f76cf7bdab35f86408a79d707 Mon Sep 17 00:00:00 2001
From: William Liu <will@willsroot.io>
Date: Fri, 30 Dec 2022 13:03:15 +0900
Subject: [PATCH 0248/1167] ksmbd: check nt_len to be at least CIFS_ENCPWD_SIZE
in ksmbd_decode_ntlmssp_auth_blob
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
"nt_len - CIFS_ENCPWD_SIZE" is passed directly from
ksmbd_decode_ntlmssp_auth_blob to ksmbd_auth_ntlmv2. Malicious requests
can set nt_len to less than CIFS_ENCPWD_SIZE, which results in a negative
number (or large unsigned value) used for a subsequent memcpy in
ksmbd_auth_ntlvm2 and can cause a panic.
Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: William Liu <will@willsroot.io>
Signed-off-by: Hrvoje Mišetić <misetichrvoje@gmail.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/auth.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c
index 2a39ffb8423b7..6e61b5bc7d86e 100644
--- a/fs/ksmbd/auth.c
+++ b/fs/ksmbd/auth.c
@@ -322,7 +322,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
dn_off = le32_to_cpu(authblob->DomainName.BufferOffset);
dn_len = le16_to_cpu(authblob->DomainName.Length);
- if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len)
+ if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len ||
+ nt_len < CIFS_ENCPWD_SIZE)
return -EINVAL;
/* TODO : use domain name that imported from configuration file */
--
GitLab
From 83dcedd5540d4ac61376ddff5362f7d9f866a6ec Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 31 Dec 2022 17:32:31 +0900
Subject: [PATCH 0249/1167] ksmbd: fix infinite loop in
ksmbd_conn_handler_loop()
If kernel_recvmsg() return -EAGAIN in ksmbd_tcp_readv() and go round
again, It will cause infinite loop issue. And all threads from next
connections would be doing that. This patch add max retry count(2) to
avoid it. kernel_recvmsg() will wait during 7sec timeout and try to
retry two time if -EAGAIN is returned. And add flags of kvmalloc to
__GFP_NOWARN and __GFP_NORETRY to disconnect immediately without
retrying on memory alloation failure.
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Cc: stable@vger.kernel.org
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-18259
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/connection.c | 7 +++++--
fs/ksmbd/transport_tcp.c | 5 ++++-
2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c
index 12be8386446a3..fd0a288af299e 100644
--- a/fs/ksmbd/connection.c
+++ b/fs/ksmbd/connection.c
@@ -316,9 +316,12 @@ int ksmbd_conn_handler_loop(void *p)
/* 4 for rfc1002 length field */
size = pdu_size + 4;
- conn->request_buf = kvmalloc(size, GFP_KERNEL);
+ conn->request_buf = kvmalloc(size,
+ GFP_KERNEL |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
if (!conn->request_buf)
- continue;
+ break;
memcpy(conn->request_buf, hdr_buf, sizeof(hdr_buf));
if (!ksmbd_smb_request(conn))
diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c
index 63d55f543bd2e..4c6bd0b699791 100644
--- a/fs/ksmbd/transport_tcp.c
+++ b/fs/ksmbd/transport_tcp.c
@@ -295,6 +295,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig,
struct msghdr ksmbd_msg;
struct kvec *iov;
struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn;
+ int max_retry = 2;
iov = get_conn_iovec(t, nr_segs);
if (!iov)
@@ -321,9 +322,11 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig,
} else if (conn->status == KSMBD_SESS_NEED_RECONNECT) {
total_read = -EAGAIN;
break;
- } else if (length == -ERESTARTSYS || length == -EAGAIN) {
+ } else if ((length == -ERESTARTSYS || length == -EAGAIN) &&
+ max_retry) {
usleep_range(1000, 2000);
length = 0;
+ max_retry--;
continue;
} else if (length <= 0) {
total_read = -EAGAIN;
--
GitLab
From cc2e9d2b26c86c1dd8687f6916e5f621bcacd6f7 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Tue, 27 Dec 2022 22:05:48 -0800
Subject: [PATCH 0250/1167] mm, slab: periodically resched in drain_freelist()
drain_freelist() can be called with a very large number of slabs to free,
such as for kmem_cache_shrink(), or depending on various settings of the
slab cache when doing periodic reaping.
If there is a potentially long list of slabs to drain, periodically
schedule to ensure we aren't saturating the cpu for too long.
Signed-off-by: David Rientjes <rientjes@google.com>
Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
mm/slab.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/mm/slab.c b/mm/slab.c
index 7a269db050eed..29300fc1289a8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2211,6 +2211,8 @@ static int drain_freelist(struct kmem_cache *cache,
raw_spin_unlock_irq(&n->list_lock);
slab_destroy(cache, slab);
nr_freed++;
+
+ cond_resched();
}
out:
return nr_freed;
--
GitLab
From 3b754ed6d1cd90017e66e5cc16f3923e4a952ffc Mon Sep 17 00:00:00 2001
From: Carlo Caione <ccaione@baylibre.com>
Date: Mon, 19 Dec 2022 09:43:05 +0100
Subject: [PATCH 0251/1167] drm/meson: Reduce the FIFO lines held when AFBC is
not used
Having a bigger number of FIFO lines held after vsync is only useful to
SoCs using AFBC to give time to the AFBC decoder to be reset, configured
and enabled again.
For SoCs not using AFBC this, on the contrary, is causing on some
displays issues and a few pixels vertical offset in the displayed image.
Conditionally increase the number of lines held after vsync only for
SoCs using AFBC, leaving the default value for all the others.
Fixes: 24e0d4058eff ("drm/meson: hold 32 lines after vsync to give time for AFBC start")
Signed-off-by: Carlo Caione <ccaione@baylibre.com>
Acked-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Acked-by: Neil Armstrong <neil.armstrong@linaro.org>
[narmstrong: added fixes tag]
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20221216-afbc_s905x-v1-0-033bebf780d9@baylibre.com
---
drivers/gpu/drm/meson/meson_viu.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index d4b907889a21d..cd399b0b71814 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -436,15 +436,14 @@ void meson_viu_init(struct meson_drm *priv)
/* Initialize OSD1 fifo control register */
reg = VIU_OSD_DDR_PRIORITY_URGENT |
- VIU_OSD_HOLD_FIFO_LINES(31) |
VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
- reg |= VIU_OSD_BURST_LENGTH_32;
+ reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31));
else
- reg |= VIU_OSD_BURST_LENGTH_64;
+ reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT));
--
GitLab
From 7adde5ac25fa50dbb1fb237042316685cafe976c Mon Sep 17 00:00:00 2001
From: Yuan Can <yuancan@huawei.com>
Date: Thu, 8 Dec 2022 11:36:20 +0000
Subject: [PATCH 0252/1167] mtd: parsers: Fix potential memory leak in
mtd_parser_tplink_safeloader_parse()
The parts needs to be freed with all its elements, otherwise it will be
leaked.
Fixes: 00a3588084be ("mtd: parsers: add TP-Link SafeLoader partitions table parser")
Signed-off-by: Yuan Can <yuancan@huawei.com>
Reviewed-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20221208113620.78855-1-yuancan@huawei.com
---
drivers/mtd/parsers/tplink_safeloader.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/mtd/parsers/tplink_safeloader.c b/drivers/mtd/parsers/tplink_safeloader.c
index f601e7bd86279..1c689dafca2ae 100644
--- a/drivers/mtd/parsers/tplink_safeloader.c
+++ b/drivers/mtd/parsers/tplink_safeloader.c
@@ -91,7 +91,7 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd,
buf = mtd_parser_tplink_safeloader_read_table(mtd);
if (!buf) {
err = -ENOENT;
- goto err_out;
+ goto err_free_parts;
}
for (idx = 0, offset = TPLINK_SAFELOADER_DATA_OFFSET;
@@ -118,6 +118,8 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd,
err_free:
for (idx -= 1; idx >= 0; idx--)
kfree(parts[idx].name);
+err_free_parts:
+ kfree(parts);
err_out:
return err;
};
--
GitLab
From 105c14b84d93168431abba5d55e6c26fa4b65abb Mon Sep 17 00:00:00 2001
From: Mikhail Zhilkin <csharper2005@gmail.com>
Date: Thu, 8 Dec 2022 23:28:29 +0300
Subject: [PATCH 0253/1167] mtd: parsers: scpart: fix __udivdi3 undefined on
mips
This fixes the following compile error on mips architecture with clang
version 16.0.0 reported by the 0-DAY CI Kernel Test Service:
ld.lld: error: undefined symbol: __udivdi3
referenced by scpart.c
mtd/parsers/scpart.o:(scpart_parse) in archive drivers/built-in.a
As a workaround this makes 'offs' a 32-bit type. This is enough, because
the mtd containing partition table practically does not exceed 1 MB. We
can revert this when the [Link] has been resolved.
Link: https://github.com/ClangBuiltLinux/linux/issues/1635
Fixes: 9b78ef0c7997 ("mtd: parsers: add support for Sercomm partitions")
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Mikhail Zhilkin <csharper2005@gmail.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/805fe58e-690f-6a3f-5ebf-2f6f6e6e4599@gmail.com
---
drivers/mtd/parsers/scpart.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/mtd/parsers/scpart.c b/drivers/mtd/parsers/scpart.c
index 02601bb33de4e..6e5e11c37078f 100644
--- a/drivers/mtd/parsers/scpart.c
+++ b/drivers/mtd/parsers/scpart.c
@@ -50,7 +50,7 @@ static int scpart_scan_partmap(struct mtd_info *master, loff_t partmap_offs,
int cnt = 0;
int res = 0;
int res2;
- loff_t offs;
+ uint32_t offs;
size_t retlen;
struct sc_part_desc *pdesc = NULL;
struct sc_part_desc *tmpdesc;
--
GitLab
From d19ab1f785d0b6b9f709799f0938658903821ba1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 20 Dec 2022 15:13:34 +0100
Subject: [PATCH 0254/1167] mtd: cfi: allow building spi-intel standalone
When MTD or MTD_CFI_GEOMETRY is disabled, the spi-intel driver
fails to build, as it includes the shared CFI header:
include/linux/mtd/cfi.h:62:2: error: #warning No CONFIG_MTD_CFI_Ix selected. No NOR chip support can work. [-Werror=cpp]
62 | #warning No CONFIG_MTD_CFI_Ix selected. No NOR chip support can work.
linux/mtd/spi-nor.h does not actually need to include cfi.h, so
remove the inclusion here to fix the warning. This uncovers a
missing #include in spi-nor/core.c so add that there to
prevent a different build issue.
Fixes: e23e5a05d1fd ("mtd: spi-nor: intel-spi: Convert to SPI MEM")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Tokunori Ikegami <ikegami.t@gmail.com>
Acked-by: Pratyush Yadav <pratyush@kernel.org>
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20221220141352.1486360-1-arnd@kernel.org
---
drivers/mtd/spi-nor/core.c | 1 +
include/linux/mtd/spi-nor.h | 1 -
2 files changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index d8703d7dfd0af..d67c926bca8ba 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -10,6 +10,7 @@
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/module.h>
+#include <linux/delay.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/math64.h>
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 25765556223a1..a3f8cdca90c83 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -7,7 +7,6 @@
#define __LINUX_MTD_SPI_NOR_H
#include <linux/bitops.h>
-#include <linux/mtd/cfi.h>
#include <linux/mtd/mtd.h>
#include <linux/spi/spi-mem.h>
--
GitLab
From 461ab10ef7e6ea9b41a0571a7fc6a72af9549a3c Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 17 Nov 2022 10:43:21 +0800
Subject: [PATCH 0255/1167] ceph: switch to vfs_inode_has_locks() to fix file
lock bug
For the POSIX locks they are using the same owner, which is the
thread id. And multiple POSIX locks could be merged into single one,
so when checking whether the 'file' has locks may fail.
For a file where some openers use locking and others don't is a
really odd usage pattern though. Locks are like stoplights -- they
only work if everyone pays attention to them.
Just switch ceph_get_caps() to check whether any locks are set on
the inode. If there are POSIX/OFD/FLOCK locks on the file at the
time, we should set CHECK_FILELOCK, regardless of what fd was used
to set the lock.
Fixes: ff5d913dfc71 ("ceph: return -EIO if read/write against filp that lost file locks")
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/caps.c | 2 +-
fs/ceph/locks.c | 4 ----
fs/ceph/super.h | 1 -
3 files changed, 1 insertion(+), 6 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 4b159f97fe7b5..f75ad432f375f 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2913,7 +2913,7 @@ int ceph_get_caps(struct file *filp, int need, int want, loff_t endoff, int *got
while (true) {
flags &= CEPH_FILE_MODE_MASK;
- if (atomic_read(&fi->num_locks))
+ if (vfs_inode_has_locks(inode))
flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index f3b461c708a8b..6b3b8c299c17a 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -32,18 +32,14 @@ void __init ceph_flock_init(void)
static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
- struct ceph_file_info *fi = dst->fl_file->private_data;
struct inode *inode = file_inode(dst->fl_file);
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
- atomic_inc(&fi->num_locks);
}
static void ceph_fl_release_lock(struct file_lock *fl)
{
- struct ceph_file_info *fi = fl->fl_file->private_data;
struct inode *inode = file_inode(fl->fl_file);
struct ceph_inode_info *ci = ceph_inode(inode);
- atomic_dec(&fi->num_locks);
if (atomic_dec_and_test(&ci->i_filelock_ref)) {
/* clear error when all locks are released */
spin_lock(&ci->i_ceph_lock);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 30bdb391a0dc0..0ed3be75bb9ae 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -790,7 +790,6 @@ struct ceph_file_info {
struct list_head rw_contexts;
u32 filp_gen;
- atomic_t num_locks;
};
struct ceph_dir_file_info {
--
GitLab
From 8e1858710d9a71d88acd922f2e95d1eddb90eea0 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 17 Nov 2022 10:57:53 +0800
Subject: [PATCH 0256/1167] ceph: avoid use-after-free in
ceph_fl_release_lock()
When ceph releasing the file_lock it will try to get the inode pointer
from the fl->fl_file, which the memory could already be released by
another thread in filp_close(). Because in VFS layer the fl->fl_file
doesn't increase the file's reference counter.
Will switch to use ceph dedicate lock info to track the inode.
And in ceph_fl_release_lock() we should skip all the operations if the
fl->fl_u.ceph.inode is not set, which should come from the request
file_lock. And we will set fl->fl_u.ceph.inode when inserting it to the
inode lock list, which is when copying the lock.
Link: https://tracker.ceph.com/issues/57986
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
fs/ceph/locks.c | 20 ++++++++++++++++++--
include/linux/fs.h | 3 +++
2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 6b3b8c299c17a..9c8dc8a55e7e1 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -34,18 +34,34 @@ static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
struct inode *inode = file_inode(dst->fl_file);
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
+ dst->fl_u.ceph.inode = igrab(inode);
}
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
static void ceph_fl_release_lock(struct file_lock *fl)
{
- struct inode *inode = file_inode(fl->fl_file);
- struct ceph_inode_info *ci = ceph_inode(inode);
+ struct inode *inode = fl->fl_u.ceph.inode;
+ struct ceph_inode_info *ci;
+
+ /*
+ * If inode is NULL it should be a request file_lock,
+ * nothing we can do.
+ */
+ if (!inode)
+ return;
+
+ ci = ceph_inode(inode);
if (atomic_dec_and_test(&ci->i_filelock_ref)) {
/* clear error when all locks are released */
spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
spin_unlock(&ci->i_ceph_lock);
}
+ fl->fl_u.ceph.inode = NULL;
+ iput(inode);
}
static const struct file_lock_operations ceph_fl_lock_ops = {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 066555ad1bf81..c1769a2c5d708 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1119,6 +1119,9 @@ struct file_lock {
int state; /* state of grant or error if -ve */
unsigned int debug_id;
} afs;
+ struct {
+ struct inode *inode;
+ } ceph;
} fl_u;
} __randomize_layout;
--
GitLab
From 694175cd8a1643cde3acb45c9294bca44a8e08e9 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Mon, 2 Jan 2023 12:20:39 +0400
Subject: [PATCH 0257/1167] gpio: sifive: Fix refcount leak in
sifive_gpio_probe
of_irq_find_parent() returns a node pointer with refcount incremented,
We should use of_node_put() on it when not needed anymore.
Add missing of_node_put() to avoid refcount leak.
Fixes: 96868dce644d ("gpio/sifive: Add GPIO driver for SiFive SoCs")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-sifive.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c
index 238f3210970cf..bc5660f61c570 100644
--- a/drivers/gpio/gpio-sifive.c
+++ b/drivers/gpio/gpio-sifive.c
@@ -215,6 +215,7 @@ static int sifive_gpio_probe(struct platform_device *pdev)
return -ENODEV;
}
parent = irq_find_host(irq_parent);
+ of_node_put(irq_parent);
if (!parent) {
dev_err(dev, "no IRQ parent domain\n");
return -ENODEV;
--
GitLab
From 1e336aa0c0250ec84c6f16efac40c9f0138e367d Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Wed, 7 Dec 2022 19:23:15 +0800
Subject: [PATCH 0258/1167] mmc: sdhci-esdhc-imx: correct the tuning start tap
and step setting
Current code logic may be impacted by the setting of ROM/Bootloader,
so unmask these bits first, then setting these bits accordingly.
Fixes: 2b16cf326b70 ("mmc: sdhci-esdhc-imx: move tuning static configuration into hwinit function")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20221207112315.1812222-1-haibo.chen@nxp.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/mmc/host/sdhci-esdhc-imx.c | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 89ef0c80ac371..9e73c34b64017 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -107,6 +107,7 @@
#define ESDHC_TUNING_START_TAP_DEFAULT 0x1
#define ESDHC_TUNING_START_TAP_MASK 0x7f
#define ESDHC_TUNING_CMD_CRC_CHECK_DISABLE (1 << 7)
+#define ESDHC_TUNING_STEP_DEFAULT 0x1
#define ESDHC_TUNING_STEP_MASK 0x00070000
#define ESDHC_TUNING_STEP_SHIFT 16
@@ -1368,7 +1369,7 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host)
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
struct cqhci_host *cq_host = host->mmc->cqe_private;
- int tmp;
+ u32 tmp;
if (esdhc_is_usdhc(imx_data)) {
/*
@@ -1423,17 +1424,24 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host)
if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
tmp = readl(host->ioaddr + ESDHC_TUNING_CTRL);
- tmp |= ESDHC_STD_TUNING_EN |
- ESDHC_TUNING_START_TAP_DEFAULT;
- if (imx_data->boarddata.tuning_start_tap) {
- tmp &= ~ESDHC_TUNING_START_TAP_MASK;
+ tmp |= ESDHC_STD_TUNING_EN;
+
+ /*
+ * ROM code or bootloader may config the start tap
+ * and step, unmask them first.
+ */
+ tmp &= ~(ESDHC_TUNING_START_TAP_MASK | ESDHC_TUNING_STEP_MASK);
+ if (imx_data->boarddata.tuning_start_tap)
tmp |= imx_data->boarddata.tuning_start_tap;
- }
+ else
+ tmp |= ESDHC_TUNING_START_TAP_DEFAULT;
if (imx_data->boarddata.tuning_step) {
- tmp &= ~ESDHC_TUNING_STEP_MASK;
tmp |= imx_data->boarddata.tuning_step
<< ESDHC_TUNING_STEP_SHIFT;
+ } else {
+ tmp |= ESDHC_TUNING_STEP_DEFAULT
+ << ESDHC_TUNING_STEP_SHIFT;
}
/* Disable the CMD CRC check for tuning, if not, need to
--
GitLab
From b3d40c3ec3dc4ad78017de6c3a38979f57aaaab8 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Date: Tue, 22 Nov 2022 21:48:23 +0800
Subject: [PATCH 0259/1167] HID: intel_ish-hid: Add check for ishtp_dma_tx_map
As the kcalloc may return NULL pointer,
it should be better to check the ishtp_dma_tx_map
before use in order to avoid NULL pointer dereference.
Fixes: 3703f53b99e4 ("HID: intel_ish-hid: ISH Transport layer")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/intel-ish-hid/ishtp/dma-if.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/hid/intel-ish-hid/ishtp/dma-if.c b/drivers/hid/intel-ish-hid/ishtp/dma-if.c
index 40554c8daca07..00046cbfd4ed0 100644
--- a/drivers/hid/intel-ish-hid/ishtp/dma-if.c
+++ b/drivers/hid/intel-ish-hid/ishtp/dma-if.c
@@ -104,6 +104,11 @@ void *ishtp_cl_get_dma_send_buf(struct ishtp_device *dev,
int required_slots = (size / DMA_SLOT_SIZE)
+ 1 * (size % DMA_SLOT_SIZE != 0);
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return NULL;
+ }
+
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) {
free = 1;
@@ -150,6 +155,11 @@ void ishtp_cl_release_dma_acked_mem(struct ishtp_device *dev,
return;
}
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return;
+ }
+
i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE;
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (j = 0; j < acked_slots; j++) {
--
GitLab
From ae066f374687d7dd06bb8c732f66d6ab3c3fd480 Mon Sep 17 00:00:00 2001
From: Tim Harvey <tharvey@gateworks.com>
Date: Wed, 28 Dec 2022 12:26:06 -0800
Subject: [PATCH 0260/1167] arm64: dts: imx8mm-venice-gw7901: fix USB2
controller OC polarity
The GW7901 has USB2 routed to a USB VBUS supply with over-current
protection via an active-low pin. Define the OC pin polarity properly.
Fixes: 2b1649a83afc ("arm64: dts: imx: Add i.mx8mm Gateworks gw7901 dts support")
Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
index 750a1f07ecb7a..6433c205f8dde 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts
@@ -771,6 +771,7 @@ &usbotg1 {
&usbotg2 {
dr_mode = "host";
vbus-supply = <®_usb2_vbus>;
+ over-current-active-low;
status = "okay";
};
--
GitLab
From 490748874ebf1875420fc29b335bba2075dd1b5e Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Sat, 31 Dec 2022 13:58:48 +0400
Subject: [PATCH 0261/1167] soc: imx8m: Fix incorrect check for
of_clk_get_by_name()
of_clk_get_by_name() returns error pointers instead of NULL.
Use IS_ERR() checks the return value to catch errors.
Fixes: 836fb30949d9 ("soc: imx8m: Enable OCOTP clock before reading the register")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
drivers/soc/imx/soc-imx8m.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c
index 28144c699b0c3..32ed9dc88e455 100644
--- a/drivers/soc/imx/soc-imx8m.c
+++ b/drivers/soc/imx/soc-imx8m.c
@@ -66,8 +66,8 @@ static u32 __init imx8mq_soc_revision(void)
ocotp_base = of_iomap(np, 0);
WARN_ON(!ocotp_base);
clk = of_clk_get_by_name(np, NULL);
- if (!clk) {
- WARN_ON(!clk);
+ if (IS_ERR(clk)) {
+ WARN_ON(IS_ERR(clk));
return 0;
}
--
GitLab
From a2965c7be0522eaa18808684b7b82b248515511b Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 1 Jan 2023 16:57:43 -0500
Subject: [PATCH 0262/1167] net: sched: atm: dont intepret cls results when
asked to drop
If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume
res.class contains a valid pointer
Fixes: b0188d4dbe5f ("[NET_SCHED]: sch_atm: Lindent")
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/sch_atm.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index f52255fea652b..4a981ca90b0bf 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -393,10 +393,13 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
result = tcf_classify(skb, NULL, fl, &res, true);
if (result < 0)
continue;
+ if (result == TC_ACT_SHOT)
+ goto done;
+
flow = (struct atm_flow_data *)res.class;
if (!flow)
flow = lookup_flow(sch, res.classid);
- goto done;
+ goto drop;
}
}
flow = NULL;
--
GitLab
From caa4b35b4317d5147b3ab0fbdc9c075c7d2e9c12 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 1 Jan 2023 16:57:44 -0500
Subject: [PATCH 0263/1167] net: sched: cbq: dont intepret cls results when
asked to drop
If asked to drop a packet via TC_ACT_SHOT it is unsafe to assume that
res.class contains a valid pointer
Sample splat reported by Kyle Zeng
[ 5.405624] 0: reclassify loop, rule prio 0, protocol 800
[ 5.406326] ==================================================================
[ 5.407240] BUG: KASAN: slab-out-of-bounds in cbq_enqueue+0x54b/0xea0
[ 5.407987] Read of size 1 at addr ffff88800e3122aa by task poc/299
[ 5.408731]
[ 5.408897] CPU: 0 PID: 299 Comm: poc Not tainted 5.10.155+ #15
[ 5.409516] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
BIOS 1.15.0-1 04/01/2014
[ 5.410439] Call Trace:
[ 5.410764] dump_stack+0x87/0xcd
[ 5.411153] print_address_description+0x7a/0x6b0
[ 5.411687] ? vprintk_func+0xb9/0xc0
[ 5.411905] ? printk+0x76/0x96
[ 5.412110] ? cbq_enqueue+0x54b/0xea0
[ 5.412323] kasan_report+0x17d/0x220
[ 5.412591] ? cbq_enqueue+0x54b/0xea0
[ 5.412803] __asan_report_load1_noabort+0x10/0x20
[ 5.413119] cbq_enqueue+0x54b/0xea0
[ 5.413400] ? __kasan_check_write+0x10/0x20
[ 5.413679] __dev_queue_xmit+0x9c0/0x1db0
[ 5.413922] dev_queue_xmit+0xc/0x10
[ 5.414136] ip_finish_output2+0x8bc/0xcd0
[ 5.414436] __ip_finish_output+0x472/0x7a0
[ 5.414692] ip_finish_output+0x5c/0x190
[ 5.414940] ip_output+0x2d8/0x3c0
[ 5.415150] ? ip_mc_finish_output+0x320/0x320
[ 5.415429] __ip_queue_xmit+0x753/0x1760
[ 5.415664] ip_queue_xmit+0x47/0x60
[ 5.415874] __tcp_transmit_skb+0x1ef9/0x34c0
[ 5.416129] tcp_connect+0x1f5e/0x4cb0
[ 5.416347] tcp_v4_connect+0xc8d/0x18c0
[ 5.416577] __inet_stream_connect+0x1ae/0xb40
[ 5.416836] ? local_bh_enable+0x11/0x20
[ 5.417066] ? lock_sock_nested+0x175/0x1d0
[ 5.417309] inet_stream_connect+0x5d/0x90
[ 5.417548] ? __inet_stream_connect+0xb40/0xb40
[ 5.417817] __sys_connect+0x260/0x2b0
[ 5.418037] __x64_sys_connect+0x76/0x80
[ 5.418267] do_syscall_64+0x31/0x50
[ 5.418477] entry_SYSCALL_64_after_hwframe+0x61/0xc6
[ 5.418770] RIP: 0033:0x473bb7
[ 5.418952] Code: 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00
00 00 90 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2a 00 00
00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 18 89 54 24 0c 48 89 34
24 89
[ 5.420046] RSP: 002b:00007fffd20eb0f8 EFLAGS: 00000246 ORIG_RAX:
000000000000002a
[ 5.420472] RAX: ffffffffffffffda RBX: 00007fffd20eb578 RCX: 0000000000473bb7
[ 5.420872] RDX: 0000000000000010 RSI: 00007fffd20eb110 RDI: 0000000000000007
[ 5.421271] RBP: 00007fffd20eb150 R08: 0000000000000001 R09: 0000000000000004
[ 5.421671] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
[ 5.422071] R13: 00007fffd20eb568 R14: 00000000004fc740 R15: 0000000000000002
[ 5.422471]
[ 5.422562] Allocated by task 299:
[ 5.422782] __kasan_kmalloc+0x12d/0x160
[ 5.423007] kasan_kmalloc+0x5/0x10
[ 5.423208] kmem_cache_alloc_trace+0x201/0x2e0
[ 5.423492] tcf_proto_create+0x65/0x290
[ 5.423721] tc_new_tfilter+0x137e/0x1830
[ 5.423957] rtnetlink_rcv_msg+0x730/0x9f0
[ 5.424197] netlink_rcv_skb+0x166/0x300
[ 5.424428] rtnetlink_rcv+0x11/0x20
[ 5.424639] netlink_unicast+0x673/0x860
[ 5.424870] netlink_sendmsg+0x6af/0x9f0
[ 5.425100] __sys_sendto+0x58d/0x5a0
[ 5.425315] __x64_sys_sendto+0xda/0xf0
[ 5.425539] do_syscall_64+0x31/0x50
[ 5.425764] entry_SYSCALL_64_after_hwframe+0x61/0xc6
[ 5.426065]
[ 5.426157] The buggy address belongs to the object at ffff88800e312200
[ 5.426157] which belongs to the cache kmalloc-128 of size 128
[ 5.426955] The buggy address is located 42 bytes to the right of
[ 5.426955] 128-byte region [ffff88800e312200, ffff88800e312280)
[ 5.427688] The buggy address belongs to the page:
[ 5.427992] page:000000009875fabc refcount:1 mapcount:0
mapping:0000000000000000 index:0x0 pfn:0xe312
[ 5.428562] flags: 0x100000000000200(slab)
[ 5.428812] raw: 0100000000000200 dead000000000100 dead000000000122
ffff888007843680
[ 5.429325] raw: 0000000000000000 0000000000100010 00000001ffffffff
ffff88800e312401
[ 5.429875] page dumped because: kasan: bad access detected
[ 5.430214] page->mem_cgroup:ffff88800e312401
[ 5.430471]
[ 5.430564] Memory state around the buggy address:
[ 5.430846] ffff88800e312180: fc fc fc fc fc fc fc fc fc fc fc fc
fc fc fc fc
[ 5.431267] ffff88800e312200: 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00 fc
[ 5.431705] >ffff88800e312280: fc fc fc fc fc fc fc fc fc fc fc fc
fc fc fc fc
[ 5.432123] ^
[ 5.432391] ffff88800e312300: 00 00 00 00 00 00 00 00 00 00 00 00
00 00 00 fc
[ 5.432810] ffff88800e312380: fc fc fc fc fc fc fc fc fc fc fc fc
fc fc fc fc
[ 5.433229] ==================================================================
[ 5.433648] Disabling lock debugging due to kernel taint
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Kyle Zeng <zengyhkyle@gmail.com>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/sch_cbq.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 6568e17c4c634..36db5f6782f2c 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -230,6 +230,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
result = tcf_classify(skb, NULL, fl, &res, true);
if (!fl || result < 0)
goto fallback;
+ if (result == TC_ACT_SHOT)
+ return NULL;
cl = (void *)res.class;
if (!cl) {
@@ -250,8 +252,6 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
- case TC_ACT_SHOT:
- return NULL;
case TC_ACT_RECLASSIFY:
return cbq_reclassify(skb, cl);
}
--
GitLab
From 43d253781f6321c6a07a5fe4ee72103a679a5f6b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Jan 2023 23:17:37 -0800
Subject: [PATCH 0264/1167] net: sched: htb: fix htb_classify() kernel-doc
Fix W=1 kernel-doc warning:
net/sched/sch_htb.c:214: warning: expecting prototype for htb_classify(). Prototype was for HTB_DIRECT() instead
by moving the HTB_DIRECT() macro above the function.
Add kernel-doc notation for function parameters as well.
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/sched/sch_htb.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index e5b4bbf3ce3d5..2238edece1a46 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -199,8 +199,14 @@ static unsigned long htb_search(struct Qdisc *sch, u32 handle)
{
return (unsigned long)htb_find(handle, sch);
}
+
+#define HTB_DIRECT ((struct htb_class *)-1L)
+
/**
* htb_classify - classify a packet into class
+ * @skb: the socket buffer
+ * @sch: the active queue discipline
+ * @qerr: pointer for returned status code
*
* It returns NULL if the packet should be dropped or -1 if the packet
* should be passed directly thru. In all other cases leaf class is returned.
@@ -211,8 +217,6 @@ static unsigned long htb_search(struct Qdisc *sch, u32 handle)
* have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful
* then finish and return direct queue.
*/
-#define HTB_DIRECT ((struct htb_class *)-1L)
-
static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
--
GitLab
From 06bf62944144a92d83dd14fd1378d2a288259561 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 2 Jan 2023 08:55:56 +0200
Subject: [PATCH 0265/1167] vxlan: Fix memory leaks in error path
The memory allocated by vxlan_vnigroup_init() is not freed in the error
path, leading to memory leaks [1]. Fix by calling
vxlan_vnigroup_uninit() in the error path.
The leaks can be reproduced by annotating gro_cells_init() with
ALLOW_ERROR_INJECTION() and then running:
# echo "100" > /sys/kernel/debug/fail_function/probability
# echo "1" > /sys/kernel/debug/fail_function/times
# echo "gro_cells_init" > /sys/kernel/debug/fail_function/inject
# printf %#x -12 > /sys/kernel/debug/fail_function/gro_cells_init/retval
# ip link add name vxlan0 type vxlan dstport 4789 external vnifilter
RTNETLINK answers: Cannot allocate memory
[1]
unreferenced object 0xffff88810db84a00 (size 512):
comm "ip", pid 330, jiffies 4295010045 (age 66.016s)
hex dump (first 32 bytes):
f8 d5 76 0e 81 88 ff ff 01 00 00 00 00 00 00 02 ..v.............
03 00 04 00 48 00 00 00 00 00 00 01 04 00 01 00 ....H...........
backtrace:
[<ffffffff81a3097a>] kmalloc_trace+0x2a/0x60
[<ffffffff82f049fc>] vxlan_vnigroup_init+0x4c/0x160
[<ffffffff82ecd69e>] vxlan_init+0x1ae/0x280
[<ffffffff836858ca>] register_netdevice+0x57a/0x16d0
[<ffffffff82ef67b7>] __vxlan_dev_create+0x7c7/0xa50
[<ffffffff82ef6ce6>] vxlan_newlink+0xd6/0x130
[<ffffffff836d02ab>] __rtnl_newlink+0x112b/0x18a0
[<ffffffff836d0a8c>] rtnl_newlink+0x6c/0xa0
[<ffffffff836c0ddf>] rtnetlink_rcv_msg+0x43f/0xd40
[<ffffffff83908ce0>] netlink_rcv_skb+0x170/0x440
[<ffffffff839066af>] netlink_unicast+0x53f/0x810
[<ffffffff839072d8>] netlink_sendmsg+0x958/0xe70
[<ffffffff835c319f>] ____sys_sendmsg+0x78f/0xa90
[<ffffffff835cd6da>] ___sys_sendmsg+0x13a/0x1e0
[<ffffffff835cd94c>] __sys_sendmsg+0x11c/0x1f0
[<ffffffff8424da78>] do_syscall_64+0x38/0x80
unreferenced object 0xffff88810e76d5f8 (size 192):
comm "ip", pid 330, jiffies 4295010045 (age 66.016s)
hex dump (first 32 bytes):
04 00 00 00 00 00 00 00 db e1 4f e7 00 00 00 00 ..........O.....
08 d6 76 0e 81 88 ff ff 08 d6 76 0e 81 88 ff ff ..v.......v.....
backtrace:
[<ffffffff81a3162e>] __kmalloc_node+0x4e/0x90
[<ffffffff81a0e166>] kvmalloc_node+0xa6/0x1f0
[<ffffffff8276e1a3>] bucket_table_alloc.isra.0+0x83/0x460
[<ffffffff8276f18b>] rhashtable_init+0x43b/0x7c0
[<ffffffff82f04a1c>] vxlan_vnigroup_init+0x6c/0x160
[<ffffffff82ecd69e>] vxlan_init+0x1ae/0x280
[<ffffffff836858ca>] register_netdevice+0x57a/0x16d0
[<ffffffff82ef67b7>] __vxlan_dev_create+0x7c7/0xa50
[<ffffffff82ef6ce6>] vxlan_newlink+0xd6/0x130
[<ffffffff836d02ab>] __rtnl_newlink+0x112b/0x18a0
[<ffffffff836d0a8c>] rtnl_newlink+0x6c/0xa0
[<ffffffff836c0ddf>] rtnetlink_rcv_msg+0x43f/0xd40
[<ffffffff83908ce0>] netlink_rcv_skb+0x170/0x440
[<ffffffff839066af>] netlink_unicast+0x53f/0x810
[<ffffffff839072d8>] netlink_sendmsg+0x958/0xe70
[<ffffffff835c319f>] ____sys_sendmsg+0x78f/0xa90
Fixes: f9c4bb0b245c ("vxlan: vni filtering support on collect metadata device")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/vxlan/vxlan_core.c | 19 +++++++++++++------
1 file changed, 13 insertions(+), 6 deletions(-)
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 92224b36787a8..b1b179effe2a1 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2917,16 +2917,23 @@ static int vxlan_init(struct net_device *dev)
vxlan_vnigroup_init(vxlan);
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->tstats)
- return -ENOMEM;
+ if (!dev->tstats) {
+ err = -ENOMEM;
+ goto err_vnigroup_uninit;
+ }
err = gro_cells_init(&vxlan->gro_cells, dev);
- if (err) {
- free_percpu(dev->tstats);
- return err;
- }
+ if (err)
+ goto err_free_percpu;
return 0;
+
+err_free_percpu:
+ free_percpu(dev->tstats);
+err_vnigroup_uninit:
+ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
+ vxlan_vnigroup_uninit(vxlan);
+ return err;
}
static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
--
GitLab
From 588ab2dc25f60efeb516b4abedb6c551949cc185 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 2 Jan 2023 13:12:15 +0100
Subject: [PATCH 0266/1167] net: sparx5: Fix reading of the MAC address
There is an issue with the checking of the return value of
'of_get_mac_address', which returns 0 on success and negative value on
failure. The driver interpretated the result the opposite way. Therefore
if there was a MAC address defined in the DT, then the driver was
generating a random MAC address otherwise it would use address 0.
Fix this by checking correctly the return value of 'of_get_mac_address'
Fixes: b74ef9f9cb91 ("net: sparx5: Do not use mac_addr uninitialized in mchp_sparx5_probe()")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/microchip/sparx5/sparx5_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index d25f4f09faa06..3c5d4fe993737 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -834,7 +834,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
if (err)
goto cleanup_config;
- if (!of_get_mac_address(np, sparx5->base_mac)) {
+ if (of_get_mac_address(np, sparx5->base_mac)) {
dev_info(sparx5->dev, "MAC addr was not set, use random MAC\n");
eth_random_addr(sparx5->base_mac);
sparx5->base_mac[5] = 0;
--
GitLab
From a31d47be64b9b74f8cfedffe03e0a8a1f9e51f23 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Fri, 30 Dec 2022 13:24:37 +0100
Subject: [PATCH 0267/1167] netfilter: ipset: fix hash:net,port,net hang with
/0 subnet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The hash:net,port,net set type supports /0 subnets. However, the patch
commit 5f7b51bf09baca8e titled "netfilter: ipset: Limit the maximal range
of consecutive elements to add/delete" did not take into account it and
resulted in an endless loop. The bug is actually older but the patch
5f7b51bf09baca8e brings it out earlier.
Handle /0 subnets properly in hash:net,port,net set types.
Fixes: 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of consecutive elements to add/delete")
Reported-by: Марк Коренберг <socketpair@gmail.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/ipset/ip_set_hash_netportnet.c | 40 ++++++++++----------
1 file changed, 21 insertions(+), 19 deletions(-)
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 19bcdb3141f6e..005a7ce87217e 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -173,17 +173,26 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
+static u32
+hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr)
+{
+ if (from == 0 && to == UINT_MAX) {
+ *cidr = 0;
+ return to;
+ }
+ return ip_set_range_to_cidr(from, to, cidr);
+}
+
static int
hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netportnet4 *h = set->data;
+ struct hash_netportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2, ipn;
- u64 n = 0, m = 0;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
int ret;
@@ -285,19 +294,6 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
@@ -310,13 +306,19 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
do {
e.ip[0] = htonl(ip);
- ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
+ ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]);
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip[1] = htonl(ip2);
- ip2 = ip_set_range_to_cidr(ip2, ip2_to,
- &e.cidr[1]);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
+ ip2 = hash_netportnet4_range_to_cidr(ip2,
+ ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
--
GitLab
From 5e29dc36bd5e2166b834ceb19990d9e68a734d7d Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@netfilter.org>
Date: Fri, 30 Dec 2022 13:24:38 +0100
Subject: [PATCH 0268/1167] netfilter: ipset: Rework long task execution when
adding/deleting entries
When adding/deleting large number of elements in one step in ipset, it can
take a reasonable amount of time and can result in soft lockup errors. The
patch 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of
consecutive elements to add/delete") tried to fix it by limiting the max
elements to process at all. However it was not enough, it is still possible
that we get hung tasks. Lowering the limit is not reasonable, so the
approach in this patch is as follows: rely on the method used at resizing
sets and save the state when we reach a smaller internal batch limit,
unlock/lock and proceed from the saved state. Thus we can avoid long
continuous tasks and at the same time removed the limit to add/delete large
number of elements in one step.
The nfnl mutex is held during the whole operation which prevents one to
issue other ipset commands in parallel.
Fixes: 5f7b51bf09ba ("netfilter: ipset: Limit the maximal range of consecutive elements to add/delete")
Reported-by: syzbot+9204e7399656300bf271@syzkaller.appspotmail.com
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/linux/netfilter/ipset/ip_set.h | 2 +-
net/netfilter/ipset/ip_set_core.c | 7 ++++---
net/netfilter/ipset/ip_set_hash_ip.c | 14 ++++++-------
net/netfilter/ipset/ip_set_hash_ipmark.c | 13 ++++++------
net/netfilter/ipset/ip_set_hash_ipport.c | 13 ++++++------
net/netfilter/ipset/ip_set_hash_ipportip.c | 13 ++++++------
net/netfilter/ipset/ip_set_hash_ipportnet.c | 13 +++++++-----
net/netfilter/ipset/ip_set_hash_net.c | 17 +++++++--------
net/netfilter/ipset/ip_set_hash_netiface.c | 15 ++++++--------
net/netfilter/ipset/ip_set_hash_netnet.c | 23 +++++++--------------
net/netfilter/ipset/ip_set_hash_netport.c | 19 +++++++----------
11 files changed, 68 insertions(+), 81 deletions(-)
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index ab934ad951a87..e8c350a3ade15 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -197,7 +197,7 @@ struct ip_set_region {
};
/* Max range where every element is added/deleted in one step */
-#define IPSET_MAX_RANGE (1<<20)
+#define IPSET_MAX_RANGE (1<<14)
/* The max revision number supported by any set type + 1 */
#define IPSET_REVISION_MAX 9
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e7ba5b6dd2b7c..46ebee9400dab 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1698,9 +1698,10 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb,
ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
ip_set_unlock(set);
retried = true;
- } while (ret == -EAGAIN &&
- set->variant->resize &&
- (ret = set->variant->resize(set, retried)) == 0);
+ } while (ret == -ERANGE ||
+ (ret == -EAGAIN &&
+ set->variant->resize &&
+ (ret = set->variant->resize(set, retried)) == 0));
if (!ret || (ret == -IPSET_ERR_EXIST && eexist))
return 0;
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index e30513cefd90e..c9f4e38596632 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -100,11 +100,11 @@ static int
hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ip4 *h = set->data;
+ struct hash_ip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = { 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, hosts;
+ u32 ip = 0, ip_to = 0, hosts, i = 0;
int ret = 0;
if (tb[IPSET_ATTR_LINENO])
@@ -149,14 +149,14 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
- /* 64bit division is not allowed on 32bit */
- if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to;) {
+ for (; ip <= ip_to; i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index 153de3457423e..a22ec1a6f6ec8 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -97,11 +97,11 @@ static int
hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipmark4 *h = set->data;
+ struct hash_ipmark4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0;
+ u32 ip, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -148,13 +148,14 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
ip_set_mask_from_to(ip, ip_to, cidr);
}
- if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to; ip++) {
+ for (; ip <= ip_to; ip++, i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipmark4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 2ffbd0b78a8c5..e977b5a9c48dc 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -112,11 +112,11 @@ static int
hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipport4 *h = set->data;
+ struct hash_ipport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
@@ -184,17 +184,18 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 334fb1ad0e86c..39a01934b1536 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -108,11 +108,11 @@ static int
hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportip4 *h = set->data;
+ struct hash_ipportip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
@@ -180,17 +180,18 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 7df94f437f600..5c6de605a9fb7 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -160,12 +160,12 @@ static int
hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportnet4 *h = set->data;
+ struct hash_ipportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
@@ -253,9 +253,6 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
ip2_to = ip2_from;
if (tb[IPSET_ATTR_IP2_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
@@ -282,9 +279,15 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip2 = htonl(ip2);
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr);
e.cidr = cidr - 1;
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 1422739d9aa25..ce0a9ce5a91f1 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -136,11 +136,11 @@ static int
hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_net4 *h = set->data;
+ struct hash_net4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -188,19 +188,16 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_net4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 9810f5bf63f5e..0310732862362 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -202,7 +202,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -256,19 +256,16 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netiface4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index cdfb78c6e0d3d..8fbe649c9dd3d 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -166,13 +166,12 @@ static int
hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netnet4 *h = set->data;
+ struct hash_netnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0;
- u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn;
- u64 n = 0, m = 0;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
@@ -248,19 +247,6 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
@@ -273,7 +259,12 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
e.ip[0] = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
do {
+ i++;
e.ip[1] = htonl(ip2);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netnet4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 09cf72eb37f8d..d1a0628df4ef3 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -154,12 +154,11 @@ static int
hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netport4 *h = set->data;
+ struct hash_netport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn;
- u64 n = 0;
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
@@ -236,14 +235,6 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip);
@@ -255,8 +246,12 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
e.ip = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &cidr);
e.cidr = cidr - 1;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
--
GitLab
From a764da46cd15f8b40292d2c0b29c4bf9a3e66c7e Mon Sep 17 00:00:00 2001
From: Xiu Jianfeng <xiujianfeng@huawei.com>
Date: Wed, 9 Nov 2022 17:19:05 +0800
Subject: [PATCH 0269/1167] drm/virtio: Fix memory leak in
virtio_gpu_object_create()
The virtio_gpu_object_shmem_init() will alloc memory and save it in
@ents, so when virtio_gpu_array_alloc() fails, this memory should be
freed, this patch fixes it.
Fixes: e7fef0923303 ("drm/virtio: Simplify error handling of virtio_gpu_object_create()")
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Reviewed-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221109091905.55451-1-xiujianfeng@huawei.com
---
drivers/gpu/drm/virtio/virtgpu_object.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c
index 8d7728181de01..c7e74cf130221 100644
--- a/drivers/gpu/drm/virtio/virtgpu_object.c
+++ b/drivers/gpu/drm/virtio/virtgpu_object.c
@@ -184,7 +184,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
struct virtio_gpu_object_array *objs = NULL;
struct drm_gem_shmem_object *shmem_obj;
struct virtio_gpu_object *bo;
- struct virtio_gpu_mem_entry *ents;
+ struct virtio_gpu_mem_entry *ents = NULL;
unsigned int nents;
int ret;
@@ -210,7 +210,7 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
ret = -ENOMEM;
objs = virtio_gpu_array_alloc(1);
if (!objs)
- goto err_put_id;
+ goto err_free_entry;
virtio_gpu_array_add_obj(objs, &bo->base.base);
ret = virtio_gpu_array_lock_resv(objs);
@@ -239,6 +239,8 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
err_put_objs:
virtio_gpu_array_put_free(objs);
+err_free_entry:
+ kvfree(ents);
err_put_id:
virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle);
err_free_gem:
--
GitLab
From 03dec92c4f788c54a7c01b40a018f601eb8a6c52 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Wed, 23 Nov 2022 03:13:03 +0300
Subject: [PATCH 0270/1167] drm/scheduler: Fix lockup in
drm_sched_entity_kill()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The drm_sched_entity_kill() is invoked twice by drm_sched_entity_destroy()
while userspace process is exiting or being killed. First time it's invoked
when sched entity is flushed and second time when entity is released. This
causes a lockup within wait_for_completion(entity_idle) due to how completion
API works.
Calling wait_for_completion() more times than complete() was invoked is a
error condition that causes lockup because completion internally uses
counter for complete/wait calls. The complete_all() must be used instead
in such cases.
This patch fixes lockup of Panfrost driver that is reproducible by killing
any application in a middle of 3d drawing operation.
Fixes: 2fdb8a8f07c2 ("drm/scheduler: rework entity flush, kill and fini")
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck
Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com
---
drivers/gpu/drm/scheduler/sched_entity.c | 2 +-
drivers/gpu/drm/scheduler/sched_main.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index fe09e5be79bdd..15d04a0ec6234 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -81,7 +81,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
init_completion(&entity->entity_idle);
/* We start in an idle state. */
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
spin_lock_init(&entity->rq_lock);
spsc_queue_init(&entity->job_queue);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 31f3a1267be44..fd22d753b4ed0 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -987,7 +987,7 @@ static int drm_sched_main(void *param)
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job) {
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
continue;
}
@@ -998,7 +998,7 @@ static int drm_sched_main(void *param)
trace_drm_run_job(sched_job, entity);
fence = sched->ops->run_job(sched_job);
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
drm_sched_fence_scheduled(s_fence);
if (!IS_ERR_OR_NULL(fence)) {
--
GitLab
From 0a6564ebd953c4590663c9a3c99a3ea9920ade6f Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 29 Dec 2022 13:09:00 +0400
Subject: [PATCH 0271/1167] perf tools: Fix resources leak in
perf_data__open_dir()
In perf_data__open_dir(), opendir() opens the directory stream. Add
missing closedir() to release it after use.
Fixes: eb6176709b235b96 ("perf data: Add perf_data__open_dir_data function")
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221229090903.1402395-1-linmq006@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/data.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index a7f68c309545d..fc16299c915f9 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -132,6 +132,7 @@ int perf_data__open_dir(struct perf_data *data)
file->size = st.st_size;
}
+ closedir(dir);
if (!files)
return -EINVAL;
@@ -140,6 +141,7 @@ int perf_data__open_dir(struct perf_data *data)
return 0;
out_err:
+ closedir(dir);
close_dir(files, nr);
return ret;
}
--
GitLab
From f685dd7a8025f2554f73748cfdb8143a21fb92c7 Mon Sep 17 00:00:00 2001
From: Paul Menzel <pmenzel@molgen.mpg.de>
Date: Mon, 2 Jan 2023 14:57:30 +0100
Subject: [PATCH 0272/1167] fbdev: matroxfb: G200eW: Increase max memory from 1
MB to 16 MB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit 62d89a7d49af ("video: fbdev: matroxfb: set maxvram of vbG200eW to
the same as vbG200 to avoid black screen") accidently decreases the
maximum memory size for the Matrox G200eW (102b:0532) from 8 MB to 1 MB
by missing one zero. This caused the driver initialization to fail with
the messages below, as the minimum required VRAM size is 2 MB:
[ 9.436420] matroxfb: Matrox MGA-G200eW (PCI) detected
[ 9.444502] matroxfb: cannot determine memory size
[ 9.449316] matroxfb: probe of 0000:0a:03.0 failed with error -1
So, add the missing 0 to make it the intended 16 MB. Successfully tested on
the Dell PowerEdge R910/0KYD3D, BIOS 2.10.0 08/29/2013, that the warning is
gone.
While at it, add a leading 0 to the maxdisplayable entry, so it’s aligned
properly. The value could probably also be increased from 8 MB to 16 MB, as
the G200 uses the same values, but I have not checked any datasheet.
Note, matroxfb is obsolete and superseded by the maintained DRM driver
mga200, which is used by default on most systems where both drivers are
available. Therefore, on most systems it was only a cosmetic issue.
Fixes: 62d89a7d49af ("video: fbdev: matroxfb: set maxvram of vbG200eW to the same as vbG200 to avoid black screen")
Link: https://lore.kernel.org/linux-fbdev/972999d3-b75d-5680-fcef-6e6905c52ac5@suse.de/T/#mb6953a9995ebd18acc8552f99d6db39787aec775
Cc: it+linux-fbdev@molgen.mpg.de
Cc: Z. Liu <liuzx@knownsec.com>
Cc: Rich Felker <dalias@libc.org>
Cc: stable@vger.kernel.org
Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
drivers/video/fbdev/matrox/matroxfb_base.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/video/fbdev/matrox/matroxfb_base.c b/drivers/video/fbdev/matrox/matroxfb_base.c
index 0d3cee7ae7268..a043a737ea9f7 100644
--- a/drivers/video/fbdev/matrox/matroxfb_base.c
+++ b/drivers/video/fbdev/matrox/matroxfb_base.c
@@ -1378,8 +1378,8 @@ static struct video_board vbG200 = {
.lowlevel = &matrox_G100
};
static struct video_board vbG200eW = {
- .maxvram = 0x100000,
- .maxdisplayable = 0x800000,
+ .maxvram = 0x1000000,
+ .maxdisplayable = 0x0800000,
.accelID = FB_ACCEL_MATROX_MGAG200,
.lowlevel = &matrox_G100
};
--
GitLab
From a8f54d940196c8bd9aced9c82557fdc63baefb02 Mon Sep 17 00:00:00 2001
From: Eric Lin <eric.lin@sifive.com>
Date: Sat, 31 Dec 2022 05:27:31 +0000
Subject: [PATCH 0273/1167] perf tools riscv: Fix build error on riscv due to
missing header for 'struct perf_sample'
Since the definition of 'struct perf_sample' has been moved to sample.h,
we need to include this header file to fix the build error as follows:
arch/riscv/util/unwind-libdw.c: In function 'libdw__arch_set_initial_registers':
arch/riscv/util/unwind-libdw.c:12:50: error: invalid use of undefined type 'struct perf_sample'
12 | struct regs_dump *user_regs = &ui->sample->user_regs;
| ^~
Fixes: 9823147da6c893d9 ("perf tools: Move 'struct perf_sample' to a separate header file to disentangle headers")
Signed-off-by: Eric Lin <eric.lin@sifive.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: greentime.hu@sifive.com
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: linux-riscv@lists.infradead.org
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Chen <vincent.chen@sifive.com>
Link: https://lore.kernel.org/r/20221231052731.24908-1-eric.lin@sifive.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/arch/riscv/util/unwind-libdw.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/arch/riscv/util/unwind-libdw.c b/tools/perf/arch/riscv/util/unwind-libdw.c
index 19536e1728507..54a198714eb82 100644
--- a/tools/perf/arch/riscv/util/unwind-libdw.c
+++ b/tools/perf/arch/riscv/util/unwind-libdw.c
@@ -4,7 +4,7 @@
#include <elfutils/libdwfl.h>
#include "../../util/unwind-libdw.h"
#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../util/sample.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
--
GitLab
From 55c41f2e4f7e81e48f3ecc9fba1e316e770213f2 Mon Sep 17 00:00:00 2001
From: Yang Jihong <yangjihong1@huawei.com>
Date: Mon, 26 Dec 2022 08:57:03 +0000
Subject: [PATCH 0274/1167] perf help: Use HAVE_LIBTRACEEVENT to filter out
unsupported commands
Commands such as kmem, kwork, lock, sched, trace and timechart depend on
libtraceevent, these commands need to be isolated using HAVE_LIBTRACEEVENT
macro when cmdlist generation.
The output of the generate-cmdlist.sh script is as follows:
# ./util/generate-cmdlist.sh
/* Automatically generated by ./util/generate-cmdlist.sh */
struct cmdname_help
{
char name[16];
char help[80];
};
static struct cmdname_help common_cmds[] = {
{"annotate", "Read perf.data (created by perf record) and display annotated code"},
{"archive", "Create archive with object files with build-ids found in perf.data file"},
{"bench", "General framework for benchmark suites"},
{"buildid-cache", "Manage build-id cache."},
{"buildid-list", "List the buildids in a perf.data file"},
{"c2c", "Shared Data C2C/HITM Analyzer."},
{"config", "Get and set variables in a configuration file."},
{"daemon", "Run record sessions on background"},
{"data", "Data file related processing"},
{"diff", "Read perf.data files and display the differential profile"},
{"evlist", "List the event names in a perf.data file"},
{"ftrace", "simple wrapper for kernel's ftrace functionality"},
{"inject", "Filter to augment the events stream with additional information"},
{"iostat", "Show I/O performance metrics"},
{"kallsyms", "Searches running kernel for symbols"},
{"kvm", "Tool to trace/measure kvm guest os"},
{"list", "List all symbolic event types"},
{"mem", "Profile memory accesses"},
{"record", "Run a command and record its profile into perf.data"},
{"report", "Read perf.data (created by perf record) and display the profile"},
{"script", "Read perf.data (created by perf record) and display trace output"},
{"stat", "Run a command and gather performance counter statistics"},
{"test", "Runs sanity tests."},
{"top", "System profiling tool."},
{"version", "display the version of perf binary"},
#ifdef HAVE_LIBELF_SUPPORT
{"probe", "Define new dynamic tracepoints"},
#endif /* HAVE_LIBELF_SUPPORT */
#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))
{"trace", "strace inspired tool"},
#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */
#ifdef HAVE_LIBTRACEEVENT
{"kmem", "Tool to trace/measure kernel memory properties"},
{"kwork", "Tool to trace/measure kernel work properties (latencies)"},
{"lock", "Analyze lock events"},
{"sched", "Tool to trace/measure scheduler properties (latencies)"},
{"timechart", "Tool to visualize total system behavior during a workload"},
#endif /* HAVE_LIBTRACEEVENT */
};
Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system")
Signed-off-by: Yang Jihong <yangjihong1@huawei.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221226085703.95081-1-yangjihong1@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/command-list.txt | 10 +++++-----
tools/perf/util/generate-cmdlist.sh | 19 +++++++++++++++++--
2 files changed, 22 insertions(+), 7 deletions(-)
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 8fcab5ad00c5c..e8d2762adade1 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -16,20 +16,20 @@ perf-ftrace mainporcelain common
perf-inject mainporcelain common
perf-iostat mainporcelain common
perf-kallsyms mainporcelain common
-perf-kmem mainporcelain common
+perf-kmem mainporcelain traceevent
perf-kvm mainporcelain common
-perf-kwork mainporcelain common
+perf-kwork mainporcelain traceevent
perf-list mainporcelain common
-perf-lock mainporcelain common
+perf-lock mainporcelain traceevent
perf-mem mainporcelain common
perf-probe mainporcelain full
perf-record mainporcelain common
perf-report mainporcelain common
-perf-sched mainporcelain common
+perf-sched mainporcelain traceevent
perf-script mainporcelain common
perf-stat mainporcelain common
perf-test mainporcelain common
-perf-timechart mainporcelain common
+perf-timechart mainporcelain traceevent
perf-top mainporcelain common
perf-trace mainporcelain audit
perf-version mainporcelain common
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index c3cef36d41768..1b5140e5ce997 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@ do
done
echo "#endif /* HAVE_LIBELF_SUPPORT */"
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
+echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))"
sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt |
sort |
while read cmd
@@ -51,5 +51,20 @@ do
p
}' "Documentation/perf-$cmd.txt"
done
-echo "#endif /* HAVE_LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */"
+
+echo "#ifdef HAVE_LIBTRACEEVENT"
+sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+ sed -n '
+ /^NAME/,/perf-'"$cmd"'/H
+ ${
+ x
+ s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBTRACEEVENT */"
echo "};"
--
GitLab
From 8509419758f2cc28dd05370385af0d91573b76b4 Mon Sep 17 00:00:00 2001
From: Samuel Holland <samuel@sholland.org>
Date: Tue, 9 Aug 2022 21:25:09 -0500
Subject: [PATCH 0275/1167] mmc: sunxi-mmc: Fix clock refcount imbalance during
unbind
If the controller is suspended by runtime PM, the clock is already
disabled, so do not try to disable it again during removal. Use
pm_runtime_disable() to flush any pending runtime PM transitions.
Fixes: 9a8e1e8cc2c0 ("mmc: sunxi: Add runtime_pm support")
Signed-off-by: Samuel Holland <samuel@sholland.org>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20220810022509.43743-1-samuel@sholland.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
drivers/mmc/host/sunxi-mmc.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index b16e12e62e722..3db9f32d6a7b9 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -1492,9 +1492,11 @@ static int sunxi_mmc_remove(struct platform_device *pdev)
struct sunxi_mmc_host *host = mmc_priv(mmc);
mmc_remove_host(mmc);
- pm_runtime_force_suspend(&pdev->dev);
- disable_irq(host->irq);
- sunxi_mmc_disable(host);
+ pm_runtime_disable(&pdev->dev);
+ if (!pm_runtime_status_suspended(&pdev->dev)) {
+ disable_irq(host->irq);
+ sunxi_mmc_disable(host);
+ }
dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma);
mmc_free_host(mmc);
--
GitLab
From 92d43bd3bc9728c1fb114d7011d46f5ea9489e28 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Tue, 8 Nov 2022 15:14:20 +0100
Subject: [PATCH 0276/1167] drm/imx: ipuv3-plane: Fix overlay plane width
ipu_src_rect_width() was introduced to support odd screen resolutions
such as 1366x768 by internally rounding up primary plane width to a
multiple of 8 and compensating with reduced horizontal blanking.
This also caused overlay plane width to be rounded up, which was not
intended. Fix overlay plane width by limiting the rounding up to the
primary plane.
drm_rect_width(&new_state->src) >> 16 is the same value as
drm_rect_width(dst) because there is no plane scaling support.
Fixes: 94dfec48fca7 ("drm/imx: Add 8 pixel alignment fix")
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Link: https://lore.kernel.org/r/20221108141420.176696-1-p.zabel@pengutronix.de
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20221108141420.176696-1-p.zabel@pengutronix.de
Tested-by: Ian Ray <ian.ray@ge.com>
(cherry picked from commit 4333472f8d7befe62359fecb1083cd57a6e07bfc)
Signed-off-by: Philipp Zabel <philipp.zabel@gmail.com>
---
drivers/gpu/drm/imx/ipuv3-plane.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index dba4f7d81d693..80142d9a4a552 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -614,6 +614,11 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
break;
}
+ if (ipu_plane->dp_flow == IPU_DP_FLOW_SYNC_BG)
+ width = ipu_src_rect_width(new_state);
+ else
+ width = drm_rect_width(&new_state->src) >> 16;
+
eba = drm_plane_state_to_eba(new_state, 0);
/*
@@ -622,8 +627,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
*/
if (ipu_state->use_pre) {
axi_id = ipu_chan_assign_axi_id(ipu_plane->dma);
- ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id,
- ipu_src_rect_width(new_state),
+ ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, width,
drm_rect_height(&new_state->src) >> 16,
fb->pitches[0], fb->format->format,
fb->modifier, &eba);
@@ -678,9 +682,8 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
break;
}
- ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8));
+ ipu_dmfc_config_wait4eot(ipu_plane->dmfc, width);
- width = ipu_src_rect_width(new_state);
height = drm_rect_height(&new_state->src) >> 16;
info = drm_format_info(fb->format->format);
ipu_calculate_bursts(width, info->cpp[0], fb->pitches[0],
@@ -744,8 +747,7 @@ static void ipu_plane_atomic_update(struct drm_plane *plane,
ipu_cpmem_set_burstsize(ipu_plane->ipu_ch, 16);
ipu_cpmem_zero(ipu_plane->alpha_ch);
- ipu_cpmem_set_resolution(ipu_plane->alpha_ch,
- ipu_src_rect_width(new_state),
+ ipu_cpmem_set_resolution(ipu_plane->alpha_ch, width,
drm_rect_height(&new_state->src) >> 16);
ipu_cpmem_set_format_passthrough(ipu_plane->alpha_ch, 8);
ipu_cpmem_set_high_priority(ipu_plane->alpha_ch);
--
GitLab
From f24fb53984cfba42ff72a47466eabfd772da647b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ahelenia=20Ziemia=C5=84ska?=
<nabijaczleweli@nabijaczleweli.xyz>
Date: Tue, 27 Dec 2022 21:58:00 +0100
Subject: [PATCH 0277/1167] perf tools: Don't include signature in version
strings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This explodes the build if HEAD is signed, since the generated version
is gpg: Signature made Mon 26 Dec 2022 20:34:48 CET, then a few more
lines, then the SHA.
Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/7c9637711271f50ec2341fb8a7c29585335dab04.1672174189.git.nabijaczleweli@nabijaczleweli.xyz
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/Makefile | 2 +-
tools/perf/util/PERF-VERSION-GEN | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index 6e7b88917ca0a..ba5d942e4c6aa 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -267,7 +267,7 @@ $(OUTPUT)%.xml : %.txt
$(ASCIIDOC) -b docbook -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
-aperf_date=$(shell git log -1 --pretty="format:%cd" \
- --date=short $<) \
+ --date=short --no-show-signature $<) \
-o $@+ $< && \
mv $@+ $@
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 3cc42821d9b39..d7dc7c28508c0 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -19,7 +19,7 @@ TAG=
if test -d ../../.git -o -f ../../.git
then
TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
- CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+ CID=$(git log -1 --abbrev=12 --pretty=format:"%h" --no-show-signature 2>/dev/null) && CID="-g$CID"
elif test -f ../../PERF-VERSION-FILE
then
TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
--
GitLab
From cad853374d85fe678d721512cecfabd7636e51f3 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 13 Dec 2022 13:08:26 -0500
Subject: [PATCH 0278/1167] nfsd: fix handling of readdir in v4root vs. mount
upcall timeout
If v4 READDIR operation hits a mountpoint and gets back an error,
then it will include that entry in the reply and set RDATTR_ERROR for it
to the error.
That's fine for "normal" exported filesystems, but on the v4root, we
need to be more careful to only expose the existence of dentries that
lead to exports.
If the mountd upcall times out while checking to see whether a
mountpoint on the v4root is exported, then we have no recourse other
than to fail the whole operation.
Cc: Steve Dickson <steved@redhat.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216777
Reported-by: JianHong Yin <yin-jianhong@163.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Cc: <stable@vger.kernel.org>
---
fs/nfsd/nfs4xdr.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2b4ae858c89be..ebb4d02a42ce6 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3629,6 +3629,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
case nfserr_noent:
xdr_truncate_encode(xdr, start_offset);
goto skip_entry;
+ case nfserr_jukebox:
+ /*
+ * The pseudoroot should only display dentries that lead to
+ * exports. If we get EJUKEBOX here, then we can't tell whether
+ * this entry should be included. Just fail the whole READDIR
+ * with NFS4ERR_DELAY in that case, and hope that the situation
+ * will resolve itself by the client's next attempt.
+ */
+ if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT)
+ goto fail;
+ fallthrough;
default:
/*
* If the client requested the RDATTR_ERROR attribute,
--
GitLab
From 77fe30fed1c0cd282eadb0728999ea3d3350e0b0 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 2 Jan 2023 13:06:45 -0300
Subject: [PATCH 0279/1167] perf tools: Fix segfault when trying to process
tracepoints in perf.data and not linked with libtraceevent
When we have a perf.data file with tracepoints, such as:
# perf evlist -f
probe_perf:lzma_decompress_to_file
# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events
#
We end up segfaulting when using perf built with NO_LIBTRACEEVENT=1 by
trying to find an evsel with a NULL 'event_name' variable:
(gdb) run report --stdio -f
Starting program: /root/bin/perf report --stdio -f
Program received signal SIGSEGV, Segmentation fault.
0x000000000055219d in find_evsel (evlist=0xfda7b0, event_name=0x0) at util/sort.c:2830
warning: Source file is more recent than executable.
2830 if (event_name[0] == '%') {
Missing separate debuginfos, use: dnf debuginfo-install bzip2-libs-1.0.8-11.fc36.x86_64 cyrus-sasl-lib-2.1.27-18.fc36.x86_64 elfutils-debuginfod-client-0.188-3.fc36.x86_64 elfutils-libelf-0.188-3.fc36.x86_64 elfutils-libs-0.188-3.fc36.x86_64 glibc-2.35-20.fc36.x86_64 keyutils-libs-1.6.1-4.fc36.x86_64 krb5-libs-1.19.2-12.fc36.x86_64 libbrotli-1.0.9-7.fc36.x86_64 libcap-2.48-4.fc36.x86_64 libcom_err-1.46.5-2.fc36.x86_64 libcurl-7.82.0-12.fc36.x86_64 libevent-2.1.12-6.fc36.x86_64 libgcc-12.2.1-4.fc36.x86_64 libidn2-2.3.4-1.fc36.x86_64 libnghttp2-1.51.0-1.fc36.x86_64 libpsl-0.21.1-5.fc36.x86_64 libselinux-3.3-4.fc36.x86_64 libssh-0.9.6-4.fc36.x86_64 libstdc++-12.2.1-4.fc36.x86_64 libunistring-1.0-1.fc36.x86_64 libunwind-1.6.2-2.fc36.x86_64 libxcrypt-4.4.33-4.fc36.x86_64 libzstd-1.5.2-2.fc36.x86_64 numactl-libs-2.0.14-5.fc36.x86_64 opencsd-1.2.0-1.fc36.x86_64 openldap-2.6.3-1.fc36.x86_64 openssl-libs-3.0.5-2.fc36.x86_64 slang-2.3.2-11.fc36.x86_64 xz-libs-5.2.5-9.fc36.x86_64 zlib-1.2.11-33.fc36.x86_64
(gdb) bt
#0 0x000000000055219d in find_evsel (evlist=0xfda7b0, event_name=0x0) at util/sort.c:2830
#1 0x0000000000552416 in add_dynamic_entry (evlist=0xfda7b0, tok=0xffb6eb "trace", level=2) at util/sort.c:2976
#2 0x0000000000552d26 in sort_dimension__add (list=0xf93e00 <perf_hpp_list>, tok=0xffb6eb "trace", evlist=0xfda7b0, level=2) at util/sort.c:3193
#3 0x0000000000552e1c in setup_sort_list (list=0xf93e00 <perf_hpp_list>, str=0xffb6eb "trace", evlist=0xfda7b0) at util/sort.c:3227
#4 0x00000000005532fa in __setup_sorting (evlist=0xfda7b0) at util/sort.c:3381
#5 0x0000000000553cdc in setup_sorting (evlist=0xfda7b0) at util/sort.c:3608
#6 0x000000000042eb9f in cmd_report (argc=0, argv=0x7fffffffe470) at builtin-report.c:1596
#7 0x00000000004aee7e in run_builtin (p=0xf64ca0 <commands+288>, argc=3, argv=0x7fffffffe470) at perf.c:330
#8 0x00000000004af0f2 in handle_internal_command (argc=3, argv=0x7fffffffe470) at perf.c:384
#9 0x00000000004af241 in run_argv (argcp=0x7fffffffe29c, argv=0x7fffffffe290) at perf.c:428
#10 0x00000000004af5fc in main (argc=3, argv=0x7fffffffe470) at perf.c:562
(gdb)
So check if we have tracepoint events in add_dynamic_entry() and bail
out instead:
# perf report --stdio -f
This perf binary isn't linked with libtraceevent, can't process probe_perf:lzma_decompress_to_file
Error:
Unknown --sort key: `trace'
#
Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system")
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/Y7MDb7kRaHZB6APC@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/sort.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index e188f74698dd3..37662cdec5eef 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2971,6 +2971,18 @@ static int add_dynamic_entry(struct evlist *evlist, const char *tok,
ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
goto out;
}
+#else
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
+ pr_err("%s %s", ret ? "," : "This perf binary isn't linked with libtraceevent, can't process", evsel__name(evsel));
+ ret = -ENOTSUP;
+ }
+ }
+
+ if (ret) {
+ pr_err("\n");
+ goto out;
+ }
#endif
evsel = find_evsel(evlist, event_name);
--
GitLab
From 5b24ac2dfd3eb3e36f794af3aa7f2828b19035bd Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Thu, 22 Dec 2022 23:28:21 -0800
Subject: [PATCH 0280/1167] kcsan: test: don't put the expect array on the
stack
Size of the 'expect' array in the __report_matches is 1536 bytes, which
is exactly the default frame size warning limit of the xtensa
architecture.
As a result allmodconfig xtensa kernel builds with the gcc that does not
support the compiler plugins (which otherwise would push the said
warning limit to 2K) fail with the following message:
kernel/kcsan/kcsan_test.c:257:1: error: the frame size of 1680 bytes
is larger than 1536 bytes
Fix it by dynamically allocating the 'expect' array.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Reviewed-by: Marco Elver <elver@google.com>
Tested-by: Marco Elver <elver@google.com>
---
kernel/kcsan/kcsan_test.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index dcec1b743c694..a60c561724be9 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -159,7 +159,7 @@ static bool __report_matches(const struct expect_report *r)
const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT;
bool ret = false;
unsigned long flags;
- typeof(observed.lines) expect;
+ typeof(*observed.lines) *expect;
const char *end;
char *cur;
int i;
@@ -168,6 +168,10 @@ static bool __report_matches(const struct expect_report *r)
if (!report_available())
return false;
+ expect = kmalloc(sizeof(observed.lines), GFP_KERNEL);
+ if (WARN_ON(!expect))
+ return false;
+
/* Generate expected report contents. */
/* Title */
@@ -253,6 +257,7 @@ static bool __report_matches(const struct expect_report *r)
strstr(observed.lines[2], expect[1])));
out:
spin_unlock_irqrestore(&observed.lock, flags);
+ kfree(expect);
return ret;
}
--
GitLab
From d00dd2f2645dca04cf399d8fc692f3f69b6dd996 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 22 Nov 2022 12:51:22 +0100
Subject: [PATCH 0281/1167] x86/kexec: Fix double-free of elf header buffer
After
b3e34a47f989 ("x86/kexec: fix memory leak of elf header buffer"),
freeing image->elf_headers in the error path of crash_load_segments()
is not needed because kimage_file_post_load_cleanup() will take
care of that later. And not clearing it could result in a double-free.
Drop the superfluous vfree() call at the error path of
crash_load_segments().
Fixes: b3e34a47f989 ("x86/kexec: fix memory leak of elf header buffer")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Baoquan He <bhe@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20221122115122.13937-1-tiwai@suse.de
---
arch/x86/kernel/crash.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 9730c88530fc8..305514431f26e 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -401,10 +401,8 @@ int crash_load_segments(struct kimage *image)
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
- if (ret) {
- vfree((void *)image->elf_headers);
+ if (ret)
return ret;
- }
image->elf_load_addr = kbuf.mem;
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
--
GitLab
From 0226635c304cfd5c9db9b78c259cb713819b057e Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Mon, 2 Jan 2023 23:05:33 +0900
Subject: [PATCH 0282/1167] fs/ntfs3: don't hold ni_lock when calling
truncate_setsize()
syzbot is reporting hung task at do_user_addr_fault() [1], for there is
a silent deadlock between PG_locked bit and ni_lock lock.
Since filemap_update_page() calls filemap_read_folio() after calling
folio_trylock() which will set PG_locked bit, ntfs_truncate() must not
call truncate_setsize() which will wait for PG_locked bit to be cleared
when holding ni_lock lock.
Link: https://lore.kernel.org/all/00000000000060d41f05f139aa44@google.com/
Link: https://syzkaller.appspot.com/bug?extid=bed15dbf10294aa4f2ae [1]
Reported-by: syzbot <syzbot+bed15dbf10294aa4f2ae@syzkaller.appspotmail.com>
Debugged-by: Linus Torvalds <torvalds@linux-foundation.org>
Co-developed-by: Hillf Danton <hdanton@sina.com>
Signed-off-by: Hillf Danton <hdanton@sina.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Fixes: 4342306f0f0d ("fs/ntfs3: Add file operations and implementation")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
fs/ntfs3/file.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index e5399ebc3a2b2..d294cd9756887 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -390,10 +390,10 @@ static int ntfs_truncate(struct inode *inode, loff_t new_size)
new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size));
- ni_lock(ni);
-
truncate_setsize(inode, new_size);
+ ni_lock(ni);
+
down_write(&ni->file.run_lock);
err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size,
&new_valid, ni->mi.sbi->options->prealloc, NULL);
--
GitLab
From af82425c6a2d2f347c79b63ce74fca6dc6be157f Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 2 Jan 2023 16:49:46 -0700
Subject: [PATCH 0283/1167] io_uring/io-wq: free worker if task_work creation
is canceled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If we cancel the task_work, the worker will never come into existance.
As this is the last reference to it, ensure that we get it freed
appropriately.
Cc: stable@vger.kernel.org
Reported-by: 진호 <wnwlsgh98@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io-wq.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 6f1d0e5df23ad..992dcd9f8c4cf 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1230,6 +1230,7 @@ static void io_wq_cancel_tw_create(struct io_wq *wq)
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
+ kfree(worker);
}
}
--
GitLab
From 9c807965483f42df1d053b7436eedd6cf28ece6f Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Mon, 2 Jan 2023 12:53:35 +0300
Subject: [PATCH 0284/1167] drivers/net/bonding/bond_3ad: return when there's
no aggregator
Otherwise we would dereference a NULL aggregator pointer when calling
__set_agg_ports_ready on the line below.
Found by Linux Verification Center (linuxtesting.org) with the SVACE
static analysis tool.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/bonding/bond_3ad.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 455b555275f12..c99ffe6c683a3 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -1549,6 +1549,7 @@ static void ad_port_selection_logic(struct port *port, bool *update_slave_arr)
slave_err(bond->dev, port->slave->dev,
"Port %d did not find a suitable aggregator\n",
port->actor_port_number);
+ return;
}
}
/* if all aggregator's ports are READY_N == TRUE, set ready=TRUE
--
GitLab
From 4af1b64f80fbe1275fb02c5f1c0cef099a4a231f Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Tue, 3 Jan 2023 09:20:12 +0530
Subject: [PATCH 0285/1167] octeontx2-pf: Fix lmtst ID used in aura free
Current code uses per_cpu pointer to get the lmtst_id mapped to
the core on which aura_free() is executed. Using per_cpu pointer
without preemption disable causing mismatch between lmtst_id and
core on which pointer gets freed. This patch fixes the issue by
disabling preemption around aura_free.
Fixes: ef6c8da71eaf ("octeontx2-pf: cn10K: Reserve LMTST lines per core")
Signed-off-by: Sunil Goutham <sgoutham@marvell.com>
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../marvell/octeontx2/nic/otx2_common.c | 30 +++++++++++++------
1 file changed, 21 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 9e10e7471b887..88f8772a61cd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1012,6 +1012,7 @@ static void otx2_pool_refill_task(struct work_struct *work)
rbpool = cq->rbpool;
free_ptrs = cq->pool_ptrs;
+ get_cpu();
while (cq->pool_ptrs) {
if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
/* Schedule a WQ if we fails to free atleast half of the
@@ -1031,6 +1032,7 @@ static void otx2_pool_refill_task(struct work_struct *work)
pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
cq->pool_ptrs--;
}
+ put_cpu();
cq->refill_task_sched = false;
}
@@ -1368,6 +1370,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
if (err)
goto fail;
+ get_cpu();
/* Allocate pointers and free them to aura/pool */
for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) {
pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx);
@@ -1376,18 +1379,24 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
sq = &qset->sq[qidx];
sq->sqb_count = 0;
sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
- if (!sq->sqb_ptrs)
- return -ENOMEM;
+ if (!sq->sqb_ptrs) {
+ err = -ENOMEM;
+ goto err_mem;
+ }
for (ptr = 0; ptr < num_sqbs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
- return -ENOMEM;
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
+ goto err_mem;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
}
}
- return 0;
+err_mem:
+ put_cpu();
+ return err ? -ENOMEM : 0;
+
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
@@ -1426,18 +1435,21 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
if (err)
goto fail;
+ get_cpu();
/* Allocate pointers and free them to aura/pool */
for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
pool = &pfvf->qset.pool[pool_id];
for (ptr = 0; ptr < num_ptrs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
- return -ENOMEM;
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
+ goto err_mem;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
bufptr + OTX2_HEAD_ROOM);
}
}
-
- return 0;
+err_mem:
+ put_cpu();
+ return err ? -ENOMEM : 0;
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
--
GitLab
From 7dc61838541928895abae6d2355258e02a251bba Mon Sep 17 00:00:00 2001
From: Sean Anderson <seanga2@gmail.com>
Date: Tue, 3 Jan 2023 01:50:38 -0500
Subject: [PATCH 0286/1167] net: dpaa: Fix dtsec check for PCS availability
We want to fail if the PCS is not available, not if it is available. Fix
this condition.
Fixes: 5d93cfcf7360 ("net: dpaa: Convert to phylink")
Reported-by: Christian Zigotzky <info@xenosoft.de>
Signed-off-by: Sean Anderson <seanga2@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/freescale/fman/fman_dtsec.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index d00bae15a9017..d528ca681b6f4 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -1430,7 +1430,7 @@ int dtsec_initialization(struct mac_device *mac_dev,
dtsec->dtsec_drv_param->tx_pad_crc = true;
phy_node = of_parse_phandle(mac_node, "tbi-handle", 0);
- if (!phy_node || of_device_is_available(phy_node)) {
+ if (!phy_node || !of_device_is_available(phy_node)) {
of_node_put(phy_node);
err = -EINVAL;
dev_err_probe(mac_dev->dev, err,
--
GitLab
From c7dd13805f8b8fc1ce3b6d40f6aff47e66b72ad2 Mon Sep 17 00:00:00 2001
From: Szymon Heidrich <szymon.heidrich@gmail.com>
Date: Tue, 3 Jan 2023 10:17:09 +0100
Subject: [PATCH 0287/1167] usb: rndis_host: Secure rndis_query check against
int overflow
Variables off and len typed as uint32 in rndis_query function
are controlled by incoming RNDIS response message thus their
value may be manipulated. Setting off to a unexpectetly large
value will cause the sum with len and 8 to overflow and pass
the implemented validation step. Consequently the response
pointer will be referring to a location past the expected
buffer boundaries allowing information leakage e.g. via
RNDIS_OID_802_3_PERMANENT_ADDRESS OID.
Fixes: ddda08624013 ("USB: rndis_host, various cleanups")
Signed-off-by: Szymon Heidrich <szymon.heidrich@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/usb/rndis_host.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index f79333fe17836..7b3739b29c8f7 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -255,7 +255,8 @@ static int rndis_query(struct usbnet *dev, struct usb_interface *intf,
off = le32_to_cpu(u.get_c->offset);
len = le32_to_cpu(u.get_c->len);
- if (unlikely((8 + off + len) > CONTROL_BUFFER_SIZE))
+ if (unlikely((off > CONTROL_BUFFER_SIZE - 8) ||
+ (len > CONTROL_BUFFER_SIZE - 8 - off)))
goto response_error;
if (*reply_len != -1 && len != *reply_len)
--
GitLab
From 703c13fe3c9af557d312f5895ed6a5fda2711104 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 19 Dec 2022 10:10:04 +0100
Subject: [PATCH 0288/1167] efi: fix NULL-deref in init error path
In cases where runtime services are not supported or have been disabled,
the runtime services workqueue will never have been allocated.
Do not try to destroy the workqueue unconditionally in the unlikely
event that EFI initialisation fails to avoid dereferencing a NULL
pointer.
Fixes: 98086df8b70c ("efi: add missed destroy_workqueue when efisubsys_init fails")
Cc: stable@vger.kernel.org
Cc: Li Heng <liheng40@huawei.com>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/efi.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 09716eebe8ac3..a2b0cbc8741c2 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -394,8 +394,8 @@ static int __init efisubsys_init(void)
efi_kobj = kobject_create_and_add("efi", firmware_kobj);
if (!efi_kobj) {
pr_err("efi: Firmware registration failed.\n");
- destroy_workqueue(efi_rts_wq);
- return -ENOMEM;
+ error = -ENOMEM;
+ goto err_destroy_wq;
}
if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
@@ -443,7 +443,10 @@ static int __init efisubsys_init(void)
err_put:
kobject_put(efi_kobj);
efi_kobj = NULL;
- destroy_workqueue(efi_rts_wq);
+err_destroy_wq:
+ if (efi_rts_wq)
+ destroy_workqueue(efi_rts_wq);
+
return error;
}
--
GitLab
From e006ac3003080177cf0b673441a4241f77aaecce Mon Sep 17 00:00:00 2001
From: Ding Hui <dinghui@sangfor.com.cn>
Date: Tue, 27 Dec 2022 23:09:36 +0800
Subject: [PATCH 0289/1167] efi: fix userspace infinite retry read efivars
after EFI runtime services page fault
After [1][2], if we catch exceptions due to EFI runtime service, we will
clear EFI_RUNTIME_SERVICES bit to disable EFI runtime service, then the
subsequent routine which invoke the EFI runtime service should fail.
But the userspace cat efivars through /sys/firmware/efi/efivars/ will stuck
and infinite loop calling read() due to efivarfs_file_read() return -EINTR.
The -EINTR is converted from EFI_ABORTED by efi_status_to_err(), and is
an improper return value in this situation, so let virt_efi_xxx() return
EFI_DEVICE_ERROR and converted to -EIO to invoker.
Cc: <stable@vger.kernel.org>
Fixes: 3425d934fc03 ("efi/x86: Handle page faults occurring while running EFI runtime services")
Fixes: 23715a26c8d8 ("arm64: efi: Recover from synchronous exceptions occurring in firmware")
Signed-off-by: Ding Hui <dinghui@sangfor.com.cn>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
drivers/firmware/efi/runtime-wrappers.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index 7feee3d9c2bfb..1fba4e09cdcff 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -62,6 +62,7 @@ struct efi_runtime_work efi_rts_work;
\
if (!efi_enabled(EFI_RUNTIME_SERVICES)) { \
pr_warn_once("EFI Runtime Services are disabled!\n"); \
+ efi_rts_work.status = EFI_DEVICE_ERROR; \
goto exit; \
} \
\
--
GitLab
From 406504c7b0405d74d74c15a667cd4c4620c3e7a9 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 20 Dec 2022 14:03:52 +0000
Subject: [PATCH 0290/1167] KVM: arm64: Fix S1PTW handling on RO memslots
A recent development on the EFI front has resulted in guests having
their page tables baked in the firmware binary, and mapped into the
IPA space as part of a read-only memslot. Not only is this legitimate,
but it also results in added security, so thumbs up.
It is possible to take an S1PTW translation fault if the S1 PTs are
unmapped at stage-2. However, KVM unconditionally treats S1PTW as a
write to correctly handle hardware AF/DB updates to the S1 PTs.
Furthermore, KVM injects an exception into the guest for S1PTW writes.
In the aforementioned case this results in the guest taking an abort
it won't recover from, as the S1 PTs mapping the vectors suffer from
the same problem.
So clearly our handling is... wrong.
Instead, switch to a two-pronged approach:
- On S1PTW translation fault, handle the fault as a read
- On S1PTW permission fault, handle the fault as a write
This is of no consequence to SW that *writes* to its PTs (the write
will trigger a non-S1PTW fault), and SW that uses RO PTs will not
use HW-assisted AF/DB anyway, as that'd be wrong.
Only in the case described in c4ad98e4b72c ("KVM: arm64: Assume write
fault on S1PTW permission fault on instruction fetch") do we end-up
with two back-to-back faults (page being evicted and faulted back).
I don't think this is a case worth optimising for.
Fixes: c4ad98e4b72c ("KVM: arm64: Assume write fault on S1PTW permission fault on instruction fetch")
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Regression-tested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
---
arch/arm64/include/asm/kvm_emulate.h | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 9bdba47f7e149..0d40c48d81329 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -373,8 +373,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_abt_iss1tw(vcpu))
- return true;
+ if (kvm_vcpu_abt_iss1tw(vcpu)) {
+ /*
+ * Only a permission fault on a S1PTW should be
+ * considered as a write. Otherwise, page tables baked
+ * in a read-only memslot will result in an exception
+ * being delivered in the guest.
+ *
+ * The drawback is that we end-up faulting twice if the
+ * guest is using any of HW AF/DB: a translation fault
+ * to map the page containing the PT (read only at
+ * first), then a permission fault to allow the flags
+ * to be set.
+ */
+ switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+ case ESR_ELx_FSC_PERM:
+ return true;
+ default:
+ return false;
+ }
+ }
if (kvm_vcpu_trap_is_iabt(vcpu))
return false;
--
GitLab
From b8f8d190fa8fa1909dda12d771df67125d6fbf0c Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 22 Dec 2022 09:26:31 +0000
Subject: [PATCH 0291/1167] KVM: arm64: Document the behaviour of S1PTW faults
on RO memslots
Although the KVM API says that a write to a RO memslot must result
in a KVM_EXIT_MMIO describing the write, the arm64 architecture
doesn't provide the *data* written by a Stage-1 page table walk
(we only get the address).
Since there isn't much userspace can do with so little information
anyway, document the fact that such an access results in a guest
exception, not an exit. This is consistent with the guest being
terminally broken anyway.
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
Documentation/virt/kvm/api.rst | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 0dd5d8733dd58..42db72a0cbe68 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1354,6 +1354,14 @@ the memory region are automatically reflected into the guest. For example, an
mmap() that affects the region will be made visible immediately. Another
example is madvise(MADV_DROP).
+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.
4.36 KVM_SET_TSS_ADDR
---------------------
--
GitLab
From b0803ba72b558957fdcfe845939ee788b7ce5919 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 20 Dec 2022 14:49:30 +0000
Subject: [PATCH 0292/1167] KVM: arm64: Convert FSC_* over to ESR_ELx_FSC_*
The former is an AArch32 legacy, so let's move over to the
verbose (and strictly identical) version.
This involves moving some of the #defines that were private
to KVM into the more generic esr.h.
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
arch/arm64/include/asm/esr.h | 9 +++++++++
arch/arm64/include/asm/kvm_arm.h | 15 ---------------
arch/arm64/include/asm/kvm_emulate.h | 20 ++++++++++----------
arch/arm64/kvm/hyp/include/hyp/fault.h | 2 +-
arch/arm64/kvm/hyp/include/hyp/switch.h | 2 +-
arch/arm64/kvm/mmu.c | 21 ++++++++++++---------
6 files changed, 33 insertions(+), 36 deletions(-)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 15b34fbfca667..206de10524e33 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -114,6 +114,15 @@
#define ESR_ELx_FSC_ACCESS (0x08)
#define ESR_ELx_FSC_FAULT (0x04)
#define ESR_ELx_FSC_PERM (0x0C)
+#define ESR_ELx_FSC_SEA_TTW0 (0x14)
+#define ESR_ELx_FSC_SEA_TTW1 (0x15)
+#define ESR_ELx_FSC_SEA_TTW2 (0x16)
+#define ESR_ELx_FSC_SEA_TTW3 (0x17)
+#define ESR_ELx_FSC_SECC (0x18)
+#define ESR_ELx_FSC_SECC_TTW0 (0x1c)
+#define ESR_ELx_FSC_SECC_TTW1 (0x1d)
+#define ESR_ELx_FSC_SECC_TTW2 (0x1e)
+#define ESR_ELx_FSC_SECC_TTW3 (0x1f)
/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV_SHIFT (24)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0df3fc3a01737..26b0c97df9863 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -319,21 +319,6 @@
BIT(18) | \
GENMASK(16, 15))
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT ESR_ELx_FSC_FAULT
-#define FSC_ACCESS ESR_ELx_FSC_ACCESS
-#define FSC_PERM ESR_ELx_FSC_PERM
-#define FSC_SEA ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0 (0x14)
-#define FSC_SEA_TTW1 (0x15)
-#define FSC_SEA_TTW2 (0x16)
-#define FSC_SEA_TTW3 (0x17)
-#define FSC_SECC (0x18)
-#define FSC_SECC_TTW0 (0x1c)
-#define FSC_SECC_TTW1 (0x1d)
-#define FSC_SECC_TTW2 (0x1e)
-#define FSC_SECC_TTW3 (0x1f)
-
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
/*
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 0d40c48d81329..193583df2d9c4 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -349,16 +349,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
{
switch (kvm_vcpu_trap_get_fault(vcpu)) {
- case FSC_SEA:
- case FSC_SEA_TTW0:
- case FSC_SEA_TTW1:
- case FSC_SEA_TTW2:
- case FSC_SEA_TTW3:
- case FSC_SECC:
- case FSC_SECC_TTW0:
- case FSC_SECC_TTW1:
- case FSC_SECC_TTW2:
- case FSC_SECC_TTW3:
+ case ESR_ELx_FSC_EXTABT:
+ case ESR_ELx_FSC_SEA_TTW0:
+ case ESR_ELx_FSC_SEA_TTW1:
+ case ESR_ELx_FSC_SEA_TTW2:
+ case ESR_ELx_FSC_SEA_TTW3:
+ case ESR_ELx_FSC_SECC:
+ case ESR_ELx_FSC_SECC_TTW0:
+ case ESR_ELx_FSC_SECC_TTW1:
+ case ESR_ELx_FSC_SECC_TTW2:
+ case ESR_ELx_FSC_SECC_TTW3:
return true;
default:
return false;
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
index 1b8a2dcd712f3..9ddcfe2c3e574 100644
--- a/arch/arm64/kvm/hyp/include/hyp/fault.h
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
*/
if (!(esr & ESR_ELx_S1PTW) &&
(cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 3330d1b76bdd2..07d37ff88a3f2 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
- valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
kvm_vcpu_dabt_isvalid(vcpu) &&
!kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 31d7fa4c7c140..a3ee3b605c9b8 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault);
- if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+ if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
@@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
- if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+ if (fault_status != ESR_ELx_FSC_PERM ||
+ (logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(kvm));
if (ret)
@@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
- if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+ if (fault_status == ESR_ELx_FSC_PERM &&
+ fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
@@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
&fault_ipa);
}
- if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+ if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (kvm_vma_mte_allowed(vma)) {
sanitise_mte_tags(kvm, pfn, vma_pagesize);
@@ -1376,7 +1378,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* permissions only if vma_pagesize equals fault_granule. Otherwise,
* kvm_pgtable_stage2_map() should be called to change block size.
*/
- if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+ if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
else
ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
@@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (fault_status == FSC_FAULT) {
+ if (fault_status == ESR_ELx_FSC_FAULT) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
@@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
- if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
- fault_status != FSC_ACCESS) {
+ if (fault_status != ESR_ELx_FSC_FAULT &&
+ fault_status != ESR_ELx_FSC_PERM &&
+ fault_status != ESR_ELx_FSC_ACCESS) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
@@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
- if (fault_status == FSC_ACCESS) {
+ if (fault_status == ESR_ELx_FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
ret = 1;
goto out_unlock;
--
GitLab
From f3cb80804b8295323919e031281768ba3bf5f8da Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 2 Jan 2023 19:28:49 -0800
Subject: [PATCH 0293/1167] time: Fix various kernel-doc problems
Clean up kernel-doc complaints about function names and non-kernel-doc
comments in kernel/time/. Fixes these warnings:
kernel/time/time.c:479: warning: expecting prototype for set_normalized_timespec(). Prototype was for set_normalized_timespec64() instead
kernel/time/time.c:553: warning: expecting prototype for msecs_to_jiffies(). Prototype was for __msecs_to_jiffies() instead
kernel/time/timekeeping.c:1595: warning: contents before sections
kernel/time/timekeeping.c:1705: warning: This comment starts with '/**', but isn't a kernel-doc comment.
* We have three kinds of time sources to use for sleep time
kernel/time/timekeeping.c:1726: warning: This comment starts with '/**', but isn't a kernel-doc comment.
* 1) can be determined whether to use or not only when doing
kernel/time/tick-oneshot.c:21: warning: missing initial short description on line:
* tick_program_event
kernel/time/tick-oneshot.c:107: warning: expecting prototype for tick_check_oneshot_mode(). Prototype was for tick_oneshot_mode_active() instead
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230103032849.12723-1-rdunlap@infradead.org
---
kernel/time/tick-oneshot.c | 4 ++--
kernel/time/time.c | 8 ++++----
kernel/time/timekeeping.c | 8 ++++----
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 475ecceda7688..5e2c2c26b3cc9 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -18,7 +18,7 @@
#include "tick-internal.h"
/**
- * tick_program_event
+ * tick_program_event - program the CPU local timer device for the next event
*/
int tick_program_event(ktime_t expires, int force)
{
@@ -99,7 +99,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *))
}
/**
- * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ * tick_oneshot_mode_active - check whether the system is in oneshot mode
*
* returns 1 when either nohz or highres are enabled. otherwise 0.
*/
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 526257b3727ca..f4198af60fee5 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -462,7 +462,7 @@ struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec)
EXPORT_SYMBOL(ns_to_kernel_old_timeval);
/**
- * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ * set_normalized_timespec64 - set timespec sec and nsec parts and normalize
*
* @ts: pointer to timespec variable to be set
* @sec: seconds to set
@@ -526,7 +526,7 @@ struct timespec64 ns_to_timespec64(s64 nsec)
EXPORT_SYMBOL(ns_to_timespec64);
/**
- * msecs_to_jiffies: - convert milliseconds to jiffies
+ * __msecs_to_jiffies: - convert milliseconds to jiffies
* @m: time in milliseconds
*
* conversion is done as follows:
@@ -541,12 +541,12 @@ EXPORT_SYMBOL(ns_to_timespec64);
* handling any 32-bit overflows.
* for the details see __msecs_to_jiffies()
*
- * msecs_to_jiffies() checks for the passed in value being a constant
+ * __msecs_to_jiffies() checks for the passed in value being a constant
* via __builtin_constant_p() allowing gcc to eliminate most of the
* code, __msecs_to_jiffies() is called if the value passed does not
* allow constant folding and the actual conversion must be done at
* runtime.
- * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * The _msecs_to_jiffies helpers are the HZ dependent conversion
* routines found in include/linux/jiffies.h
*/
unsigned long __msecs_to_jiffies(const unsigned int m)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f72b9f1de178e..5579ead449f25 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1590,10 +1590,10 @@ void __weak read_persistent_clock64(struct timespec64 *ts)
/**
* read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
* from the boot.
+ * @wall_time: current time as returned by persistent clock
+ * @boot_offset: offset that is defined as wall_time - boot_time
*
* Weak dummy function for arches that do not yet support it.
- * @wall_time: - current time as returned by persistent clock
- * @boot_offset: - offset that is defined as wall_time - boot_time
*
* The default function calculates offset based on the current value of
* local_clock(). This way architectures that support sched_clock() but don't
@@ -1701,7 +1701,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
}
#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
-/**
+/*
* We have three kinds of time sources to use for sleep time
* injection, the preference order is:
* 1) non-stop clocksource
@@ -1722,7 +1722,7 @@ bool timekeeping_rtc_skipresume(void)
return !suspend_timing_needed;
}
-/**
+/*
* 1) can be determined whether to use or not only when doing
* timekeeping_resume() which is invoked after rtc_suspend(),
* so we can't skip rtc_suspend() surely if system has 1).
--
GitLab
From 13678f3feb3009b23aab424864fd0dac0765c83e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 29 Oct 2022 22:56:36 -0700
Subject: [PATCH 0294/1167] reset: ti-sci: honor TI_SCI_PROTOCOL setting when
not COMPILE_TEST
There is a build error when COMPILE_TEST=y, TI_SCI_PROTOCOL=m,
and RESET_TI_SCI=y:
drivers/reset/reset-ti-sci.o: in function `ti_sci_reset_probe':
reset-ti-sci.c:(.text+0x22c): undefined reference to `devm_ti_sci_get_handle'
Fix this by making RESET_TI_SCI honor the Kconfig setting of
TI_SCI_PROTOCOL when COMPILE_TEST is not set. When COMPILE_TEST is set,
TI_SCI_PROTOCOL must be disabled (=n).
Fixes: a6af504184c9 ("reset: ti-sci: Allow building under COMPILE_TEST")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Nishanth Menon <nm@ti.com>
Cc: Tero Kristo <kristo@kernel.org>
Cc: Santosh Shilimkar <ssantosh@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20221030055636.3139-1-rdunlap@infradead.org
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
drivers/reset/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index de176c2fbad96..2a52c990d4fec 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -257,7 +257,7 @@ config RESET_SUNXI
config RESET_TI_SCI
tristate "TI System Control Interface (TI-SCI) reset driver"
- depends on TI_SCI_PROTOCOL || COMPILE_TEST
+ depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n)
help
This enables the reset driver support over TI System Control Interface
available on some new TI's SoCs. If you wish to use reset resources
--
GitLab
From 3a2390c6777e3f6662980c6cfc25cafe9e4fef98 Mon Sep 17 00:00:00 2001
From: Hui Tang <tanghui20@huawei.com>
Date: Mon, 14 Nov 2022 08:49:58 +0800
Subject: [PATCH 0295/1167] reset: uniphier-glue: Fix possible null-ptr-deref
It will cause null-ptr-deref when resource_size(res) invoked,
if platform_get_resource() returns NULL.
Fixes: 499fef09a323 ("reset: uniphier: add USB3 core reset control")
Signed-off-by: Hui Tang <tanghui20@huawei.com>
Reviewed-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Link: https://lore.kernel.org/r/20221114004958.258513-1-tanghui20@huawei.com
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
drivers/reset/reset-uniphier-glue.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/reset/reset-uniphier-glue.c b/drivers/reset/reset-uniphier-glue.c
index 146fd5d45e99d..15abac9fc72c0 100644
--- a/drivers/reset/reset-uniphier-glue.c
+++ b/drivers/reset/reset-uniphier-glue.c
@@ -47,7 +47,6 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev)
struct device *dev = &pdev->dev;
struct uniphier_glue_reset_priv *priv;
struct resource *res;
- resource_size_t size;
int i, ret;
priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -60,7 +59,6 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev)
return -EINVAL;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- size = resource_size(res);
priv->rdata.membase = devm_ioremap_resource(dev, res);
if (IS_ERR(priv->rdata.membase))
return PTR_ERR(priv->rdata.membase);
@@ -96,7 +94,7 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev)
spin_lock_init(&priv->rdata.lock);
priv->rdata.rcdev.owner = THIS_MODULE;
- priv->rdata.rcdev.nr_resets = size * BITS_PER_BYTE;
+ priv->rdata.rcdev.nr_resets = resource_size(res) * BITS_PER_BYTE;
priv->rdata.rcdev.ops = &reset_simple_ops;
priv->rdata.rcdev.of_node = dev->of_node;
priv->rdata.active_low = true;
--
GitLab
From 69555549cfa42e10f2fdd2699ed4e34d9d4f392b Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Date: Wed, 23 Nov 2022 03:13:03 +0300
Subject: [PATCH 0296/1167] drm/scheduler: Fix lockup in
drm_sched_entity_kill()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The drm_sched_entity_kill() is invoked twice by drm_sched_entity_destroy()
while userspace process is exiting or being killed. First time it's invoked
when sched entity is flushed and second time when entity is released. This
causes a lockup within wait_for_completion(entity_idle) due to how completion
API works.
Calling wait_for_completion() more times than complete() was invoked is a
error condition that causes lockup because completion internally uses
counter for complete/wait calls. The complete_all() must be used instead
in such cases.
This patch fixes lockup of Panfrost driver that is reproducible by killing
any application in a middle of 3d drawing operation.
Fixes: 2fdb8a8f07c2 ("drm/scheduler: rework entity flush, kill and fini")
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com> # Steam Deck
Link: https://patchwork.freedesktop.org/patch/msgid/20221123001303.533968-1-dmitry.osipenko@collabora.com
---
drivers/gpu/drm/scheduler/sched_entity.c | 2 +-
drivers/gpu/drm/scheduler/sched_main.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index fe09e5be79bdd..15d04a0ec6234 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -81,7 +81,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
init_completion(&entity->entity_idle);
/* We start in an idle state. */
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
spin_lock_init(&entity->rq_lock);
spsc_queue_init(&entity->job_queue);
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 31f3a1267be44..fd22d753b4ed0 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -987,7 +987,7 @@ static int drm_sched_main(void *param)
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job) {
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
continue;
}
@@ -998,7 +998,7 @@ static int drm_sched_main(void *param)
trace_drm_run_job(sched_job, entity);
fence = sched->ops->run_job(sched_job);
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
drm_sched_fence_scheduled(s_fence);
if (!IS_ERR_OR_NULL(fence)) {
--
GitLab
From b963c1d6261eb7fba1ba14074fb447521be84add Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 3 Jan 2023 10:21:01 -0300
Subject: [PATCH 0297/1167] perf test record_probe_libc_inet_pton: Fix failure
due to extra inet_pton() backtrace in glibc >= 2.35
Starting with glibc 2.35 there are extra inet_pton() calls when doing a
IPv6 ping as in one of the 'perf test' entry, which makes it fail:
# perf test inet_pton
89: probe libc's inet_pton & backtrace it with ping : FAILED!
#
If we look at what this script is expecting (commenting out the removal
of the temporary files in it):
# cat /tmp/expected.aT6
ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)
.*inet_pton\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/libc.so.6|inlined\)$
getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/libc.so.6\)$
.*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$
#
And looking at what we are getting out of 'perf script', to match with
the above:
# cat /tmp/perf.script.IUC
ping 623883 [006] 265438.471610: probe_libc:inet_pton: (7f32bcf314c0)
1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6)
29510 __libc_start_call_main+0x80 (/usr/lib64/libc.so.6)
ping 623883 [006] 265438.471664: probe_libc:inet_pton: (7f32bcf314c0)
1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6)
fa6c6 getaddrinfo+0x126 (/usr/lib64/libc.so.6)
491e [unknown] (/usr/bin/ping)
#
We see that its just the first call to inet_pton() that didn't came thru
getaddrinfo(), so if we ignore the first the script matches what it
expects, testing that using 'perf probe' + 'perf record' + 'perf script'
with callchains on userspace targets is producing the expected results.
Since we don't have a 'perf script --skip' to help us here, use tac +
grep to do that, resulting in a one liner that makes this script work on
both older glibc versions as well as with 2.35.
With it, on fedora 36, x86, glibc 2.35:
# perf test inet_pton
90: probe libc's inet_pton & backtrace it with ping : Ok
# perf test -v inet_pton
90: probe libc's inet_pton & backtrace it with ping :
--- start ---
test child forked, pid 627197
ping 627220 1 267956.962402: probe_libc:inet_pton_1: (7f488bf314c0)
1314c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6)
fa6c6 getaddrinfo+0x126 (/usr/lib64/libc.so.6)
491e n (/usr/bin/ping)
test child finished with 0
---- end ----
probe libc's inet_pton & backtrace it with ping: Ok
#
And on Ubuntu 22.04.1 LTS on a Libre Computer ROC-RK3399-PC arm64 system:
Before this patch it works (see that the script used has no 'tac' to
remove the first event):
root@roc-rk3399-pc:~# dpkg -l | grep libc-bin
ii libc-bin 2.35-0ubuntu3.1 arm64 GNU C Library: Binaries
root@roc-rk3399-pc:~# grep -w tac ~acme/libexec/perf-core/tests/shell/record+probe_libc_inet_pton.sh
root@roc-rk3399-pc:~# perf test inet_pton
86: probe libc's inet_pton & backtrace it with ping : Ok
root@roc-rk3399-pc:~# perf test -v inet_pton
86: probe libc's inet_pton & backtrace it with ping :
--- start ---
test child forked, pid 1375
ping 1399 [000] 4114.417450: probe_libc:inet_pton: (ffffb3e26120)
106120 inet_pton+0x0 (/usr/lib/aarch64-linux-gnu/libc.so.6)
d18bc getaddrinfo+0xec (/usr/lib/aarch64-linux-gnu/libc.so.6)
2b68 [unknown] (/usr/bin/ping)
test child finished with 0
---- end ----
probe libc's inet_pton & backtrace it with ping: Ok
root@roc-rk3399-pc:~#
And after it continues to work:
root@roc-rk3399-pc:~# grep -w tac ~acme/libexec/perf-core/tests/shell/record+probe_libc_inet_pton.sh
perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script
root@roc-rk3399-pc:~# perf test inet_pton
86: probe libc's inet_pton & backtrace it with ping : Ok
root@roc-rk3399-pc:~# perf test -v inet_pton
86: probe libc's inet_pton & backtrace it with ping :
--- start ---
test child forked, pid 6995
ping 7019 [005] 4832.160741: probe_libc:inet_pton: (ffffa62e6120)
106120 inet_pton+0x0 (/usr/lib/aarch64-linux-gnu/libc.so.6)
d18bc getaddrinfo+0xec (/usr/lib/aarch64-linux-gnu/libc.so.6)
2b68 [unknown] (/usr/bin/ping)
test child finished with 0
---- end ----
probe libc's inet_pton & backtrace it with ping: Ok
root@roc-rk3399-pc:~#
Reported-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/Y7QyPkPlDYip3cZH@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 34c400ccbe046..216b6b64caa30 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -57,7 +57,7 @@ trace_libc_inet_pton_backtrace() {
perf_data=`mktemp -u /tmp/perf.data.XXX`
perf_script=`mktemp -u /tmp/perf.script.XXX`
perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
- perf script -i $perf_data > $perf_script
+ perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script
exec 3<$perf_script
exec 4<$expected
--
GitLab
From 946c2923e76327343e4460e8bb7ec7b4d4589397 Mon Sep 17 00:00:00 2001
From: Tanmay Bhushan <007047221b@gmail.com>
Date: Sat, 31 Dec 2022 16:05:01 +0100
Subject: [PATCH 0298/1167] btrfs: fix ASSERT em->len condition in
btrfs_get_extent
The em->len value is supposed to be verified in the assertion condition
though we expect it to be same as the sectorsize.
Fixes: a196a8944f77 ("btrfs: do not reset extent map members for inline extents read")
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Tanmay Bhushan <007047221b@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/inode.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index bfcbe64eb8b3a..940b404c8f289 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7092,7 +7092,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
* Other members are not utilized for inline extents.
*/
ASSERT(em->block_start == EXTENT_MAP_INLINE);
- ASSERT(em->len = fs_info->sectorsize);
+ ASSERT(em->len == fs_info->sectorsize);
ret = read_inline_extent(inode, path, page);
if (ret < 0)
--
GitLab
From 77177ed17d24ba060117bdb6efb8a01da7531676 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 29 Dec 2022 07:32:23 +0800
Subject: [PATCH 0299/1167] btrfs: add error message for metadata level
mismatch
From a recent regression report, we found that after commit 947a629988f1
("btrfs: move tree block parentness check into
validate_extent_buffer()") if we have a level mismatch (false alert
though), there is no error message at all.
This makes later debugging harder. This patch will add the proper error
message for such case.
Link: https://lore.kernel.org/linux-btrfs/CABXGCsNzVxo4iq-tJSGm_kO1UggHXgq6CdcHDL=z5FL4njYXSQ@mail.gmail.com/
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/disk-io.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0888d484df80c..9940cc39dbc94 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -530,6 +530,9 @@ static int validate_extent_buffer(struct extent_buffer *eb,
}
if (found_level != check->level) {
+ btrfs_err(fs_info,
+ "level verify failed on logical %llu mirror %u wanted %u found %u",
+ eb->start, eb->read_mirror, check->level, found_level);
ret = -EIO;
goto out;
}
--
GitLab
From 1d854e4fbabb0cb12ca4a7fcd784eb67a65de5f8 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 29 Dec 2022 07:32:24 +0800
Subject: [PATCH 0300/1167] btrfs: fix false alert on bad tree level check
[BUG]
There is a bug report that on a RAID0 NVMe btrfs system, under heavy
write load the filesystem can flip RO randomly.
With extra debugging, it shows some tree blocks failed to pass their
level checks, and if that happens at critical path of a transaction, we
abort the transaction:
BTRFS error (device nvme0n1p3): level verify failed on logical 5446121209856 mirror 1 wanted 0 found 1
BTRFS error (device nvme0n1p3: state A): Transaction aborted (error -5)
BTRFS: error (device nvme0n1p3: state A) in btrfs_finish_ordered_io:3343: errno=-5 IO failure
BTRFS info (device nvme0n1p3: state EA): forced readonly
[CAUSE]
The reporter has already bisected to commit 947a629988f1 ("btrfs: move
tree block parentness check into validate_extent_buffer()").
And with extra debugging, it shows we can have btrfs_tree_parent_check
filled with all zeros in the following call trace:
submit_one_bio+0xd4/0xe0
submit_extent_page+0x142/0x550
read_extent_buffer_pages+0x584/0x9c0
? __pfx_end_bio_extent_readpage+0x10/0x10
? folio_unlock+0x1d/0x50
btrfs_read_extent_buffer+0x98/0x150
read_tree_block+0x43/0xa0
read_block_for_search+0x266/0x370
btrfs_search_slot+0x351/0xd30
? lock_is_held_type+0xe8/0x140
btrfs_lookup_csum+0x63/0x150
btrfs_csum_file_blocks+0x197/0x6c0
? sched_clock_cpu+0x9f/0xc0
? lock_release+0x14b/0x440
? _raw_read_unlock+0x29/0x50
btrfs_finish_ordered_io+0x441/0x860
btrfs_work_helper+0xfe/0x400
? lock_is_held_type+0xe8/0x140
process_one_work+0x294/0x5b0
worker_thread+0x4f/0x3a0
? __pfx_worker_thread+0x10/0x10
kthread+0xf5/0x120
? __pfx_kthread+0x10/0x10
ret_from_fork+0x2c/0x50
Currently we only copy the btrfs_tree_parent_check structure into bbio
at read_extent_buffer_pages() after we have assembled the bbio.
But as shown above, submit_extent_page() itself can already submit the
bbio, leaving the bbio->parent_check uninitialized, and cause the false
alert.
[FIX]
Instead of copying @check into bbio after bbio is assembled, we pass
@check in btrfs_bio_ctrl::parent_check, and copy the content of
parent_check in submit_one_bio() for metadata read.
By this we should be able to pass the needed info for metadata endio
verification, and fix the false alert.
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/CABXGCsNzVxo4iq-tJSGm_kO1UggHXgq6CdcHDL=z5FL4njYXSQ@mail.gmail.com/
Fixes: 947a629988f1 ("btrfs: move tree block parentness check into validate_extent_buffer()")
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/extent_io.c | 30 +++++++++++++++++++++++++-----
1 file changed, 25 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 83dd3aa596635..9bd32daa9b9a6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -103,6 +103,15 @@ struct btrfs_bio_ctrl {
u32 len_to_oe_boundary;
btrfs_bio_end_io_t end_io_func;
+ /*
+ * This is for metadata read, to provide the extra needed verification
+ * info. This has to be provided for submit_one_bio(), as
+ * submit_one_bio() can submit a bio if it ends at stripe boundary. If
+ * no such parent_check is provided, the metadata can hit false alert at
+ * endio time.
+ */
+ struct btrfs_tree_parent_check *parent_check;
+
/*
* Tell writepage not to lock the state bits for this range, it still
* does the unlocking.
@@ -133,13 +142,24 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
- if (!is_data_inode(&inode->vfs_inode))
+ if (!is_data_inode(&inode->vfs_inode)) {
+ if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
+ /*
+ * For metadata read, we should have the parent_check,
+ * and copy it to bbio for metadata verification.
+ */
+ ASSERT(bio_ctrl->parent_check);
+ memcpy(&btrfs_bio(bio)->parent_check,
+ bio_ctrl->parent_check,
+ sizeof(struct btrfs_tree_parent_check));
+ }
btrfs_submit_metadata_bio(inode, bio, mirror_num);
- else if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+ } else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
btrfs_submit_data_write_bio(inode, bio, mirror_num);
- else
+ } else {
btrfs_submit_data_read_bio(inode, bio, mirror_num,
bio_ctrl->compress_type);
+ }
/* The bio is owned by the end_io handler now */
bio_ctrl->bio = NULL;
@@ -4829,6 +4849,7 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,
struct extent_state *cached_state = NULL;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
int ret = 0;
@@ -4878,7 +4899,6 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,
*/
atomic_dec(&eb->io_pages);
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE) {
free_extent_state(cached_state);
@@ -4905,6 +4925,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
unsigned long num_reads = 0;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
@@ -4996,7 +5017,6 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
}
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE)
--
GitLab
From 2f2e84ca60660402bd81d0859703567c59556e6a Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 23 Dec 2022 18:28:53 +0000
Subject: [PATCH 0301/1167] btrfs: fix off-by-one in delalloc search during
lseek
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
During lseek, when searching for delalloc in a range that represents a
hole and that range has a length of 1 byte, we end up not doing the actual
delalloc search in the inode's io tree, resulting in not correctly
reporting the offset with data or a hole. This actually only happens when
the start offset is 0 because with any other start offset we round it down
by sector size.
Reproducer:
$ mkfs.btrfs -f /dev/sdc
$ mount /dev/sdc /mnt/sdc
$ xfs_io -f -c "pwrite -q 0 1" /mnt/sdc/foo
$ xfs_io -c "seek -d 0" /mnt/sdc/foo
Whence Result
DATA EOF
It should have reported an offset of 0 instead of EOF.
Fix this by updating btrfs_find_delalloc_in_range() and count_range_bits()
to deal with inclusive ranges properly. These functions are already
supposed to work with inclusive end offsets, they just got it wrong in a
couple places due to off-by-one mistakes.
A test case for fstests will be added later.
Reported-by: Joan Bruguera Micó <joanbrugueram@gmail.com>
Link: https://lore.kernel.org/linux-btrfs/20221223020509.457113-1-joanbrugueram@gmail.com/
Fixes: b6e833567ea1 ("btrfs: make hole and data seeking a lot more efficient")
CC: stable@vger.kernel.org # 6.1
Tested-by: Joan Bruguera Micó <joanbrugueram@gmail.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/extent-io-tree.c | 2 +-
fs/btrfs/file.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 9ae9cd1e70352..3c7766dfaa694 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -1551,7 +1551,7 @@ u64 count_range_bits(struct extent_io_tree *tree,
u64 last = 0;
int found = 0;
- if (WARN_ON(search_end <= cur_start))
+ if (WARN_ON(search_end < cur_start))
return 0;
spin_lock(&tree->lock);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 91b00eb2440e7..834bbcb91102f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3354,7 +3354,7 @@ bool btrfs_find_delalloc_in_range(struct btrfs_inode *inode, u64 start, u64 end,
bool search_io_tree = true;
bool ret = false;
- while (cur_offset < end) {
+ while (cur_offset <= end) {
u64 delalloc_start;
u64 delalloc_end;
bool delalloc;
--
GitLab
From d73a27b86fc722c28a26ec64002e3a7dc86d1c07 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Sun, 1 Jan 2023 09:02:21 +0800
Subject: [PATCH 0302/1167] btrfs: handle case when repair happens with
dev-replace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
[BUG]
There is a bug report that a BUG_ON() in btrfs_repair_io_failure()
(originally repair_io_failure() in v6.0 kernel) got triggered when
replacing a unreliable disk:
BTRFS warning (device sda1): csum failed root 257 ino 2397453 off 39624704 csum 0xb0d18c75 expected csum 0x4dae9c5e mirror 3
kernel BUG at fs/btrfs/extent_io.c:2380!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 9 PID: 3614331 Comm: kworker/u257:2 Tainted: G OE 6.0.0-5-amd64 #1 Debian 6.0.10-2
Hardware name: Micro-Star International Co., Ltd. MS-7C60/TRX40 PRO WIFI (MS-7C60), BIOS 2.70 07/01/2021
Workqueue: btrfs-endio btrfs_end_bio_work [btrfs]
RIP: 0010:repair_io_failure+0x24a/0x260 [btrfs]
Call Trace:
<TASK>
clean_io_failure+0x14d/0x180 [btrfs]
end_bio_extent_readpage+0x412/0x6e0 [btrfs]
? __switch_to+0x106/0x420
process_one_work+0x1c7/0x380
worker_thread+0x4d/0x380
? rescuer_thread+0x3a0/0x3a0
kthread+0xe9/0x110
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x22/0x30
[CAUSE]
Before the BUG_ON(), we got some read errors from the replace target
first, note the mirror number (3, which is beyond RAID1 duplication,
thus it's read from the replace target device).
Then at the BUG_ON() location, we are trying to writeback the repaired
sectors back the failed device.
The check looks like this:
ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
&map_length, &bioc, mirror_num);
if (ret)
goto out_counter_dec;
BUG_ON(mirror_num != bioc->mirror_num);
But inside btrfs_map_block(), we can modify bioc->mirror_num especially
for dev-replace:
if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
!need_full_stripe(op) && dev_replace->tgtdev != NULL) {
ret = get_extra_mirror_from_replace(fs_info, logical, *length,
dev_replace->srcdev->devid,
&mirror_num,
&physical_to_patch_in_first_stripe);
patch_the_first_stripe_for_dev_replace = 1;
}
Thus if we're repairing the replace target device, we're going to
trigger that BUG_ON().
But in reality, the read failure from the replace target device may be
that, our replace hasn't reached the range we're reading, thus we're
reading garbage, but with replace running, the range would be properly
filled later.
Thus in that case, we don't need to do anything but let the replace
routine to handle it.
[FIX]
Instead of a BUG_ON(), just skip the repair if we're repairing the
device replace target device.
Reported-by: å°å¤ª <nospam@kota.moe>
Link: https://lore.kernel.org/linux-btrfs/CACsxjPYyJGQZ+yvjzxA1Nn2LuqkYqTCcUH43S=+wXhyf8S00Ag@mail.gmail.com/
CC: stable@vger.kernel.org # 6.0+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/bio.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index b8fb7ef6b5206..8affc88b0e0a4 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -329,7 +329,16 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
&map_length, &bioc, mirror_num);
if (ret)
goto out_counter_dec;
- BUG_ON(mirror_num != bioc->mirror_num);
+ /*
+ * This happens when dev-replace is also running, and the
+ * mirror_num indicates the dev-replace target.
+ *
+ * In this case, we don't need to do anything, as the read
+ * error just means the replace progress hasn't reached our
+ * read range, and later replace routine would handle it well.
+ */
+ if (mirror_num != bioc->mirror_num)
+ goto out_counter_dec;
}
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
--
GitLab
From 1f680609bf1beac20e2a31ddcb1b88874123c39f Mon Sep 17 00:00:00 2001
From: Yuchi Yang <yangyuchi66@gmail.com>
Date: Fri, 30 Dec 2022 15:22:25 +0800
Subject: [PATCH 0303/1167] ALSA: hda/realtek - Turn on power early
Turn on power early to avoid wrong state for power relation register.
This can earlier update JD state when resume back.
Signed-off-by: Yuchi Yang <yangyuchi66@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/e35d8f4fa18f4448a2315cc7d4a3715f@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 3794b522c2222..937b227e17c51 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3564,6 +3564,15 @@ static void alc256_init(struct hda_codec *codec)
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
+ alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
+ alc_update_coef_idx(codec, 0x08, 7<<4, 0);
+ alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ msleep(30);
+ }
+
if (!hp_pin)
hp_pin = 0x21;
@@ -3575,14 +3584,6 @@ static void alc256_init(struct hda_codec *codec)
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
- alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
- alc_update_coef_idx(codec, 0x08, 7<<4, 0);
- alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- msleep(30);
- }
snd_hda_codec_write(codec, hp_pin, 0,
AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
@@ -3713,6 +3714,13 @@ static void alc225_init(struct hda_codec *codec)
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp1_pin_sense, hp2_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ alc_update_coef_idx(codec, 0x33, 1<<11, 0);
+ msleep(30);
+ }
+
if (spec->codec_variant != ALC269_TYPE_ALC287 &&
spec->codec_variant != ALC269_TYPE_ALC245)
/* required only at boot or S3 and S4 resume time */
@@ -3734,12 +3742,6 @@ static void alc225_init(struct hda_codec *codec)
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- alc_update_coef_idx(codec, 0x33, 1<<11, 0);
- msleep(30);
- }
if (hp1_pin_sense || spec->ultra_low_power)
snd_hda_codec_write(codec, hp_pin, 0,
--
GitLab
From a5751933a7f6abbdad90d98f25a25bb4b133a9e6 Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Tue, 3 Jan 2023 17:53:32 +0800
Subject: [PATCH 0304/1167] ALSA: hda - Enable headset mic on another Dell
laptop with ALC3254
There is another Dell Latitude laptop (1028:0c03) with Realtek
codec ALC3254 which needs the ALC269_FIXUP_DELL4_MIC_NO_PRESENCE
instead of the default matched ALC269_FIXUP_DELL1_MIC_NO_PRESENCE.
Apply correct fixup for this particular model to enable headset mic.
Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20230103095332.730677-1-chris.chiu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 937b227e17c51..eda4914b8aeb1 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9241,6 +9241,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+ SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
--
GitLab
From 39f501d68ec1ed5cd5c66ac6ec2a7131c517bb92 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 26 Dec 2022 09:00:40 +0800
Subject: [PATCH 0305/1167] btrfs: always report error in run_one_delayed_ref()
Currently we have a btrfs_debug() for run_one_delayed_ref() failure, but
if end users hit such problem, there will be no chance that
btrfs_debug() is enabled. This can lead to very little useful info for
debugging.
This patch will:
- Add extra info for error reporting
Including:
* logical bytenr
* num_bytes
* type
* action
* ref_mod
- Replace the btrfs_debug() with btrfs_err()
- Move the error reporting into run_one_delayed_ref()
This is to avoid use-after-free, the @node can be freed in the caller.
This error should only be triggered at most once.
As if run_one_delayed_ref() failed, we trigger the error message, then
causing the call chain to error out:
btrfs_run_delayed_refs()
`- btrfs_run_delayed_refs()
`- btrfs_run_delayed_refs_for_head()
`- run_one_delayed_ref()
And we will abort the current transaction in btrfs_run_delayed_refs().
If we have to run delayed refs for the abort transaction,
run_one_delayed_ref() will just cleanup the refs and do nothing, thus no
new error messages would be output.
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/extent-tree.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 892d78c1853c7..72ba13b027a9e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1713,6 +1713,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
BUG();
if (ret && insert_reserved)
btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+ if (ret < 0)
+ btrfs_err(trans->fs_info,
+"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d",
+ node->bytenr, node->num_bytes, node->type,
+ node->action, node->ref_mod, ret);
return ret;
}
@@ -1954,8 +1959,6 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
if (ret) {
unselect_delayed_ref_head(delayed_refs, locked_ref);
btrfs_put_delayed_ref(ref);
- btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
- ret);
return ret;
}
--
GitLab
From 2ba48b20049b5a76f34a85f853c9496d1b10533a Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 22 Dec 2022 07:59:17 +0800
Subject: [PATCH 0306/1167] btrfs: fix compat_ro checks against remount
[BUG]
Even with commit 81d5d61454c3 ("btrfs: enhance unsupported compat RO
flags handling"), btrfs can still mount a fs with unsupported compat_ro
flags read-only, then remount it RW:
# btrfs ins dump-super /dev/loop0 | grep compat_ro_flags -A 3
compat_ro_flags 0x403
( FREE_SPACE_TREE |
FREE_SPACE_TREE_VALID |
unknown flag: 0x400 )
# mount /dev/loop0 /mnt/btrfs
mount: /mnt/btrfs: wrong fs type, bad option, bad superblock on /dev/loop0, missing codepage or helper program, or other error.
dmesg(1) may have more information after failed mount system call.
^^^ RW mount failed as expected ^^^
# dmesg -t | tail -n5
loop0: detected capacity change from 0 to 1048576
BTRFS: device fsid cb5b82f5-0fdd-4d81-9b4b-78533c324afa devid 1 transid 7 /dev/loop0 scanned by mount (1146)
BTRFS info (device loop0): using crc32c (crc32c-intel) checksum algorithm
BTRFS info (device loop0): using free space tree
BTRFS error (device loop0): cannot mount read-write because of unknown compat_ro features (0x403)
BTRFS error (device loop0): open_ctree failed
# mount /dev/loop0 -o ro /mnt/btrfs
# mount -o remount,rw /mnt/btrfs
^^^ RW remount succeeded unexpectedly ^^^
[CAUSE]
Currently we use btrfs_check_features() to check compat_ro flags against
our current mount flags.
That function get reused between open_ctree() and btrfs_remount().
But for btrfs_remount(), the super block we passed in still has the old
mount flags, thus btrfs_check_features() still believes we're mounting
read-only.
[FIX]
Replace the existing @sb argument with @is_rw_mount.
As originally we only use @sb to determine if the mount is RW.
Now it's callers' responsibility to determine if the mount is RW, and
since there are only two callers, the check is pretty simple:
- caller in open_ctree()
Just pass !sb_rdonly().
- caller in btrfs_remount()
Pass !(*flags & SB_RDONLY), as our check should be against the new
flags.
Now we can correctly reject the RW remount:
# mount /dev/loop0 -o ro /mnt/btrfs
# mount -o remount,rw /mnt/btrfs
mount: /mnt/btrfs: mount point not mounted or bad option.
dmesg(1) may have more information after failed mount system call.
# dmesg -t | tail -n 1
BTRFS error (device loop0: state M): cannot mount read-write because of unknown compat_ro features (0x403)
Reported-by: Chung-Chiang Cheng <shepjeng@gmail.com>
Fixes: 81d5d61454c3 ("btrfs: enhance unsupported compat RO flags handling")
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/disk-io.c | 8 +++++---
fs/btrfs/disk-io.h | 2 +-
fs/btrfs/super.c | 2 +-
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9940cc39dbc94..8aeaada1fcaec 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3384,6 +3384,8 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
/*
* Do various sanity and dependency checks of different features.
*
+ * @is_rw_mount: If the mount is read-write.
+ *
* This is the place for less strict checks (like for subpage or artificial
* feature dependencies).
*
@@ -3394,7 +3396,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
* (space cache related) can modify on-disk format like free space tree and
* screw up certain feature dependencies.
*/
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb)
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
{
struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 incompat = btrfs_super_incompat_flags(disk_super);
@@ -3433,7 +3435,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb)
if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
- if (compat_ro_unsupp && !sb_rdonly(sb)) {
+ if (compat_ro_unsupp && is_rw_mount) {
btrfs_err(fs_info,
"cannot mount read-write because of unknown compat_ro features (0x%llx)",
compat_ro);
@@ -3636,7 +3638,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
goto fail_alloc;
}
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !sb_rdonly(sb));
if (ret < 0) {
err = ret;
goto fail_alloc;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 363935cfc0844..f2f295eb6103d 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -50,7 +50,7 @@ int __cold open_ctree(struct super_block *sb,
void __cold close_ctree(struct btrfs_fs_info *fs_info);
int btrfs_validate_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb, int mirror_num);
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb);
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d5de18d6517e7..433ce221dc5c7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1705,7 +1705,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
if (ret)
goto restore;
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY));
if (ret < 0)
goto restore;
--
GitLab
From f528fe213a6ad21a6e8644dbd5de10dc264a89fd Mon Sep 17 00:00:00 2001
From: Neil Armstrong <neil.armstrong@linaro.org>
Date: Mon, 2 Jan 2023 12:23:20 +0100
Subject: [PATCH 0307/1167] regulator: qcom-rpmh: PM8550 ldo11 regulator is an
nldo
This fixes the definition of the PM8550 ldo11 regulator matching it's
capabilities since this LDO is designed to work between 1,2V and 1,5V.
Fixes: e6e3776d682d ("regulator: qcom-rpmh: Add support for PM8550 regulators")
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://lore.kernel.org/r/20230102-topic-sm8550-upstream-fixes-reg-l11b-nldo-v1-1-d97def246338@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/regulator/qcom-rpmh-regulator.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index 43b5b93777149..ae6021390143c 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -1016,7 +1016,7 @@ static const struct rpmh_vreg_init_data pm8550_vreg_data[] = {
RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"),
RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"),
RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"),
- RPMH_VREG("ldo11", "ldo%s11", &pmic5_pldo, "vdd-l11"),
+ RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"),
RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"),
RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"),
RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"),
--
GitLab
From e7a293658c20a7945014570e1921bf7d25d68a36 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 29 Dec 2022 09:48:24 +0400
Subject: [PATCH 0308/1167] EDAC/highbank: Fix memory leak in
highbank_mc_probe()
When devres_open_group() fails, it returns -ENOMEM without freeing memory
allocated by edac_mc_alloc().
Call edac_mc_free() on the error handling path to avoid a memory leak.
[ bp: Massage commit message. ]
Fixes: a1b01edb2745 ("edac: add support for Calxeda highbank memory controller")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Link: https://lore.kernel.org/r/20221229054825.1361993-1-linmq006@gmail.com
---
drivers/edac/highbank_mc_edac.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c
index 61b76ec226af1..19fba258ae108 100644
--- a/drivers/edac/highbank_mc_edac.c
+++ b/drivers/edac/highbank_mc_edac.c
@@ -174,8 +174,10 @@ static int highbank_mc_probe(struct platform_device *pdev)
drvdata = mci->pvt_info;
platform_set_drvdata(pdev, mci);
- if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL))
- return -ENOMEM;
+ if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+ res = -ENOMEM;
+ goto free;
+ }
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!r) {
@@ -243,6 +245,7 @@ static int highbank_mc_probe(struct platform_device *pdev)
edac_mc_del_mc(&pdev->dev);
err:
devres_release_group(&pdev->dev, NULL);
+free:
edac_mc_free(mci);
return res;
}
--
GitLab
From f6ca5059dc0d6608dc46070f48e396d611f240d6 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 22 Dec 2022 18:38:19 +0000
Subject: [PATCH 0309/1167] firmware: arm_scmi: Clear stale xfer->hdr.status
Stale error status reported from a previous message transaction must be
cleared before starting a new transaction to avoid being confusingly
reported in the following SCMI message dump traces.
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20221222183823.518856-2-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
drivers/firmware/arm_scmi/driver.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index f818d00bb2c69..ffdad59ec81fc 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -910,6 +910,8 @@ static int do_xfer(const struct scmi_protocol_handle *ph,
xfer->hdr.protocol_id, xfer->hdr.seq,
xfer->hdr.poll_completion);
+ /* Clear any stale status */
+ xfer->hdr.status = SCMI_SUCCESS;
xfer->state = SCMI_XFER_SENT_OK;
/*
* Even though spinlocking is not needed here since no race is possible
--
GitLab
From ad78b81a1077f7d956952cd8bdfe1e61504e3eb8 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 22 Dec 2022 18:38:20 +0000
Subject: [PATCH 0310/1167] firmware: arm_scmi: Harden shared memory access in
fetch_response
A misbheaving SCMI platform firmware could reply with out-of-spec messages,
shorter than the mimimum size comprising a header and a status field.
Harden shmem_fetch_response to properly truncate such a bad messages.
Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20221222183823.518856-3-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
drivers/firmware/arm_scmi/shmem.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 1dfe534b85184..135f8718000f5 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -81,10 +81,11 @@ u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem)
void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem,
struct scmi_xfer *xfer)
{
+ size_t len = ioread32(&shmem->length);
+
xfer->hdr.status = ioread32(shmem->msg_payload);
/* Skip the length of header and status in shmem area i.e 8 bytes */
- xfer->rx.len = min_t(size_t, xfer->rx.len,
- ioread32(&shmem->length) - 8);
+ xfer->rx.len = min_t(size_t, xfer->rx.len, len > 8 ? len - 8 : 0);
/* Take a copy to the rx buffer.. */
memcpy_fromio(xfer->rx.buf, shmem->msg_payload + 4, xfer->rx.len);
--
GitLab
From 9bae076cd4e3e3c3dc185cae829d80b2dddec86e Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 22 Dec 2022 18:38:21 +0000
Subject: [PATCH 0311/1167] firmware: arm_scmi: Harden shared memory access in
fetch_notification
A misbheaving SCMI platform firmware could reply with out-of-spec
notifications, shorter than the mimimum size comprising a header.
Fixes: d5141f37c42e ("firmware: arm_scmi: Add notifications support in transport layer")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20221222183823.518856-4-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
drivers/firmware/arm_scmi/shmem.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 135f8718000f5..87b4f4d35f062 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -94,8 +94,10 @@ void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem,
void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem,
size_t max_len, struct scmi_xfer *xfer)
{
+ size_t len = ioread32(&shmem->length);
+
/* Skip only the length of header in shmem area i.e 4 bytes */
- xfer->rx.len = min_t(size_t, max_len, ioread32(&shmem->length) - 4);
+ xfer->rx.len = min_t(size_t, max_len, len > 4 ? len - 4 : 0);
/* Take a copy to the rx buffer.. */
memcpy_fromio(xfer->rx.buf, shmem->msg_payload, xfer->rx.len);
--
GitLab
From e325285de2cd82fbdcc4df8898e4c6a597674816 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 22 Dec 2022 18:38:23 +0000
Subject: [PATCH 0312/1167] firmware: arm_scmi: Fix virtio channels cleanup on
shutdown
When unloading the SCMI core stack module, configured to use the virtio
SCMI transport, LOCKDEP reports the splat down below about unsafe locks
dependencies.
In order to avoid this possible unsafe locking scenario call upfront
virtio_break_device() before getting hold of vioch->lock.
=====================================================
WARNING: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected
6.1.0-00067-g6b934395ba07-dirty #4 Not tainted
-----------------------------------------------------
rmmod/307 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire:
ffff000080c510e0 (&dev->vqs_list_lock){+.+.}-{3:3}, at: virtio_break_device+0x28/0x68
and this task is already holding:
ffff00008288ada0 (&channels[i].lock){-.-.}-{3:3}, at: virtio_chan_free+0x60/0x168 [scmi_module]
which would create a new lock dependency:
(&channels[i].lock){-.-.}-{3:3} -> (&dev->vqs_list_lock){+.+.}-{3:3}
but this new dependency connects a HARDIRQ-irq-safe lock:
(&channels[i].lock){-.-.}-{3:3}
... which became HARDIRQ-irq-safe at:
lock_acquire+0x128/0x398
_raw_spin_lock_irqsave+0x78/0x140
scmi_vio_complete_cb+0xb4/0x3b8 [scmi_module]
vring_interrupt+0x84/0x120
vm_interrupt+0x94/0xe8
__handle_irq_event_percpu+0xb4/0x3d8
handle_irq_event_percpu+0x20/0x68
handle_irq_event+0x50/0xb0
handle_fasteoi_irq+0xac/0x138
generic_handle_domain_irq+0x34/0x50
gic_handle_irq+0xa0/0xd8
call_on_irq_stack+0x2c/0x54
do_interrupt_handler+0x8c/0x90
el1_interrupt+0x40/0x78
el1h_64_irq_handler+0x18/0x28
el1h_64_irq+0x64/0x68
_raw_write_unlock_irq+0x48/0x80
ep_start_scan+0xf0/0x128
do_epoll_wait+0x390/0x858
do_compat_epoll_pwait.part.34+0x1c/0xb8
__arm64_sys_epoll_pwait+0x80/0xd0
invoke_syscall+0x4c/0x110
el0_svc_common.constprop.3+0x98/0x120
do_el0_svc+0x34/0xd0
el0_svc+0x40/0x98
el0t_64_sync_handler+0x98/0xc0
el0t_64_sync+0x170/0x174
to a HARDIRQ-irq-unsafe lock:
(&dev->vqs_list_lock){+.+.}-{3:3}
... which became HARDIRQ-irq-unsafe at:
...
lock_acquire+0x128/0x398
_raw_spin_lock+0x58/0x70
__vring_new_virtqueue+0x130/0x1c0
vring_create_virtqueue+0xc4/0x2b8
vm_find_vqs+0x20c/0x430
init_vq+0x308/0x390
virtblk_probe+0x114/0x9b0
virtio_dev_probe+0x1a4/0x248
really_probe+0xc8/0x3a8
__driver_probe_device+0x84/0x190
driver_probe_device+0x44/0x110
__driver_attach+0x104/0x1e8
bus_for_each_dev+0x7c/0xd0
driver_attach+0x2c/0x38
bus_add_driver+0x1e4/0x258
driver_register+0x6c/0x128
register_virtio_driver+0x2c/0x48
virtio_blk_init+0x70/0xac
do_one_initcall+0x84/0x420
kernel_init_freeable+0x2d0/0x340
kernel_init+0x2c/0x138
ret_from_fork+0x10/0x20
other info that might help us debug this:
Possible interrupt unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&dev->vqs_list_lock);
local_irq_disable();
lock(&channels[i].lock);
lock(&dev->vqs_list_lock);
<Interrupt>
lock(&channels[i].lock);
*** DEADLOCK ***
================
Fixes: 42e90eb53bf3f ("firmware: arm_scmi: Add a virtio channel refcount")
Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Link: https://lore.kernel.org/r/20221222183823.518856-6-cristian.marussi@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
drivers/firmware/arm_scmi/virtio.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c
index 33c9b81a55cd1..1db975c088969 100644
--- a/drivers/firmware/arm_scmi/virtio.c
+++ b/drivers/firmware/arm_scmi/virtio.c
@@ -160,7 +160,6 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch)
}
vioch->shutdown_done = &vioch_shutdown_done;
- virtio_break_device(vioch->vqueue->vdev);
if (!vioch->is_rx && vioch->deferred_tx_wq)
/* Cannot be kicked anymore after this...*/
vioch->deferred_tx_wq = NULL;
@@ -482,6 +481,12 @@ static int virtio_chan_free(int id, void *p, void *data)
struct scmi_chan_info *cinfo = p;
struct scmi_vio_channel *vioch = cinfo->transport_info;
+ /*
+ * Break device to inhibit further traffic flowing while shutting down
+ * the channels: doing it later holding vioch->lock creates unsafe
+ * locking dependency chains as reported by LOCKDEP.
+ */
+ virtio_break_device(vioch->vqueue->vdev);
scmi_vio_channel_cleanup_sync(vioch);
scmi_free_channel(cinfo, data, id);
--
GitLab
From 55d235361fccef573990dfa5724ab453866e7816 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 3 Jan 2023 10:24:11 -0500
Subject: [PATCH 0313/1167] x86/asm: Fix an assembler warning with current
binutils
Fix a warning: "found `movsd'; assuming `movsl' was meant"
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org
---
arch/x86/lib/iomap_copy_64.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
index a1f9416bf67a5..6ff2f56cb0f71 100644
--- a/arch/x86/lib/iomap_copy_64.S
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -10,6 +10,6 @@
*/
SYM_FUNC_START(__iowrite32_copy)
movl %edx,%ecx
- rep movsd
+ rep movsl
RET
SYM_FUNC_END(__iowrite32_copy)
--
GitLab
From b3d83066cbebc76dbac8a5fca931f64b4c6fff34 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Fri, 30 Dec 2022 23:43:32 +0800
Subject: [PATCH 0314/1167] f2fs: fix to avoid NULL pointer dereference in
f2fs_issue_flush()
With below two cases, it will cause NULL pointer dereference when
accessing SM_I(sbi)->fcc_info in f2fs_issue_flush().
a) If kthread_run() fails in f2fs_create_flush_cmd_control(), it will
release SM_I(sbi)->fcc_info,
- mount -o noflush_merge /dev/vda /mnt/f2fs
- mount -o remount,flush_merge /dev/vda /mnt/f2fs -- kthread_run() fails
- dd if=/dev/zero of=/mnt/f2fs/file bs=4k count=1 conv=fsync
b) we will never allocate memory for SM_I(sbi)->fcc_info w/ below
testcase,
- mount -o ro /dev/vda /mnt/f2fs
- mount -o rw,remount /dev/vda /mnt/f2fs
- dd if=/dev/zero of=/mnt/f2fs/file bs=4k count=1 conv=fsync
In order to fix this issue, let change as below:
- fix error path handling in f2fs_create_flush_cmd_control().
- allocate SM_I(sbi)->fcc_info even if readonly is on.
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/segment.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 25ddea478fc1a..c3f8c8208eeca 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -663,8 +663,7 @@ int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi)
if (IS_ERR(fcc->f2fs_issue_flush)) {
int err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->fcc_info = NULL;
+ fcc->f2fs_issue_flush = NULL;
return err;
}
@@ -5138,11 +5137,9 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
init_f2fs_rwsem(&sm_info->curseg_lock);
- if (!f2fs_readonly(sbi->sb)) {
- err = f2fs_create_flush_cmd_control(sbi);
- if (err)
- return err;
- }
+ err = f2fs_create_flush_cmd_control(sbi);
+ if (err)
+ return err;
err = create_discard_cmd_control(sbi);
if (err)
--
GitLab
From fe59109ae5c0b34a8c7c07f693fc501b12b57787 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 16 Dec 2022 14:05:44 -0800
Subject: [PATCH 0315/1167] f2fs: initialize extent_cache parameter
This can avoid confusing tracepoint values.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/data.c | 2 +-
fs/f2fs/extent_cache.c | 2 +-
fs/f2fs/file.c | 2 +-
fs/f2fs/segment.c | 2 +-
4 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 6e43e19c7d1ca..97e816590cd95 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2183,7 +2183,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
sector_t last_block_in_file;
const unsigned blocksize = blks_to_bytes(inode, 1);
struct decompress_io_ctx *dic = NULL;
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
bool from_dnode = true;
int i;
int ret = 0;
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 1bd38a78ebba9..3aa2f82960455 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -938,7 +938,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
{
- struct extent_info ei;
+ struct extent_info ei = {};
if (!__may_extent_tree(dn->inode, type))
return;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index a6c4012798860..ecbc8c135b494 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2559,7 +2559,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE,
.m_may_create = false };
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index c3f8c8208eeca..ae3c4e5474efa 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -3160,7 +3160,7 @@ static int __get_segment_type_4(struct f2fs_io_info *fio)
static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct extent_info ei;
+ struct extent_info ei = {};
if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) {
if (!ei.age)
--
GitLab
From ed2724765e58e3310d3de48f4a1761631b3dd640 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 16 Dec 2022 14:41:54 -0800
Subject: [PATCH 0316/1167] f2fs: don't mix to use union values in extent_info
Let's explicitly use the defined values in block_age case only.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/extent_cache.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 3aa2f82960455..cc3fed04dd6f7 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -881,7 +881,8 @@ static unsigned long long __calculate_block_age(unsigned long long new,
}
/* This returns a new age and allocated blocks in ei */
-static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
+ block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t f_size = i_size_read(inode);
@@ -894,7 +895,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
* block here.
*/
if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
- ei->blk == NEW_ADDR)
+ blkaddr == NEW_ADDR)
return -EINVAL;
if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
@@ -915,14 +916,14 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
return 0;
}
- f2fs_bug_on(sbi, ei->blk == NULL_ADDR);
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
/* the data block was allocated for the first time */
- if (ei->blk == NEW_ADDR)
+ if (blkaddr == NEW_ADDR)
goto out;
- if (__is_valid_data_blkaddr(ei->blk) &&
- !f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) {
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
f2fs_bug_on(sbi, 1);
return -EINVAL;
}
@@ -953,8 +954,7 @@ static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type typ
else
ei.blk = dn->data_blkaddr;
} else if (type == EX_BLOCK_AGE) {
- ei.blk = dn->data_blkaddr;
- if (__get_new_block_age(dn->inode, &ei))
+ if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr))
return;
}
__update_extent_tree_range(dn->inode, &ei, type);
--
GitLab
From 22a341b43036415718f2d50f5f98b2f891fe17e9 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 16 Dec 2022 16:36:36 -0800
Subject: [PATCH 0317/1167] f2fs: should use a temp extent_info for lookup
Otherwise, __lookup_extent_tree() will override the given extent_info which will
be used by caller.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/extent_cache.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index cc3fed04dd6f7..7b191ff656319 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -888,6 +888,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
loff_t f_size = i_size_read(inode);
unsigned long long cur_blocks =
atomic64_read(&sbi->allocated_data_blocks);
+ struct extent_info tei = *ei; /* only fofs and len are valid */
/*
* When I/O is not aligned to a PAGE_SIZE, update will happen to the last
@@ -898,17 +899,17 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
blkaddr == NEW_ADDR)
return -EINVAL;
- if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
+ if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) {
unsigned long long cur_age;
- if (cur_blocks >= ei->last_blocks)
- cur_age = cur_blocks - ei->last_blocks;
+ if (cur_blocks >= tei.last_blocks)
+ cur_age = cur_blocks - tei.last_blocks;
else
/* allocated_data_blocks overflow */
- cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks;
+ cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
- if (ei->age)
- ei->age = __calculate_block_age(cur_age, ei->age);
+ if (tei.age)
+ ei->age = __calculate_block_age(cur_age, tei.age);
else
ei->age = cur_age;
ei->last_blocks = cur_blocks;
--
GitLab
From df9d44b645b83fffccfb4e28c1f93376585fdec8 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 21 Dec 2022 16:14:10 -0800
Subject: [PATCH 0318/1167] f2fs: let's avoid panic if extent_tree is not
created
This patch avoids the below panic.
pc : __lookup_extent_tree+0xd8/0x760
lr : f2fs_do_write_data_page+0x104/0x87c
sp : ffffffc010cbb3c0
x29: ffffffc010cbb3e0 x28: 0000000000000000
x27: ffffff8803e7f020 x26: ffffff8803e7ed40
x25: ffffff8803e7f020 x24: ffffffc010cbb460
x23: ffffffc010cbb480 x22: 0000000000000000
x21: 0000000000000000 x20: ffffffff22e90900
x19: 0000000000000000 x18: ffffffc010c5d080
x17: 0000000000000000 x16: 0000000000000020
x15: ffffffdb1acdbb88 x14: ffffff888759e2b0
x13: 0000000000000000 x12: ffffff802da49000
x11: 000000000a001200 x10: ffffff8803e7ed40
x9 : ffffff8023195800 x8 : ffffff802da49078
x7 : 0000000000000001 x6 : 0000000000000000
x5 : 0000000000000006 x4 : ffffffc010cbba28
x3 : 0000000000000000 x2 : ffffffc010cbb480
x1 : 0000000000000000 x0 : ffffff8803e7ed40
Call trace:
__lookup_extent_tree+0xd8/0x760
f2fs_do_write_data_page+0x104/0x87c
f2fs_write_single_data_page+0x420/0xb60
f2fs_write_cache_pages+0x418/0xb1c
__f2fs_write_data_pages+0x428/0x58c
f2fs_write_data_pages+0x30/0x40
do_writepages+0x88/0x190
__writeback_single_inode+0x48/0x448
writeback_sb_inodes+0x468/0x9e8
__writeback_inodes_wb+0xb8/0x2a4
wb_writeback+0x33c/0x740
wb_do_writeback+0x2b4/0x400
wb_workfn+0xe4/0x34c
process_one_work+0x24c/0x5bc
worker_thread+0x3e8/0xa50
kthread+0x150/0x1b4
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
fs/f2fs/extent_cache.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 7b191ff656319..342af24b2f8cf 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -546,7 +546,8 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
struct extent_node *en;
bool ret = false;
- f2fs_bug_on(sbi, !et);
+ if (!et)
+ return false;
trace_f2fs_lookup_extent_tree_start(inode, pgofs, type);
--
GitLab
From 72bb8f8cc088730c4d84117a6906f458c2fc64bb Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Sun, 1 Jan 2023 17:29:04 +0100
Subject: [PATCH 0319/1167] x86/insn: Avoid namespace clash by separating
instruction decoder MMIO type from MMIO trace type
Both <linux/mmiotrace.h> and <asm/insn-eval.h> define various MMIO_ enum constants,
whose namespace overlaps.
Rename the <asm/insn-eval.h> ones to have a INSN_ prefix, so that the headers can be
used from the same source file.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230101162910.710293-2-Jason@zx2c4.com
---
arch/x86/coco/tdx/tdx.c | 26 +++++++++++++-------------
arch/x86/include/asm/insn-eval.h | 18 +++++++++---------
arch/x86/kernel/sev.c | 18 +++++++++---------
arch/x86/lib/insn-eval.c | 20 ++++++++++----------
4 files changed, 41 insertions(+), 41 deletions(-)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index cfd4c95b9f045..669d9e4f29015 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -386,8 +386,8 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
{
unsigned long *reg, val, vaddr;
char buffer[MAX_INSN_SIZE];
+ enum insn_mmio_type mmio;
struct insn insn = {};
- enum mmio_type mmio;
int size, extend_size;
u8 extend_val = 0;
@@ -402,10 +402,10 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
return -EINVAL;
mmio = insn_decode_mmio(&insn, &size);
- if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+ if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED))
return -EINVAL;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg = insn_get_modrm_reg_ptr(&insn, regs);
if (!reg)
return -EINVAL;
@@ -426,23 +426,23 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
/* Handle writes first */
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(&val, reg, size);
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
val = insn.immediate.value;
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_READ:
- case MMIO_READ_ZERO_EXTEND:
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ:
+ case INSN_MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Reads are handled below */
break;
- case MMIO_MOVS:
- case MMIO_DECODE_FAILED:
+ case INSN_MMIO_MOVS:
+ case INSN_MMIO_DECODE_FAILED:
/*
* MMIO was accessed with an instruction that could not be
* decoded or handled properly. It was likely not using io.h
@@ -459,15 +459,15 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
return -EIO;
switch (mmio) {
- case MMIO_READ:
+ case INSN_MMIO_READ:
/* Zero-extend for 32-bit operation */
extend_size = size == 4 ? sizeof(*reg) : 0;
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
/* Zero extend based on operand size */
extend_size = insn.opnd_bytes;
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Sign extend based on operand size */
extend_size = insn.opnd_bytes;
if (size == 1 && val & BIT(7))
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index f07faa61c7f31..54368a43abf67 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -32,16 +32,16 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs,
bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE], int buf_size);
-enum mmio_type {
- MMIO_DECODE_FAILED,
- MMIO_WRITE,
- MMIO_WRITE_IMM,
- MMIO_READ,
- MMIO_READ_ZERO_EXTEND,
- MMIO_READ_SIGN_EXTEND,
- MMIO_MOVS,
+enum insn_mmio_type {
+ INSN_MMIO_DECODE_FAILED,
+ INSN_MMIO_WRITE,
+ INSN_MMIO_WRITE_IMM,
+ INSN_MMIO_READ,
+ INSN_MMIO_READ_ZERO_EXTEND,
+ INSN_MMIO_READ_SIGN_EXTEND,
+ INSN_MMIO_MOVS,
};
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
#endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index a428c62330d37..679026a640efd 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -1536,32 +1536,32 @@ static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
struct insn *insn = &ctxt->insn;
+ enum insn_mmio_type mmio;
unsigned int bytes = 0;
- enum mmio_type mmio;
enum es_result ret;
u8 sign_byte;
long *reg_data;
mmio = insn_decode_mmio(insn, &bytes);
- if (mmio == MMIO_DECODE_FAILED)
+ if (mmio == INSN_MMIO_DECODE_FAILED)
return ES_DECODE_FAILED;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
if (!reg_data)
return ES_DECODE_FAILED;
}
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(ghcb->shared_buffer, reg_data, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_READ:
+ case INSN_MMIO_READ:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
@@ -1572,7 +1572,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
@@ -1581,7 +1581,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
memset(reg_data, 0, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
@@ -1600,7 +1600,7 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
memset(reg_data, sign_byte, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_MOVS:
+ case INSN_MMIO_MOVS:
ret = vc_handle_mmio_movs(ctxt, bytes);
break;
default:
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 21104c41cba04..558a605929db5 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -1595,16 +1595,16 @@ bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
* Returns:
*
* Type of the instruction. Size of the memory operand is stored in
- * @bytes. If decode failed, MMIO_DECODE_FAILED returned.
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
*/
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
{
- enum mmio_type type = MMIO_DECODE_FAILED;
+ enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
*bytes = 0;
if (insn_get_opcode(insn))
- return MMIO_DECODE_FAILED;
+ return INSN_MMIO_DECODE_FAILED;
switch (insn->opcode.bytes[0]) {
case 0x88: /* MOV m8,r8 */
@@ -1613,7 +1613,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE;
+ type = INSN_MMIO_WRITE;
break;
case 0xc6: /* MOV m8, imm8 */
@@ -1622,7 +1622,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE_IMM;
+ type = INSN_MMIO_WRITE_IMM;
break;
case 0x8a: /* MOV r8, m8 */
@@ -1631,7 +1631,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_READ;
+ type = INSN_MMIO_READ;
break;
case 0xa4: /* MOVS m8, m8 */
@@ -1640,7 +1640,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_MOVS;
+ type = INSN_MMIO_MOVS;
break;
case 0x0f: /* Two-byte instruction */
@@ -1651,7 +1651,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0xb7: /* MOVZX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_ZERO_EXTEND;
+ type = INSN_MMIO_READ_ZERO_EXTEND;
break;
case 0xbe: /* MOVSX r16/r32/r64, m8 */
@@ -1660,7 +1660,7 @@ enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
case 0xbf: /* MOVSX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_SIGN_EXTEND;
+ type = INSN_MMIO_READ_SIGN_EXTEND;
break;
}
break;
--
GitLab
From c07311b5509f6035f1dd828db3e90ff4859cf3b9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 28 Dec 2022 06:34:54 -0500
Subject: [PATCH 0320/1167] perf/x86/rapl: Treat Tigerlake like Icelake
Since Tigerlake seems to have inherited its cstates and other RAPL power
caps from Icelake, assume it also follows Icelake for its RAPL events.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20221228113454.1199118-1-rodrigo.vivi@intel.com
---
arch/x86/events/rapl.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index a829492bca4c1..ae5779ea44174 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -800,6 +800,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
--
GitLab
From c0f399ff51495ac8d30367418f4f6292ecd61fbe Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Mon, 26 Dec 2022 10:11:18 -0800
Subject: [PATCH 0321/1167] xfs: fix off-by-one error in
xfs_btree_space_to_height
Lately I've been stress-testing extreme-sized rmap btrees by using the
(new) xfs_db bmap_inflate command to clone bmbt mappings billions of
times and then using xfs_repair to build new rmap and refcount btrees.
This of course is /much/ faster than actually FICLONEing a file billions
of times.
Unfortunately, xfs_repair fails in xfs_btree_bload_compute_geometry with
EOVERFLOW, which indicates that xfs_mount.m_rmap_maxlevels is not
sufficiently large for the test scenario. For a 1TB filesystem (~67
million AG blocks, 4 AGs) the btheight command reports:
$ xfs_db -c 'btheight -n 4400801200 -w min rmapbt' /dev/sda
rmapbt: worst case per 4096-byte block: 84 records (leaf) / 45 keyptrs (node)
level 0: 4400801200 records, 52390491 blocks
level 1: 52390491 records, 1164234 blocks
level 2: 1164234 records, 25872 blocks
level 3: 25872 records, 575 blocks
level 4: 575 records, 13 blocks
level 5: 13 records, 1 block
6 levels, 53581186 blocks total
The AG is sufficiently large to build this rmap btree. Unfortunately,
m_rmap_maxlevels is 5. Augmenting the loop in the space->height
function to report height, node blocks, and blocks remaining produces
this:
ht 1 node_blocks 45 blockleft 67108863
ht 2 node_blocks 2025 blockleft 67108818
ht 3 node_blocks 91125 blockleft 67106793
ht 4 node_blocks 4100625 blockleft 67015668
final height: 5
The goal of this function is to compute the maximum height btree that
can be stored in the given number of ondisk fsblocks. Starting with the
top level of the tree, each iteration through the loop adds the fanout
factor of the next level down until we run out of blocks. IOWs, maximum
height is achieved by using the smallest fanout factor that can apply
to that level.
However, the loop setup is not correct. Top level btree blocks are
allowed to contain fewer than minrecs items, so the computation is
incorrect because the first time through the loop it should be using a
fanout factor of 2. With this corrected, the above becomes:
ht 1 node_blocks 2 blockleft 67108863
ht 2 node_blocks 90 blockleft 67108861
ht 3 node_blocks 4050 blockleft 67108771
ht 4 node_blocks 182250 blockleft 67104721
ht 5 node_blocks 8201250 blockleft 66922471
final height: 6
Fixes: 9ec691205e7d ("xfs: compute the maximum height of the rmap btree when reflink enabled")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
---
fs/xfs/libxfs/xfs_btree.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 4c16c8c31fcbc..35f574421670d 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4666,7 +4666,12 @@ xfs_btree_space_to_height(
const unsigned int *limits,
unsigned long long leaf_blocks)
{
- unsigned long long node_blocks = limits[1];
+ /*
+ * The root btree block can have fewer than minrecs pointers in it
+ * because the tree might not be big enough to require that amount of
+ * fanout. Hence it has a minimum size of 2 pointers, not limits[1].
+ */
+ unsigned long long node_blocks = 2;
unsigned long long blocks_left = leaf_blocks - 1;
unsigned int height = 1;
--
GitLab
From 817644fa4525258992f17fecf4f1d6cdd2e1b731 Mon Sep 17 00:00:00 2001
From: Hironori Shiina <shiina.hironori@gmail.com>
Date: Mon, 26 Dec 2022 10:11:19 -0800
Subject: [PATCH 0322/1167] xfs: get root inode correctly at bulkstat
The root inode number should be set to `breq->startino` for getting stat
information of the root when XFS_BULK_IREQ_SPECIAL_ROOT is used.
Otherwise, the inode search is started from 1
(XFS_BULK_IREQ_SPECIAL_ROOT) and the inode with the lowest number in a
filesystem is returned.
Fixes: bf3cb3944792 ("xfs: allow single bulkstat of special inodes")
Signed-off-by: Hironori Shiina <shiina.hironori@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_ioctl.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 13f1b2add3904..736510bc241b8 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -754,7 +754,7 @@ xfs_bulkstat_fmt(
static int
xfs_bulk_ireq_setup(
struct xfs_mount *mp,
- struct xfs_bulk_ireq *hdr,
+ const struct xfs_bulk_ireq *hdr,
struct xfs_ibulk *breq,
void __user *ubuffer)
{
@@ -780,7 +780,7 @@ xfs_bulk_ireq_setup(
switch (hdr->ino) {
case XFS_BULK_IREQ_SPECIAL_ROOT:
- hdr->ino = mp->m_sb.sb_rootino;
+ breq->startino = mp->m_sb.sb_rootino;
break;
default:
return -EINVAL;
--
GitLab
From 4da112513c01d7d0acf1025b8764349d46e177d6 Mon Sep 17 00:00:00 2001
From: Wu Guanghao <wuguanghao3@huawei.com>
Date: Tue, 27 Dec 2022 09:41:30 -0800
Subject: [PATCH 0323/1167] xfs: Fix deadlock on xfs_inodegc_worker
We are doing a test about deleting a large number of files
when memory is low. A deadlock problem was found.
[ 1240.279183] -> #1 (fs_reclaim){+.+.}-{0:0}:
[ 1240.280450] lock_acquire+0x197/0x460
[ 1240.281548] fs_reclaim_acquire.part.0+0x20/0x30
[ 1240.282625] kmem_cache_alloc+0x2b/0x940
[ 1240.283816] xfs_trans_alloc+0x8a/0x8b0
[ 1240.284757] xfs_inactive_ifree+0xe4/0x4e0
[ 1240.285935] xfs_inactive+0x4e9/0x8a0
[ 1240.286836] xfs_inodegc_worker+0x160/0x5e0
[ 1240.287969] process_one_work+0xa19/0x16b0
[ 1240.289030] worker_thread+0x9e/0x1050
[ 1240.290131] kthread+0x34f/0x460
[ 1240.290999] ret_from_fork+0x22/0x30
[ 1240.291905]
[ 1240.291905] -> #0 ((work_completion)(&gc->work)){+.+.}-{0:0}:
[ 1240.293569] check_prev_add+0x160/0x2490
[ 1240.294473] __lock_acquire+0x2c4d/0x5160
[ 1240.295544] lock_acquire+0x197/0x460
[ 1240.296403] __flush_work+0x6bc/0xa20
[ 1240.297522] xfs_inode_mark_reclaimable+0x6f0/0xdc0
[ 1240.298649] destroy_inode+0xc6/0x1b0
[ 1240.299677] dispose_list+0xe1/0x1d0
[ 1240.300567] prune_icache_sb+0xec/0x150
[ 1240.301794] super_cache_scan+0x2c9/0x480
[ 1240.302776] do_shrink_slab+0x3f0/0xaa0
[ 1240.303671] shrink_slab+0x170/0x660
[ 1240.304601] shrink_node+0x7f7/0x1df0
[ 1240.305515] balance_pgdat+0x766/0xf50
[ 1240.306657] kswapd+0x5bd/0xd20
[ 1240.307551] kthread+0x34f/0x460
[ 1240.308346] ret_from_fork+0x22/0x30
[ 1240.309247]
[ 1240.309247] other info that might help us debug this:
[ 1240.309247]
[ 1240.310944] Possible unsafe locking scenario:
[ 1240.310944]
[ 1240.312379] CPU0 CPU1
[ 1240.313363] ---- ----
[ 1240.314433] lock(fs_reclaim);
[ 1240.315107] lock((work_completion)(&gc->work));
[ 1240.316828] lock(fs_reclaim);
[ 1240.318088] lock((work_completion)(&gc->work));
[ 1240.319203]
[ 1240.319203] *** DEADLOCK ***
...
[ 2438.431081] Workqueue: xfs-inodegc/sda xfs_inodegc_worker
[ 2438.432089] Call Trace:
[ 2438.432562] __schedule+0xa94/0x1d20
[ 2438.435787] schedule+0xbf/0x270
[ 2438.436397] schedule_timeout+0x6f8/0x8b0
[ 2438.445126] wait_for_completion+0x163/0x260
[ 2438.448610] __flush_work+0x4c4/0xa40
[ 2438.455011] xfs_inode_mark_reclaimable+0x6ef/0xda0
[ 2438.456695] destroy_inode+0xc6/0x1b0
[ 2438.457375] dispose_list+0xe1/0x1d0
[ 2438.458834] prune_icache_sb+0xe8/0x150
[ 2438.461181] super_cache_scan+0x2b3/0x470
[ 2438.461950] do_shrink_slab+0x3cf/0xa50
[ 2438.462687] shrink_slab+0x17d/0x660
[ 2438.466392] shrink_node+0x87e/0x1d40
[ 2438.467894] do_try_to_free_pages+0x364/0x1300
[ 2438.471188] try_to_free_pages+0x26c/0x5b0
[ 2438.473567] __alloc_pages_slowpath.constprop.136+0x7aa/0x2100
[ 2438.482577] __alloc_pages+0x5db/0x710
[ 2438.485231] alloc_pages+0x100/0x200
[ 2438.485923] allocate_slab+0x2c0/0x380
[ 2438.486623] ___slab_alloc+0x41f/0x690
[ 2438.490254] __slab_alloc+0x54/0x70
[ 2438.491692] kmem_cache_alloc+0x23e/0x270
[ 2438.492437] xfs_trans_alloc+0x88/0x880
[ 2438.493168] xfs_inactive_ifree+0xe2/0x4e0
[ 2438.496419] xfs_inactive+0x4eb/0x8b0
[ 2438.497123] xfs_inodegc_worker+0x16b/0x5e0
[ 2438.497918] process_one_work+0xbf7/0x1a20
[ 2438.500316] worker_thread+0x8c/0x1060
[ 2438.504938] ret_from_fork+0x22/0x30
When the memory is insufficient, xfs_inonodegc_worker will trigger memory
reclamation when memory is allocated, then flush_work() may be called to
wait for the work to complete. This causes a deadlock.
So use memalloc_nofs_save() to avoid triggering memory reclamation in
xfs_inodegc_worker.
Signed-off-by: Wu Guanghao <wuguanghao3@huawei.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_icache.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index f35e2cee52655..ddeaccc04aec9 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1853,12 +1853,20 @@ xfs_inodegc_worker(
struct xfs_inodegc, work);
struct llist_node *node = llist_del_all(&gc->list);
struct xfs_inode *ip, *n;
+ unsigned int nofs_flag;
WRITE_ONCE(gc->items, 0);
if (!node)
return;
+ /*
+ * We can allocate memory here while doing writeback on behalf of
+ * memory reclaim. To avoid memory allocation deadlocks set the
+ * task-wide nofs context for the following operations.
+ */
+ nofs_flag = memalloc_nofs_save();
+
ip = llist_entry(node, struct xfs_inode, i_gclist);
trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits));
@@ -1867,6 +1875,8 @@ xfs_inodegc_worker(
xfs_iflags_set(ip, XFS_INACTIVATING);
xfs_inodegc_inactivate(ip);
}
+
+ memalloc_nofs_restore(nofs_flag);
}
/*
--
GitLab
From e195605ed28b5581dc2d509283cfea2e8635a251 Mon Sep 17 00:00:00 2001
From: Li zeming <zeming@nfschina.com>
Date: Tue, 3 Jan 2023 09:54:28 -0800
Subject: [PATCH 0324/1167] =?UTF-8?q?xfs:=20xfs=5Fqm:=20remove=20unnecessa?=
=?UTF-8?q?ry=20=E2=80=980=E2=80=99=20values=20from=20error?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
error is assigned first, so it does not need to initialize the
assignment.
Signed-off-by: Li zeming <zeming@nfschina.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_qm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index ff53d40a2dae3..e2c542f6dcd4d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -68,7 +68,7 @@ xfs_qm_dquot_walk(
while (1) {
struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH];
- int error = 0;
+ int error;
int i;
mutex_lock(&qi->qi_tree_lock);
--
GitLab
From f89fb55714b620ff1352141a9f9315611f16573e Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 2 Jan 2023 23:09:16 -0800
Subject: [PATCH 0325/1167] perf build: Don't propagate subdir to submakes for
install_headers
subdir is added to the OUTPUT which fails as part of building
install_headers when passed from "make -C tools perf_install".
Committer testing:
The original reporter (see the Link: below) had trouble with this:
$ make -C tools perf_install
That ended up with errors like this:
/var/home/acme/git/perf-urgent/tools/scripts/Makefile.include:17: *** output directory "/var/home/acme/git/perf-urgent/tools/perf/libperf/perf/" does not exist. Stop.
With this patch applied we now get it installed at:
INSTALL /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h
As expected:
$ ls -la /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h
-rw-r--r--. 1 acme acme 1146 Jan 3 15:42 /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h
And if we clean tools with:
$ make -C tools clean
it gets cleaned up:
$ ls -la /var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h
ls: cannot access '/var/home/acme/git/perf-urgent/tools/perf/libperf/include/perf/bpf_perf.h': No such file or directory
$
Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path")
Reported-by: Torsten Hilbrich <torsten.hilbrich@secunet.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/fa4b3115-d555-3d7f-54d1-018002e99350@secunet.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.perf | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 13e7d26e77f04..1e32c93b80429 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -819,7 +819,7 @@ $(patsubst perf-%,%.o,$(PROGRAMS)): $(wildcard */*.h)
$(LIBAPI): FORCE | $(LIBAPI_OUTPUT)
$(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \
- DESTDIR=$(LIBAPI_DESTDIR) prefix= \
+ DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBAPI)-clean:
@@ -828,7 +828,7 @@ $(LIBAPI)-clean:
$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
- O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+ O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBBPF)-clean:
@@ -837,7 +837,7 @@ $(LIBBPF)-clean:
$(LIBPERF): FORCE | $(LIBPERF_OUTPUT)
$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \
- DESTDIR=$(LIBPERF_DESTDIR) prefix= \
+ DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBPERF)-clean:
@@ -846,7 +846,7 @@ $(LIBPERF)-clean:
$(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT)
$(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \
- DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= \
+ DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSUBCMD)-clean:
@@ -855,7 +855,7 @@ $(LIBSUBCMD)-clean:
$(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT)
$(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \
- DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= \
+ DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSYMBOL)-clean:
--
GitLab
From d8d85ce86dc82de4f88b821a78f533b9d5b22a45 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 30 Dec 2022 11:26:27 +0100
Subject: [PATCH 0326/1167] perf lock contention: Fix core dump related to not
finding the "__sched_text_end" symbol on s/390
The test case perf lock contention dumps core on s390. Run the following
commands:
# ./perf lock record -- ./perf bench sched messaging
# Running 'sched/messaging' benchmark:
# 20 sender and receiver processes per group
# 10 groups == 400 processes run
Total time: 2.799 [sec]
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.073 MB perf.data (100 samples) ]
#
# ./perf lock contention
Segmentation fault (core dumped)
#
The function call stack is lengthy, here are the top 5 functions:
# gdb ./perf core.24048
GNU gdb (GDB) Fedora Linux 12.1-6.fc37
Core was generated by `./perf lock contention'.
Program terminated with signal SIGSEGV, Segmentation fault.
#0 0x00000000011dd25c in machine__is_lock_function (machine=0x3029e28, addr=1789230) at util/machine.c:3356
3356 machine->sched.text_end = kmap->unmap_ip(kmap, sym->start);
(gdb) where
#0 0x00000000011dd25c in machine__is_lock_function (machine=0x3029e28, addr=1789230) at util/machine.c:3356
#1 0x000000000109f244 in callchain_id (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:957
#2 0x000000000109e094 in get_key_by_aggr_mode (key=0x3ffea4f7290, addr=27758136, evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:586
#3 0x000000000109f4d0 in report_lock_contention_begin_event (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:1004
#4 0x00000000010a00ae in evsel__process_contention_begin (evsel=0x30313e0, sample=0x3ffea4f77d0) at builtin-lock.c:1254
#5 0x00000000010a0e14 in process_sample_event (tool=0x3ffea4f8480, event=0x3ff85601ef8, sample=0x3ffea4f77d0, evsel=0x30313e0, machine=0x3029e28) at builtin-lock.c:1464
.....
The issue is in function machine__is_lock_function() in file
./util/machine.c lines 3355:
/* should not fail from here */
sym = machine__find_kernel_symbol_by_name(machine, "__sched_text_end", &kmap);
machine->sched.text_end = kmap->unmap_ip(kmap, sym->start)
On s390 the symbol __sched_text_end is *NOT* in the symbol list and the
resulting pointer sym is set to NULL. The sym->start is then a NULL pointer
access and generates the core dump.
The reason why __sched_text_end is not in the symbol list on s390 is
simple:
When the symbol list is created at perf start up with function calls
dso__load
+--> dso__load_vmlinux_path
+--> dso__load_vmlinux
+--> dso__load_sym
+--> dso__load_sym_internal (reads kernel symbols)
+--> symbols__fixup_end
+--> symbols__fixup_duplicate
The issue is in function symbols__fixup_duplicate(). It deletes all
symbols with have the same address. On s390:
# nm -g ~/linux/vmlinux| fgrep c68390
0000000000c68390 T __cpuidle_text_start
0000000000c68390 T __sched_text_end
#
two symbols have identical addresses and __sched_text_end is considered
duplicate (in ascending sort order) and removed from the symbol list.
Therefore it is missing and an invalid pointer reference occurs. The
code checks for symbol __sched_text_start and when it exists assumes
symbol __sched_text_end is also in the symbol table. However this is not
the case on s390.
Same situation exists for symbol __lock_text_start:
0000000000c68770 T __cpuidle_text_end
0000000000c68770 T __lock_text_start
This symbol is also removed from the symbol table but used in function
machine__is_lock_function().
To fix this and keep duplicate symbols in the symbol table, set
symbol_conf.allow_aliases to true. This prevents the removal of
duplicate symbols in function symbols__fixup_duplicate().
Output After:
# ./perf lock contention
contended total wait max wait avg wait type caller
48 124.39 ms 123.99 ms 2.59 ms rwsem:W unlink_anon_vmas+0x24a
47 83.68 ms 83.26 ms 1.78 ms rwsem:W free_pgtables+0x132
5 41.22 us 10.55 us 8.24 us rwsem:W free_pgtables+0x140
4 40.12 us 20.55 us 10.03 us rwsem:W copy_process+0x1ac8
#
Fixes: 0d2997f750d1de39 ("perf lock: Look up callchain for the contended locks")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20221230102627.2410847-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-lock.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 718b82bfcdff9..506c2fe42d523 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1670,6 +1670,7 @@ static int __cmd_report(bool display_info)
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (!data.is_pipe) {
@@ -1757,6 +1758,7 @@ static int __cmd_contention(int argc, const char **argv)
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (use_bpf) {
--
GitLab
From cf97eb7e47d4671084c7e114c5d88a3d0540ecbd Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Tue, 20 Dec 2022 17:11:24 -0500
Subject: [PATCH 0327/1167] drm/amdkfd: Fix kernel warning during topology
setup
This patch fixes the following kernel warning seen during
driver load by correctly initializing the p2plink attr before
creating the sysfs file:
[ +0.002865] ------------[ cut here ]------------
[ +0.002327] kobject: '(null)' (0000000056260cfb): is not initialized, yet kobject_put() is being called.
[ +0.004780] WARNING: CPU: 32 PID: 1006 at lib/kobject.c:718 kobject_put+0xaa/0x1c0
[ +0.001361] Call Trace:
[ +0.001234] <TASK>
[ +0.001067] kfd_remove_sysfs_node_entry+0x24a/0x2d0 [amdgpu]
[ +0.003147] kfd_topology_update_sysfs+0x3d/0x750 [amdgpu]
[ +0.002890] kfd_topology_add_device+0xbd7/0xc70 [amdgpu]
[ +0.002844] ? lock_release+0x13c/0x2e0
[ +0.001936] ? smu_cmn_send_smc_msg_with_param+0x1e8/0x2d0 [amdgpu]
[ +0.003313] ? amdgpu_dpm_get_mclk+0x54/0x60 [amdgpu]
[ +0.002703] kgd2kfd_device_init.cold+0x39f/0x4ed [amdgpu]
[ +0.002930] amdgpu_amdkfd_device_init+0x13d/0x1f0 [amdgpu]
[ +0.002944] amdgpu_device_init.cold+0x1464/0x17b4 [amdgpu]
[ +0.002970] ? pci_bus_read_config_word+0x43/0x80
[ +0.002380] amdgpu_driver_load_kms+0x15/0x100 [amdgpu]
[ +0.002744] amdgpu_pci_probe+0x147/0x370 [amdgpu]
[ +0.002522] local_pci_probe+0x40/0x80
[ +0.001896] work_for_cpu_fn+0x10/0x20
[ +0.001892] process_one_work+0x26e/0x5a0
[ +0.002029] worker_thread+0x1fd/0x3e0
[ +0.001890] ? process_one_work+0x5a0/0x5a0
[ +0.002115] kthread+0xea/0x110
[ +0.001618] ? kthread_complete_and_exit+0x20/0x20
[ +0.002422] ret_from_fork+0x1f/0x30
[ +0.001808] </TASK>
[ +0.001103] irq event stamp: 59837
[ +0.001718] hardirqs last enabled at (59849): [<ffffffffb30fab12>] __up_console_sem+0x52/0x60
[ +0.004414] hardirqs last disabled at (59860): [<ffffffffb30faaf7>] __up_console_sem+0x37/0x60
[ +0.004414] softirqs last enabled at (59654): [<ffffffffb307d9c7>] irq_exit_rcu+0xd7/0x130
[ +0.004205] softirqs last disabled at (59649): [<ffffffffb307d9c7>] irq_exit_rcu+0xd7/0x130
[ +0.004203] ---[ end trace 0000000000000000 ]---
Fixes: 0f28cca87e9a ("drm/amdkfd: Extend KFD device topology to surface peer-to-peer links")
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index bceb1a5b25186..3fdaba56be6fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -801,7 +801,7 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev,
p2plink->attr.name = "properties";
p2plink->attr.mode = KFD_SYSFS_FILE_MODE;
- sysfs_attr_init(&iolink->attr);
+ sysfs_attr_init(&p2plink->attr);
ret = sysfs_create_file(p2plink->kobj, &p2plink->attr);
if (ret < 0)
return ret;
--
GitLab
From f3c23bea598ab7e8e4b8c5ca66598921310f718e Mon Sep 17 00:00:00 2001
From: Samson Tam <samson.tam@amd.com>
Date: Mon, 5 Dec 2022 11:08:40 -0500
Subject: [PATCH 0328/1167] drm/amd/display: Uninitialized variables causing
4k60 UCLK to stay at DPM1 and not DPM0
[Why]
SwathSizePerSurfaceY[] and SwathSizePerSurfaceC[] values are uninitialized
because we are using += instead of = operator.
[How]
Assign values in loop with = operator.
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Samson Tam <samson.tam@amd.com>
Reviewed-by: Aric Cyr <aric.cyr@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0.x, 6.1.x
---
.../drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index 5af601cff1a0f..b53feeaf5cf11 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -6257,12 +6257,12 @@ bool dml32_CalculateDETSwathFillLatencyHiding(unsigned int NumberOfActiveSurface
double SwathSizePerSurfaceC[DC__NUM_DPP__MAX];
bool NotEnoughDETSwathFillLatencyHiding = false;
- /* calculate sum of single swath size for all pipes in bytes*/
+ /* calculate sum of single swath size for all pipes in bytes */
for (k = 0; k < NumberOfActiveSurfaces; k++) {
- SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
+ SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
if (SwathHeightC[k] != 0)
- SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
+ SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
else
SwathSizePerSurfaceC[k] = 0;
--
GitLab
From 2a12187d5853d9fd5102278cecef7dac7c8ce7ea Mon Sep 17 00:00:00 2001
From: Andreas Rammhold <andreas@rammhold.de>
Date: Fri, 23 Dec 2022 12:27:47 +0100
Subject: [PATCH 0329/1167] of/fdt: run soc memory setup when
early_init_dt_scan_memory fails
If memory has been found early_init_dt_scan_memory now returns 1. If
it hasn't found any memory it will return 0, allowing other memory
setup mechanisms to carry on.
Previously early_init_dt_scan_memory always returned 0 without
distinguishing between any kind of memory setup being done or not. Any
code path after the early_init_dt_scan memory call in the ramips
plat_mem_setup code wouldn't be executed anymore. Making
early_init_dt_scan_memory the only way to initialize the memory.
Some boards, including my mt7621 based Cudy X6 board, depend on memory
initialization being done via the soc_info.mem_detect function
pointer. Those wouldn't be able to obtain memory and panic the kernel
during early bootup with the message "early_init_dt_alloc_memory_arch:
Failed to allocate 12416 bytes align=0x40".
Fixes: 1f012283e936 ("of/fdt: Rework early_init_dt_scan_memory() to call directly")
Cc: stable@vger.kernel.org
Signed-off-by: Andreas Rammhold <andreas@rammhold.de>
Link: https://lore.kernel.org/r/20221223112748.2935235-1-andreas@rammhold.de
Signed-off-by: Rob Herring <robh@kernel.org>
---
arch/mips/ralink/of.c | 2 +-
drivers/of/fdt.c | 6 ++++--
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c
index 01c132bc33d54..4d06de77d92a6 100644
--- a/arch/mips/ralink/of.c
+++ b/arch/mips/ralink/of.c
@@ -64,7 +64,7 @@ void __init plat_mem_setup(void)
dtb = get_fdt();
__dt_setup_arch(dtb);
- if (!early_init_dt_scan_memory())
+ if (early_init_dt_scan_memory())
return;
if (soc_info.mem_detect)
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index b2272bccf85c9..02cc4a285cb98 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1099,7 +1099,7 @@ u64 __init dt_mem_next_cell(int s, const __be32 **cellp)
*/
int __init early_init_dt_scan_memory(void)
{
- int node;
+ int node, found_memory = 0;
const void *fdt = initial_boot_params;
fdt_for_each_subnode(node, fdt, 0) {
@@ -1139,6 +1139,8 @@ int __init early_init_dt_scan_memory(void)
early_init_dt_add_memory_arch(base, size);
+ found_memory = 1;
+
if (!hotpluggable)
continue;
@@ -1147,7 +1149,7 @@ int __init early_init_dt_scan_memory(void)
base, base + size);
}
}
- return 0;
+ return found_memory;
}
int __init early_init_dt_scan_chosen(char *cmdline)
--
GitLab
From 1d7a4a40bf76e2305c8beed4a019bf58af6121ac Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 23 Dec 2022 14:21:59 +0100
Subject: [PATCH 0330/1167] dt-bindings: soundwire: qcom,soundwire: correct
sizes related to number of ports
There are several properties depending on number of ports. Some of them
had maximum limit of 5 and some of 8. SM8450 AudioReach comes with 8
ports, so fix the limits:
sm8450-sony-xperia-nagara-pdx224.dtb: soundwire-controller@3250000: qcom,ports-word-length: 'oneOf' conditional failed, one must be fixed:
[[255, 255, 255, 255, 255, 255, 255, 255]] is too short
[255, 255, 255, 255, 255, 255, 255, 255] is too long
Fixes: febc50b82bc9 ("dt-bindings: soundwire: Convert text bindings to DT Schema")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20221223132159.81211-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
.../devicetree/bindings/soundwire/qcom,soundwire.yaml | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml b/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml
index bcbfa71536cda..3efdc192ab019 100644
--- a/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml
+++ b/Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml
@@ -80,7 +80,7 @@ properties:
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-sinterval-low:
$ref: /schemas/types.yaml#/definitions/uint8-array
@@ -124,7 +124,7 @@ properties:
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-block-pack-mode:
$ref: /schemas/types.yaml#/definitions/uint8-array
@@ -154,7 +154,7 @@ properties:
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
@@ -171,7 +171,7 @@ properties:
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
@@ -187,7 +187,7 @@ properties:
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
--
GitLab
From 937e7a39068d806c1a951f19e38e1326be20f1b0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 29 Dec 2022 12:07:46 +0200
Subject: [PATCH 0331/1167] pinctrl: nomadik: Add missing header(s)
Do not imply that some of the generic headers may be always included.
Instead, include explicitly what we are direct user of.
While at it, sort headers alphabetically.
Fixes: e5530adc17a7 ("pinctrl: Clean up headers")
Cc: Randy Dunlap <rdunlap@infradead.org>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20221229100746.35047-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/pinctrl/nomadik/pinctrl-ab8500.c | 3 +-
drivers/pinctrl/nomadik/pinctrl-ab8505.c | 3 +-
drivers/pinctrl/nomadik/pinctrl-abx500.c | 32 +++++++++++--------
drivers/pinctrl/nomadik/pinctrl-abx500.h | 4 +++
.../pinctrl/nomadik/pinctrl-nomadik-db8500.c | 3 ++
.../pinctrl/nomadik/pinctrl-nomadik-stn8815.c | 3 ++
drivers/pinctrl/nomadik/pinctrl-nomadik.c | 32 ++++++++++---------
drivers/pinctrl/nomadik/pinctrl-nomadik.h | 5 +++
8 files changed, 54 insertions(+), 31 deletions(-)
diff --git a/drivers/pinctrl/nomadik/pinctrl-ab8500.c b/drivers/pinctrl/nomadik/pinctrl-ab8500.c
index 3106a21cd277f..d7b244df058f2 100644
--- a/drivers/pinctrl/nomadik/pinctrl-ab8500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-ab8500.c
@@ -6,9 +6,10 @@
*/
#include <linux/kernel.h>
-#include <linux/gpio/driver.h>
#include <linux/pinctrl/pinctrl.h>
+
#include <linux/mfd/abx500/ab8500.h>
+
#include "pinctrl-abx500.h"
/* All the pins that can be used for GPIO and some other functions */
diff --git a/drivers/pinctrl/nomadik/pinctrl-ab8505.c b/drivers/pinctrl/nomadik/pinctrl-ab8505.c
index b93af1fb37f01..45aa958b573e0 100644
--- a/drivers/pinctrl/nomadik/pinctrl-ab8505.c
+++ b/drivers/pinctrl/nomadik/pinctrl-ab8505.c
@@ -6,9 +6,10 @@
*/
#include <linux/kernel.h>
-#include <linux/gpio/driver.h>
#include <linux/pinctrl/pinctrl.h>
+
#include <linux/mfd/abx500/ab8500.h>
+
#include "pinctrl-abx500.h"
/* All the pins that can be used for GPIO and some other functions */
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 7aa534576a459..28c3403df1b03 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -6,33 +6,37 @@
*
* Driver allows to use AxB5xx unused pins to be used as GPIO
*/
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/init.h>
+#include <linux/bitops.h>
#include <linux/err.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
#include <linux/gpio/driver.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
-#include <linux/interrupt.h>
-#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
#include <linux/mfd/abx500.h>
#include <linux/mfd/abx500/ab8500.h>
-#include <linux/pinctrl/pinctrl.h>
+
#include <linux/pinctrl/consumer.h>
-#include <linux/pinctrl/pinmux.h>
-#include <linux/pinctrl/pinconf.h>
-#include <linux/pinctrl/pinconf-generic.h>
#include <linux/pinctrl/machine.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
-#include "pinctrl-abx500.h"
#include "../core.h"
#include "../pinconf.h"
#include "../pinctrl-utils.h"
+#include "pinctrl-abx500.h"
+
/*
* GPIO registers offset
* Bank: 0x10
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.h b/drivers/pinctrl/nomadik/pinctrl-abx500.h
index 90bb12fe8073f..d675220846752 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.h
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.h
@@ -2,6 +2,10 @@
#ifndef PINCTRL_PINCTRL_ABx500_H
#define PINCTRL_PINCTRL_ABx500_H
+#include <linux/types.h>
+
+struct pinctrl_pin_desc;
+
/* Package definitions */
#define PINCTRL_AB8500 0
#define PINCTRL_AB8505 1
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c b/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c
index 758d21f0a8503..490e0959e8be6 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c
@@ -1,6 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
+#include <linux/types.h>
+
#include <linux/pinctrl/pinctrl.h>
+
#include "pinctrl-nomadik.h"
/* All the pins that can be used for GPIO and some other functions */
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
index c0d7c86d09391..1552222ac68e7 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c
@@ -1,6 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
+#include <linux/types.h>
+
#include <linux/pinctrl/pinctrl.h>
+
#include "pinctrl-nomadik.h"
/* All the pins that can be used for GPIO and some other functions */
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index f7d02513d8cc1..86a638077a697 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -7,30 +7,34 @@
* Rewritten based on work by Prafulla WADASKAR <prafulla.wadaskar@st.com>
* Copyright (C) 2011-2013 Linus Walleij <linus.walleij@linaro.org>
*/
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
+#include <linux/bitops.h>
#include <linux/clk.h>
+#include <linux/device.h>
#include <linux/err.h>
#include <linux/gpio/driver.h>
-#include <linux/spinlock.h>
+#include <linux/init.h>
#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/of_device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
#include <linux/of_address.h>
-#include <linux/bitops.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+/* Since we request GPIOs from ourself */
+#include <linux/pinctrl/consumer.h>
#include <linux/pinctrl/machine.h>
+#include <linux/pinctrl/pinconf.h>
#include <linux/pinctrl/pinctrl.h>
#include <linux/pinctrl/pinmux.h>
-#include <linux/pinctrl/pinconf.h>
-/* Since we request GPIOs from ourself */
-#include <linux/pinctrl/consumer.h>
-#include "pinctrl-nomadik.h"
+
#include "../core.h"
#include "../pinctrl-utils.h"
+#include "pinctrl-nomadik.h"
+
/*
* The GPIO module in the Nomadik family of Systems-on-Chip is an
* AMBA device, managing 32 pins and alternate functions. The logic block
@@ -907,8 +911,6 @@ static int nmk_gpio_get_mode(struct nmk_gpio_chip *nmk_chip, int offset)
return (afunc ? NMK_GPIO_ALT_A : 0) | (bfunc ? NMK_GPIO_ALT_B : 0);
}
-#include <linux/seq_file.h>
-
static void nmk_gpio_dbg_show_one(struct seq_file *s,
struct pinctrl_dev *pctldev, struct gpio_chip *chip,
unsigned offset, unsigned gpio)
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.h b/drivers/pinctrl/nomadik/pinctrl-nomadik.h
index 84e2977573357..1ef2559bc5710 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.h
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.h
@@ -2,6 +2,11 @@
#ifndef PINCTRL_PINCTRL_NOMADIK_H
#define PINCTRL_PINCTRL_NOMADIK_H
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include <linux/pinctrl/pinctrl.h>
+
/* Package definitions */
#define PINCTRL_NMK_STN8815 0
#define PINCTRL_NMK_DB8500 1
--
GitLab
From 9ffa13ff78a0a55df968a72d6f0ebffccee5c9f4 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 4 Jan 2023 01:34:02 +0000
Subject: [PATCH 0332/1167] io_uring: pin context while queueing deferred tw
Unlike normal tw, nothing prevents deferred tw to be executed right
after an tw item added to ->work_llist in io_req_local_work_add(). For
instance, the waiting task may get waken up by CQ posting or a normal
tw. Thus we need to pin the ring for the rest of io_req_local_work_add()
Cc: stable@vger.kernel.org
Fixes: c0e0d6ba25f18 ("io_uring: add IORING_SETUP_DEFER_TASKRUN")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/1a79362b9c10b8523ef70b061d96523650a23344.1672795998.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 58ac13b69dc8d..6bed448556798 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1236,13 +1236,18 @@ static void io_req_local_work_add(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- if (!llist_add(&req->io_task_work.node, &ctx->work_llist))
+ percpu_ref_get(&ctx->refs);
+
+ if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) {
+ percpu_ref_put(&ctx->refs);
return;
+ }
/* need it for the following io_cqring_wake() */
smp_mb__after_atomic();
if (unlikely(atomic_read(&req->task->io_uring->in_idle))) {
io_move_task_work_from_local(ctx);
+ percpu_ref_put(&ctx->refs);
return;
}
@@ -1252,6 +1257,7 @@ static void io_req_local_work_add(struct io_kiocb *req)
if (ctx->has_evfd)
io_eventfd_signal(ctx);
__io_cqring_wake(ctx);
+ percpu_ref_put(&ctx->refs);
}
void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
--
GitLab
From f26cc9593581bd734c846bf827401350b36dc3c9 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 4 Jan 2023 01:34:57 +0000
Subject: [PATCH 0333/1167] io_uring: lockdep annotate CQ locking
Locking around CQE posting is complex and depends on options the ring is
created with, add more thorough lockdep annotations checking all
invariants.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/aa3770b4eacae3915d782cc2ab2f395a99b4b232.1672795976.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 5 ++---
io_uring/io_uring.h | 15 +++++++++++++++
2 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 6bed448556798..472574192dd63 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -731,6 +731,8 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+ lockdep_assert_held(&ctx->completion_lock);
+
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
@@ -820,9 +822,6 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
{
struct io_uring_cqe *cqe;
- if (!ctx->task_complete)
- lockdep_assert_held(&ctx->completion_lock);
-
ctx->cq_extra++;
/*
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index e9f0d41ebb996..ab4b2a1c3b7e8 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -79,6 +79,19 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
+#define io_lockdep_assert_cq_locked(ctx) \
+ do { \
+ if (ctx->flags & IORING_SETUP_IOPOLL) { \
+ lockdep_assert_held(&ctx->uring_lock); \
+ } else if (!ctx->task_complete) { \
+ lockdep_assert_held(&ctx->completion_lock); \
+ } else if (ctx->submitter_task->flags & PF_EXITING) { \
+ lockdep_assert(current_work()); \
+ } else { \
+ lockdep_assert(current == ctx->submitter_task); \
+ } \
+ } while (0)
+
static inline void io_req_task_work_add(struct io_kiocb *req)
{
__io_req_task_work_add(req, true);
@@ -92,6 +105,8 @@ void io_cq_unlock_post(struct io_ring_ctx *ctx);
static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx,
bool overflow)
{
+ io_lockdep_assert_cq_locked(ctx);
+
if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
struct io_uring_cqe *cqe = ctx->cqe_cached;
--
GitLab
From 1cba0d150fa102439114a91b3e215909efc9f169 Mon Sep 17 00:00:00 2001
From: Kuogee Hsieh <quic_khsieh@quicinc.com>
Date: Tue, 27 Dec 2022 18:16:24 -0800
Subject: [PATCH 0334/1167] drm/msm/dp: do not complete dp_aux_cmd_fifo_tx() if
irq is not for aux transfer
There are 3 possible interrupt sources are handled by DP controller,
HPDstatus, Controller state changes and Aux read/write transaction.
At every irq, DP controller have to check isr status of every interrupt
sources and service the interrupt if its isr status bits shows interrupts
are pending. There is potential race condition may happen at current aux
isr handler implementation since it is always complete dp_aux_cmd_fifo_tx()
even irq is not for aux read or write transaction. This may cause aux read
transaction return premature if host aux data read is in the middle of
waiting for sink to complete transferring data to host while irq happen.
This will cause host's receiving buffer contains unexpected data. This
patch fixes this problem by checking aux isr and return immediately at
aux isr handler if there are no any isr status bits set.
Current there is a bug report regrading eDP edid corruption happen during
system booting up. After lengthy debugging to found that VIDEO_READY
interrupt was continuously firing during system booting up which cause
dp_aux_isr() to complete dp_aux_cmd_fifo_tx() prematurely to retrieve data
from aux hardware buffer which is not yet contains complete data transfer
from sink. This cause edid corruption.
Follows are the signature at kernel logs when problem happen,
EDID has corrupt header
panel-simple-dp-aux aux-aea0000.edp: Couldn't identify panel via EDID
Changes in v2:
-- do complete if (ret == IRQ_HANDLED) ay dp-aux_isr()
-- add more commit text
Changes in v3:
-- add Stephen suggested
-- dp_aux_isr() return IRQ_XXX back to caller
-- dp_ctrl_isr() return IRQ_XXX back to caller
Changes in v4:
-- split into two patches
Changes in v5:
-- delete empty line between tags
Changes in v6:
-- remove extra "that" and fixed line more than 75 char at commit text
Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: Kuogee Hsieh <quic_khsieh@quicinc.com>
Tested-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/516121/
Link: https://lore.kernel.org/r/1672193785-11003-2-git-send-email-quic_khsieh@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/dp/dp_aux.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index d030a93a08c36..cc3efed593aa1 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -423,6 +423,10 @@ void dp_aux_isr(struct drm_dp_aux *dp_aux)
isr = dp_catalog_aux_get_irq(aux->catalog);
+ /* no interrupts pending, return immediately */
+ if (!isr)
+ return;
+
if (!aux->cmd_busy)
return;
--
GitLab
From 67fcb2c598bc7643f694e8194d5c300a52af5aa9 Mon Sep 17 00:00:00 2001
From: Ira Weiny <ira.weiny@intel.com>
Date: Thu, 29 Dec 2022 14:04:46 -0800
Subject: [PATCH 0335/1167] cifs: Fix kmap_local_page() unmapping
kmap_local_page() requires kunmap_local() to unmap the mapping. In
addition memcpy_page() is provided to perform this common memcpy
pattern.
Replace the kmap_local_page() and broken kunmap() with memcpy_page()
Fixes: d406d26745ab ("cifs: skip alloc when request has no pages")
Reviewed-by: Paulo Alcantara <pc@cjr.nz>
Reviewed-by: "Fabio M. De Francesco" <fmdefrancesco@gmail.com>
Cc: linux-cifs@vger.kernel.org
Cc: samba-technical@lists.samba.org
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb2ops.c | 9 ++-------
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index dc160de7a6de4..0d7e9bcd9f345 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4488,17 +4488,12 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
/* copy pages form the old */
for (j = 0; j < npages; j++) {
- char *dst, *src;
unsigned int offset, len;
rqst_page_get_length(new, j, &len, &offset);
- dst = kmap_local_page(new->rq_pages[j]) + offset;
- src = kmap_local_page(old->rq_pages[j]) + offset;
-
- memcpy(dst, src, len);
- kunmap(new->rq_pages[j]);
- kunmap(old->rq_pages[j]);
+ memcpy_page(new->rq_pages[j], offset,
+ old->rq_pages[j], offset, len);
}
}
--
GitLab
From 9e6002c8738a9d5675ba706fcdbc0a544f814974 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Thu, 29 Dec 2022 12:33:55 -0300
Subject: [PATCH 0336/1167] cifs: ignore ipc reconnect failures during dfs
failover
If it failed to reconnect ipc used for getting referrals, we can just
ignore it as it is not required for reconnecting the share. The worst
case would be not being able to detect or chase nested links as long
as dfs root server is unreachable.
Before patch:
$ mount.cifs //root/dfs/link /mnt -o echo_interval=10,...
-> target share: /fs0/share
disconnect root & fs0
$ ls /mnt
ls: cannot access '/mnt': Host is down
connect fs0
$ ls /mnt
ls: cannot access '/mnt': Resource temporarily unavailable
After patch:
$ mount.cifs //root/dfs/link /mnt -o echo_interval=10,...
-> target share: /fs0/share
disconnect root & fs0
$ ls /mnt
ls: cannot access '/mnt': Host is down
connect fs0
$ ls /mnt
bar.rtf dir1 foo
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c
index b541e68378f64..30086f2060a10 100644
--- a/fs/cifs/dfs.c
+++ b/fs/cifs/dfs.c
@@ -401,8 +401,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t
if (ipc->need_reconnect) {
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls);
- if (rc)
- break;
+ cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc);
}
scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
--
GitLab
From 775e44d6d86dca400d614cbda5dab4def4951fe7 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Thu, 29 Dec 2022 12:33:56 -0300
Subject: [PATCH 0337/1167] cifs: fix race in assemble_neg_contexts()
Serialise access of TCP_Server_Info::hostname in
assemble_neg_contexts() by holding the server's mutex otherwise it
might end up accessing an already-freed hostname pointer from
cifs_reconnect() or cifs_resolve_server().
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb2pdu.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index a5695748a89b1..2c484d47c5922 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -541,9 +541,10 @@ static void
assemble_neg_contexts(struct smb2_negotiate_req *req,
struct TCP_Server_Info *server, unsigned int *total_len)
{
- char *pneg_ctxt;
- char *hostname = NULL;
unsigned int ctxt_len, neg_context_count;
+ struct TCP_Server_Info *pserver;
+ char *pneg_ctxt;
+ char *hostname;
if (*total_len > 200) {
/* In case length corrupted don't want to overrun smb buffer */
@@ -574,8 +575,9 @@ assemble_neg_contexts(struct smb2_negotiate_req *req,
* secondary channels don't have the hostname field populated
* use the hostname field in the primary channel instead
*/
- hostname = CIFS_SERVER_IS_CHAN(server) ?
- server->primary_server->hostname : server->hostname;
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+ cifs_server_lock(pserver);
+ hostname = pserver->hostname;
if (hostname && (hostname[0] != 0)) {
ctxt_len = build_netname_ctxt((struct smb2_netname_neg_context *)pneg_ctxt,
hostname);
@@ -584,6 +586,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req,
neg_context_count = 3;
} else
neg_context_count = 2;
+ cifs_server_unlock(pserver);
build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
*total_len += sizeof(struct smb2_posix_neg_context);
--
GitLab
From faf28e240dd118d9521c68aeb9388b9b8f02d9d0 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Tue, 3 Jan 2023 18:11:29 +0100
Subject: [PATCH 0338/1167] cpufreq: Add SM6375 to cpufreq-dt-platdev blocklist
The Qualcomm SM6375 platform uses the qcom-cpufreq-hw driver, so add
it to the cpufreq-dt-platdev driver's blocklist.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/cpufreq-dt-platdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index e329d29d1f9d1..e857036510986 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -151,6 +151,7 @@ static const struct of_device_id blocklist[] __initconst = {
{ .compatible = "qcom,sdm845", },
{ .compatible = "qcom,sm6115", },
{ .compatible = "qcom,sm6350", },
+ { .compatible = "qcom,sm6375", },
{ .compatible = "qcom,sm8150", },
{ .compatible = "qcom,sm8250", },
{ .compatible = "qcom,sm8350", },
--
GitLab
From 53cd37c1368d07649421517ed0aab94a49cca003 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 27 Dec 2022 15:42:02 +0100
Subject: [PATCH 0339/1167] dt-bindings: cpufreq: cpufreq-qcom-hw: document
interrupts
The Qualcomm Soc cpufreq hardware engine has LMh/thermal throttling
interrupts (already present in SM8250 and SM8450 DTS) and Linux driver
uses them:
sm8250-hdk.dtb: cpufreq@18591000: 'interrupt-names', 'interrupts' do not match any of the regexes: 'pinctrl-[0-9]+'
sm8450-qrd.dtb: cpufreq@17d91000: 'interrupt-names', 'interrupts' do not match any of the regexes: 'pinctrl-[0-9]+'
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
.../devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml
index 903b31129f012..99e159bc5fb13 100644
--- a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml
@@ -54,6 +54,17 @@ properties:
- const: xo
- const: alternate
+ interrupts:
+ minItems: 1
+ maxItems: 3
+
+ interrupt-names:
+ minItems: 1
+ items:
+ - const: dcvsh-irq-0
+ - const: dcvsh-irq-1
+ - const: dcvsh-irq-2
+
'#freq-domain-cells':
const: 1
--
GitLab
From 558016722e9d5bc0ac79c246ccd14a8a4eb028d4 Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat (VMware)" <srivatsa@csail.mit.edu>
Date: Tue, 3 Jan 2023 14:09:41 -0800
Subject: [PATCH 0340/1167] MAINTAINERS: Update maintainers for ptp_vmw driver
Vivek has decided to transfer the maintainership of the VMware virtual
PTP clock driver (ptp_vmw) to Srivatsa and Deep. Update the
MAINTAINERS file to reflect this change, and also add Alexey as a
reviewer for the driver.
Signed-off-by: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Acked-by: Vivek Thampi <vivek@vivekthampi.com>
Acked-by: Deep Shah <sdeep@vmware.com>
Acked-by: Alexey Makhalov <amakhalov@vmware.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
MAINTAINERS | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f0b7181e60a5..758878c0eddf3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22243,7 +22243,9 @@ F: drivers/scsi/vmw_pvscsi.c
F: drivers/scsi/vmw_pvscsi.h
VMWARE VIRTUAL PTP CLOCK DRIVER
-M: Vivek Thampi <vithampi@vmware.com>
+M: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
+M: Deep Shah <sdeep@vmware.com>
+R: Alexey Makhalov <amakhalov@vmware.com>
R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
L: netdev@vger.kernel.org
S: Supported
--
GitLab
From 0599313e26666e79f6e7fe1450588431b8cb25d5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 2 Jan 2023 18:07:57 +0100
Subject: [PATCH 0341/1167] ALSA: usb-audio: Make sure to stop endpoints before
closing EPs
At the PCM hw params, we may re-configure the endpoints and it's done
by a temporary EP close followed by re-open. A potential problem
there is that the EP might be already running internally at the PCM
prepare stage; it's seen typically in the playback stream with the
implicit feedback sync. As this stream start isn't tracked by the
core PCM layer, we'd need to stop it explicitly, and that's the
missing piece.
This patch adds the stop_endpoints() call at snd_usb_hw_params() to
assure the stream stop before closing the EPs.
Fixes: bf6313a0ff76 ("ALSA: usb-audio: Refactor endpoint management")
Link: https://lore.kernel.org/r/4e509aea-e563-e592-e652-ba44af6733fe@veniogames.com
Link: https://lore.kernel.org/r/20230102170759.29610-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/pcm.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 99a66d0ef5b26..7fc95ae9b2f0b 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -525,6 +525,8 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
if (snd_usb_endpoint_compatible(chip, subs->data_endpoint,
fmt, hw_params))
goto unlock;
+ if (stop_endpoints(subs, false))
+ sync_pending_stops(subs);
close_endpoints(chip, subs);
}
--
GitLab
From d463ac1acb454fafed58f695cb3067fbf489f3a0 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 2 Jan 2023 18:07:58 +0100
Subject: [PATCH 0342/1167] ALSA: usb-audio: Relax hw constraints for implicit
fb sync
The fix commit the commit e4ea77f8e53f ("ALSA: usb-audio: Always apply
the hw constraints for implicit fb sync") tried to address the bug
where an incorrect PCM parameter is chosen when two (implicit fb)
streams are set up at the same time. This change had, however, some
side effect: once when the sync endpoint is chosen and set up, this
restriction is applied at the next hw params unless it's freed via hw
free explicitly.
This patch is a workaround for the problem by relaxing the hw
constraints a bit for the implicit fb sync. We still keep applying
the hw constraints for implicit fb sync, but only when the matching
sync EP is being used by other streams.
Fixes: e4ea77f8e53f ("ALSA: usb-audio: Always apply the hw constraints for implicit fb sync")
Reported-by: Ruud van Asseldonk <ruud@veniogames.com>
Link: https://lore.kernel.org/r/4e509aea-e563-e592-e652-ba44af6733fe@veniogames.com
Link: https://lore.kernel.org/r/20230102170759.29610-3-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/pcm.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 7fc95ae9b2f0b..2fd4ecc1b25a7 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -937,8 +937,13 @@ get_sync_ep_from_substream(struct snd_usb_substream *subs)
continue;
/* for the implicit fb, check the sync ep as well */
ep = snd_usb_get_endpoint(chip, fp->sync_ep);
- if (ep && ep->cur_audiofmt)
- return ep;
+ if (ep && ep->cur_audiofmt) {
+ /* ditto, if the sync (data) ep is used by others,
+ * this stream is restricted by the sync ep
+ */
+ if (ep != subs->sync_endpoint || ep->opened > 1)
+ return ep;
+ }
}
return NULL;
}
--
GitLab
From 37b3e56d8911f9ec1e1aaa5cccdff33cb0a7a832 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 2 Jan 2023 18:07:59 +0100
Subject: [PATCH 0343/1167] ALSA: usb-audio: More refactoring of hw constraint
rules
Although we applied a workaround for the hw constraints code with the
implicit feedback sync, it still has a potential problem. Namely, as
the code treats only the first matching (sync) endpoint, it might be
too restrictive when multiple endpoints are listed in the substream's
format list.
This patch is another attempt to improve the hw constraint handling
for the implicit feedback sync. The code is rewritten and the sync EP
handling for the rate and the format is put inside the fmt_list loop
in each hw_rule_*() function instead of the additional rules. The
rules for the period size and periods are extended to loop over the
fmt_list like others, and they apply the constraints only if needed.
Link: https://lore.kernel.org/r/4e509aea-e563-e592-e652-ba44af6733fe@veniogames.com
Link: https://lore.kernel.org/r/20230102170759.29610-4-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/pcm.c | 218 +++++++++++++++++++++++++++++-------------------
1 file changed, 131 insertions(+), 87 deletions(-)
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 2fd4ecc1b25a7..fbd4798834e5f 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -789,11 +789,27 @@ static int apply_hw_params_minmax(struct snd_interval *it, unsigned int rmin,
return changed;
}
+/* get the specified endpoint object that is being used by other streams
+ * (i.e. the parameter is locked)
+ */
+static const struct snd_usb_endpoint *
+get_endpoint_in_use(struct snd_usb_audio *chip, int endpoint,
+ const struct snd_usb_endpoint *ref_ep)
+{
+ const struct snd_usb_endpoint *ep;
+
+ ep = snd_usb_get_endpoint(chip, endpoint);
+ if (ep && ep->cur_audiofmt && (ep != ref_ep || ep->opened > 1))
+ return ep;
+ return NULL;
+}
+
static int hw_rule_rate(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_interval *it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
unsigned int rmin, rmax, r;
@@ -805,6 +821,29 @@ static int hw_rule_rate(struct snd_pcm_hw_params *params,
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for ep#%x\n",
+ ep->cur_rate, fp->endpoint);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for sync_ep#%x\n",
+ ep->cur_rate, fp->sync_ep);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+ }
+
r = snd_usb_endpoint_get_clock_rate(chip, fp->clock);
if (r > 0) {
if (!snd_interval_test(it, r))
@@ -874,6 +913,8 @@ static int hw_rule_format(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
u64 fbits;
@@ -883,6 +924,27 @@ static int hw_rule_format(struct snd_pcm_hw_params *params,
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for ep#%x\n",
+ ep->cur_format, fp->endpoint);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for sync_ep#%x\n",
+ ep->cur_format, fp->sync_ep);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+ }
+
fbits |= fp->formats;
}
return apply_hw_params_format_bits(fmt, fbits);
@@ -915,103 +977,95 @@ static int hw_rule_period_time(struct snd_pcm_hw_params *params,
return apply_hw_params_minmax(it, pmin, UINT_MAX);
}
-/* get the EP or the sync EP for implicit fb when it's already set up */
-static const struct snd_usb_endpoint *
-get_sync_ep_from_substream(struct snd_usb_substream *subs)
+/* additional hw constraints for implicit feedback mode */
+static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule)
{
+ struct snd_usb_substream *subs = rule->private;
struct snd_usb_audio *chip = subs->stream->chip;
const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
+ struct snd_interval *it;
+ unsigned int rmin, rmax;
+ it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
+ hwc_debug("hw_rule_period_size: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
list_for_each_entry(fp, &subs->fmt_list, list) {
- ep = snd_usb_get_endpoint(chip, fp->endpoint);
- if (ep && ep->cur_audiofmt) {
- /* if EP is already opened solely for this substream,
- * we still allow us to change the parameter; otherwise
- * this substream has to follow the existing parameter
- */
- if (ep->cur_audiofmt != subs->cur_audiofmt || ep->opened > 1)
- return ep;
- }
- if (!fp->implicit_fb)
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for ep#%x\n",
+ ep->cur_period_frames, fp->endpoint);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
continue;
- /* for the implicit fb, check the sync ep as well */
- ep = snd_usb_get_endpoint(chip, fp->sync_ep);
- if (ep && ep->cur_audiofmt) {
- /* ditto, if the sync (data) ep is used by others,
- * this stream is restricted by the sync ep
- */
- if (ep != subs->sync_endpoint || ep->opened > 1)
- return ep;
}
- }
- return NULL;
-}
-/* additional hw constraints for implicit feedback mode */
-static int hw_rule_format_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- return apply_hw_params_format_bits(fmt, pcm_format_to_bits(ep->cur_format));
-}
-
-static int hw_rule_rate_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_interval *it;
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
- return apply_hw_params_minmax(it, ep->cur_rate, ep->cur_rate);
-}
-
-static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_interval *it;
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for sync_ep#%x\n",
+ ep->cur_period_frames, fp->sync_ep);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
+ continue;
+ }
+ }
+ }
- hwc_debug("applying %s\n", __func__);
- it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
- return apply_hw_params_minmax(it, ep->cur_period_frames,
- ep->cur_period_frames);
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
static int hw_rule_periods_implicit_fb(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
struct snd_interval *it;
+ unsigned int rmin, rmax;
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIODS);
- return apply_hw_params_minmax(it, ep->cur_buffer_periods,
- ep->cur_buffer_periods);
+ hwc_debug("hw_rule_periods: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
+ list_for_each_entry(fp, &subs->fmt_list, list) {
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for ep#%x\n",
+ ep->cur_buffer_periods, fp->endpoint);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for sync_ep#%x\n",
+ ep->cur_buffer_periods, fp->sync_ep);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+ }
+ }
+
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
/*
@@ -1120,16 +1174,6 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre
return err;
/* additional hw constraints for implicit fb */
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
- hw_rule_format_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_FORMAT, -1);
- if (err < 0)
- return err;
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
- hw_rule_rate_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_RATE, -1);
- if (err < 0)
- return err;
err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
hw_rule_period_size_implicit_fb, subs,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1);
--
GitLab
From a664ec9158eeddd75121d39c9a0758016097fa96 Mon Sep 17 00:00:00 2001
From: Rodrigo Branco <bsdaemon@google.com>
Date: Tue, 3 Jan 2023 14:17:51 -0600
Subject: [PATCH 0344/1167] x86/bugs: Flush IBP in ib_prctl_set()
We missed the window between the TIF flag update and the next reschedule.
Signed-off-by: Rodrigo Branco <bsdaemon@google.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: <stable@vger.kernel.org>
---
arch/x86/kernel/cpu/bugs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d970ddb0cc65b..bca0bd8f48464 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1981,6 +1981,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl)
if (ctrl == PR_SPEC_FORCE_DISABLE)
task_set_spec_ib_force_disable(task);
task_update_spec_tif(task);
+ if (task == current)
+ indirect_branch_prediction_barrier();
break;
default:
return -ERANGE;
--
GitLab
From 340726747336716350eb5a928b860a29db955f05 Mon Sep 17 00:00:00 2001
From: Aaron Thompson <dev@aaront.org>
Date: Wed, 4 Jan 2023 10:07:37 +0000
Subject: [PATCH 0345/1167] memblock tests: Fix compilation error.
Commit cf4694be2b2cf ("tools: Add atomic_test_and_set_bit()") changed
tools/arch/x86/include/asm/atomic.h to include <asm/asm.h>, which causes
'make -C tools/testing/memblock' to fail with:
In file included from ../../include/asm/atomic.h:6,
from ../../include/linux/atomic.h:5,
from ./linux/mmzone.h:5,
from ../../include/linux/mm.h:5,
from ../../include/linux/pfn.h:5,
from ./linux/memory_hotplug.h:6,
from ./linux/init.h:7,
from ./linux/memblock.h:11,
from tests/common.h:8,
from tests/basic_api.h:5,
from main.c:2:
../../include/asm/../../arch/x86/include/asm/atomic.h:11:10: fatal error: asm/asm.h: No such file or directory
11 | #include <asm/asm.h>
| ^~~~~~~~~~~
Create a symlink to asm/asm.h in the same manner as the existing one to
asm/cmpxchg.h.
Signed-off-by: Aaron Thompson <dev@aaront.org>
Link: https://lore.kernel.org/r/010101857c402765-96e2dbc6-b82b-47e2-a437-4834dbe0b96b-000000@us-west-2.amazonses.com
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
tools/testing/memblock/.gitignore | 1 +
tools/testing/memblock/Makefile | 3 ++-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/tools/testing/memblock/.gitignore b/tools/testing/memblock/.gitignore
index 654338e0be52e..4cc7cd5aac2b1 100644
--- a/tools/testing/memblock/.gitignore
+++ b/tools/testing/memblock/.gitignore
@@ -1,4 +1,5 @@
main
memblock.c
linux/memblock.h
+asm/asm.h
asm/cmpxchg.h
diff --git a/tools/testing/memblock/Makefile b/tools/testing/memblock/Makefile
index 2310ac4d080ec..7a1ca694a9825 100644
--- a/tools/testing/memblock/Makefile
+++ b/tools/testing/memblock/Makefile
@@ -29,13 +29,14 @@ include: ../../../include/linux/memblock.h ../../include/linux/*.h \
@mkdir -p linux
test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h
+ test -L asm/asm.h || ln -s ../../../arch/x86/include/asm/asm.h asm/asm.h
test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h
memblock.c: $(EXTR_SRC)
test -L memblock.c || ln -s $(EXTR_SRC) memblock.c
clean:
- $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h
+ $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/asm.h asm/cmpxchg.h
help:
@echo 'Memblock simulator'
--
GitLab
From fa81ab49bbe4e1ce756581c970486de0ddb14309 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Fri, 16 Dec 2022 14:03:03 +0400
Subject: [PATCH 0346/1167] memblock: Fix doc for memblock_phys_free
memblock_phys_free() is the counterpart to memblock_phys_alloc.
Change memblock_alloc_xx() with memblock_phys_alloc_xx() to keep
consistency.
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Link: https://lore.kernel.org/r/20221216100304.688209-1-linmq006@gmail.com
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
mm/memblock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/memblock.c b/mm/memblock.c
index 511d4783dcf1d..d036c7861310c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -836,7 +836,7 @@ void __init_memblock memblock_free(void *ptr, size_t size)
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
- * Free boot memory block previously allocated by memblock_alloc_xx() API.
+ * Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
--
GitLab
From c956541736b94944047ee52ebfc5ee4babcd6ca1 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 4 Jan 2023 19:21:49 +0900
Subject: [PATCH 0347/1167] cpufreq: apple-soc: Switch to the lowest frequency
on suspend
Without this, the CPUs are left in a random pstate. Since we don't
support deep idle yet (which powers down the CPUs), this results in
significantly increased idle power consumption in suspend.
Fixes: 6286bbb40576 ("cpufreq: apple-soc: Add new driver to control Apple SoC CPU P-states")
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/apple-soc-cpufreq.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 6f26395184c41..c11d22fd84c37 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -280,6 +280,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
policy->cpuinfo.transition_latency = transition_latency;
policy->dvfs_possible_from_any_cpu = true;
policy->fast_switch_possible = true;
+ policy->suspend_freq = freq_table[0].frequency;
if (policy_has_boost_freq(policy)) {
ret = cpufreq_enable_boost_support();
@@ -328,6 +329,7 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = {
.fast_switch = apple_soc_cpufreq_fast_switch,
.register_em = cpufreq_register_em_with_opp,
.attr = apple_soc_cpufreq_hw_attr,
+ .suspend = cpufreq_generic_suspend,
};
static int __init apple_soc_cpufreq_module_init(void)
--
GitLab
From 760d560f71c828a97c77596af5c3f9978aefd9d1 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Date: Thu, 15 Dec 2022 11:34:52 +0100
Subject: [PATCH 0348/1167] PCI: dwc: Adjust to recent removal of
PCI_MSI_IRQ_DOMAIN
a474d3fbe287 ("PCI/MSI: Get rid of PCI_MSI_IRQ_DOMAIN") removed
PCI_MSI_IRQ_DOMAIN and changed all references to refer to PCI_MSI instead.
ba6ed462dcf4 ("PCI: dwc: Add Baikal-T1 PCIe controller support")
independently added PCIE_BT1, depending on PCI_MSI_IRQ_DOMAIN.
Both commits appeared in v6.2-rc1, so the latter missed the conversion from
PCI_MSI_IRQ_DOMAIN to PCI_MSI. Update PCIE_BT1 to depend on PCI_MSI
instead.
[bhelgaas: commit log]
Link: https://lore.kernel.org/r/20221215103452.23131-1-lukas.bulwahn@gmail.com
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
---
drivers/pci/controller/dwc/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index a0d2713f0e889..99ec91e2a5cfa 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -225,7 +225,7 @@ config PCIE_ARTPEC6_EP
config PCIE_BT1
tristate "Baikal-T1 PCIe controller"
depends on MIPS_BAIKAL_T1 || COMPILE_TEST
- depends on PCI_MSI_IRQ_DOMAIN
+ depends on PCI_MSI
select PCIE_DW_HOST
help
Enables support for the PCIe controller in the Baikal-T1 SoC to work
--
GitLab
From fb710ddee75fb96f50ee6d004ef777a0cf7ad5a3 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 28 Dec 2022 15:57:03 +0100
Subject: [PATCH 0349/1167] perf test record_probe_libc_inet_pton: Fix test on
s/390 where 'text_to_binary_address' now appears on the backtrace
perf test '84: probe libc's inet_pton & backtrace it with ping' fails on
s390. Debugging revealed a changed stack trace for the ping command
using probes:
ping 35729 [002] 8006.365063: probe_libc:inet_pton: (3ff9603e7c0)
13e7c0 __GI___inet_pton+0x0 (/usr/lib64/libc.so.6)
---> 104371 text_to_binary_address+0xef1 (inlined)
104371 gaih_inet+0xef1 (inlined)
104371 __GI_getaddrinfo+0xef1 (inlined)
5d4b main+0x139b (/usr/bin/ping)
The line "---> text_to_binary_address ..." is new. It was introduced
with glibc version 2.36.7.2 released with Fedora 37 for s390.
Output before
# perf test inet_pton
84: probe libc's inet_pton & backtrace it with ping : FAILED!
#
Output after:
# perf test inet_pton
84: probe libc's inet_pton & backtrace it with ping : Ok
#
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: https://lore.kernel.org/r/20221228145704.2702487-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 216b6b64caa30..57e7a6a470c93 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -37,6 +37,7 @@ trace_libc_inet_pton_backtrace() {
case "$(uname -m)" in
s390x)
eventattr='call-graph=dwarf,max-stack=4'
+ echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
--
GitLab
From 2d656b0f81b22101db0447f890e39fdd736b745e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 3 Jan 2023 22:44:01 -0800
Subject: [PATCH 0350/1167] perf stat: Fix handling of unsupported cgroup
events when using BPF counters
When --for-each-cgroup option is used, it fails when any of events is
not supported and exits immediately. This is not how 'perf stat'
handles unsupported events.
Let's ignore the failure and proceed with others so that the output is
similar to when BPF counters are not used:
Before:
$ sudo ./perf stat -a --bpf-counters -e L1-icache-loads,L1-dcache-loads --for-each-cgroup system.slice,user.slice sleep 1
Failed to open first cgroup events
$
After it shows output similat to when --bpf-counters isn't specified:
$ sudo ./perf stat -a --bpf-counters -e L1-icache-loads,L1-dcache-loads --for-each-cgroup system.slice,user.slice sleep 1
Performance counter stats for 'system wide':
<not supported> L1-icache-loads system.slice
29,892,418 L1-dcache-loads system.slice
<not supported> L1-icache-loads user.slice
52,497,220 L1-dcache-loads user.slice
$
Fixes: 944138f048f7d759 ("perf stat: Enable BPF counter with --for-each-cgroup")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/r/20230104064402.1551516-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/bpf_counter_cgroup.c | 14 +++-----------
1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index 3c2df7522f6fc..1c82377ed78b9 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -116,27 +116,19 @@ static int bperf_load_program(struct evlist *evlist)
/* open single copy of the events w/o cgroup */
err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
- if (err) {
- pr_err("Failed to open first cgroup events\n");
- goto out;
- }
+ if (err == 0)
+ evsel->supported = true;
map_fd = bpf_map__fd(skel->maps.events);
perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
int fd = FD(evsel, j);
__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
- err = bpf_map_update_elem(map_fd, &idx, &fd,
- BPF_ANY);
- if (err < 0) {
- pr_err("Failed to update perf_event fd\n");
- goto out;
- }
+ bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY);
}
evsel->cgrp = leader_cgrp;
}
- evsel->supported = true;
if (evsel->cgrp == cgrp)
continue;
--
GitLab
From 54b353a20c7e8be98414754f5aff98c8a68fcc1f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 3 Jan 2023 22:44:02 -0800
Subject: [PATCH 0351/1167] perf stat: Fix handling of --for-each-cgroup with
--bpf-counters to match non BPF mode
The --for-each-cgroup can have the same cgroup multiple times, but this
confuses BPF counters (since they have the same cgroup id), making only
the last cgroup events to be counted.
Let's check the cgroup name before adding a new entry to the cgroups
list.
Before:
$ sudo ./perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1
Performance counter stats for 'system wide':
<not counted> msec cpu-clock /
<not counted> context-switches /
<not counted> cpu-migrations /
<not counted> page-faults /
<not counted> cycles /
<not counted> instructions /
<not counted> branches /
<not counted> branch-misses /
8,016.04 msec cpu-clock / # 7.998 CPUs utilized
6,152 context-switches / # 767.461 /sec
250 cpu-migrations / # 31.187 /sec
442 page-faults / # 55.139 /sec
613,111,487 cycles / # 0.076 GHz
280,599,604 instructions / # 0.46 insn per cycle
57,692,724 branches / # 7.197 M/sec
3,385,168 branch-misses / # 5.87% of all branches
1.002220125 seconds time elapsed
After it becomes similar to the non-BPF mode:
$ sudo ./perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1
Performance counter stats for 'system wide':
8,013.38 msec cpu-clock / # 7.998 CPUs utilized
6,859 context-switches / # 855.944 /sec
334 cpu-migrations / # 41.680 /sec
345 page-faults / # 43.053 /sec
782,326,119 cycles / # 0.098 GHz
471,645,724 instructions / # 0.60 insn per cycle
94,963,430 branches / # 11.851 M/sec
3,685,511 branch-misses / # 3.88% of all branches
1.001864539 seconds time elapsed
Committer notes:
As a reminder, to test with BPF counters one has to use BUILD_BPF_SKEL=1
in the make command line and have clang/llvm installed when building
perf, otherwise the --bpf-counters option will not be available:
# perf stat -a --bpf-counters --for-each-cgroup /,/ sleep 1
Error: unknown option `bpf-counters'
Usage: perf stat [<options>] [<command>]
-a, --all-cpus system-wide collection from all CPUs
<SNIP>
#
Fixes: bb1c15b60b981d10 ("perf stat: Support regex pattern in --for-each-cgroup")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: bpf@vger.kernel.org
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/r/20230104064402.1551516-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/cgroup.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index e99b41f9be45a..cd978c240e0dd 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -224,6 +224,19 @@ static int add_cgroup_name(const char *fpath, const struct stat *sb __maybe_unus
return 0;
}
+static int check_and_add_cgroup_name(const char *fpath)
+{
+ struct cgroup_name *cn;
+
+ list_for_each_entry(cn, &cgroup_list, list) {
+ if (!strcmp(cn->name, fpath))
+ return 0;
+ }
+
+ /* pretend if it's added by ftw() */
+ return add_cgroup_name(fpath, NULL, FTW_D, NULL);
+}
+
static void release_cgroup_list(void)
{
struct cgroup_name *cn;
@@ -242,7 +255,7 @@ static int list_cgroups(const char *str)
struct cgroup_name *cn;
char *s;
- /* use given name as is - for testing purpose */
+ /* use given name as is when no regex is given */
for (;;) {
p = strchr(str, ',');
e = p ? p : eos;
@@ -253,13 +266,13 @@ static int list_cgroups(const char *str)
s = strndup(str, e - str);
if (!s)
return -1;
- /* pretend if it's added by ftw() */
- ret = add_cgroup_name(s, NULL, FTW_D, NULL);
+
+ ret = check_and_add_cgroup_name(s);
free(s);
- if (ret)
+ if (ret < 0)
return -1;
} else {
- if (add_cgroup_name("", NULL, FTW_D, NULL) < 0)
+ if (check_and_add_cgroup_name("/") < 0)
return -1;
}
--
GitLab
From 191f8453fc99a537ea78b727acea739782378b0d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 07:48:37 -0700
Subject: [PATCH 0352/1167] ARM: renumber bits related to _TIF_WORK_MASK
We want to ensure that the mask related to calling do_work_pending()
is within the first 16 bits. Move bits unrelated to that outside of
that range, to avoid spuriously calling do_work_pending() when we don't
need to.
Cc: stable@vger.kernel.org
Fixes: 32d59773da38 ("arm: add support for TIF_NOTIFY_SIGNAL")
Reported-and-tested-by: Hui Tang <tanghui20@huawei.com>
Suggested-by: Russell King (Oracle) <linux@armlinux.org.uk>
Link: https://lore.kernel.org/lkml/7ecb8f3c-2aeb-a905-0d4a-aa768b9649b5@huawei.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
arch/arm/include/asm/thread_info.h | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index aecc403b28804..7f092cb55a417 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -128,15 +128,16 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
-#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */
+#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */
#define TIF_USING_IWMMXT 17
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK 20
+#define TIF_RESTORE_SIGMASK 19
+#define TIF_SYSCALL_TRACE 20 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 23 /* seccomp syscall filtering active */
+
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
--
GitLab
From 39a154fc2d172a3a5865e5a9fa2a2983eb7a99ac Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Thu, 29 Dec 2022 18:43:46 -0300
Subject: [PATCH 0353/1167] cifs: protect access of
TCP_Server_Info::{dstaddr,hostname}
Use the appropriate locks to protect access of hostname and dstaddr
fields in cifs_tree_connect() as they might get changed by other
tasks.
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs.c | 22 +++++++++++-----------
fs/cifs/misc.c | 2 ++
2 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/fs/cifs/dfs.c b/fs/cifs/dfs.c
index 30086f2060a10..b64d20374b9c8 100644
--- a/fs/cifs/dfs.c
+++ b/fs/cifs/dfs.c
@@ -327,8 +327,8 @@ static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb
return rc;
}
-static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host,
- size_t tcp_host_len, char *share, bool *target_match)
+static int target_share_matches_server(struct TCP_Server_Info *server, char *share,
+ bool *target_match)
{
int rc = 0;
const char *dfs_host;
@@ -338,13 +338,16 @@ static int target_share_matches_server(struct TCP_Server_Info *server, const cha
extract_unc_hostname(share, &dfs_host, &dfs_host_len);
/* Check if hostnames or addresses match */
- if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
- cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
- dfs_host, (int)tcp_host_len, tcp_host);
+ cifs_server_lock(server);
+ if (dfs_host_len != strlen(server->hostname) ||
+ strncasecmp(dfs_host, server->hostname, dfs_host_len)) {
+ cifs_dbg(FYI, "%s: %.*s doesn't match %s\n", __func__,
+ (int)dfs_host_len, dfs_host, server->hostname);
rc = match_target_ip(server, dfs_host, dfs_host_len, target_match);
if (rc)
cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
}
+ cifs_server_unlock(server);
return rc;
}
@@ -358,13 +361,9 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t
struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses);
struct cifs_tcon *ipc = root_ses->tcon_ipc;
char *share = NULL, *prefix = NULL;
- const char *tcp_host;
- size_t tcp_host_len;
struct dfs_cache_tgt_iterator *tit;
bool target_match;
- extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
-
tit = dfs_cache_get_tgt_iterator(tl);
if (!tit) {
rc = -ENOENT;
@@ -387,8 +386,7 @@ static int __tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *t
break;
}
- rc = target_share_matches_server(server, tcp_host, tcp_host_len, share,
- &target_match);
+ rc = target_share_matches_server(server, share, &target_match);
if (rc)
break;
if (!target_match) {
@@ -497,7 +495,9 @@ int cifs_tree_connect(const unsigned int xid, struct cifs_tcon *tcon, const stru
}
if (tcon->ipc) {
+ cifs_server_lock(server);
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+ cifs_server_unlock(server);
rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
goto out;
}
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 4d3c586785a59..2a19c7987c5bd 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1277,7 +1277,9 @@ int match_target_ip(struct TCP_Server_Info *server,
if (rc < 0)
return rc;
+ spin_lock(&server->srv_lock);
*result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss);
+ spin_unlock(&server->srv_lock);
cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result);
return 0;
}
--
GitLab
From 16f1f838442dc6430d32d51ddda347b8421ec34b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jan 2023 16:09:44 +0100
Subject: [PATCH 0354/1167] Revert "ALSA: usb-audio: Drop superfluous interface
setup at parsing"
This reverts commit ac5e2fb425e1121ceef2b9d1b3ffccc195d55707.
The commit caused a regression on Behringer UMC404HD (and likely
others). As the change was meant only as a minor optimization, it's
better to revert it to address the regression.
Reported-and-tested-by: Michael Ralston <michael@ralston.id.au>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/CAC2975JXkS1A5Tj9b02G_sy25ZWN-ys+tc9wmkoS=qPgKCogSg@mail.gmail.com
Link: https://lore.kernel.org/r/20230104150944.24918-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/stream.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index f75601ca2d525..f10f4e6d3fb85 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -1222,6 +1222,12 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip,
if (err < 0)
return err;
}
+
+ /* try to set the interface... */
+ usb_set_interface(chip->dev, iface_no, 0);
+ snd_usb_init_pitch(chip, fp);
+ snd_usb_init_sample_rate(chip, fp, fp->rate_max);
+ usb_set_interface(chip->dev, iface_no, altno);
}
return 0;
}
--
GitLab
From 3792fc508c095abd84b10ceae12bd773e61fdc36 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Tue, 15 Nov 2022 16:15:18 +0300
Subject: [PATCH 0355/1167] drm/i915: unpin on error in
intel_vgpu_shadow_mm_pin()
Call intel_vgpu_unpin_mm() on this error path.
Fixes: 418741480809 ("drm/i915/gvt: Adding ppgtt to GVT GEM context after shadow pdps settled.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/Y3OQ5tgZIVxyQ/WV@kili
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
drivers/gpu/drm/i915/gvt/scheduler.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 9cd8fcbf7cad1..8009239935f7b 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -695,6 +695,7 @@ intel_vgpu_shadow_mm_pin(struct intel_vgpu_workload *workload)
if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT ||
!workload->shadow_mm->ppgtt_mm.shadowed) {
+ intel_vgpu_unpin_mm(workload->shadow_mm);
gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
return -EINVAL;
}
--
GitLab
From c4b850d1f448a901fbf4f7f36dec38c84009b489 Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Mon, 19 Dec 2022 22:03:56 +0800
Subject: [PATCH 0356/1167] drm/i915/gvt: fix gvt debugfs destroy
When gvt debug fs is destroyed, need to have a sane check if drm
minor's debugfs root is still available or not, otherwise in case like
device remove through unbinding, drm minor's debugfs directory has
already been removed, then intel_gvt_debugfs_clean() would act upon
dangling pointer like below oops.
i915 0000:00:02.0: Direct firmware load for i915/gvt/vid_0x8086_did_0x1926_rid_0x0a.golden_hw_state failed with error -2
i915 0000:00:02.0: MDEV: Registered
Console: switching to colour dummy device 80x25
i915 0000:00:02.0: MDEV: Unregistering
BUG: kernel NULL pointer dereference, address: 00000000000000a0
PGD 0 P4D 0
Oops: 0002 [#1] PREEMPT SMP PTI
CPU: 2 PID: 2486 Comm: gfx-unbind.sh Tainted: G I 6.1.0-rc8+ #15
Hardware name: Dell Inc. XPS 13 9350/0JXC1H, BIOS 1.13.0 02/10/2020
RIP: 0010:down_write+0x1f/0x90
Code: 1d ff ff 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 53 48 89 fb e8 62 c0 ff ff bf 01 00 00 00 e8 28 5e 31 ff 31 c0 ba 01 00 00 00 <f0> 48 0f b1 13 75 33 65 48 8b 04 25 c0 bd 01 00 48 89 43 08 bf 01
RSP: 0018:ffff9eb3036ffcc8 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 00000000000000a0 RCX: ffffff8100000000
RDX: 0000000000000001 RSI: 0000000000000064 RDI: ffffffffa48787a8
RBP: ffff9eb3036ffd30 R08: ffffeb1fc45a0608 R09: ffffeb1fc45a05c0
R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000000
R13: ffff91acc33fa328 R14: ffff91acc033f080 R15: ffff91acced533e0
FS: 00007f6947bba740(0000) GS:ffff91ae36d00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000a0 CR3: 00000001133a2002 CR4: 00000000003706e0
Call Trace:
<TASK>
simple_recursive_removal+0x9f/0x2a0
? start_creating.part.0+0x120/0x120
? _raw_spin_lock+0x13/0x40
debugfs_remove+0x40/0x60
intel_gvt_debugfs_clean+0x15/0x30 [kvmgt]
intel_gvt_clean_device+0x49/0xe0 [kvmgt]
intel_gvt_driver_remove+0x2f/0xb0
i915_driver_remove+0xa4/0xf0
i915_pci_remove+0x1a/0x30
pci_device_remove+0x33/0xa0
device_release_driver_internal+0x1b2/0x230
unbind_store+0xe0/0x110
kernfs_fop_write_iter+0x11b/0x1f0
vfs_write+0x203/0x3d0
ksys_write+0x63/0xe0
do_syscall_64+0x37/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7f6947cb5190
Code: 40 00 48 8b 15 71 9c 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 80 3d 51 24 0e 00 00 74 17 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 48 89
RSP: 002b:00007ffcbac45a28 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f6947cb5190
RDX: 000000000000000d RSI: 0000555e35c866a0 RDI: 0000000000000001
RBP: 0000555e35c866a0 R08: 0000000000000002 R09: 0000555e358cb97c
R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000001
R13: 000000000000000d R14: 0000000000000000 R15: 0000555e358cb8e0
</TASK>
Modules linked in: kvmgt
CR2: 00000000000000a0
---[ end trace 0000000000000000 ]---
Cc: Wang, Zhi <zhi.a.wang@intel.com>
Cc: He, Yu <yu.he@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure")
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-1-zhenyuw@linux.intel.com
---
drivers/gpu/drm/i915/gvt/debugfs.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index 9f1c209d92511..d7df27feee8c2 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -199,6 +199,10 @@ void intel_gvt_debugfs_init(struct intel_gvt *gvt)
*/
void intel_gvt_debugfs_clean(struct intel_gvt *gvt)
{
- debugfs_remove_recursive(gvt->debugfs_root);
- gvt->debugfs_root = NULL;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root) {
+ debugfs_remove_recursive(gvt->debugfs_root);
+ gvt->debugfs_root = NULL;
+ }
}
--
GitLab
From 704f3384f322b40ba24d958473edfb1c9750c8fd Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Mon, 19 Dec 2022 22:03:57 +0800
Subject: [PATCH 0357/1167] drm/i915/gvt: fix vgpu debugfs clean in remove
Check carefully on root debugfs available when destroying vgpu,
e.g in remove case drm minor's debugfs root might already be destroyed,
which led to kernel oops like below.
Console: switching to colour dummy device 80x25
i915 0000:00:02.0: MDEV: Unregistering
intel_vgpu_mdev b1338b2d-a709-4c23-b766-cc436c36cdf0: Removing from iommu group 14
BUG: kernel NULL pointer dereference, address: 0000000000000150
PGD 0 P4D 0
Oops: 0000 [#1] PREEMPT SMP
CPU: 3 PID: 1046 Comm: driverctl Not tainted 6.1.0-rc2+ #6
Hardware name: HP HP ProDesk 600 G3 MT/829D, BIOS P02 Ver. 02.44 09/13/2022
RIP: 0010:__lock_acquire+0x5e2/0x1f90
Code: 87 ad 09 00 00 39 05 e1 1e cc 02 0f 82 f1 09 00 00 ba 01 00 00 00 48 83 c4 48 89 d0 5b 5d 41 5c 41 5d 41 5e 41 5f c3 45 31 ff <48> 81 3f 60 9e c2 b6 45 0f 45 f8 83 fe 01 0f 87 55 fa ff ff 89 f0
RSP: 0018:ffff9f770274f948 EFLAGS: 00010046
RAX: 0000000000000003 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000150
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
R10: ffff8895d1173300 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000150 R14: 0000000000000000 R15: 0000000000000000
FS: 00007fc9b2ba0740(0000) GS:ffff889cdfcc0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000150 CR3: 000000010fd93005 CR4: 00000000003706e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
lock_acquire+0xbf/0x2b0
? simple_recursive_removal+0xa5/0x2b0
? lock_release+0x13d/0x2d0
down_write+0x2a/0xd0
? simple_recursive_removal+0xa5/0x2b0
simple_recursive_removal+0xa5/0x2b0
? start_creating.part.0+0x110/0x110
? _raw_spin_unlock+0x29/0x40
debugfs_remove+0x40/0x60
intel_gvt_debugfs_remove_vgpu+0x15/0x30 [kvmgt]
intel_gvt_destroy_vgpu+0x60/0x100 [kvmgt]
intel_vgpu_release_dev+0xe/0x20 [kvmgt]
device_release+0x30/0x80
kobject_put+0x79/0x1b0
device_release_driver_internal+0x1b8/0x230
bus_remove_device+0xec/0x160
device_del+0x189/0x400
? up_write+0x9c/0x1b0
? mdev_device_remove_common+0x60/0x60 [mdev]
mdev_device_remove_common+0x22/0x60 [mdev]
mdev_device_remove_cb+0x17/0x20 [mdev]
device_for_each_child+0x56/0x80
mdev_unregister_parent+0x5a/0x81 [mdev]
intel_gvt_clean_device+0x2d/0xe0 [kvmgt]
intel_gvt_driver_remove+0x2e/0xb0 [i915]
i915_driver_remove+0xac/0x100 [i915]
i915_pci_remove+0x1a/0x30 [i915]
pci_device_remove+0x31/0xa0
device_release_driver_internal+0x1b8/0x230
unbind_store+0xd8/0x100
kernfs_fop_write_iter+0x156/0x210
vfs_write+0x236/0x4a0
ksys_write+0x61/0xd0
do_syscall_64+0x55/0x80
? find_held_lock+0x2b/0x80
? lock_release+0x13d/0x2d0
? up_read+0x17/0x20
? lock_is_held_type+0xe3/0x140
? asm_exc_page_fault+0x22/0x30
? lockdep_hardirqs_on+0x7d/0x100
entry_SYSCALL_64_after_hwframe+0x46/0xb0
RIP: 0033:0x7fc9b2c9e0c4
Code: 15 71 7d 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 80 3d 3d 05 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 48 83 ec 28 48 89 54 24 18 48
RSP: 002b:00007ffec29c81c8 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007fc9b2c9e0c4
RDX: 000000000000000d RSI: 0000559f8b5f48a0 RDI: 0000000000000001
RBP: 0000559f8b5f48a0 R08: 0000559f8b5f3540 R09: 00007fc9b2d76d30
R10: 0000000000000000 R11: 0000000000000202 R12: 000000000000000d
R13: 00007fc9b2d77780 R14: 000000000000000d R15: 00007fc9b2d72a00
</TASK>
Modules linked in: sunrpc intel_rapl_msr intel_rapl_common intel_pmc_core_pltdrv intel_pmc_core intel_tcc_cooling x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ee1004 igbvf rapl vfat fat intel_cstate intel_uncore pktcdvd i2c_i801 pcspkr wmi_bmof i2c_smbus acpi_pad vfio_pci vfio_pci_core vfio_virqfd zram fuse dm_multipath kvmgt mdev vfio_iommu_type1 vfio kvm irqbypass i915 nvme e1000e igb nvme_core crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic serio_raw ghash_clmulni_intel sha512_ssse3 dca drm_buddy intel_gtt video wmi drm_display_helper ttm
CR2: 0000000000000150
---[ end trace 0000000000000000 ]---
Cc: Wang Zhi <zhi.a.wang@intel.com>
Cc: He Yu <yu.he@intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: stable@vger.kernel.org
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Tested-by: Yu He <yu.he@intel.com>
Fixes: bc7b0be316ae ("drm/i915/gvt: Add basic debugfs infrastructure")
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20221219140357.769557-2-zhenyuw@linux.intel.com
---
drivers/gpu/drm/i915/gvt/debugfs.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index d7df27feee8c2..e08ed0e9f1653 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -175,8 +175,13 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
*/
void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
{
- debugfs_remove_recursive(vgpu->debugfs);
- vgpu->debugfs = NULL;
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root && gvt->debugfs_root) {
+ debugfs_remove_recursive(vgpu->debugfs);
+ vgpu->debugfs = NULL;
+ }
}
/**
--
GitLab
From a06d4b9e15c0ea4e05b200cfb1f1050e785a5e87 Mon Sep 17 00:00:00 2001
From: Zhi Wang <zhi.a.wang@intel.com>
Date: Thu, 10 Nov 2022 12:20:34 +0000
Subject: [PATCH 0358/1167] drm/i915/gvt: use atomic operations to change the
vGPU status
Several vGPU status are used to decide the availability of GVT-g core
logics when creating a vGPU. Use atomic operations on changing the vGPU
status to avoid the racing.
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: intel-gvt-dev@lists.freedesktop.org
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20221110122034.3382-2-zhi.a.wang@intel.com
---
drivers/gpu/drm/i915/gvt/debugfs.c | 19 ++++++++++++++-
drivers/gpu/drm/i915/gvt/dmabuf.c | 3 ++-
drivers/gpu/drm/i915/gvt/gtt.c | 4 ++--
drivers/gpu/drm/i915/gvt/gvt.h | 15 ++++++++----
drivers/gpu/drm/i915/gvt/interrupt.c | 2 +-
drivers/gpu/drm/i915/gvt/kvmgt.c | 35 +++++++++++-----------------
drivers/gpu/drm/i915/gvt/scheduler.c | 3 ++-
drivers/gpu/drm/i915/gvt/vgpu.c | 12 ++++------
8 files changed, 53 insertions(+), 40 deletions(-)
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index e08ed0e9f1653..0616b73175f3e 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -151,6 +151,22 @@ DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops,
vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set,
"0x%llx\n");
+static int vgpu_status_get(void *data, u64 *val)
+{
+ struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+
+ *val = 0;
+
+ if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ATTACHED);
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ACTIVE);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n");
+
/**
* intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU
* @vgpu: a vGPU
@@ -162,11 +178,12 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
snprintf(name, 16, "vgpu%d", vgpu->id);
vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
- debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active);
debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu,
&vgpu_mmio_diff_fops);
debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu,
&vgpu_scan_nonprivbb_fops);
+ debugfs_create_file("status", 0644, vgpu->debugfs, vgpu,
+ &vgpu_status_fops);
}
/**
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 355f1c0e86641..ffe41e9be04fc 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -134,7 +134,8 @@ static void dmabuf_gem_object_free(struct kref *kref)
struct list_head *pos;
struct intel_vgpu_dmabuf_obj *dmabuf_obj;
- if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) {
+ if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) &&
+ !list_empty(&vgpu->dmabuf_obj_list_head)) {
list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
if (dmabuf_obj == obj) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 51e5e8fb505bc..6b4039010caee 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -55,7 +55,7 @@ static bool intel_gvt_is_valid_gfn(struct intel_vgpu *vgpu, unsigned long gfn)
int idx;
bool ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return false;
idx = srcu_read_lock(&kvm->srcu);
@@ -1178,7 +1178,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
return 0;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
if (is_error_noslot_pfn(pfn))
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 62823c0e13ab8..2d65800d8e93b 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -172,13 +172,18 @@ struct intel_vgpu_submission {
#define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries"
+enum {
+ INTEL_VGPU_STATUS_ATTACHED = 0,
+ INTEL_VGPU_STATUS_ACTIVE,
+ INTEL_VGPU_STATUS_NR_BITS,
+};
+
struct intel_vgpu {
struct vfio_device vfio_device;
struct intel_gvt *gvt;
struct mutex vgpu_lock;
int id;
- bool active;
- bool attached;
+ DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS);
bool pv_notified;
bool failsafe;
unsigned int resetting_eng;
@@ -467,7 +472,7 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
#define for_each_active_vgpu(gvt, vgpu, id) \
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \
- for_each_if(vgpu->active)
+ for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu,
u32 offset, u32 val, bool low)
@@ -725,7 +730,7 @@ static inline bool intel_gvt_mmio_is_cmd_write_patch(
static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
}
@@ -743,7 +748,7 @@ static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
unsigned long gpa, void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
}
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index a6b2021b665ff..68eca023bbc68 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -433,7 +433,7 @@ static int inject_virtual_interrupt(struct intel_vgpu *vgpu)
* enabled by guest. so if msi_trigger is null, success is still
* returned and don't inject interrupt into guest.
*/
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
return -EFAULT;
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index f5451adcd4890..8ae7039b36832 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -638,7 +638,7 @@ static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu)
mutex_lock(&vgpu->gvt->lock);
for_each_active_vgpu(vgpu->gvt, itr, id) {
- if (!itr->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status))
continue;
if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
@@ -655,9 +655,6 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (vgpu->attached)
- return -EEXIST;
-
if (!vgpu->vfio_device.kvm ||
vgpu->vfio_device.kvm->mm != current->mm) {
gvt_vgpu_err("KVM is required to use Intel vGPU\n");
@@ -667,14 +664,14 @@ static int intel_vgpu_open_device(struct vfio_device *vfio_dev)
if (__kvmgt_vgpu_exist(vgpu))
return -EEXIST;
- vgpu->attached = true;
-
vgpu->track_node.track_write = kvmgt_page_track_write;
vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
kvm_get_kvm(vgpu->vfio_device.kvm);
kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
&vgpu->track_node);
+ set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
&vgpu->nr_cache_entries);
@@ -698,11 +695,10 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (!vgpu->attached)
- return;
-
intel_gvt_release_vgpu(vgpu);
+ clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
@@ -718,8 +714,6 @@ static void intel_vgpu_close_device(struct vfio_device *vfio_dev)
vgpu->dma_addr_cache = RB_ROOT;
intel_vgpu_release_msi_eventfd_ctx(vgpu);
-
- vgpu->attached = false;
}
static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
@@ -1512,9 +1506,6 @@ static void intel_vgpu_remove(struct mdev_device *mdev)
{
struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev);
- if (WARN_ON_ONCE(vgpu->attached))
- return;
-
vfio_unregister_group_dev(&vgpu->vfio_device);
vfio_put_device(&vgpu->vfio_device);
}
@@ -1559,7 +1550,7 @@ int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn)
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
@@ -1589,8 +1580,8 @@ int intel_gvt_page_track_remove(struct intel_vgpu *info, u64 gfn)
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
- return 0;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
+ return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
slot = gfn_to_memslot(kvm, gfn);
@@ -1668,7 +1659,7 @@ int intel_gvt_dma_map_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
struct gvt_dma *entry;
int ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
mutex_lock(&vgpu->cache_lock);
@@ -1714,8 +1705,8 @@ int intel_gvt_dma_pin_guest_page(struct intel_vgpu *vgpu, dma_addr_t dma_addr)
struct gvt_dma *entry;
int ret = 0;
- if (!vgpu->attached)
- return -ENODEV;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ return -EINVAL;
mutex_lock(&vgpu->cache_lock);
entry = __gvt_cache_find_dma_addr(vgpu, dma_addr);
@@ -1742,7 +1733,7 @@ void intel_gvt_dma_unmap_guest_page(struct intel_vgpu *vgpu,
{
struct gvt_dma *entry;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return;
mutex_lock(&vgpu->cache_lock);
@@ -1778,7 +1769,7 @@ static void intel_gvt_test_and_emulate_vblank(struct intel_gvt *gvt)
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) {
if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id,
(void *)&gvt->service_request)) {
- if (vgpu->active)
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
intel_vgpu_emulate_vblank(vgpu);
}
}
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 8009239935f7b..f4055804aad1f 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -866,7 +866,8 @@ pick_next_workload(struct intel_gvt *gvt, struct intel_engine_cs *engine)
goto out;
}
- if (!scheduler->current_vgpu->active ||
+ if (!test_bit(INTEL_VGPU_STATUS_ACTIVE,
+ scheduler->current_vgpu->status) ||
list_empty(workload_q_head(scheduler->current_vgpu, engine)))
goto out;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 3c529c2705ddc..a5497440484f1 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -166,9 +166,7 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt)
*/
void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
{
- mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = true;
- mutex_unlock(&vgpu->vgpu_lock);
+ set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
}
/**
@@ -183,7 +181,7 @@ void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
{
mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = false;
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
if (atomic_read(&vgpu->submission.running_workload_num)) {
mutex_unlock(&vgpu->vgpu_lock);
@@ -228,7 +226,8 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
struct intel_gvt *gvt = vgpu->gvt;
struct drm_i915_private *i915 = gvt->gt->i915;
- drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n");
+ drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status),
+ "vGPU is still active!\n");
/*
* remove idr first so later clean can judge if need to stop
@@ -285,8 +284,7 @@ struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt)
if (ret)
goto out_free_vgpu;
- vgpu->active = false;
-
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
return vgpu;
out_free_vgpu:
--
GitLab
From 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 Mon Sep 17 00:00:00 2001
From: Zheng Wang <zyytlz.wz@163.com>
Date: Fri, 30 Dec 2022 00:56:41 +0800
Subject: [PATCH 0359/1167] drm/i915/gvt: fix double free bug in
split_2MB_gtt_entry
If intel_gvt_dma_map_guest_page failed, it will call
ppgtt_invalidate_spt, which will finally free the spt.
But the caller function ppgtt_populate_spt_by_guest_entry
does not notice that, it will free spt again in its error
path.
Fix this by canceling the mapping of DMA address and freeing sub_spt.
Besides, leave the handle of spt destroy to caller function instead
of callee function when error occurs.
Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support")
Signed-off-by: Zheng Wang <zyytlz.wz@163.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20221229165641.1192455-1-zyytlz.wz@163.com
---
drivers/gpu/drm/i915/gvt/gtt.c | 17 +++++++++++++----
1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 6b4039010caee..4ec85308379a4 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1209,10 +1209,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index,
PAGE_SIZE, &dma_addr);
- if (ret) {
- ppgtt_invalidate_spt(spt);
- return ret;
- }
+ if (ret)
+ goto err;
sub_se.val64 = se->val64;
/* Copy the PAT field from PDE. */
@@ -1231,6 +1229,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
ops->set_pfn(se, sub_spt->shadow_page.mfn);
ppgtt_set_shadow_entry(spt, se, index);
return 0;
+err:
+ /* Cancel the existing addess mappings of DMA addr. */
+ for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) {
+ gvt_vdbg_mm("invalidate 4K entry\n");
+ ppgtt_invalidate_pte(sub_spt, &sub_se);
+ }
+ /* Release the new allocated spt. */
+ trace_spt_change(sub_spt->vgpu->id, "release", sub_spt,
+ sub_spt->guest_page.gfn, sub_spt->shadow_page.type);
+ ppgtt_free_spt(sub_spt);
+ return ret;
}
static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
--
GitLab
From 613b14884b8595e20b9fac4126bf627313827fbe Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 08:51:19 -0700
Subject: [PATCH 0360/1167] block: handle bio_split_to_limits() NULL return
This can't happen right now, but in preparation for allowing
bio_split_to_limits() returning NULL if it ended the bio, check for it
in all the callers.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-merge.c | 4 +++-
block/blk-mq.c | 5 ++++-
drivers/block/drbd/drbd_req.c | 2 ++
drivers/block/ps3vram.c | 2 ++
drivers/md/dm.c | 2 ++
drivers/md/md.c | 2 ++
drivers/nvme/host/multipath.c | 2 ++
drivers/s390/block/dcssblk.c | 2 ++
8 files changed, 19 insertions(+), 2 deletions(-)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 35a8f75cc45d1..071c5f8cf0cfe 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -358,11 +358,13 @@ struct bio *__bio_split_to_limits(struct bio *bio,
default:
split = bio_split_rw(bio, lim, nr_segs, bs,
get_max_io_size(bio, lim) << SECTOR_SHIFT);
+ if (IS_ERR(split))
+ return NULL;
break;
}
if (split) {
- /* there isn't chance to merge the splitted bio */
+ /* there isn't chance to merge the split bio */
split->bi_opf |= REQ_NOMERGE;
blkcg_bio_issue_init(split);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c5cf0dbca1db8..2c49b4151da15 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2951,8 +2951,11 @@ void blk_mq_submit_bio(struct bio *bio)
blk_status_t ret;
bio = blk_queue_bounce(bio, q);
- if (bio_may_exceed_limits(bio, &q->limits))
+ if (bio_may_exceed_limits(bio, &q->limits)) {
bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+ return;
+ }
if (!bio_integrity_prep(bio))
return;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index eb14ec8ec04cf..e36216d50753c 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1607,6 +1607,8 @@ void drbd_submit_bio(struct bio *bio)
struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
/*
* what we "blindly" assume:
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index c76e0148eada3..574e470b220b0 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -587,6 +587,8 @@ static void ps3vram_submit_bio(struct bio *bio)
dev_dbg(&dev->core, "%s\n", __func__);
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
spin_lock_irq(&priv->lock);
busy = !bio_list_empty(&priv->list);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e1ea3a7bd9d9f..b424a6ee27baf 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1742,6 +1742,8 @@ static void dm_split_and_process_bio(struct mapped_device *md,
* otherwise associated queue_limits won't be imposed.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
}
init_clone_info(&ci, md, map, bio, is_abnormal);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 775f1dde190a2..8af639296b3c8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -455,6 +455,8 @@ static void md_submit_bio(struct bio *bio)
}
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index c03093b6813c5..fc39d01e7b63b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -376,6 +376,8 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
* pool from the original queue to allocate the bvecs from.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index b392b9f5482e0..c0f85ffb2b62d 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -865,6 +865,8 @@ dcssblk_submit_bio(struct bio *bio)
unsigned long bytes_done;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
bytes_done = 0;
dev_info = bio->bi_bdev->bd_disk->private_data;
--
GitLab
From be79f805a1e1b95605c825f1c513bdd2c8b167ed Mon Sep 17 00:00:00 2001
From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Date: Thu, 29 Dec 2022 12:44:38 +0000
Subject: [PATCH 0361/1167] dt-bindings: msm: dsi-phy-28nm: Add missing qcom,
dsi-phy-regulator-ldo-mode
Add in missing qcom,dsi-phy-regulator-ldo-mode to the 28nm DSI PHY.
When converting from .txt to .yaml we missed this one.
Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/516205/
Link: https://lore.kernel.org/r/20221229124438.504770-2-bryan.odonoghue@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
.../devicetree/bindings/display/msm/dsi-phy-28nm.yaml | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
index 3d8540a06fe22..2f1fd140c87df 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml
@@ -34,6 +34,10 @@ properties:
vddio-supply:
description: Phandle to vdd-io regulator device node.
+ qcom,dsi-phy-regulator-ldo-mode:
+ type: boolean
+ description: Indicates if the LDO mode PHY regulator is wanted.
+
required:
- compatible
- reg
--
GitLab
From 481028dbf1daa2808e1be06f6a865b5fe5939efc Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesussanp@google.com>
Date: Wed, 4 Jan 2023 11:34:14 -0800
Subject: [PATCH 0362/1167] perf tools: Fix build on uClibc systems by adding
missing sys/types.h include
Not all libc implementations define ssize_t as part of stdio.h like
glibc does since the standard only requires this type to be defined by
unistd.h and sys/types.h. For this reason the perf build is currently
broken for toolchains based on uClibc, for instance.
Include sys/types.h explicitly to fix that.
Committer notes:
In addition, in the past this worked in uClibc test systems as there was
another way to get to sys/types.h that got removed in that cset:
tools/perf/util/trace-event.h
/usr/include/traceevent/event_parse.h # This got removed from util/trace-event.h in 378ef0f5d9d7f465
/usr/include/regex.h
/usr/include/sys/types.h
typedef __ssize_t ssize_t;
So the size_t that is used in tools/perf/util/trace-event.h was being
obtained indirectly, by chance.
Fixes: 378ef0f5d9d7f465 ("perf build: Use libtraceevent from the system")
Signed-off-by: Jesus Sanchez-Palencia <jesussanp@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/20230104193414.606905-1-jesussanp@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/trace-event.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index add6c5d9531cd..9b3cd79cca121 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -4,6 +4,7 @@
#include <stdbool.h>
#include <stdio.h>
+#include <sys/types.h>
#include <linux/types.h>
struct evlist;
--
GitLab
From f52853a668bfeddd79f319d536a506f68cc2b478 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Wed, 4 Jan 2023 22:58:30 +0800
Subject: [PATCH 0363/1167] perf/x86/rapl: Add support for Intel Meteor Lake
Meteor Lake RAPL support is the same as previous Sky Lake.
Add Meteor Lake model for RAPL.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230104145831.25498-1-rui.zhang@intel.com
---
arch/x86/events/rapl.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index ae5779ea44174..589c6885560d2 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -809,6 +809,8 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
--
GitLab
From 57512b57dcfaf63c52d8ad2fb35321328cde31b0 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Wed, 4 Jan 2023 22:58:31 +0800
Subject: [PATCH 0364/1167] perf/x86/rapl: Add support for Intel Emerald Rapids
Emerald Rapids RAPL support is the same as previous Sapphire Rapids.
Add Emerald Rapids model for RAPL.
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230104145831.25498-2-rui.zhang@intel.com
---
arch/x86/events/rapl.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 589c6885560d2..52e6e7ed4f78a 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -806,6 +806,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
--
GitLab
From 9cea62b2cbabff8ed46f2df17778b624ad9dd25a Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 08:52:06 -0700
Subject: [PATCH 0365/1167] block: don't allow splitting of a REQ_NOWAIT bio
If we split a bio marked with REQ_NOWAIT, then we can trigger spurious
EAGAIN if constituent parts of that split bio end up failing request
allocations. Parts will complete just fine, but just a single failure
in one of the chained bios will yield an EAGAIN final result for the
parent bio.
Return EAGAIN early if we end up needing to split such a bio, which
allows for saner recovery handling.
Cc: stable@vger.kernel.org # 5.15+
Link: https://github.com/axboe/liburing/issues/766
Reported-by: Michael Kelley <mikelley@microsoft.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-merge.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 071c5f8cf0cfe..b7c193d67185d 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -309,6 +309,16 @@ static struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
*segs = nsegs;
return NULL;
split:
+ /*
+ * We can't sanely support splitting for a REQ_NOWAIT bio. End it
+ * with EAGAIN if splitting is required and return an error pointer.
+ */
+ if (bio->bi_opf & REQ_NOWAIT) {
+ bio->bi_status = BLK_STS_AGAIN;
+ bio_endio(bio);
+ return ERR_PTR(-EAGAIN);
+ }
+
*segs = nsegs;
/*
--
GitLab
From fa8e442e832a3647cdd90f3e606c473a51bc1b26 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 4 Jan 2023 21:32:35 +0800
Subject: [PATCH 0366/1167] ublk: honor IO_URING_F_NONBLOCK for handling
control command
Most of control command handlers may sleep, so return -EAGAIN in case
of IO_URING_F_NONBLOCK to defer the handling into io wq context.
Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver")
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230104133235.836536-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/block/ublk_drv.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index e9de9d846b730..17b677b5d3b22 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1992,6 +1992,9 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
int ret = -EINVAL;
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
ublk_ctrl_cmd_dump(cmd);
if (!(issue_flags & IO_URING_F_SQE128))
--
GitLab
From 59b745bb4e0bd445366c45b8df6b51b69134f4f5 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 13:49:54 -0700
Subject: [PATCH 0367/1167] io_uring: move 'poll_multi_queue' bool in
io_ring_ctx
The cacheline section holding this variable has two gaps, where one is
caused by this bool not packing well with structs. This causes it to
blow into the next cacheline. Move the variable, shrinking io_ring_ctx
by a full cacheline in size.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
include/linux/io_uring_types.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index dcd8a563ab522..128a67a40065f 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -292,6 +292,8 @@ struct io_ring_ctx {
struct {
spinlock_t completion_lock;
+ bool poll_multi_queue;
+
/*
* ->iopoll_list is protected by the ctx->uring_lock for
* io_uring instances that don't use IORING_SETUP_SQPOLL.
@@ -300,7 +302,6 @@ struct io_ring_ctx {
*/
struct io_wq_work_list iopoll_list;
struct io_hash_table cancel_table;
- bool poll_multi_queue;
struct llist_head work_llist;
--
GitLab
From ee4b4e2248565babfba807d82c0f3e00c392a4c0 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 14:43:27 -0700
Subject: [PATCH 0368/1167] Revert "block: bio_copy_data_iter"
This reverts commit db1c7d77976775483a8ef240b4c705f113e13ea1.
We're reinstating the pktcdvd driver, which needs this API.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/bio.c | 37 ++++++++++++++++++++++---------------
include/linux/bio.h | 2 ++
2 files changed, 24 insertions(+), 15 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 5f96fcae3f754..ab59a491a883e 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1401,6 +1401,27 @@ void __bio_advance(struct bio *bio, unsigned bytes)
}
EXPORT_SYMBOL(__bio_advance);
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter)
+{
+ while (src_iter->bi_size && dst_iter->bi_size) {
+ struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+ struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+ unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+ void *src_buf = bvec_kmap_local(&src_bv);
+ void *dst_buf = bvec_kmap_local(&dst_bv);
+
+ memcpy(dst_buf, src_buf, bytes);
+
+ kunmap_local(dst_buf);
+ kunmap_local(src_buf);
+
+ bio_advance_iter_single(src, src_iter, bytes);
+ bio_advance_iter_single(dst, dst_iter, bytes);
+ }
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
/**
* bio_copy_data - copy contents of data buffers from one bio to another
* @src: source bio
@@ -1414,21 +1435,7 @@ void bio_copy_data(struct bio *dst, struct bio *src)
struct bvec_iter src_iter = src->bi_iter;
struct bvec_iter dst_iter = dst->bi_iter;
- while (src_iter.bi_size && dst_iter.bi_size) {
- struct bio_vec src_bv = bio_iter_iovec(src, src_iter);
- struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter);
- unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
- void *src_buf = bvec_kmap_local(&src_bv);
- void *dst_buf = bvec_kmap_local(&dst_bv);
-
- memcpy(dst_buf, src_buf, bytes);
-
- kunmap_local(dst_buf);
- kunmap_local(src_buf);
-
- bio_advance_iter_single(src, &src_iter, bytes);
- bio_advance_iter_single(dst, &dst_iter, bytes);
- }
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
EXPORT_SYMBOL(bio_copy_data);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 22078a28d7cb1..c1da63f6c8080 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -475,6 +475,8 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
void guard_bio_eod(struct bio *bio);
--
GitLab
From 050a4f341f35bf51db321c7f68700f9e0b1a7552 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 14:44:02 -0700
Subject: [PATCH 0369/1167] Revert "block: remove devnode callback from struct
block_device_operations"
This reverts commit 85d6ce58e493ac8b7122e2fbe3f41b94d6ebdc11.
We're reinstating the pktcdvd driver, which needs this API.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/genhd.c | 11 +++++++++++
include/linux/blkdev.h | 1 +
2 files changed, 12 insertions(+)
diff --git a/block/genhd.c b/block/genhd.c
index 08f76135a6373..14329dc278b29 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1201,10 +1201,21 @@ struct class block_class = {
.dev_uevent = block_uevent,
};
+static char *block_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (disk->fops->devnode)
+ return disk->fops->devnode(disk, mode);
+ return NULL;
+}
+
const struct device_type disk_type = {
.name = "disk",
.groups = disk_attr_groups,
.release = disk_release,
+ .devnode = block_devnode,
};
#ifdef CONFIG_PROC_FS
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 301cf1cf4f2fa..43d4e073b1115 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1395,6 +1395,7 @@ struct block_device_operations {
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
int (*report_zones)(struct gendisk *, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+ char *(*devnode)(struct gendisk *disk, umode_t *mode);
/* returns the length of the identifier or a negative errno: */
int (*get_unique_id)(struct gendisk *disk, u8 id[16],
enum blk_unique_id id_type);
--
GitLab
From 4b83e99ee7092df37a5cf292fde976ebc475ea63 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 4 Jan 2023 14:44:13 -0700
Subject: [PATCH 0370/1167] Revert "pktcdvd: remove driver."
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This reverts commit f40eb99897af665f11858dd7b56edcb62c3f3c67.
There are apparently still users out there of this driver. While we'd
love to remove it to ease the maintenance burden, let's reinstate it
for now until better (userspace) solutions can be developed.
Link: https://lore.kernel.org/lkml/20230104190115.ceglfefco475ev6c@pali/
Reported-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
Documentation/ABI/testing/debugfs-pktcdvd | 18 +
Documentation/ABI/testing/sysfs-class-pktcdvd | 97 +
MAINTAINERS | 7 +
drivers/block/Kconfig | 43 +
drivers/block/Makefile | 1 +
drivers/block/pktcdvd.c | 2944 +++++++++++++++++
include/linux/pktcdvd.h | 197 ++
include/uapi/linux/pktcdvd.h | 112 +
8 files changed, 3419 insertions(+)
create mode 100644 Documentation/ABI/testing/debugfs-pktcdvd
create mode 100644 Documentation/ABI/testing/sysfs-class-pktcdvd
create mode 100644 drivers/block/pktcdvd.c
create mode 100644 include/linux/pktcdvd.h
create mode 100644 include/uapi/linux/pktcdvd.h
diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd
new file mode 100644
index 0000000000000..f6f65a4faea06
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-pktcdvd
@@ -0,0 +1,18 @@
+What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+The pktcdvd module (packet writing driver) creates
+these files in debugfs:
+
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
+
+ ==== ====== ====================================
+ info 0444 Lots of driver statistics and infos.
+ ==== ====== ====================================
+
+Example::
+
+ cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
diff --git a/Documentation/ABI/testing/sysfs-class-pktcdvd b/Documentation/ABI/testing/sysfs-class-pktcdvd
new file mode 100644
index 0000000000000..ba1ce626591d9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-pktcdvd
@@ -0,0 +1,97 @@
+sysfs interface
+---------------
+The pktcdvd module (packet writing driver) creates the following files in the
+sysfs: (<devid> is in the format major:minor)
+
+What: /sys/class/pktcdvd/add
+What: /sys/class/pktcdvd/remove
+What: /sys/class/pktcdvd/device_map
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+ ========== ==============================================
+ add (WO) Write a block device id (major:minor) to
+ create a new pktcdvd device and map it to the
+ block device.
+
+ remove (WO) Write the pktcdvd device id (major:minor)
+ to remove the pktcdvd device.
+
+ device_map (RO) Shows the device mapping in format:
+ pktcdvd[0-7] <pktdevid> <blkdevid>
+ ========== ==============================================
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/dev
+What: /sys/class/pktcdvd/pktcdvd[0-7]/uevent
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ dev: (RO) Device id
+
+ uevent: (WO) To send a uevent
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/reset
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ packets_started: (RO) Number of started packets.
+
+ packets_finished: (RO) Number of finished packets.
+
+ kb_written: (RO) kBytes written.
+
+ kb_read: (RO) kBytes read.
+
+ kb_read_gather: (RO) kBytes read to fill write packets.
+
+ reset: (WO) Write any value to it to reset
+ pktcdvd device statistic values, like
+ bytes read/written.
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ ============== ================================================
+ size (RO) Contains the size of the bio write queue.
+
+ congestion_off (RW) If bio write queue size is below this mark,
+ accept new bio requests from the block layer.
+
+ congestion_on (RW) If bio write queue size is higher as this
+ mark, do no longer accept bio write requests
+ from the block layer and wait till the pktcdvd
+ device has processed enough bio's so that bio
+ write queue size is below congestion off mark.
+ A value of <= 0 disables congestion control.
+ ============== ================================================
+
+
+Example:
+--------
+To use the pktcdvd sysfs interface directly, you can do::
+
+ # create a new pktcdvd device mapped to /dev/hdc
+ echo "22:0" >/sys/class/pktcdvd/add
+ cat /sys/class/pktcdvd/device_map
+ # assuming device pktcdvd0 was created, look at stat's
+ cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+ # print the device id of the mapped block device
+ fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+ # remove device, using pktcdvd0 device id 253:0
+ echo "253:0" >/sys/class/pktcdvd/remove
diff --git a/MAINTAINERS b/MAINTAINERS
index d53b3a6cdc67d..3ef137fea4f6d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16520,6 +16520,13 @@ S: Supported
F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
F: drivers/input/keyboard/pinephone-keyboard.c
+PKTCDVD DRIVER
+M: linux-block@vger.kernel.org
+S: Orphan
+F: drivers/block/pktcdvd.c
+F: include/linux/pktcdvd.h
+F: include/uapi/linux/pktcdvd.h
+
PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
M: Tomasz Duszynski <tduszyns@gmail.com>
S: Maintained
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index a2184b4284936..a41145d52de94 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -285,6 +285,49 @@ config BLK_DEV_RAM_SIZE
The default value is 4096 kilobytes. Only change this if you know
what you are doing.
+config CDROM_PKTCDVD
+ tristate "Packet writing on CD/DVD media (DEPRECATED)"
+ depends on !UML
+ depends on SCSI
+ select CDROM
+ help
+ Note: This driver is deprecated and will be removed from the
+ kernel in the near future!
+
+ If you have a CDROM/DVD drive that supports packet writing, say
+ Y to include support. It should work with any MMC/Mt Fuji
+ compliant ATAPI or SCSI drive, which is just about any newer
+ DVD/CD writer.
+
+ Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs
+ is possible.
+ DVD-RW disks must be in restricted overwrite mode.
+
+ See the file <file:Documentation/cdrom/packet-writing.rst>
+ for further information on the use of this driver.
+
+ To compile this driver as a module, choose M here: the
+ module will be called pktcdvd.
+
+config CDROM_PKTCDVD_BUFFERS
+ int "Free buffers for data gathering"
+ depends on CDROM_PKTCDVD
+ default "8"
+ help
+ This controls the maximum number of active concurrent packets. More
+ concurrent packets can increase write performance, but also require
+ more memory. Each concurrent packet will require approximately 64Kb
+ of non-swappable kernel memory, memory which will be allocated when
+ a disc is opened for writing.
+
+config CDROM_PKTCDVD_WCACHE
+ bool "Enable write caching"
+ depends on CDROM_PKTCDVD
+ help
+ If enabled, write caching will be set for the CD-R/W device. For now
+ this option is dangerous unless the CD-RW media is known good, as we
+ don't do deferred write error handling yet.
+
config ATA_OVER_ETH
tristate "ATA over Ethernet support"
depends on NET
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 962ee65d8ca30..101612cba303a 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o
obj-$(CONFIG_N64CART) += n64cart.o
obj-$(CONFIG_BLK_DEV_RAM) += brd.o
obj-$(CONFIG_BLK_DEV_LOOP) += loop.o
+obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
new file mode 100644
index 0000000000000..4cea3b08087ed
--- /dev/null
+++ b/drivers/block/pktcdvd.c
@@ -0,0 +1,2944 @@
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ * Copyright (C) 2006 Thomas Maier <balagi@justmail.de>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
+ * DVD-RAM devices.
+ *
+ * Theory of operation:
+ *
+ * At the lowest level, there is the standard driver for the CD/DVD device,
+ * such as drivers/scsi/sr.c. This driver can handle read and write requests,
+ * but it doesn't know anything about the special restrictions that apply to
+ * packet writing. One restriction is that write requests must be aligned to
+ * packet boundaries on the physical media, and the size of a write request
+ * must be equal to the packet size. Another restriction is that a
+ * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
+ * command, if the previous command was a write.
+ *
+ * The purpose of the packet writing driver is to hide these restrictions from
+ * higher layers, such as file systems, and present a block device that can be
+ * randomly read and written using 2kB-sized blocks.
+ *
+ * The lowest layer in the packet writing driver is the packet I/O scheduler.
+ * Its data is defined by the struct packet_iosched and includes two bio
+ * queues with pending read and write requests. These queues are processed
+ * by the pkt_iosched_process_queue() function. The write requests in this
+ * queue are already properly aligned and sized. This layer is responsible for
+ * issuing the flush cache commands and scheduling the I/O in a good order.
+ *
+ * The next layer transforms unaligned write requests to aligned writes. This
+ * transformation requires reading missing pieces of data from the underlying
+ * block device, assembling the pieces to full packets and queuing them to the
+ * packet I/O scheduler.
+ *
+ * At the top layer there is a custom ->submit_bio function that forwards
+ * read requests directly to the iosched queue and puts write requests in the
+ * unaligned write queue. A kernel thread performs the necessary read
+ * gathering to convert the unaligned writes to aligned writes and then feeds
+ * them to the packet I/O scheduler.
+ *
+ *************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/pktcdvd.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compat.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+#include <linux/freezer.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/backing-dev.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+
+#define DRIVER_NAME "pktcdvd"
+
+#define pkt_err(pd, fmt, ...) \
+ pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...) \
+ pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
+
+#define pkt_dbg(level, pd, fmt, ...) \
+do { \
+ if (level == 2 && PACKET_DEBUG >= 2) \
+ pr_notice("%s: %s():" fmt, \
+ pd->name, __func__, ##__VA_ARGS__); \
+ else if (level == 1 && PACKET_DEBUG >= 1) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \
+} while (0)
+
+#define MAX_SPEED 0xffff
+
+static DEFINE_MUTEX(pktcdvd_mutex);
+static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
+static struct proc_dir_entry *pkt_proc;
+static int pktdev_major;
+static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
+static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
+static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
+
+static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
+static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
+
+/* forward declaration */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
+static int pkt_remove_dev(dev_t pkt_dev);
+static int pkt_seq_show(struct seq_file *m, void *p);
+
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+ return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
+
+/**********************************************************
+ * sysfs interface for pktcdvd
+ * by (C) 2006 Thomas Maier <balagi@justmail.de>
+
+ /sys/class/pktcdvd/pktcdvd[0-7]/
+ stat/reset
+ stat/packets_started
+ stat/packets_finished
+ stat/kb_written
+ stat/kb_read
+ stat/kb_read_gather
+ write_queue/size
+ write_queue/congestion_off
+ write_queue/congestion_on
+ **********************************************************/
+
+static ssize_t packets_started_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
+}
+static DEVICE_ATTR_RO(packets_started);
+
+static ssize_t packets_finished_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
+}
+static DEVICE_ATTR_RO(packets_finished);
+
+static ssize_t kb_written_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
+}
+static DEVICE_ATTR_RO(kb_written);
+
+static ssize_t kb_read_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
+}
+static DEVICE_ATTR_RO(kb_read);
+
+static ssize_t kb_read_gather_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
+}
+static DEVICE_ATTR_RO(kb_read_gather);
+
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ if (len > 0) {
+ pd->stats.pkt_started = 0;
+ pd->stats.pkt_ended = 0;
+ pd->stats.secs_w = 0;
+ pd->stats.secs_rg = 0;
+ pd->stats.secs_r = 0;
+ }
+ return len;
+}
+static DEVICE_ATTR_WO(reset);
+
+static struct attribute *pkt_stat_attrs[] = {
+ &dev_attr_packets_finished.attr,
+ &dev_attr_packets_started.attr,
+ &dev_attr_kb_read.attr,
+ &dev_attr_kb_written.attr,
+ &dev_attr_kb_read_gather.attr,
+ &dev_attr_reset.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_stat_group = {
+ .name = "stat",
+ .attrs = pkt_stat_attrs,
+};
+
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
+ spin_unlock(&pd->lock);
+ return n;
+}
+static DEVICE_ATTR_RO(size);
+
+static void init_write_congestion_marks(int* lo, int* hi)
+{
+ if (*hi > 0) {
+ *hi = max(*hi, 500);
+ *hi = min(*hi, 1000000);
+ if (*lo <= 0)
+ *lo = *hi - 100;
+ else {
+ *lo = min(*lo, *hi - 100);
+ *lo = max(*lo, 100);
+ }
+ } else {
+ *hi = -1;
+ *lo = -1;
+ }
+}
+
+static ssize_t congestion_off_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_off_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_off = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_off);
+
+static ssize_t congestion_on_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_on_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_on = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_on);
+
+static struct attribute *pkt_wq_attrs[] = {
+ &dev_attr_congestion_on.attr,
+ &dev_attr_congestion_off.attr,
+ &dev_attr_size.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_wq_group = {
+ .name = "write_queue",
+ .attrs = pkt_wq_attrs,
+};
+
+static const struct attribute_group *pkt_groups[] = {
+ &pkt_stat_group,
+ &pkt_wq_group,
+ NULL,
+};
+
+static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd) {
+ pd->dev = device_create_with_groups(class_pktcdvd, NULL,
+ MKDEV(0, 0), pd, pkt_groups,
+ "%s", pd->name);
+ if (IS_ERR(pd->dev))
+ pd->dev = NULL;
+ }
+}
+
+static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd)
+ device_unregister(pd->dev);
+}
+
+
+/********************************************************************
+ /sys/class/pktcdvd/
+ add map block device
+ remove unmap packet dev
+ device_map show mappings
+ *******************************************************************/
+
+static void class_pktcdvd_release(struct class *cls)
+{
+ kfree(cls);
+}
+
+static ssize_t device_map_show(struct class *c, struct class_attribute *attr,
+ char *data)
+{
+ int n = 0;
+ int idx;
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ struct pktcdvd_device *pd = pkt_devs[idx];
+ if (!pd)
+ continue;
+ n += sprintf(data+n, "%s %u:%u %u:%u\n",
+ pd->name,
+ MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
+ MAJOR(pd->bdev->bd_dev),
+ MINOR(pd->bdev->bd_dev));
+ }
+ mutex_unlock(&ctl_mutex);
+ return n;
+}
+static CLASS_ATTR_RO(device_map);
+
+static ssize_t add_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ /* pkt_setup_dev() expects caller to hold reference to self */
+ if (!try_module_get(THIS_MODULE))
+ return -ENODEV;
+
+ pkt_setup_dev(MKDEV(major, minor), NULL);
+
+ module_put(THIS_MODULE);
+
+ return count;
+ }
+
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(add);
+
+static ssize_t remove_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ pkt_remove_dev(MKDEV(major, minor));
+ return count;
+ }
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(remove);
+
+static struct attribute *class_pktcdvd_attrs[] = {
+ &class_attr_add.attr,
+ &class_attr_remove.attr,
+ &class_attr_device_map.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(class_pktcdvd);
+
+static int pkt_sysfs_init(void)
+{
+ int ret = 0;
+
+ /*
+ * create control files in sysfs
+ * /sys/class/pktcdvd/...
+ */
+ class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL);
+ if (!class_pktcdvd)
+ return -ENOMEM;
+ class_pktcdvd->name = DRIVER_NAME;
+ class_pktcdvd->owner = THIS_MODULE;
+ class_pktcdvd->class_release = class_pktcdvd_release;
+ class_pktcdvd->class_groups = class_pktcdvd_groups;
+ ret = class_register(class_pktcdvd);
+ if (ret) {
+ kfree(class_pktcdvd);
+ class_pktcdvd = NULL;
+ pr_err("failed to create class pktcdvd\n");
+ return ret;
+ }
+ return 0;
+}
+
+static void pkt_sysfs_cleanup(void)
+{
+ if (class_pktcdvd)
+ class_destroy(class_pktcdvd);
+ class_pktcdvd = NULL;
+}
+
+/********************************************************************
+ entries in debugfs
+
+ /sys/kernel/debug/pktcdvd[0-7]/
+ info
+
+ *******************************************************************/
+
+static int pkt_debugfs_seq_show(struct seq_file *m, void *p)
+{
+ return pkt_seq_show(m, p);
+}
+
+static int pkt_debugfs_fops_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, pkt_debugfs_seq_show, inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+ .open = pkt_debugfs_fops_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root);
+ if (!pd->dfs_d_root)
+ return;
+
+ pd->dfs_f_info = debugfs_create_file("info", 0444,
+ pd->dfs_d_root, pd, &debug_fops);
+}
+
+static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ debugfs_remove(pd->dfs_f_info);
+ debugfs_remove(pd->dfs_d_root);
+ pd->dfs_f_info = NULL;
+ pd->dfs_d_root = NULL;
+}
+
+static void pkt_debugfs_init(void)
+{
+ pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
+}
+
+static void pkt_debugfs_cleanup(void)
+{
+ debugfs_remove(pkt_debugfs_root);
+ pkt_debugfs_root = NULL;
+}
+
+/* ----------------------------------------------------------*/
+
+
+static void pkt_bio_finished(struct pktcdvd_device *pd)
+{
+ BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
+ if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
+ pkt_dbg(2, pd, "queue empty\n");
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+ }
+}
+
+/*
+ * Allocate a packet_data struct
+ */
+static struct packet_data *pkt_alloc_packet_data(int frames)
+{
+ int i;
+ struct packet_data *pkt;
+
+ pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
+ if (!pkt)
+ goto no_pkt;
+
+ pkt->frames = frames;
+ pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
+ if (!pkt->w_bio)
+ goto no_bio;
+
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
+ pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+ if (!pkt->pages[i])
+ goto no_page;
+ }
+
+ spin_lock_init(&pkt->lock);
+ bio_list_init(&pkt->orig_bios);
+
+ for (i = 0; i < frames; i++) {
+ pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
+ if (!pkt->r_bios[i])
+ goto no_rd_bio;
+ }
+
+ return pkt;
+
+no_rd_bio:
+ for (i = 0; i < frames; i++)
+ kfree(pkt->r_bios[i]);
+no_page:
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
+ if (pkt->pages[i])
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+no_bio:
+ kfree(pkt);
+no_pkt:
+ return NULL;
+}
+
+/*
+ * Free a packet_data struct
+ */
+static void pkt_free_packet_data(struct packet_data *pkt)
+{
+ int i;
+
+ for (i = 0; i < pkt->frames; i++)
+ kfree(pkt->r_bios[i]);
+ for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+ kfree(pkt);
+}
+
+static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));
+
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
+ pkt_free_packet_data(pkt);
+ }
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+}
+
+static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
+{
+ struct packet_data *pkt;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));
+
+ while (nr_packets > 0) {
+ pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
+ if (!pkt) {
+ pkt_shrink_pktlist(pd);
+ return 0;
+ }
+ pkt->id = nr_packets;
+ pkt->pd = pd;
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ nr_packets--;
+ }
+ return 1;
+}
+
+static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
+{
+ struct rb_node *n = rb_next(&node->rb_node);
+ if (!n)
+ return NULL;
+ return rb_entry(n, struct pkt_rb_node, rb_node);
+}
+
+static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ rb_erase(&node->rb_node, &pd->bio_queue);
+ mempool_free(node, &pd->rb_pool);
+ pd->bio_queue_size--;
+ BUG_ON(pd->bio_queue_size < 0);
+}
+
+/*
+ * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
+ */
+static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
+{
+ struct rb_node *n = pd->bio_queue.rb_node;
+ struct rb_node *next;
+ struct pkt_rb_node *tmp;
+
+ if (!n) {
+ BUG_ON(pd->bio_queue_size > 0);
+ return NULL;
+ }
+
+ for (;;) {
+ tmp = rb_entry(n, struct pkt_rb_node, rb_node);
+ if (s <= tmp->bio->bi_iter.bi_sector)
+ next = n->rb_left;
+ else
+ next = n->rb_right;
+ if (!next)
+ break;
+ n = next;
+ }
+
+ if (s > tmp->bio->bi_iter.bi_sector) {
+ tmp = pkt_rbtree_next(tmp);
+ if (!tmp)
+ return NULL;
+ }
+ BUG_ON(s > tmp->bio->bi_iter.bi_sector);
+ return tmp;
+}
+
+/*
+ * Insert a node into the pd->bio_queue rb tree.
+ */
+static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ struct rb_node **p = &pd->bio_queue.rb_node;
+ struct rb_node *parent = NULL;
+ sector_t s = node->bio->bi_iter.bi_sector;
+ struct pkt_rb_node *tmp;
+
+ while (*p) {
+ parent = *p;
+ tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
+ if (s < tmp->bio->bi_iter.bi_sector)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+ rb_link_node(&node->rb_node, parent, p);
+ rb_insert_color(&node->rb_node, &pd->bio_queue);
+ pd->bio_queue_size++;
+}
+
+/*
+ * Send a packet_command to the underlying block device and
+ * wait for completion.
+ */
+static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ struct request_queue *q = bdev_get_queue(pd->bdev);
+ struct scsi_cmnd *scmd;
+ struct request *rq;
+ int ret = 0;
+
+ rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+ REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+ scmd = blk_mq_rq_to_pdu(rq);
+
+ if (cgc->buflen) {
+ ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
+ GFP_NOIO);
+ if (ret)
+ goto out;
+ }
+
+ scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+ memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);
+
+ rq->timeout = 60*HZ;
+ if (cgc->quiet)
+ rq->rq_flags |= RQF_QUIET;
+
+ blk_execute_rq(rq, false);
+ if (scmd->result)
+ ret = -EIO;
+out:
+ blk_mq_free_request(rq);
+ return ret;
+}
+
+static const char *sense_key_string(__u8 index)
+{
+ static const char * const info[] = {
+ "No sense", "Recovered error", "Not ready",
+ "Medium error", "Hardware error", "Illegal request",
+ "Unit attention", "Data protect", "Blank check",
+ };
+
+ return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
+/*
+ * A generic sense dump / resolve mechanism should be implemented across
+ * all ATAPI + SCSI devices.
+ */
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+ struct packet_command *cgc)
+{
+ struct scsi_sense_hdr *sshdr = cgc->sshdr;
+
+ if (sshdr)
+ pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+ CDROM_PACKET_SIZE, cgc->cmd,
+ sshdr->sense_key, sshdr->asc, sshdr->ascq,
+ sense_key_string(sshdr->sense_key));
+ else
+ pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
+}
+
+/*
+ * flush the drive cache to media
+ */
+static int pkt_flush_cache(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_FLUSH_CACHE;
+ cgc.quiet = 1;
+
+ /*
+ * the IMMED bit -- we default to not setting it, although that
+ * would allow a much faster close, this is safer
+ */
+#if 0
+ cgc.cmd[1] = 1 << 1;
+#endif
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * speed is given as the normal factor, e.g. 4 for 4x
+ */
+static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
+ unsigned write_speed, unsigned read_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_SET_SPEED;
+ cgc.cmd[2] = (read_speed >> 8) & 0xff;
+ cgc.cmd[3] = read_speed & 0xff;
+ cgc.cmd[4] = (write_speed >> 8) & 0xff;
+ cgc.cmd[5] = write_speed & 0xff;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+
+ return ret;
+}
+
+/*
+ * Queue a bio for processing by the low-level CD device. Must be called
+ * from process context.
+ */
+static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
+{
+ spin_lock(&pd->iosched.lock);
+ if (bio_data_dir(bio) == READ)
+ bio_list_add(&pd->iosched.read_queue, bio);
+ else
+ bio_list_add(&pd->iosched.write_queue, bio);
+ spin_unlock(&pd->iosched.lock);
+
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Process the queued read/write requests. This function handles special
+ * requirements for CDRW drives:
+ * - A cache flush command must be inserted before a read request if the
+ * previous request was a write.
+ * - Switching between reading and writing is slow, so don't do it more often
+ * than necessary.
+ * - Optimize for throughput at the expense of latency. This means that streaming
+ * writes will never be interrupted by a read, but if the drive has to seek
+ * before the next write, switch to reading instead if there are any pending
+ * read requests.
+ * - Set the read speed according to current usage pattern. When only reading
+ * from the device, it's best to use the highest possible read speed, but
+ * when switching often between reading and writing, it's better to have the
+ * same read and write speeds.
+ */
+static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
+{
+
+ if (atomic_read(&pd->iosched.attention) == 0)
+ return;
+ atomic_set(&pd->iosched.attention, 0);
+
+ for (;;) {
+ struct bio *bio;
+ int reads_queued, writes_queued;
+
+ spin_lock(&pd->iosched.lock);
+ reads_queued = !bio_list_empty(&pd->iosched.read_queue);
+ writes_queued = !bio_list_empty(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!reads_queued && !writes_queued)
+ break;
+
+ if (pd->iosched.writing) {
+ int need_write_seek = 1;
+ spin_lock(&pd->iosched.lock);
+ bio = bio_list_peek(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+ if (bio && (bio->bi_iter.bi_sector ==
+ pd->iosched.last_write))
+ need_write_seek = 0;
+ if (need_write_seek && reads_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "write, waiting\n");
+ break;
+ }
+ pkt_flush_cache(pd);
+ pd->iosched.writing = 0;
+ }
+ } else {
+ if (!reads_queued && writes_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "read, waiting\n");
+ break;
+ }
+ pd->iosched.writing = 1;
+ }
+ }
+
+ spin_lock(&pd->iosched.lock);
+ if (pd->iosched.writing)
+ bio = bio_list_pop(&pd->iosched.write_queue);
+ else
+ bio = bio_list_pop(&pd->iosched.read_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!bio)
+ continue;
+
+ if (bio_data_dir(bio) == READ)
+ pd->iosched.successive_reads +=
+ bio->bi_iter.bi_size >> 10;
+ else {
+ pd->iosched.successive_reads = 0;
+ pd->iosched.last_write = bio_end_sector(bio);
+ }
+ if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
+ if (pd->read_speed == pd->write_speed) {
+ pd->read_speed = MAX_SPEED;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ } else {
+ if (pd->read_speed != pd->write_speed) {
+ pd->read_speed = pd->write_speed;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ }
+
+ atomic_inc(&pd->cdrw.pending_bios);
+ submit_bio_noacct(bio);
+ }
+}
+
+/*
+ * Special care is needed if the underlying block device has a small
+ * max_phys_segments value.
+ */
+static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
+{
+ if ((pd->settings.size << 9) / CD_FRAMESIZE
+ <= queue_max_segments(q)) {
+ /*
+ * The cdrom device can handle one segment/frame
+ */
+ clear_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else if ((pd->settings.size << 9) / PAGE_SIZE
+ <= queue_max_segments(q)) {
+ /*
+ * We can handle this case at the expense of some extra memory
+ * copies during write operations
+ */
+ set_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else {
+ pkt_err(pd, "cdrom max_phys_segments too small\n");
+ return -EIO;
+ }
+}
+
+static void pkt_end_io_read(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+ bio, (unsigned long long)pkt->sector,
+ (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
+
+ if (bio->bi_status)
+ atomic_inc(&pkt->io_errors);
+ bio_uninit(bio);
+ if (atomic_dec_and_test(&pkt->io_wait)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ pkt_bio_finished(pd);
+}
+
+static void pkt_end_io_packet_write(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
+
+ pd->stats.pkt_ended++;
+
+ bio_uninit(bio);
+ pkt_bio_finished(pd);
+ atomic_dec(&pkt->io_wait);
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Schedule reads for the holes in a packet
+ */
+static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int frames_read = 0;
+ struct bio *bio;
+ int f;
+ char written[PACKET_MAX_SIZE];
+
+ BUG_ON(bio_list_empty(&pkt->orig_bios));
+
+ atomic_set(&pkt->io_wait, 0);
+ atomic_set(&pkt->io_errors, 0);
+
+ /*
+ * Figure out which frames we need to read before we can write.
+ */
+ memset(written, 0, sizeof(written));
+ spin_lock(&pkt->lock);
+ bio_list_for_each(bio, &pkt->orig_bios) {
+ int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
+ (CD_FRAMESIZE >> 9);
+ int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
+ pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
+ BUG_ON(first_frame < 0);
+ BUG_ON(first_frame + num_frames > pkt->frames);
+ for (f = first_frame; f < first_frame + num_frames; f++)
+ written[f] = 1;
+ }
+ spin_unlock(&pkt->lock);
+
+ if (pkt->cache_valid) {
+ pkt_dbg(2, pd, "zone %llx cached\n",
+ (unsigned long long)pkt->sector);
+ goto out_account;
+ }
+
+ /*
+ * Schedule reads for missing parts of the packet.
+ */
+ for (f = 0; f < pkt->frames; f++) {
+ int p, offset;
+
+ if (written[f])
+ continue;
+
+ bio = pkt->r_bios[f];
+ bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ);
+ bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
+ bio->bi_end_io = pkt_end_io_read;
+ bio->bi_private = pkt;
+
+ p = (f * CD_FRAMESIZE) / PAGE_SIZE;
+ offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+ pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
+ f, pkt->pages[p], offset);
+ if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
+ BUG();
+
+ atomic_inc(&pkt->io_wait);
+ pkt_queue_bio(pd, bio);
+ frames_read++;
+ }
+
+out_account:
+ pkt_dbg(2, pd, "need %d frames for zone %llx\n",
+ frames_read, (unsigned long long)pkt->sector);
+ pd->stats.pkt_started++;
+ pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
+}
+
+/*
+ * Find a packet matching zone, or the least recently used packet if
+ * there is no match.
+ */
+static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
+{
+ struct packet_data *pkt;
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
+ if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
+ list_del_init(&pkt->list);
+ if (pkt->sector != zone)
+ pkt->cache_valid = 0;
+ return pkt;
+ }
+ }
+ BUG();
+ return NULL;
+}
+
+static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ if (pkt->cache_valid) {
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ } else {
+ list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
+ }
+}
+
+static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state)
+{
+#if PACKET_DEBUG > 1
+ static const char *state_name[] = {
+ "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
+ };
+ enum packet_data_state old_state = pkt->state;
+ pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+ pkt->id, (unsigned long long)pkt->sector,
+ state_name[old_state], state_name[state]);
+#endif
+ pkt->state = state;
+}
+
+/*
+ * Scan the work queue to see if we can start a new packet.
+ * returns non-zero if any work was done.
+ */
+static int pkt_handle_queue(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *p;
+ struct bio *bio = NULL;
+ sector_t zone = 0; /* Suppress gcc warning */
+ struct pkt_rb_node *node, *first_node;
+ struct rb_node *n;
+
+ atomic_set(&pd->scan_queue, 0);
+
+ if (list_empty(&pd->cdrw.pkt_free_list)) {
+ pkt_dbg(2, pd, "no pkt\n");
+ return 0;
+ }
+
+ /*
+ * Try to find a zone we are not already working on.
+ */
+ spin_lock(&pd->lock);
+ first_node = pkt_rbtree_find(pd, pd->current_sector);
+ if (!first_node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ first_node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ node = first_node;
+ while (node) {
+ bio = node->bio;
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+ list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
+ if (p->sector == zone) {
+ bio = NULL;
+ goto try_next_bio;
+ }
+ }
+ break;
+try_next_bio:
+ node = pkt_rbtree_next(node);
+ if (!node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ if (node == first_node)
+ node = NULL;
+ }
+ spin_unlock(&pd->lock);
+ if (!bio) {
+ pkt_dbg(2, pd, "no bio\n");
+ return 0;
+ }
+
+ pkt = pkt_get_packet_data(pd, zone);
+
+ pd->current_sector = zone + pd->settings.size;
+ pkt->sector = zone;
+ BUG_ON(pkt->frames != pd->settings.size >> 2);
+ pkt->write_size = 0;
+
+ /*
+ * Scan work queue for bios in the same zone and link them
+ * to this packet.
+ */
+ spin_lock(&pd->lock);
+ pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
+ while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
+ bio = node->bio;
+ pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long)
+ get_zone(bio->bi_iter.bi_sector, pd));
+ if (get_zone(bio->bi_iter.bi_sector, pd) != zone)
+ break;
+ pkt_rbtree_erase(pd, node);
+ spin_lock(&pkt->lock);
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
+ spin_unlock(&pkt->lock);
+ }
+ /* check write congestion marks, and if bio_queue_size is
+ * below, wake up any waiters
+ */
+ if (pd->congested &&
+ pd->bio_queue_size <= pd->write_congestion_off) {
+ pd->congested = false;
+ wake_up_var(&pd->congested);
+ }
+ spin_unlock(&pd->lock);
+
+ pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
+ pkt_set_state(pkt, PACKET_WAITING_STATE);
+ atomic_set(&pkt->run_sm, 1);
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_add(&pkt->list, &pd->cdrw.pkt_active_list);
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ return 1;
+}
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+static void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+ struct bvec_iter src_iter = src->bi_iter;
+ struct bvec_iter dst_iter = dst->bi_iter;
+
+ while (1) {
+ if (!src_iter.bi_size) {
+ src = src->bi_next;
+ if (!src)
+ break;
+
+ src_iter = src->bi_iter;
+ }
+
+ if (!dst_iter.bi_size) {
+ dst = dst->bi_next;
+ if (!dst)
+ break;
+
+ dst_iter = dst->bi_iter;
+ }
+
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+ }
+}
+
+/*
+ * Assemble a bio to write one packet and queue the bio for processing
+ * by the underlying block device.
+ */
+static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int f;
+
+ bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames,
+ REQ_OP_WRITE);
+ pkt->w_bio->bi_iter.bi_sector = pkt->sector;
+ pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
+ pkt->w_bio->bi_private = pkt;
+
+ /* XXX: locking? */
+ for (f = 0; f < pkt->frames; f++) {
+ struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
+ unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+
+ if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
+ BUG();
+ }
+ pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
+
+ /*
+ * Fill-in bvec with data from orig_bios.
+ */
+ spin_lock(&pkt->lock);
+ bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
+
+ pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
+ spin_unlock(&pkt->lock);
+
+ pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
+ pkt->write_size, (unsigned long long)pkt->sector);
+
+ if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
+ pkt->cache_valid = 1;
+ else
+ pkt->cache_valid = 0;
+
+ /* Start the write request */
+ atomic_set(&pkt->io_wait, 1);
+ pkt_queue_bio(pd, pkt->w_bio);
+}
+
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
+{
+ struct bio *bio;
+
+ if (status)
+ pkt->cache_valid = 0;
+
+ /* Finish all bios corresponding to this packet */
+ while ((bio = bio_list_pop(&pkt->orig_bios))) {
+ bio->bi_status = status;
+ bio_endio(bio);
+ }
+}
+
+static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ pkt_dbg(2, pd, "pkt %d\n", pkt->id);
+
+ for (;;) {
+ switch (pkt->state) {
+ case PACKET_WAITING_STATE:
+ if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
+ return;
+
+ pkt->sleep_time = 0;
+ pkt_gather_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_READ_WAIT_STATE);
+ break;
+
+ case PACKET_READ_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (atomic_read(&pkt->io_errors) > 0) {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ } else {
+ pkt_start_write(pd, pkt);
+ }
+ break;
+
+ case PACKET_WRITE_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (!pkt->w_bio->bi_status) {
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ } else {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ }
+ break;
+
+ case PACKET_RECOVERY_STATE:
+ pkt_dbg(2, pd, "No recovery possible\n");
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ break;
+
+ case PACKET_FINISHED_STATE:
+ pkt_finish_packet(pkt, pkt->w_bio->bi_status);
+ return;
+
+ default:
+ BUG();
+ break;
+ }
+ }
+}
+
+static void pkt_handle_packets(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ /*
+ * Run state machine for active packets
+ */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0) {
+ atomic_set(&pkt->run_sm, 0);
+ pkt_run_state_machine(pd, pkt);
+ }
+ }
+
+ /*
+ * Move no longer active packets to the free list
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->state == PACKET_FINISHED_STATE) {
+ list_del(&pkt->list);
+ pkt_put_packet_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_IDLE_STATE);
+ atomic_set(&pd->scan_queue, 1);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+static void pkt_count_states(struct pktcdvd_device *pd, int *states)
+{
+ struct packet_data *pkt;
+ int i;
+
+ for (i = 0; i < PACKET_NUM_STATES; i++)
+ states[i] = 0;
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ states[pkt->state]++;
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+/*
+ * kcdrwd is woken up when writes have been queued for one of our
+ * registered devices
+ */
+static int kcdrwd(void *foobar)
+{
+ struct pktcdvd_device *pd = foobar;
+ struct packet_data *pkt;
+ long min_sleep_time, residue;
+
+ set_user_nice(current, MIN_NICE);
+ set_freezable();
+
+ for (;;) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ /*
+ * Wait until there is something to do
+ */
+ add_wait_queue(&pd->wqueue, &wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* Check if we need to run pkt_handle_queue */
+ if (atomic_read(&pd->scan_queue) > 0)
+ goto work_to_do;
+
+ /* Check if we need to run the state machine for some packet */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0)
+ goto work_to_do;
+ }
+
+ /* Check if we need to process the iosched queues */
+ if (atomic_read(&pd->iosched.attention) != 0)
+ goto work_to_do;
+
+ /* Otherwise, go to sleep */
+ if (PACKET_DEBUG > 1) {
+ int states[PACKET_NUM_STATES];
+ pkt_count_states(pd, states);
+ pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2],
+ states[3], states[4], states[5]);
+ }
+
+ min_sleep_time = MAX_SCHEDULE_TIMEOUT;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
+ min_sleep_time = pkt->sleep_time;
+ }
+
+ pkt_dbg(2, pd, "sleeping\n");
+ residue = schedule_timeout(min_sleep_time);
+ pkt_dbg(2, pd, "wake up\n");
+
+ /* make swsusp happy with our thread */
+ try_to_freeze();
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (!pkt->sleep_time)
+ continue;
+ pkt->sleep_time -= min_sleep_time - residue;
+ if (pkt->sleep_time <= 0) {
+ pkt->sleep_time = 0;
+ atomic_inc(&pkt->run_sm);
+ }
+ }
+
+ if (kthread_should_stop())
+ break;
+ }
+work_to_do:
+ set_current_state(TASK_RUNNING);
+ remove_wait_queue(&pd->wqueue, &wait);
+
+ if (kthread_should_stop())
+ break;
+
+ /*
+ * if pkt_handle_queue returns true, we can queue
+ * another request.
+ */
+ while (pkt_handle_queue(pd))
+ ;
+
+ /*
+ * Handle packet state machine
+ */
+ pkt_handle_packets(pd);
+
+ /*
+ * Handle iosched queues
+ */
+ pkt_iosched_process_queue(pd);
+ }
+
+ return 0;
+}
+
+static void pkt_print_settings(struct pktcdvd_device *pd)
+{
+ pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+ pd->settings.fp ? "Fixed" : "Variable",
+ pd->settings.size >> 2,
+ pd->settings.block_mode == 8 ? '1' : '2');
+}
+
+static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+
+ cgc->cmd[0] = GPCMD_MODE_SENSE_10;
+ cgc->cmd[2] = page_code | (page_control << 6);
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_READ;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+ memset(cgc->buffer, 0, 2);
+ cgc->cmd[0] = GPCMD_MODE_SELECT_10;
+ cgc->cmd[1] = 0x10; /* PF */
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_WRITE;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
+{
+ struct packet_command cgc;
+ int ret;
+
+ /* set up command and get the disc info */
+ init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_DISC_INFO;
+ cgc.cmd[8] = cgc.buflen = 2;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ /* not all drives have the same disc_info length, so requeue
+ * packet with the length the drive tells us it can supply
+ */
+ cgc.buflen = be16_to_cpu(di->disc_information_length) +
+ sizeof(di->disc_information_length);
+
+ if (cgc.buflen > sizeof(disc_information))
+ cgc.buflen = sizeof(disc_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
+{
+ struct packet_command cgc;
+ int ret;
+
+ init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
+ cgc.cmd[1] = type & 3;
+ cgc.cmd[4] = (track & 0xff00) >> 8;
+ cgc.cmd[5] = track & 0xff;
+ cgc.cmd[8] = 8;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ cgc.buflen = be16_to_cpu(ti->track_information_length) +
+ sizeof(ti->track_information_length);
+
+ if (cgc.buflen > sizeof(track_information))
+ cgc.buflen = sizeof(track_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
+ long *last_written)
+{
+ disc_information di;
+ track_information ti;
+ __u32 last_track;
+ int ret;
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret)
+ return ret;
+
+ last_track = (di.last_track_msb << 8) | di.last_track_lsb;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+
+ /* if this track is blank, try the previous. */
+ if (ti.blank) {
+ last_track--;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+ }
+
+ /* if last recorded field is valid, return it. */
+ if (ti.lra_v) {
+ *last_written = be32_to_cpu(ti.last_rec_address);
+ } else {
+ /* make it up instead */
+ *last_written = be32_to_cpu(ti.track_start) +
+ be32_to_cpu(ti.track_size);
+ if (ti.free_blocks)
+ *last_written -= (be32_to_cpu(ti.free_blocks) + 7);
+ }
+ return 0;
+}
+
+/*
+ * write mode select package based on pd->settings
+ */
+static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ write_param_page *wp;
+ char buffer[128];
+ int ret, size;
+
+ /* doesn't apply to DVD+RW or DVD-RAM */
+ if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
+ return 0;
+
+ memset(buffer, 0, sizeof(buffer));
+ init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff));
+ pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff);
+ if (size > sizeof(buffer))
+ size = sizeof(buffer);
+
+ /*
+ * now get it all
+ */
+ init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ /*
+ * write page is offset header + block descriptor length
+ */
+ wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];
+
+ wp->fp = pd->settings.fp;
+ wp->track_mode = pd->settings.track_mode;
+ wp->write_type = pd->settings.write_type;
+ wp->data_block_type = pd->settings.block_mode;
+
+ wp->multi_session = 0;
+
+#ifdef PACKET_USE_LS
+ wp->link_size = 7;
+ wp->ls_v = 1;
+#endif
+
+ if (wp->data_block_type == PACKET_BLOCK_MODE1) {
+ wp->session_format = 0;
+ wp->subhdr2 = 0x20;
+ } else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
+ wp->session_format = 0x20;
+ wp->subhdr2 = 8;
+#if 0
+ wp->mcn[0] = 0x80;
+ memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
+#endif
+ } else {
+ /*
+ * paranoia
+ */
+ pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
+ return 1;
+ }
+ wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
+
+ cgc.buflen = cgc.cmd[8] = size;
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ pkt_print_settings(pd);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this track, 0 -- we can't
+ */
+static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
+{
+ switch (pd->mmc3_profile) {
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ /* The track is always writable on DVD+RW/DVD-RAM */
+ return 1;
+ default:
+ break;
+ }
+
+ if (!ti->packet || !ti->fp)
+ return 0;
+
+ /*
+ * "good" settings as per Mt Fuji.
+ */
+ if (ti->rt == 0 && ti->blank == 0)
+ return 1;
+
+ if (ti->rt == 0 && ti->blank == 1)
+ return 1;
+
+ if (ti->rt == 1 && ti->blank == 0)
+ return 1;
+
+ pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this disc, 0 -- we can't
+ */
+static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
+{
+ switch (pd->mmc3_profile) {
+ case 0x0a: /* CD-RW */
+ case 0xffff: /* MMC3 not supported */
+ break;
+ case 0x1a: /* DVD+RW */
+ case 0x13: /* DVD-RW */
+ case 0x12: /* DVD-RAM */
+ return 1;
+ default:
+ pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+ pd->mmc3_profile);
+ return 0;
+ }
+
+ /*
+ * for disc type 0xff we should probably reserve a new track.
+ * but i'm not sure, should we leave this to user apps? probably.
+ */
+ if (di->disc_type == 0xff) {
+ pkt_notice(pd, "unknown disc - no track?\n");
+ return 0;
+ }
+
+ if (di->disc_type != 0x20 && di->disc_type != 0) {
+ pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
+ return 0;
+ }
+
+ if (di->erasable == 0) {
+ pkt_notice(pd, "disc not erasable\n");
+ return 0;
+ }
+
+ if (di->border_status == PACKET_SESSION_RESERVED) {
+ pkt_err(pd, "can't write to last track (reserved)\n");
+ return 0;
+ }
+
+ return 1;
+}
+
+static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ unsigned char buf[12];
+ disc_information di;
+ track_information ti;
+ int ret, track;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
+ cgc.cmd[8] = 8;
+ ret = pkt_generic_packet(pd, &cgc);
+ pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7];
+
+ memset(&di, 0, sizeof(disc_information));
+ memset(&ti, 0, sizeof(track_information));
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret) {
+ pkt_err(pd, "failed get_disc\n");
+ return ret;
+ }
+
+ if (!pkt_writable_disc(pd, &di))
+ return -EROFS;
+
+ pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
+
+ track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
+ ret = pkt_get_track_info(pd, track, 1, &ti);
+ if (ret) {
+ pkt_err(pd, "failed get_track\n");
+ return ret;
+ }
+
+ if (!pkt_writable_track(pd, &ti)) {
+ pkt_err(pd, "can't write to this track\n");
+ return -EROFS;
+ }
+
+ /*
+ * we keep packet size in 512 byte units, makes it easier to
+ * deal with request calculations.
+ */
+ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
+ if (pd->settings.size == 0) {
+ pkt_notice(pd, "detected zero packet size!\n");
+ return -ENXIO;
+ }
+ if (pd->settings.size > PACKET_MAX_SECTORS) {
+ pkt_err(pd, "packet size is too big\n");
+ return -EROFS;
+ }
+ pd->settings.fp = ti.fp;
+ pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);
+
+ if (ti.nwa_v) {
+ pd->nwa = be32_to_cpu(ti.next_writable);
+ set_bit(PACKET_NWA_VALID, &pd->flags);
+ }
+
+ /*
+ * in theory we could use lra on -RW media as well and just zero
+ * blocks that haven't been written yet, but in practice that
+ * is just a no-go. we'll use that for -R, naturally.
+ */
+ if (ti.lra_v) {
+ pd->lra = be32_to_cpu(ti.last_rec_address);
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ } else {
+ pd->lra = 0xffffffff;
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ }
+
+ /*
+ * fine for now
+ */
+ pd->settings.link_loss = 7;
+ pd->settings.write_type = 0; /* packet */
+ pd->settings.track_mode = ti.track_mode;
+
+ /*
+ * mode1 or mode2 disc
+ */
+ switch (ti.data_mode) {
+ case PACKET_MODE1:
+ pd->settings.block_mode = PACKET_BLOCK_MODE1;
+ break;
+ case PACKET_MODE2:
+ pd->settings.block_mode = PACKET_BLOCK_MODE2;
+ break;
+ default:
+ pkt_err(pd, "unknown data mode\n");
+ return -EROFS;
+ }
+ return 0;
+}
+
+/*
+ * enable/disable write caching on drive
+ */
+static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
+ int set)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ int ret;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.buflen = pd->mode_offset + 12;
+
+ /*
+ * caching mode page might not be there, so quiet this command
+ */
+ cgc.quiet = 1;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+ if (ret)
+ return ret;
+
+ buf[pd->mode_offset + 10] |= (!!set << 2);
+
+ cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_err(pd, "write caching control failed\n");
+ pkt_dump_sense(pd, &cgc);
+ } else if (!ret && set)
+ pkt_notice(pd, "enabled write caching\n");
+ return ret;
+}
+
+static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
+ cgc.cmd[4] = lockflag ? 1 : 0;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * Returns drive maximum write speed
+ */
+static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
+ unsigned *write_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[256+18];
+ unsigned char *cap_buf;
+ int ret, offset;
+
+ cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
+ cgc.sshdr = &sshdr;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
+ sizeof(struct mode_page_header);
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ }
+
+ offset = 20; /* Obsoleted field, used by older drives */
+ if (cap_buf[1] >= 28)
+ offset = 28; /* Current write speed selected */
+ if (cap_buf[1] >= 30) {
+ /* If the drive reports at least one "Logical Unit Write
+ * Speed Performance Descriptor Block", use the information
+ * in the first block. (contains the highest speed)
+ */
+ int num_spdb = (cap_buf[30] << 8) + cap_buf[31];
+ if (num_spdb > 0)
+ offset = 34;
+ }
+
+ *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1];
+ return 0;
+}
+
+/* These tables from cdrecord - I don't have orange book */
+/* standard speed CD-RW (1-4x) */
+static char clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* high speed CD-RW (-10x) */
+static char hs_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* ultra high speed CD-RW */
+static char us_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
+};
+
+/*
+ * reads the maximum media speed from ATIP
+ */
+static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
+ unsigned *speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ unsigned int size, st, sp;
+ int ret;
+
+ init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4; /* READ ATIP */
+ cgc.cmd[8] = 2;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+
+ init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4;
+ cgc.cmd[8] = size;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ if (!(buf[6] & 0x40)) {
+ pkt_notice(pd, "disc type is not CD-RW\n");
+ return 1;
+ }
+ if (!(buf[6] & 0x4)) {
+ pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
+ return 1;
+ }
+
+ st = (buf[6] >> 3) & 0x7; /* disc sub-type */
+
+ sp = buf[16] & 0xf; /* max speed from ATIP A1 field */
+
+ /* Info from cdrecord */
+ switch (st) {
+ case 0: /* standard speed */
+ *speed = clv_to_speed[sp];
+ break;
+ case 1: /* high speed */
+ *speed = hs_clv_to_speed[sp];
+ break;
+ case 2: /* ultra high speed */
+ *speed = us_clv_to_speed[sp];
+ break;
+ default:
+ pkt_notice(pd, "unknown disc sub-type %d\n", st);
+ return 1;
+ }
+ if (*speed) {
+ pkt_info(pd, "maximum media speed: %d\n", *speed);
+ return 0;
+ } else {
+ pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
+ return 1;
+ }
+}
+
+static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ pkt_dbg(2, pd, "Performing OPC\n");
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.timeout = 60*HZ;
+ cgc.cmd[0] = GPCMD_SEND_OPC;
+ cgc.cmd[1] = 1;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+}
+
+static int pkt_open_write(struct pktcdvd_device *pd)
+{
+ int ret;
+ unsigned int write_speed, media_write_speed, read_speed;
+
+ ret = pkt_probe_settings(pd);
+ if (ret) {
+ pkt_dbg(2, pd, "failed probe\n");
+ return ret;
+ }
+
+ ret = pkt_set_write_settings(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "failed saving write settings\n");
+ return -EIO;
+ }
+
+ pkt_write_caching(pd, USE_WCACHING);
+
+ ret = pkt_get_max_speed(pd, &write_speed);
+ if (ret)
+ write_speed = 16 * 177;
+ switch (pd->mmc3_profile) {
+ case 0x13: /* DVD-RW */
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
+ break;
+ default:
+ ret = pkt_media_speed(pd, &media_write_speed);
+ if (ret)
+ media_write_speed = 16;
+ write_speed = min(write_speed, media_write_speed * 177);
+ pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
+ break;
+ }
+ read_speed = write_speed;
+
+ ret = pkt_set_speed(pd, write_speed, read_speed);
+ if (ret) {
+ pkt_dbg(1, pd, "couldn't set write speed\n");
+ return -EIO;
+ }
+ pd->write_speed = write_speed;
+ pd->read_speed = read_speed;
+
+ ret = pkt_perform_opc(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
+ }
+
+ return 0;
+}
+
+/*
+ * called at open time.
+ */
+static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
+{
+ int ret;
+ long lba;
+ struct request_queue *q;
+ struct block_device *bdev;
+
+ /*
+ * We need to re-open the cdrom device without O_NONBLOCK to be able
+ * to read/write from/to it. It is already opened in O_NONBLOCK mode
+ * so open should not fail.
+ */
+ bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd);
+ if (IS_ERR(bdev)) {
+ ret = PTR_ERR(bdev);
+ goto out;
+ }
+
+ ret = pkt_get_last_written(pd, &lba);
+ if (ret) {
+ pkt_err(pd, "pkt_get_last_written failed\n");
+ goto out_putdev;
+ }
+
+ set_capacity(pd->disk, lba << 2);
+ set_capacity_and_notify(pd->bdev->bd_disk, lba << 2);
+
+ q = bdev_get_queue(pd->bdev);
+ if (write) {
+ ret = pkt_open_write(pd);
+ if (ret)
+ goto out_putdev;
+ /*
+ * Some CDRW drives can not handle writes larger than one packet,
+ * even if the size is a multiple of the packet size.
+ */
+ blk_queue_max_hw_sectors(q, pd->settings.size);
+ set_bit(PACKET_WRITABLE, &pd->flags);
+ } else {
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ clear_bit(PACKET_WRITABLE, &pd->flags);
+ }
+
+ ret = pkt_set_segment_merging(pd, q);
+ if (ret)
+ goto out_putdev;
+
+ if (write) {
+ if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
+ pkt_err(pd, "not enough memory for buffers\n");
+ ret = -ENOMEM;
+ goto out_putdev;
+ }
+ pkt_info(pd, "%lukB available on disc\n", lba << 1);
+ }
+
+ return 0;
+
+out_putdev:
+ blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
+out:
+ return ret;
+}
+
+/*
+ * called when the device is closed. makes sure that the device flushes
+ * the internal cache before we close.
+ */
+static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
+{
+ if (flush && pkt_flush_cache(pd))
+ pkt_dbg(1, pd, "not flushing cache\n");
+
+ pkt_lock_door(pd, 0);
+
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
+
+ pkt_shrink_pktlist(pd);
+}
+
+static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
+{
+ if (dev_minor >= MAX_WRITERS)
+ return NULL;
+
+ dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
+ return pkt_devs[dev_minor];
+}
+
+static int pkt_open(struct block_device *bdev, fmode_t mode)
+{
+ struct pktcdvd_device *pd = NULL;
+ int ret;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
+ if (!pd) {
+ ret = -ENODEV;
+ goto out;
+ }
+ BUG_ON(pd->refcnt < 0);
+
+ pd->refcnt++;
+ if (pd->refcnt > 1) {
+ if ((mode & FMODE_WRITE) &&
+ !test_bit(PACKET_WRITABLE, &pd->flags)) {
+ ret = -EBUSY;
+ goto out_dec;
+ }
+ } else {
+ ret = pkt_open_dev(pd, mode & FMODE_WRITE);
+ if (ret)
+ goto out_dec;
+ /*
+ * needed here as well, since ext2 (among others) may change
+ * the blocksize at mount time
+ */
+ set_blocksize(bdev, CD_FRAMESIZE);
+ }
+
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return 0;
+
+out_dec:
+ pd->refcnt--;
+out:
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return ret;
+}
+
+static void pkt_close(struct gendisk *disk, fmode_t mode)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd->refcnt--;
+ BUG_ON(pd->refcnt < 0);
+ if (pd->refcnt == 0) {
+ int flush = test_bit(PACKET_WRITABLE, &pd->flags);
+ pkt_release_dev(pd, flush);
+ }
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+}
+
+
+static void pkt_end_io_read_cloned(struct bio *bio)
+{
+ struct packet_stacked_data *psd = bio->bi_private;
+ struct pktcdvd_device *pd = psd->pd;
+
+ psd->bio->bi_status = bio->bi_status;
+ bio_put(bio);
+ bio_endio(psd->bio);
+ mempool_free(psd, &psd_pool);
+ pkt_bio_finished(pd);
+}
+
+static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
+{
+ struct bio *cloned_bio =
+ bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set);
+ struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
+
+ psd->pd = pd;
+ psd->bio = bio;
+ cloned_bio->bi_private = psd;
+ cloned_bio->bi_end_io = pkt_end_io_read_cloned;
+ pd->stats.secs_r += bio_sectors(bio);
+ pkt_queue_bio(pd, cloned_bio);
+}
+
+static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+{
+ struct pktcdvd_device *pd = q->queuedata;
+ sector_t zone;
+ struct packet_data *pkt;
+ int was_empty, blocked_bio;
+ struct pkt_rb_node *node;
+
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+
+ /*
+ * If we find a matching packet in state WAITING or READ_WAIT, we can
+ * just append this bio to that packet.
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ blocked_bio = 0;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sector == zone) {
+ spin_lock(&pkt->lock);
+ if ((pkt->state == PACKET_WAITING_STATE) ||
+ (pkt->state == PACKET_READ_WAIT_STATE)) {
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size +=
+ bio->bi_iter.bi_size / CD_FRAMESIZE;
+ if ((pkt->write_size >= pkt->frames) &&
+ (pkt->state == PACKET_WAITING_STATE)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ spin_unlock(&pkt->lock);
+ spin_unlock(&pd->cdrw.active_list_lock);
+ return;
+ } else {
+ blocked_bio = 1;
+ }
+ spin_unlock(&pkt->lock);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ /*
+ * Test if there is enough room left in the bio work queue
+ * (queue size >= congestion on mark).
+ * If not, wait till the work queue size is below the congestion off mark.
+ */
+ spin_lock(&pd->lock);
+ if (pd->write_congestion_on > 0
+ && pd->bio_queue_size >= pd->write_congestion_on) {
+ struct wait_bit_queue_entry wqe;
+
+ init_wait_var_entry(&wqe, &pd->congested, 0);
+ for (;;) {
+ prepare_to_wait_event(__var_waitqueue(&pd->congested),
+ &wqe.wq_entry,
+ TASK_UNINTERRUPTIBLE);
+ if (pd->bio_queue_size <= pd->write_congestion_off)
+ break;
+ pd->congested = true;
+ spin_unlock(&pd->lock);
+ schedule();
+ spin_lock(&pd->lock);
+ }
+ }
+ spin_unlock(&pd->lock);
+
+ /*
+ * No matching packet found. Store the bio in the work queue.
+ */
+ node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
+ node->bio = bio;
+ spin_lock(&pd->lock);
+ BUG_ON(pd->bio_queue_size < 0);
+ was_empty = (pd->bio_queue_size == 0);
+ pkt_rbtree_insert(pd, node);
+ spin_unlock(&pd->lock);
+
+ /*
+ * Wake up the worker thread.
+ */
+ atomic_set(&pd->scan_queue, 1);
+ if (was_empty) {
+ /* This wake_up is required for correct operation */
+ wake_up(&pd->wqueue);
+ } else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
+ /*
+ * This wake up is not required for correct operation,
+ * but improves performance in some cases.
+ */
+ wake_up(&pd->wqueue);
+ }
+}
+
+static void pkt_submit_bio(struct bio *bio)
+{
+ struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+ struct bio *split;
+
+ bio = bio_split_to_limits(bio);
+
+ pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ (unsigned long long)bio_end_sector(bio));
+
+ /*
+ * Clone READ bios so we can have our own bi_end_io callback.
+ */
+ if (bio_data_dir(bio) == READ) {
+ pkt_make_request_read(pd, bio);
+ return;
+ }
+
+ if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
+ pkt_notice(pd, "WRITE for ro device (%llu)\n",
+ (unsigned long long)bio->bi_iter.bi_sector);
+ goto end_io;
+ }
+
+ if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
+ pkt_err(pd, "wrong bio size\n");
+ goto end_io;
+ }
+
+ do {
+ sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
+ sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
+
+ if (last_zone != zone) {
+ BUG_ON(last_zone != zone + pd->settings.size);
+
+ split = bio_split(bio, last_zone -
+ bio->bi_iter.bi_sector,
+ GFP_NOIO, &pkt_bio_set);
+ bio_chain(split, bio);
+ } else {
+ split = bio;
+ }
+
+ pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+ } while (split != bio);
+
+ return;
+end_io:
+ bio_io_error(bio);
+}
+
+static void pkt_init_queue(struct pktcdvd_device *pd)
+{
+ struct request_queue *q = pd->disk->queue;
+
+ blk_queue_logical_block_size(q, CD_FRAMESIZE);
+ blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
+ q->queuedata = pd;
+}
+
+static int pkt_seq_show(struct seq_file *m, void *p)
+{
+ struct pktcdvd_device *pd = m->private;
+ char *msg;
+ int states[PACKET_NUM_STATES];
+
+ seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev);
+
+ seq_printf(m, "\nSettings:\n");
+ seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
+
+ if (pd->settings.write_type == 0)
+ msg = "Packet";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\twrite type:\t\t%s\n", msg);
+
+ seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
+ seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);
+
+ seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);
+
+ if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
+ msg = "Mode 1";
+ else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
+ msg = "Mode 2";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\tblock mode:\t\t%s\n", msg);
+
+ seq_printf(m, "\nStatistics:\n");
+ seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
+ seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
+ seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
+ seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
+ seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);
+
+ seq_printf(m, "\nMisc:\n");
+ seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
+ seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
+ seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
+ seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
+ seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
+ seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);
+
+ seq_printf(m, "\nQueue state:\n");
+ seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
+ seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
+ seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector);
+
+ pkt_count_states(pd, states);
+ seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2], states[3], states[4], states[5]);
+
+ seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
+ pd->write_congestion_off,
+ pd->write_congestion_on);
+ return 0;
+}
+
+static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
+{
+ int i;
+ struct block_device *bdev;
+ struct scsi_device *sdev;
+
+ if (pd->pkt_dev == dev) {
+ pkt_err(pd, "recursive setup not allowed\n");
+ return -EBUSY;
+ }
+ for (i = 0; i < MAX_WRITERS; i++) {
+ struct pktcdvd_device *pd2 = pkt_devs[i];
+ if (!pd2)
+ continue;
+ if (pd2->bdev->bd_dev == dev) {
+ pkt_err(pd, "%pg already setup\n", pd2->bdev);
+ return -EBUSY;
+ }
+ if (pd2->pkt_dev == dev) {
+ pkt_err(pd, "can't chain pktcdvd devices\n");
+ return -EBUSY;
+ }
+ }
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
+ if (IS_ERR(bdev))
+ return PTR_ERR(bdev);
+ sdev = scsi_device_from_queue(bdev->bd_disk->queue);
+ if (!sdev) {
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ return -EINVAL;
+ }
+ put_device(&sdev->sdev_gendev);
+
+ /* This is safe, since we have a reference from open(). */
+ __module_get(THIS_MODULE);
+
+ pd->bdev = bdev;
+ set_blocksize(bdev, CD_FRAMESIZE);
+
+ pkt_init_queue(pd);
+
+ atomic_set(&pd->cdrw.pending_bios, 0);
+ pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
+ if (IS_ERR(pd->cdrw.thread)) {
+ pkt_err(pd, "can't start kernel thread\n");
+ goto out_mem;
+ }
+
+ proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
+ pkt_dbg(1, pd, "writer mapped to %pg\n", bdev);
+ return 0;
+
+out_mem:
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+ return -ENOMEM;
+}
+
+static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
+{
+ struct pktcdvd_device *pd = bdev->bd_disk->private_data;
+ int ret;
+
+ pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+ cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+
+ mutex_lock(&pktcdvd_mutex);
+ switch (cmd) {
+ case CDROMEJECT:
+ /*
+ * The door gets locked when the device is opened, so we
+ * have to unlock it or else the eject command fails.
+ */
+ if (pd->refcnt == 1)
+ pkt_lock_door(pd, 0);
+ fallthrough;
+ /*
+ * forward selected CDROM ioctls to CD-ROM, for UDF
+ */
+ case CDROMMULTISESSION:
+ case CDROMREADTOCENTRY:
+ case CDROM_LAST_WRITTEN:
+ case CDROM_SEND_PACKET:
+ case SCSI_IOCTL_SEND_COMMAND:
+ if (!bdev->bd_disk->fops->ioctl)
+ ret = -ENOTTY;
+ else
+ ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
+ break;
+ default:
+ pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
+ ret = -ENOTTY;
+ }
+ mutex_unlock(&pktcdvd_mutex);
+
+ return ret;
+}
+
+static unsigned int pkt_check_events(struct gendisk *disk,
+ unsigned int clearing)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+ struct gendisk *attached_disk;
+
+ if (!pd)
+ return 0;
+ if (!pd->bdev)
+ return 0;
+ attached_disk = pd->bdev->bd_disk;
+ if (!attached_disk || !attached_disk->fops->check_events)
+ return 0;
+ return attached_disk->fops->check_events(attached_disk, clearing);
+}
+
+static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
+{
+ return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
+}
+
+static const struct block_device_operations pktcdvd_ops = {
+ .owner = THIS_MODULE,
+ .submit_bio = pkt_submit_bio,
+ .open = pkt_open,
+ .release = pkt_close,
+ .ioctl = pkt_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
+ .check_events = pkt_check_events,
+ .devnode = pkt_devnode,
+};
+
+/*
+ * Set up mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
+{
+ int idx;
+ int ret = -ENOMEM;
+ struct pktcdvd_device *pd;
+ struct gendisk *disk;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++)
+ if (!pkt_devs[idx])
+ break;
+ if (idx == MAX_WRITERS) {
+ pr_err("max %d writers supported\n", MAX_WRITERS);
+ ret = -EBUSY;
+ goto out_mutex;
+ }
+
+ pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
+ if (!pd)
+ goto out_mutex;
+
+ ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+ sizeof(struct pkt_rb_node));
+ if (ret)
+ goto out_mem;
+
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+ INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
+ spin_lock_init(&pd->cdrw.active_list_lock);
+
+ spin_lock_init(&pd->lock);
+ spin_lock_init(&pd->iosched.lock);
+ bio_list_init(&pd->iosched.read_queue);
+ bio_list_init(&pd->iosched.write_queue);
+ sprintf(pd->name, DRIVER_NAME"%d", idx);
+ init_waitqueue_head(&pd->wqueue);
+ pd->bio_queue = RB_ROOT;
+
+ pd->write_congestion_on = write_congestion_on;
+ pd->write_congestion_off = write_congestion_off;
+
+ ret = -ENOMEM;
+ disk = blk_alloc_disk(NUMA_NO_NODE);
+ if (!disk)
+ goto out_mem;
+ pd->disk = disk;
+ disk->major = pktdev_major;
+ disk->first_minor = idx;
+ disk->minors = 1;
+ disk->fops = &pktcdvd_ops;
+ disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
+ strcpy(disk->disk_name, pd->name);
+ disk->private_data = pd;
+
+ pd->pkt_dev = MKDEV(pktdev_major, idx);
+ ret = pkt_new_dev(pd, dev);
+ if (ret)
+ goto out_mem2;
+
+ /* inherit events of the host device */
+ disk->events = pd->bdev->bd_disk->events;
+
+ ret = add_disk(disk);
+ if (ret)
+ goto out_mem2;
+
+ pkt_sysfs_dev_new(pd);
+ pkt_debugfs_dev_new(pd);
+
+ pkt_devs[idx] = pd;
+ if (pkt_dev)
+ *pkt_dev = pd->pkt_dev;
+
+ mutex_unlock(&ctl_mutex);
+ return 0;
+
+out_mem2:
+ put_disk(disk);
+out_mem:
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+out_mutex:
+ mutex_unlock(&ctl_mutex);
+ pr_err("setup of pktcdvd device failed\n");
+ return ret;
+}
+
+/*
+ * Tear down mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_remove_dev(dev_t pkt_dev)
+{
+ struct pktcdvd_device *pd;
+ int idx;
+ int ret = 0;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ pd = pkt_devs[idx];
+ if (pd && (pd->pkt_dev == pkt_dev))
+ break;
+ }
+ if (idx == MAX_WRITERS) {
+ pr_debug("dev not setup\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (pd->refcnt > 0) {
+ ret = -EBUSY;
+ goto out;
+ }
+ if (!IS_ERR(pd->cdrw.thread))
+ kthread_stop(pd->cdrw.thread);
+
+ pkt_devs[idx] = NULL;
+
+ pkt_debugfs_dev_remove(pd);
+ pkt_sysfs_dev_remove(pd);
+
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
+
+ remove_proc_entry(pd->name, pkt_proc);
+ pkt_dbg(1, pd, "writer unmapped\n");
+
+ del_gendisk(pd->disk);
+ put_disk(pd->disk);
+
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+
+out:
+ mutex_unlock(&ctl_mutex);
+ return ret;
+}
+
+static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
+{
+ struct pktcdvd_device *pd;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
+ if (pd) {
+ ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev);
+ ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
+ } else {
+ ctrl_cmd->dev = 0;
+ ctrl_cmd->pkt_dev = 0;
+ }
+ ctrl_cmd->num_devices = MAX_WRITERS;
+
+ mutex_unlock(&ctl_mutex);
+}
+
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct pkt_ctrl_command ctrl_cmd;
+ int ret = 0;
+ dev_t pkt_dev = 0;
+
+ if (cmd != PACKET_CTRL_CMD)
+ return -ENOTTY;
+
+ if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+
+ switch (ctrl_cmd.command) {
+ case PKT_CTRL_CMD_SETUP:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
+ ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+ break;
+ case PKT_CTRL_CMD_TEARDOWN:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+ break;
+ case PKT_CTRL_CMD_STATUS:
+ pkt_get_status(&ctrl_cmd);
+ break;
+ default:
+ return -ENOTTY;
+ }
+
+ if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+ return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations pkt_ctl_fops = {
+ .open = nonseekable_open,
+ .unlocked_ioctl = pkt_ctl_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pkt_ctl_compat_ioctl,
+#endif
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+};
+
+static struct miscdevice pkt_misc = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = DRIVER_NAME,
+ .nodename = "pktcdvd/control",
+ .fops = &pkt_ctl_fops
+};
+
+static int __init pkt_init(void)
+{
+ int ret;
+
+ mutex_init(&ctl_mutex);
+
+ ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+ sizeof(struct packet_stacked_data));
+ if (ret)
+ return ret;
+ ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret) {
+ mempool_exit(&psd_pool);
+ return ret;
+ }
+
+ ret = register_blkdev(pktdev_major, DRIVER_NAME);
+ if (ret < 0) {
+ pr_err("unable to register block device\n");
+ goto out2;
+ }
+ if (!pktdev_major)
+ pktdev_major = ret;
+
+ ret = pkt_sysfs_init();
+ if (ret)
+ goto out;
+
+ pkt_debugfs_init();
+
+ ret = misc_register(&pkt_misc);
+ if (ret) {
+ pr_err("unable to register misc device\n");
+ goto out_misc;
+ }
+
+ pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
+
+ return 0;
+
+out_misc:
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+out:
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+out2:
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+ return ret;
+}
+
+static void __exit pkt_exit(void)
+{
+ remove_proc_entry("driver/"DRIVER_NAME, NULL);
+ misc_deregister(&pkt_misc);
+
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+}
+
+MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
+MODULE_AUTHOR("Jens Axboe <axboe@suse.de>");
+MODULE_LICENSE("GPL");
+
+module_init(pkt_init);
+module_exit(pkt_exit);
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
new file mode 100644
index 0000000000000..f9c5ac80d59b3
--- /dev/null
+++ b/include/linux/pktcdvd.h
@@ -0,0 +1,197 @@
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef __PKTCDVD_H
+#define __PKTCDVD_H
+
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/mempool.h>
+#include <uapi/linux/pktcdvd.h>
+
+/* default bio write queue congestion marks */
+#define PKT_WRITE_CONGESTION_ON 10000
+#define PKT_WRITE_CONGESTION_OFF 9000
+
+
+struct packet_settings
+{
+ __u32 size; /* packet size in (512 byte) sectors */
+ __u8 fp; /* fixed packets */
+ __u8 link_loss; /* the rest is specified
+ * as per Mt Fuji */
+ __u8 write_type;
+ __u8 track_mode;
+ __u8 block_mode;
+};
+
+/*
+ * Very crude stats for now
+ */
+struct packet_stats
+{
+ unsigned long pkt_started;
+ unsigned long pkt_ended;
+ unsigned long secs_w;
+ unsigned long secs_rg;
+ unsigned long secs_r;
+};
+
+struct packet_cdrw
+{
+ struct list_head pkt_free_list;
+ struct list_head pkt_active_list;
+ spinlock_t active_list_lock; /* Serialize access to pkt_active_list */
+ struct task_struct *thread;
+ atomic_t pending_bios;
+};
+
+/*
+ * Switch to high speed reading after reading this many kilobytes
+ * with no interspersed writes.
+ */
+#define HI_SPEED_SWITCH 512
+
+struct packet_iosched
+{
+ atomic_t attention; /* Set to non-zero when queue processing is needed */
+ int writing; /* Non-zero when writing, zero when reading */
+ spinlock_t lock; /* Protecting read/write queue manipulations */
+ struct bio_list read_queue;
+ struct bio_list write_queue;
+ sector_t last_write; /* The sector where the last write ended */
+ int successive_reads;
+};
+
+/*
+ * 32 buffers of 2048 bytes
+ */
+#if (PAGE_SIZE % CD_FRAMESIZE) != 0
+#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
+#endif
+#define PACKET_MAX_SIZE 128
+#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE)
+#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
+
+enum packet_data_state {
+ PACKET_IDLE_STATE, /* Not used at the moment */
+ PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */
+ /* we don't have to do as much */
+ /* data gathering */
+ PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */
+ PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */
+ PACKET_RECOVERY_STATE, /* Recover after read/write errors */
+ PACKET_FINISHED_STATE, /* After write has finished */
+
+ PACKET_NUM_STATES /* Number of possible states */
+};
+
+/*
+ * Information needed for writing a single packet
+ */
+struct pktcdvd_device;
+
+struct packet_data
+{
+ struct list_head list;
+
+ spinlock_t lock; /* Lock protecting state transitions and */
+ /* orig_bios list */
+
+ struct bio_list orig_bios; /* Original bios passed to pkt_make_request */
+ /* that will be handled by this packet */
+ int write_size; /* Total size of all bios in the orig_bios */
+ /* list, measured in number of frames */
+
+ struct bio *w_bio; /* The bio we will send to the real CD */
+ /* device once we have all data for the */
+ /* packet we are going to write */
+ sector_t sector; /* First sector in this packet */
+ int frames; /* Number of frames in this packet */
+
+ enum packet_data_state state; /* Current state */
+ atomic_t run_sm; /* Incremented whenever the state */
+ /* machine needs to be run */
+ long sleep_time; /* Set this to non-zero to make the state */
+ /* machine run after this many jiffies. */
+
+ atomic_t io_wait; /* Number of pending IO operations */
+ atomic_t io_errors; /* Number of read/write errors during IO */
+
+ struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
+ struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
+
+ int cache_valid; /* If non-zero, the data for the zone defined */
+ /* by the sector variable is completely cached */
+ /* in the pages[] vector. */
+
+ int id; /* ID number for debugging */
+ struct pktcdvd_device *pd;
+};
+
+struct pkt_rb_node {
+ struct rb_node rb_node;
+ struct bio *bio;
+};
+
+struct packet_stacked_data
+{
+ struct bio *bio; /* Original read request bio */
+ struct pktcdvd_device *pd;
+};
+#define PSD_POOL_SIZE 64
+
+struct pktcdvd_device
+{
+ struct block_device *bdev; /* dev attached */
+ dev_t pkt_dev; /* our dev */
+ char name[20];
+ struct packet_settings settings;
+ struct packet_stats stats;
+ int refcnt; /* Open count */
+ int write_speed; /* current write speed, kB/s */
+ int read_speed; /* current read speed, kB/s */
+ unsigned long offset; /* start offset */
+ __u8 mode_offset; /* 0 / 8 */
+ __u8 type;
+ unsigned long flags;
+ __u16 mmc3_profile;
+ __u32 nwa; /* next writable address */
+ __u32 lra; /* last recorded address */
+ struct packet_cdrw cdrw;
+ wait_queue_head_t wqueue;
+
+ spinlock_t lock; /* Serialize access to bio_queue */
+ struct rb_root bio_queue; /* Work queue of bios we need to handle */
+ int bio_queue_size; /* Number of nodes in bio_queue */
+ bool congested; /* Someone is waiting for bio_queue_size
+ * to drop. */
+ sector_t current_sector; /* Keep track of where the elevator is */
+ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */
+ /* needs to be run. */
+ mempool_t rb_pool; /* mempool for pkt_rb_node allocations */
+
+ struct packet_iosched iosched;
+ struct gendisk *disk;
+
+ int write_congestion_off;
+ int write_congestion_on;
+
+ struct device *dev; /* sysfs pktcdvd[0-7] dev */
+
+ struct dentry *dfs_d_root; /* debugfs: devname directory */
+ struct dentry *dfs_f_info; /* debugfs: info file */
+};
+
+#endif /* __PKTCDVD_H */
diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h
new file mode 100644
index 0000000000000..9cbb55d21c94a
--- /dev/null
+++ b/include/uapi/linux/pktcdvd.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef _UAPI__PKTCDVD_H
+#define _UAPI__PKTCDVD_H
+
+#include <linux/types.h>
+
+/*
+ * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
+ */
+#define PACKET_DEBUG 1
+
+#define MAX_WRITERS 8
+
+#define PKT_RB_POOL_SIZE 512
+
+/*
+ * How long we should hold a non-full packet before starting data gathering.
+ */
+#define PACKET_WAIT_TIME (HZ * 5 / 1000)
+
+/*
+ * use drive write caching -- we need deferred error handling to be
+ * able to successfully recover with this option (drive will return good
+ * status as soon as the cdb is validated).
+ */
+#if defined(CONFIG_CDROM_PKTCDVD_WCACHE)
+#define USE_WCACHING 1
+#else
+#define USE_WCACHING 0
+#endif
+
+/*
+ * No user-servicable parts beyond this point ->
+ */
+
+/*
+ * device types
+ */
+#define PACKET_CDR 1
+#define PACKET_CDRW 2
+#define PACKET_DVDR 3
+#define PACKET_DVDRW 4
+
+/*
+ * flags
+ */
+#define PACKET_WRITABLE 1 /* pd is writable */
+#define PACKET_NWA_VALID 2 /* next writable address valid */
+#define PACKET_LRA_VALID 3 /* last recorded address valid */
+#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */
+ /* underlying cdrom device happy */
+
+/*
+ * Disc status -- from READ_DISC_INFO
+ */
+#define PACKET_DISC_EMPTY 0
+#define PACKET_DISC_INCOMPLETE 1
+#define PACKET_DISC_COMPLETE 2
+#define PACKET_DISC_OTHER 3
+
+/*
+ * write type, and corresponding data block type
+ */
+#define PACKET_MODE1 1
+#define PACKET_MODE2 2
+#define PACKET_BLOCK_MODE1 8
+#define PACKET_BLOCK_MODE2 10
+
+/*
+ * Last session/border status
+ */
+#define PACKET_SESSION_EMPTY 0
+#define PACKET_SESSION_INCOMPLETE 1
+#define PACKET_SESSION_RESERVED 2
+#define PACKET_SESSION_COMPLETE 3
+
+#define PACKET_MCN "4a656e734178626f65323030300000"
+
+#undef PACKET_USE_LS
+
+#define PKT_CTRL_CMD_SETUP 0
+#define PKT_CTRL_CMD_TEARDOWN 1
+#define PKT_CTRL_CMD_STATUS 2
+
+struct pkt_ctrl_command {
+ __u32 command; /* in: Setup, teardown, status */
+ __u32 dev_index; /* in/out: Device index */
+ __u32 dev; /* in/out: Device nr for cdrw device */
+ __u32 pkt_dev; /* in/out: Device nr for packet device */
+ __u32 num_devices; /* out: Largest device index + 1 */
+ __u32 padding; /* Not used */
+};
+
+/*
+ * packet ioctls
+ */
+#define PACKET_IOCTL_MAGIC ('X')
+#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command)
+
+
+#endif /* _UAPI__PKTCDVD_H */
--
GitLab
From 6fe6ece398f7431784847e922a2c8c385dc58a35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michel=20D=C3=A4nzer?= <mdaenzer@redhat.com>
Date: Wed, 21 Dec 2022 16:24:13 +0100
Subject: [PATCH 0371/1167] Revert "drm/amd/display: Enable Freesync Video Mode
by default"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This reverts commit de05abe6b9d0fe08f65d744f7f75a4cba4df27ad.
The bug referenced below was bisected to this commit. There has been no
activity toward fixing it in 3 months, so let's revert for now.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2162
Signed-off-by: Michel Dänzer <mdaenzer@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 27 +++++++++++++++++++
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++----
3 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 6b74df446694b..e3e2e6e3b4859 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -195,6 +195,7 @@ extern int amdgpu_emu_mode;
extern uint amdgpu_smu_memory_pool_size;
extern int amdgpu_smu_pptable_id;
extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dc_visual_confirm;
extern uint amdgpu_dm_abm_level;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b4f2d61ea0d53..1353ffd089882 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -181,6 +181,7 @@ int amdgpu_mes_kiq;
int amdgpu_noretry = -1;
int amdgpu_force_asic_type = -1;
int amdgpu_tmz = -1; /* auto */
+uint amdgpu_freesync_vid_mode;
int amdgpu_reset_method = -1; /* auto */
int amdgpu_num_kcq = -1;
int amdgpu_smartshift_bias;
@@ -879,6 +880,32 @@ module_param_named(backlight, amdgpu_backlight, bint, 0444);
MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on)");
module_param_named(tmz, amdgpu_tmz, int, 0444);
+/**
+ * DOC: freesync_video (uint)
+ * Enable the optimization to adjust front porch timing to achieve seamless
+ * mode change experience when setting a freesync supported mode for which full
+ * modeset is not needed.
+ *
+ * The Display Core will add a set of modes derived from the base FreeSync
+ * video mode into the corresponding connector's mode list based on commonly
+ * used refresh rates and VRR range of the connected display, when users enable
+ * this feature. From the userspace perspective, they can see a seamless mode
+ * change experience when the change between different refresh rates under the
+ * same resolution. Additionally, userspace applications such as Video playback
+ * can read this modeset list and change the refresh rate based on the video
+ * frame rate. Finally, the userspace can also derive an appropriate mode for a
+ * particular refresh rate based on the FreeSync Mode and add it to the
+ * connector's mode list.
+ *
+ * Note: This is an experimental feature.
+ *
+ * The default value: 0 (off).
+ */
+MODULE_PARM_DESC(
+ freesync_video,
+ "Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
+
/**
* DOC: reset_method (int)
* GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 86bc23a67d973..1b7f20a9d4aeb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5835,7 +5835,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
*/
DRM_DEBUG_DRIVER("No preferred mode found\n");
} else {
- recalculate_timing = is_freesync_video_mode(&mode, aconnector);
+ recalculate_timing = amdgpu_freesync_vid_mode &&
+ is_freesync_video_mode(&mode, aconnector);
if (recalculate_timing) {
freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
drm_mode_copy(&saved_mode, &mode);
@@ -6986,7 +6987,7 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect
struct amdgpu_dm_connector *amdgpu_dm_connector =
to_amdgpu_dm_connector(connector);
- if (!edid)
+ if (!(amdgpu_freesync_vid_mode && edid))
return;
if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
@@ -8850,7 +8851,8 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
* TODO: Refactor this function to allow this check to work
* in all conditions.
*/
- if (dm_new_crtc_state->stream &&
+ if (amdgpu_freesync_vid_mode &&
+ dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state))
goto skip_modeset;
@@ -8885,7 +8887,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
if (!dm_old_crtc_state->stream)
goto skip_modeset;
- if (dm_new_crtc_state->stream &&
+ if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state,
old_crtc_state)) {
new_crtc_state->mode_changed = false;
@@ -8897,7 +8899,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
set_freesync_fixed_config(dm_new_crtc_state);
goto skip_modeset;
- } else if (aconnector &&
+ } else if (amdgpu_freesync_vid_mode && aconnector &&
is_freesync_video_mode(&new_crtc_state->mode,
aconnector)) {
struct drm_display_mode *high_mode;
--
GitLab
From bd0ddcfc83d85bc30c868f2c3457312c7f1ccee2 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 3 Jan 2023 12:00:31 -0600
Subject: [PATCH 0372/1167] Revert "of: fdt: Honor CONFIG_CMDLINE* even without
/chosen node"
This reverts commit a7d550f82b445cf218b47a2c1a9c56e97ecb8c7a.
Some arches (PPC at least) don't call early_init_dt_scan_nodes(), so
moving the cmdline processing there breaks them.
Reported-by: Geoff Levand <geoff@infradead.org>
Cc: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Tested-by: Geoff Levand <geoff@infradead.org>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Link: https://lore.kernel.org/r/20230103-dt-cmdline-fix-v1-1-7038e88b18b6@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/fdt.c | 40 ++++++++++++++++++++--------------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 02cc4a285cb98..4f88e8bbdd279 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1175,6 +1175,26 @@ int __init early_init_dt_scan_chosen(char *cmdline)
if (p != NULL && l > 0)
strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
+ /*
+ * CONFIG_CMDLINE is meant to be a default in case nothing else
+ * managed to set the command line, unless CONFIG_CMDLINE_FORCE
+ * is set in which case we override whatever was found earlier.
+ */
+#ifdef CONFIG_CMDLINE
+#if defined(CONFIG_CMDLINE_EXTEND)
+ strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#else
+ /* No arguments from boot loader, use kernel's cmdl*/
+ if (!((char *)cmdline)[0])
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif
+#endif /* CONFIG_CMDLINE */
+
+ pr_debug("Command line is: %s\n", (char *)cmdline);
+
rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
if (rng_seed && l > 0) {
add_bootloader_randomness(rng_seed, l);
@@ -1279,26 +1299,6 @@ void __init early_init_dt_scan_nodes(void)
if (rc)
pr_warn("No chosen node found, continuing without\n");
- /*
- * CONFIG_CMDLINE is meant to be a default in case nothing else
- * managed to set the command line, unless CONFIG_CMDLINE_FORCE
- * is set in which case we override whatever was found earlier.
- */
-#ifdef CONFIG_CMDLINE
-#if defined(CONFIG_CMDLINE_EXTEND)
- strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
- strlcat(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#else
- /* No arguments from boot loader, use kernel's cmdl */
- if (!boot_command_line[0])
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif
-#endif /* CONFIG_CMDLINE */
-
- pr_debug("Command line is: %s\n", boot_command_line);
-
/* Setup memory, calling early_init_dt_add_memory_arch */
early_init_dt_scan_memory();
--
GitLab
From 064e32dc5b03114d0767893fecdaf7b5dfd8c286 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 3 Jan 2023 12:00:32 -0600
Subject: [PATCH 0373/1167] of: fdt: Honor CONFIG_CMDLINE* even without /chosen
node, take 2
I do not read a strict requirement on /chosen node in either ePAPR or in
Documentation/devicetree. Help text for CONFIG_CMDLINE and
CONFIG_CMDLINE_EXTEND doesn't make their behavior explicitly dependent on
the presence of /chosen or the presense of /chosen/bootargs.
However the early check for /chosen and bailing out in
early_init_dt_scan_chosen() skips CONFIG_CMDLINE handling which is not
really related to /chosen node or the particular method of passing cmdline
from bootloader.
This leads to counterintuitive combinations (assuming
CONFIG_CMDLINE_EXTEND=y):
a) bootargs="foo", CONFIG_CMDLINE="bar" => cmdline=="foo bar"
b) /chosen missing, CONFIG_CMDLINE="bar" => cmdline==""
c) bootargs="", CONFIG_CMDLINE="bar" => cmdline==" bar"
Rework early_init_dt_scan_chosen() so that the cmdline config options are
always handled.
[commit msg written by Alexander Sverdlin]
Cc: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Tested-by: Geoff Levand <geoff@infradead.org>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Link: https://lore.kernel.org/r/20230103-dt-cmdline-fix-v1-2-7038e88b18b6@kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
drivers/of/fdt.c | 28 +++++++++++++++-------------
1 file changed, 15 insertions(+), 13 deletions(-)
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 4f88e8bbdd279..f08b25195ae79 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1163,18 +1163,32 @@ int __init early_init_dt_scan_chosen(char *cmdline)
if (node < 0)
node = fdt_path_offset(fdt, "/chosen@0");
if (node < 0)
- return -ENOENT;
+ /* Handle the cmdline config options even if no /chosen node */
+ goto handle_cmdline;
chosen_node_offset = node;
early_init_dt_check_for_initrd(node);
early_init_dt_check_for_elfcorehdr(node);
+ rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
+ if (rng_seed && l > 0) {
+ add_bootloader_randomness(rng_seed, l);
+
+ /* try to clear seed so it won't be found. */
+ fdt_nop_property(initial_boot_params, node, "rng-seed");
+
+ /* update CRC check value */
+ of_fdt_crc32 = crc32_be(~0, initial_boot_params,
+ fdt_totalsize(initial_boot_params));
+ }
+
/* Retrieve command line */
p = of_get_flat_dt_prop(node, "bootargs", &l);
if (p != NULL && l > 0)
strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
+handle_cmdline:
/*
* CONFIG_CMDLINE is meant to be a default in case nothing else
* managed to set the command line, unless CONFIG_CMDLINE_FORCE
@@ -1195,18 +1209,6 @@ int __init early_init_dt_scan_chosen(char *cmdline)
pr_debug("Command line is: %s\n", (char *)cmdline);
- rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
- if (rng_seed && l > 0) {
- add_bootloader_randomness(rng_seed, l);
-
- /* try to clear seed so it won't be found. */
- fdt_nop_property(initial_boot_params, node, "rng-seed");
-
- /* update CRC check value */
- of_fdt_crc32 = crc32_be(~0, initial_boot_params,
- fdt_totalsize(initial_boot_params));
- }
-
return 0;
}
--
GitLab
From 5401c3e0992860b11fb4b25796e4c4f1921740df Mon Sep 17 00:00:00 2001
From: Caleb Sander <csander@purestorage.com>
Date: Tue, 3 Jan 2023 16:30:21 -0700
Subject: [PATCH 0374/1167] qed: allow sleep in qed_mcp_trace_dump()
By default, qed_mcp_cmd_and_union() delays 10us at a time in a loop
that can run 500K times, so calls to qed_mcp_nvm_rd_cmd()
may block the current thread for over 5s.
We observed thread scheduling delays over 700ms in production,
with stacktraces pointing to this code as the culprit.
qed_mcp_trace_dump() is called from ethtool, so sleeping is permitted.
It already can sleep in qed_mcp_halt(), which calls qed_mcp_cmd().
Add a "can sleep" parameter to qed_find_nvram_image() and
qed_nvram_read() so they can sleep during qed_mcp_trace_dump().
qed_mcp_trace_get_meta_info() and qed_mcp_trace_read_meta(),
called only by qed_mcp_trace_dump(), allow these functions to sleep.
I can't tell if the other caller (qed_grc_dump_mcp_hw_dump()) can sleep,
so keep b_can_sleep set to false when it calls these functions.
An example stacktrace from a custom warning we added to the kernel
showing a thread that has not scheduled despite long needing resched:
[ 2745.362925,17] ------------[ cut here ]------------
[ 2745.362941,17] WARNING: CPU: 23 PID: 5640 at arch/x86/kernel/irq.c:233 do_IRQ+0x15e/0x1a0()
[ 2745.362946,17] Thread not rescheduled for 744 ms after irq 99
[ 2745.362956,17] Modules linked in: ...
[ 2745.363339,17] CPU: 23 PID: 5640 Comm: lldpd Tainted: P O 4.4.182+ #202104120910+6d1da174272d.61x
[ 2745.363343,17] Hardware name: FOXCONN MercuryB/Quicksilver Controller, BIOS H11P1N09 07/08/2020
[ 2745.363346,17] 0000000000000000 ffff885ec07c3ed8 ffffffff8131eb2f ffff885ec07c3f20
[ 2745.363358,17] ffffffff81d14f64 ffff885ec07c3f10 ffffffff81072ac2 ffff88be98ed0000
[ 2745.363369,17] 0000000000000063 0000000000000174 0000000000000074 0000000000000000
[ 2745.363379,17] Call Trace:
[ 2745.363382,17] <IRQ> [<ffffffff8131eb2f>] dump_stack+0x8e/0xcf
[ 2745.363393,17] [<ffffffff81072ac2>] warn_slowpath_common+0x82/0xc0
[ 2745.363398,17] [<ffffffff81072b4c>] warn_slowpath_fmt+0x4c/0x50
[ 2745.363404,17] [<ffffffff810d5a8e>] ? rcu_irq_exit+0xae/0xc0
[ 2745.363408,17] [<ffffffff817c99fe>] do_IRQ+0x15e/0x1a0
[ 2745.363413,17] [<ffffffff817c7ac9>] common_interrupt+0x89/0x89
[ 2745.363416,17] <EOI> [<ffffffff8132aa74>] ? delay_tsc+0x24/0x50
[ 2745.363425,17] [<ffffffff8132aa04>] __udelay+0x34/0x40
[ 2745.363457,17] [<ffffffffa04d45ff>] qed_mcp_cmd_and_union+0x36f/0x7d0 [qed]
[ 2745.363473,17] [<ffffffffa04d5ced>] qed_mcp_nvm_rd_cmd+0x4d/0x90 [qed]
[ 2745.363490,17] [<ffffffffa04e1dc7>] qed_mcp_trace_dump+0x4a7/0x630 [qed]
[ 2745.363504,17] [<ffffffffa04e2556>] ? qed_fw_asserts_dump+0x1d6/0x1f0 [qed]
[ 2745.363520,17] [<ffffffffa04e4ea7>] qed_dbg_mcp_trace_get_dump_buf_size+0x37/0x80 [qed]
[ 2745.363536,17] [<ffffffffa04ea881>] qed_dbg_feature_size+0x61/0xa0 [qed]
[ 2745.363551,17] [<ffffffffa04eb427>] qed_dbg_all_data_size+0x247/0x260 [qed]
[ 2745.363560,17] [<ffffffffa0482c10>] qede_get_regs_len+0x30/0x40 [qede]
[ 2745.363566,17] [<ffffffff816c9783>] ethtool_get_drvinfo+0xe3/0x190
[ 2745.363570,17] [<ffffffff816cc152>] dev_ethtool+0x1362/0x2140
[ 2745.363575,17] [<ffffffff8109bcc6>] ? finish_task_switch+0x76/0x260
[ 2745.363580,17] [<ffffffff817c2116>] ? __schedule+0x3c6/0x9d0
[ 2745.363585,17] [<ffffffff810dbd50>] ? hrtimer_start_range_ns+0x1d0/0x370
[ 2745.363589,17] [<ffffffff816c1e5b>] ? dev_get_by_name_rcu+0x6b/0x90
[ 2745.363594,17] [<ffffffff816de6a8>] dev_ioctl+0xe8/0x710
[ 2745.363599,17] [<ffffffff816a58a8>] sock_do_ioctl+0x48/0x60
[ 2745.363603,17] [<ffffffff816a5d87>] sock_ioctl+0x1c7/0x280
[ 2745.363608,17] [<ffffffff8111f393>] ? seccomp_phase1+0x83/0x220
[ 2745.363612,17] [<ffffffff811e3503>] do_vfs_ioctl+0x2b3/0x4e0
[ 2745.363616,17] [<ffffffff811e3771>] SyS_ioctl+0x41/0x70
[ 2745.363619,17] [<ffffffff817c6ffe>] entry_SYSCALL_64_fastpath+0x1e/0x79
[ 2745.363622,17] ---[ end trace f6954aa440266421 ]---
Fixes: c965db4446291 ("qed: Add support for debug data collection")
Signed-off-by: Caleb Sander <csander@purestorage.com>
Acked-by: Alok Prasad <palok@marvell.com>
Link: https://lore.kernel.org/r/20230103233021.1457646-1-csander@purestorage.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/qlogic/qed/qed_debug.c | 28 +++++++++++++++------
1 file changed, 20 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 86ecb080b1536..cdcead614e9fa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -1832,7 +1832,8 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u32 image_type,
u32 *nvram_offset_bytes,
- u32 *nvram_size_bytes)
+ u32 *nvram_size_bytes,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_txn_size;
struct mcp_file_att file_att;
@@ -1846,7 +1847,8 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
&ret_mcp_resp,
&ret_mcp_param,
&ret_txn_size,
- (u32 *)&file_att, false);
+ (u32 *)&file_att,
+ b_can_sleep);
/* Check response */
if (nvm_result || (ret_mcp_resp & FW_MSG_CODE_MASK) !=
@@ -1873,7 +1875,9 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u32 nvram_offset_bytes,
- u32 nvram_size_bytes, u32 *ret_buf)
+ u32 nvram_size_bytes,
+ u32 *ret_buf,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_read_size, bytes_to_copy;
s32 bytes_left = nvram_size_bytes;
@@ -1899,7 +1903,7 @@ static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
&ret_mcp_resp,
&ret_mcp_param, &ret_read_size,
(u32 *)((u8 *)ret_buf + read_offset),
- false))
+ b_can_sleep))
return DBG_STATUS_NVRAM_READ_FAILED;
/* Check response */
@@ -3380,7 +3384,8 @@ static u32 qed_grc_dump_mcp_hw_dump(struct qed_hwfn *p_hwfn,
p_ptt,
NVM_TYPE_HW_DUMP_OUT,
&hw_dump_offset_bytes,
- &hw_dump_size_bytes);
+ &hw_dump_size_bytes,
+ false);
if (status != DBG_STATUS_OK)
return 0;
@@ -3397,7 +3402,9 @@ static u32 qed_grc_dump_mcp_hw_dump(struct qed_hwfn *p_hwfn,
status = qed_nvram_read(p_hwfn,
p_ptt,
hw_dump_offset_bytes,
- hw_dump_size_bytes, dump_buf + offset);
+ hw_dump_size_bytes,
+ dump_buf + offset,
+ false);
if (status != DBG_STATUS_OK) {
DP_NOTICE(p_hwfn,
"Failed to read MCP HW Dump image from NVRAM\n");
@@ -4123,7 +4130,9 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
return qed_find_nvram_image(p_hwfn,
p_ptt,
nvram_image_type,
- trace_meta_offset, trace_meta_size);
+ trace_meta_offset,
+ trace_meta_size,
+ true);
}
/* Reads the MCP Trace meta data from NVRAM into the specified buffer */
@@ -4139,7 +4148,10 @@ static enum dbg_status qed_mcp_trace_read_meta(struct qed_hwfn *p_hwfn,
/* Read meta data from NVRAM */
status = qed_nvram_read(p_hwfn,
p_ptt,
- nvram_offset_in_bytes, size_in_bytes, buf);
+ nvram_offset_in_bytes,
+ size_in_bytes,
+ buf,
+ true);
if (status != DBG_STATUS_OK)
return status;
--
GitLab
From 2c02d41d71f90a5168391b6a5f2954112ba2307c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 3 Jan 2023 12:19:17 +0100
Subject: [PATCH 0375/1167] net/ulp: prevent ULP without clone op from entering
the LISTEN status
When an ULP-enabled socket enters the LISTEN status, the listener ULP data
pointer is copied inside the child/accepted sockets by sk_clone_lock().
The relevant ULP can take care of de-duplicating the context pointer via
the clone() operation, but only MPTCP and SMC implement such op.
Other ULPs may end-up with a double-free at socket disposal time.
We can't simply clear the ULP data at clone time, as TLS replaces the
socket ops with custom ones assuming a valid TLS ULP context is
available.
Instead completely prevent clone-less ULP sockets from entering the
LISTEN status.
Fixes: 734942cc4ea6 ("tcp: ULP infrastructure")
Reported-by: slipper <slipper.alive@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://lore.kernel.org/r/4b80c3d1dbe3d0ab072f80450c202d9bc88b4b03.1672740602.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/inet_connection_sock.c | 14 ++++++++++++++
net/ipv4/tcp_ulp.c | 4 ++++
2 files changed, 18 insertions(+)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 848ffc3e0239c..d1f8375793983 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1200,12 +1200,26 @@ void inet_csk_prepare_forced_close(struct sock *sk)
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+ return -EINVAL;
+
+ return 0;
+}
+
int inet_csk_listen_start(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
int err;
+ err = inet_ulp_can_listen(sk);
+ if (unlikely(err))
+ return err;
+
reqsk_queue_alloc(&icsk->icsk_accept_queue);
sk->sk_ack_backlog = 0;
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 9ae50b1bd8444..05b6077b9f2c3 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -139,6 +139,10 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
if (sk->sk_socket)
clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+ err = -EINVAL;
+ if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
+ goto out_err;
+
err = ulp_ops->init(sk);
if (err)
goto out_err;
--
GitLab
From 1ac88557447088ccd15eb2f2520ce46d463c8e0b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 3 Jan 2023 19:27:36 +0000
Subject: [PATCH 0376/1167] inet: control sockets should not use current thread
task_frag
Because ICMP handlers run from softirq contexts,
they must not use current thread task_frag.
Previously, all sockets allocated by inet_ctl_sock_create()
would use the per-socket page fragment, with no chance of
recursion.
Fixes: 98123866fcf3 ("Treewide: Stop corrupting socket's task_frag")
Reported-by: syzbot+bebc6f1acdf4cbb79b03@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Benjamin Coddington <bcodding@redhat.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Link: https://lore.kernel.org/r/20230103192736.454149-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/af_inet.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ab4a06be489b5..6c0ec27899431 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1665,6 +1665,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
if (rc == 0) {
*sk = sock->sk;
(*sk)->sk_allocation = GFP_ATOMIC;
+ (*sk)->sk_use_task_frag = false;
/*
* Unhash it so that IP input processing does not even see it,
* we do not wish this socket to see incoming packets.
--
GitLab
From 7246210ecdd0cda97fa3e3bb15c32c6c2d9a23b5 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Tue, 27 Dec 2022 11:29:28 +0000
Subject: [PATCH 0377/1167] cifs: refcount only the selected iface during
interface update
When the server interface for a channel is not active anymore,
we have the logic to select an alternative interface. However
this was not breaking out of the loop as soon as a new alternative
was found. As a result, some interfaces may get refcounted unintentionally.
There was also a bug in checking if we found an alternate iface.
Fixed that too.
Fixes: b54034a73baf ("cifs: during reconnect, update interface if necessary")
Cc: stable@vger.kernel.org # 5.19+
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/sess.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 9e7d9f0baa18a..0b842a07e1579 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -292,9 +292,10 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server)
continue;
}
kref_get(&iface->refcount);
+ break;
}
- if (!list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+ if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
rc = 1;
iface = NULL;
cifs_dbg(FYI, "unable to find a suitable iface\n");
--
GitLab
From cc7d79d4fad6a4eab3f88c4bb237de72be4478f1 Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Thu, 22 Dec 2022 12:54:44 +0000
Subject: [PATCH 0378/1167] cifs: fix interface count calculation during
refresh
The last fix to iface_count did fix the overcounting issue.
However, during each refresh, we could end up undercounting
the iface_count, if a match was found.
Fixing this by doing increments and decrements instead of
setting it to 0 before each parsing of server interfaces.
Fixes: 096bbeec7bd6 ("smb3: interface count displayed incorrectly")
Cc: stable@vger.kernel.org # 6.1
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb2ops.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 0d7e9bcd9f345..e6bcd2baf446a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -530,7 +530,6 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
p = buf;
spin_lock(&ses->iface_lock);
- ses->iface_count = 0;
/*
* Go through iface_list and do kref_put to remove
* any unused ifaces. ifaces in use will be removed
@@ -540,6 +539,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
iface_head) {
iface->is_active = 0;
kref_put(&iface->refcount, release_iface);
+ ses->iface_count--;
}
spin_unlock(&ses->iface_lock);
@@ -618,6 +618,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf,
/* just get a ref so that it doesn't get picked/freed */
iface->is_active = 1;
kref_get(&iface->refcount);
+ ses->iface_count++;
spin_unlock(&ses->iface_lock);
goto next_iface;
} else if (ret < 0) {
--
GitLab
From a53da43decaa3936998fa7dce2346855a6942166 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 1 Jan 2023 15:07:09 +0900
Subject: [PATCH 0379/1167] kbuild: fix single *.ko build
The single *.ko build is broken since commit f65a486821cf ("kbuild:
change module.order to list *.o instead of *.ko").
Fixes: f65a486821cf ("kbuild: change module.order to list *.o instead of *.ko")
Reported-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Tested-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index c05b4fb7121e5..dfba294ae7907 100644
--- a/Makefile
+++ b/Makefile
@@ -1986,7 +1986,7 @@ $(single-no-ko): $(build-dir)
# Remove MODORDER when done because it is not the real one.
PHONY += single_modules
single_modules: $(single-no-ko) modules_prepare
- $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$m;) } > $(MODORDER)
+ $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$(m:%.ko=%.o);) } > $(MODORDER)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
ifneq ($(KBUILD_MODPOST_NOFINAL),1)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal
--
GitLab
From 735aec59afb18c3e2da0a637037e69ad62dbda6a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Wed, 4 Jan 2023 23:04:59 +0900
Subject: [PATCH 0380/1167] kbuild: readd -w option when vmlinux.o or
Module.symver is missing
Commit 63ffe00d8c93 ("kbuild: Fix running modpost with musl libc")
accidentally turned the unresolved symbol warnings into errors when
vmlinux.o (for in-tree builds) or Module.symver (for external module
builds) is missing.
In those cases, unresolved symbols are expected, but the -w option
is not set because 'missing-input' is referenced before set.
Move $(missing-input) back to the original place. This should be fine
for musl libc because vmlinux.o and -w are not added at the same time.
With this change, -w may be passed twice, but it is not a big deal.
Link: https://lore.kernel.org/all/b56a03b8-2a2a-f833-a5d2-cdc50a7ca2bb@cschramm.eu/
Fixes: 63ffe00d8c93 ("kbuild: Fix running modpost with musl libc")
Reported-by: Christopher Schramm <debian@cschramm.eu>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Tested-by: Samuel Holland <samuel@sholland.org>
---
scripts/Makefile.modpost | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 0ee296cf520c2..43343e13c5425 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -44,6 +44,7 @@ modpost-args = \
$(if $(CONFIG_MODVERSIONS),-m) \
$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \
$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \
+ $(if $(KBUILD_MODPOST_WARN),-w) \
$(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \
$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \
-o $@
@@ -55,10 +56,6 @@ ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),)
modpost-args += -n
endif
-ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
-modpost-args += -w
-endif
-
# Read out modules.order to pass in modpost.
# Otherwise, allmodconfig would fail with "Argument list too long".
ifdef KBUILD_MODULES
@@ -124,6 +121,10 @@ modpost-args += -e $(addprefix -i , $(KBUILD_EXTRA_SYMBOLS))
endif # ($(KBUILD_EXTMOD),)
+ifneq ($(missing-input),)
+modpost-args += -w
+endif
+
quiet_cmd_modpost = MODPOST $@
cmd_modpost = \
$(if $(missing-input), \
--
GitLab
From 9c694fbfe6f36017b060ad74c7565cb379852e40 Mon Sep 17 00:00:00 2001
From: Jeremy Szu <jeremy.szu@canonical.com>
Date: Thu, 5 Jan 2023 12:41:53 +0800
Subject: [PATCH 0381/1167] ALSA: hda/realtek: fix mute/micmute LEDs don't work
for a HP platform
There is a HP platform uses ALC236 codec which using GPIO2 to control
mute LED and GPIO1 to control micmute LED.
Thus, add a quirk to make them work.
Signed-off-by: Jeremy Szu <jeremy.szu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20230105044154.8242-1-jeremy.szu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index eda4914b8aeb1..8362eb4642d86 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -9409,6 +9409,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+ SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
--
GitLab
From fe69230f05897b3de758427b574fc98025dfc907 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Wed, 4 Jan 2023 14:51:46 +0800
Subject: [PATCH 0382/1167] caif: fix memory leak in cfctrl_linkup_request()
When linktype is unknown or kzalloc failed in cfctrl_linkup_request(),
pkt is not released. Add release process to error path.
Fixes: b482cd2053e3 ("net-caif: add CAIF core protocol stack")
Fixes: 8d545c8f958f ("caif: Disconnect without waiting for response")
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230104065146.1153009-1-shaozhengchao@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/caif/cfctrl.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c
index cc405d8c7c303..8480684f27625 100644
--- a/net/caif/cfctrl.c
+++ b/net/caif/cfctrl.c
@@ -269,11 +269,15 @@ int cfctrl_linkup_request(struct cflayer *layer,
default:
pr_warn("Request setup of bad link type = %d\n",
param->linktype);
+ cfpkt_destroy(pkt);
return -EINVAL;
}
req = kzalloc(sizeof(*req), GFP_KERNEL);
- if (!req)
+ if (!req) {
+ cfpkt_destroy(pkt);
return -ENOMEM;
+ }
+
req->client_layer = user_layer;
req->cmd = CFCTRL_CMD_LINK_SETUP;
req->param = *param;
--
GitLab
From 634cf6ead93988b0da9ac054521ab63a3ba189db Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 18:02:28 +0100
Subject: [PATCH 0383/1167] fbdev: omapfb: avoid stack overflow warning
The dsi_irq_stats structure is a little too big to fit on the
stack of a 32-bit task, depending on the specific gcc options:
fbdev/omap2/omapfb/dss/dsi.c: In function 'dsi_dump_dsidev_irqs':
fbdev/omap2/omapfb/dss/dsi.c:1621:1: error: the frame size of 1064 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]
Since this is only a debugfs file, performance is not critical,
so just dynamically allocate it, and print an error message
in there in place of a failure code when the allocation fails.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
drivers/video/fbdev/omap2/omapfb/dss/dsi.c | 28 ++++++++++++++--------
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
index 54b0f034c2edf..7cddb7b8ae344 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dsi.c
@@ -1536,22 +1536,28 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev,
{
struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
unsigned long flags;
- struct dsi_irq_stats stats;
+ struct dsi_irq_stats *stats;
+
+ stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+ if (!stats) {
+ seq_printf(s, "out of memory\n");
+ return;
+ }
spin_lock_irqsave(&dsi->irq_stats_lock, flags);
- stats = dsi->irq_stats;
+ *stats = dsi->irq_stats;
memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats));
dsi->irq_stats.last_reset = jiffies;
spin_unlock_irqrestore(&dsi->irq_stats_lock, flags);
seq_printf(s, "period %u ms\n",
- jiffies_to_msecs(jiffies - stats.last_reset));
+ jiffies_to_msecs(jiffies - stats->last_reset));
- seq_printf(s, "irqs %d\n", stats.irq_count);
+ seq_printf(s, "irqs %d\n", stats->irq_count);
#define PIS(x) \
- seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1])
+ seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1])
seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1);
PIS(VC0);
@@ -1575,10 +1581,10 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev,
#define PIS(x) \
seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \
- stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
+ stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
seq_printf(s, "-- VC interrupts --\n");
PIS(CS);
@@ -1594,7 +1600,7 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev,
#define PIS(x) \
seq_printf(s, "%-20s %10d\n", #x, \
- stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
+ stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
seq_printf(s, "-- CIO interrupts --\n");
PIS(ERRSYNCESC1);
@@ -1618,6 +1624,8 @@ static void dsi_dump_dsidev_irqs(struct platform_device *dsidev,
PIS(ULPSACTIVENOT_ALL0);
PIS(ULPSACTIVENOT_ALL1);
#undef PIS
+
+ kfree(stats);
}
static void dsi1_dump_irqs(struct seq_file *s)
--
GitLab
From 4b9880dbf3bdba3a7c56445137c3d0e30aaa0a40 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 5 Jan 2023 22:05:04 +1100
Subject: [PATCH 0384/1167] powerpc/vmlinux.lds: Define RUNTIME_DISCARD_EXIT
The powerpc linker script explicitly includes .exit.text, because
otherwise the link fails due to references from __bug_table and
__ex_table. The code is freed (discarded) at runtime along with
.init.text and data.
That has worked in the past despite powerpc not defining
RUNTIME_DISCARD_EXIT because DISCARDS appears late in the powerpc linker
script (line 410), and the explicit inclusion of .exit.text
earlier (line 280) supersedes the discard.
However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and
riscv") introduced an earlier use of DISCARD as part of the RO_DATA
macro (line 136). With binutils < 2.36 that causes the DISCARD
directives later in the script to be applied earlier [1], causing
.exit.text to actually be discarded at link time, leading to build
errors:
'.exit.text' referenced in section '__bug_table' of crypto/algboss.o: defined in
discarded section '.exit.text' of crypto/algboss.o
'.exit.text' referenced in section '__ex_table' of drivers/nvdimm/core.o: defined in
discarded section '.exit.text' of drivers/nvdimm/core.o
Fix it by defining RUNTIME_DISCARD_EXIT, which causes the generic
DISCARDS macro to not include .exit.text at all.
1: https://lore.kernel.org/lkml/87fscp2v7k.fsf@igel.home/
Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20230105132349.384666-1-mpe@ellerman.id.au
---
arch/powerpc/kernel/vmlinux.lds.S | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8c3862b4c259d..c5ea7d03d5390 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -8,6 +8,7 @@
#define BSS_FIRST_SECTIONS *(.bss.prominit)
#define EMITS_PT_NOTE
#define RO_EXCEPTION_TABLE_ALIGN 0
+#define RUNTIME_DISCARD_EXIT
#define SOFT_MASK_TABLE(align) \
. = ALIGN(align); \
--
GitLab
From 07b050f9290ee012a407a0f64151db902a1520f5 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 5 Jan 2023 22:28:36 +1100
Subject: [PATCH 0385/1167] powerpc/vmlinux.lds: Don't discard .rela* for
relocatable builds
Relocatable kernels must not discard relocations, they need to be
processed at runtime. As such they are included for CONFIG_RELOCATABLE
builds in the powerpc linker script (line 340).
However they are also unconditionally discarded later in the
script (line 414). Previously that worked because the earlier inclusion
superseded the discard.
However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and
riscv") introduced an earlier use of DISCARD as part of the RO_DATA
macro (line 137). With binutils < 2.36 that causes the DISCARD
directives later in the script to be applied earlier, causing .rela* to
actually be discarded at link time, leading to build warnings and a
kernel that doesn't boot:
ld: warning: discarding dynamic section .rela.init.rodata
Fix it by conditionally discarding .rela* only when CONFIG_RELOCATABLE
is disabled.
Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20230105132349.384666-2-mpe@ellerman.id.au
---
arch/powerpc/kernel/vmlinux.lds.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index c5ea7d03d5390..a4c6efadc90c1 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -411,9 +411,12 @@ SECTIONS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt .comment)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
--
GitLab
From be5f95c8779e19779dd81927c8574fec5aaba36c Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 5 Jan 2023 22:42:59 +1100
Subject: [PATCH 0386/1167] powerpc/vmlinux.lds: Don't discard .comment
Although the powerpc linker script mentions .comment in the DISCARD
section, that has never actually caused it to be discarded, because the
earlier ELF_DETAILS macro (previously STABS_DEBUG) explicitly includes
.comment.
However commit 99cb0d917ffa ("arch: fix broken BuildID for arm64 and
riscv") introduced an earlier use of DISCARD as part of the RO_DATA
macro. With binutils < 2.36 that causes the DISCARD directives later in
the script to be applied earlier, causing .comment to actually be
discarded.
It's confusing to explicitly include and discard .comment, and even more
so if the behaviour depends on the toolchain version. So don't discard
.comment in order to maintain the existing behaviour in all cases.
Fixes: 83a092cf95f2 ("powerpc: Link warning for orphan sections")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20230105132349.384666-3-mpe@ellerman.id.au
---
arch/powerpc/kernel/vmlinux.lds.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index a4c6efadc90c1..958e77a24f85b 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -411,7 +411,7 @@ SECTIONS
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .comment)
+ *(.glink .iplt .plt)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
--
GitLab
From 12521a5d5cb7ff0ad43eadfc9c135d86e1131fa8 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 5 Jan 2023 10:49:15 +0000
Subject: [PATCH 0387/1167] io_uring: fix CQ waiting timeout handling
Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in
particular we rearm it anew every time we get into
io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2
CQEs and getting a task_work in the middle may double the timeout value,
or even worse in some cases task may wait indefinitely.
Cc: stable@vger.kernel.org
Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.1672915663.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 472574192dd63..2ac1cd8d23ea6 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2470,7 +2470,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- ktime_t timeout)
+ ktime_t *timeout)
{
int ret;
unsigned long check_cq;
@@ -2488,7 +2488,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
return -ETIME;
/*
@@ -2564,7 +2564,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
}
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
if (__io_cqring_events_user(ctx) >= min_events)
break;
cond_resched();
--
GitLab
From 74c2f81054510d45b813548cb0a1c4ebf87cdd5f Mon Sep 17 00:00:00 2001
From: Liu Shixin <liushixin2@huawei.com>
Date: Mon, 21 Nov 2022 15:36:08 +0800
Subject: [PATCH 0388/1167] arm64/mm: fix incorrect file_map_count for invalid
pmd
The page table check trigger BUG_ON() unexpectedly when split hugepage:
------------[ cut here ]------------
kernel BUG at mm/page_table_check.c:119!
Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
Dumping ftrace buffer:
(ftrace buffer empty)
Modules linked in:
CPU: 7 PID: 210 Comm: transhuge-stres Not tainted 6.1.0-rc3+ #748
Hardware name: linux,dummy-virt (DT)
pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : page_table_check_set.isra.0+0x398/0x468
lr : page_table_check_set.isra.0+0x1c0/0x468
[...]
Call trace:
page_table_check_set.isra.0+0x398/0x468
__page_table_check_pte_set+0x160/0x1c0
__split_huge_pmd_locked+0x900/0x1648
__split_huge_pmd+0x28c/0x3b8
unmap_page_range+0x428/0x858
unmap_single_vma+0xf4/0x1c8
zap_page_range+0x2b0/0x410
madvise_vma_behavior+0xc44/0xe78
do_madvise+0x280/0x698
__arm64_sys_madvise+0x90/0xe8
invoke_syscall.constprop.0+0xdc/0x1d8
do_el0_svc+0xf4/0x3f8
el0_svc+0x58/0x120
el0t_64_sync_handler+0xb8/0xc0
el0t_64_sync+0x19c/0x1a0
[...]
On arm64, pmd_leaf() will return true even if the pmd is invalid due to
pmd_present_invalid() check. So in pmdp_invalidate() the file_map_count
will not only decrease once but also increase once. Then in set_pte_at(),
the file_map_count increase again, and so trigger BUG_ON() unexpectedly.
Add !pmd_present_invalid() check in pmd_user_accessible_page() to fix the
problem.
Fixes: 42b2547137f5 ("arm64/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK")
Reported-by: Denys Vlasenko <dvlasenk@redhat.com>
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Acked-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20221121073608.4183459-1-liushixin2@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/pgtable.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b4bbeed80fb6e..67fc6fdb03fd2 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -862,7 +862,7 @@ static inline bool pte_user_accessible_page(pte_t pte)
static inline bool pmd_user_accessible_page(pmd_t pmd)
{
- return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+ return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
}
static inline bool pud_user_accessible_page(pud_t pud)
--
GitLab
From 730a11f982e61aaef758ab552dfb7c30de79e99b Mon Sep 17 00:00:00 2001
From: Liu Shixin <liushixin2@huawei.com>
Date: Tue, 22 Nov 2022 20:31:37 +0800
Subject: [PATCH 0389/1167] arm64/mm: add pud_user_exec() check in
pud_user_accessible_page()
Add check for the executable case in pud_user_accessible_page() too
like what we did for pte and pmd.
Fixes: 42b2547137f5 ("arm64/mm: enable ARCH_SUPPORTS_PAGE_TABLE_CHECK")
Suggested-by: Will Deacon <will@kernel.org>
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Link: https://lore.kernel.org/r/20221122123137.429686-1-liushixin2@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/pgtable.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 67fc6fdb03fd2..780973a6cbb61 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud))
#define pud_valid(pud) pte_valid(pud_pte(pud))
#define pud_user(pud) pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud) pte_user_exec(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
@@ -867,7 +867,7 @@ static inline bool pmd_user_accessible_page(pmd_t pmd)
static inline bool pud_user_accessible_page(pud_t pud)
{
- return pud_leaf(pud) && pud_user(pud);
+ return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
}
#endif
--
GitLab
From eb9a85261e297292c4cc44b628c1373c996cedc2 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Wed, 14 Dec 2022 21:59:43 +0800
Subject: [PATCH 0390/1167] arm64: ptrace: Use ARM64_SME to guard the SME
register enumerations
We currently guard REGSET_{SSVE, ZA} using ARM64_SVE for no good reason.
Both enumerations would be pointless without ARM64_SME and create two empty
entries in aarch64_regsets[] which would then become part of a process's
native regset view (they should be ignored though).
Switch to use ARM64_SME instead.
Fixes: e12310a0d30f ("arm64/sme: Implement ptrace support for streaming mode SVE registers")
Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20221214135943.379-1-yuzenghui@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/ptrace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 2686ab1576017..0c321ad23cd3a 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1357,7 +1357,7 @@ enum aarch64_regset {
#ifdef CONFIG_ARM64_SVE
REGSET_SVE,
#endif
-#ifdef CONFIG_ARM64_SVE
+#ifdef CONFIG_ARM64_SME
REGSET_SSVE,
REGSET_ZA,
#endif
--
GitLab
From 736eedc974eaafbf4360e0ea85fc892cea72a223 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 22 Dec 2022 18:12:49 +0000
Subject: [PATCH 0391/1167] arm64: mte: Fix double-freeing of the temporary tag
storage during coredump
Commit 16decce22efa ("arm64: mte: Fix the stack frame size warning in
mte_dump_tag_range()") moved the temporary tag storage array from the
stack to slab but it also introduced an error in double freeing this
object. Remove the in-loop freeing.
Fixes: 16decce22efa ("arm64: mte: Fix the stack frame size warning in mte_dump_tag_range()")
Cc: <stable@vger.kernel.org> # 5.18.x
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Seth Jenkins <sethjenkins@google.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20221222181251.1345752-2-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/elfcore.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 353009d7f307f..45f0aba1d8752 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -65,7 +65,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
mte_save_page_tags(page_address(page), tags);
put_page(page);
if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
- mte_free_tag_storage(tags);
ret = 0;
break;
}
--
GitLab
From 19e183b54528f11fafeca60fc6d0821e29ff281e Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 22 Dec 2022 18:12:50 +0000
Subject: [PATCH 0392/1167] elfcore: Add a cprm parameter to
elf_core_extra_{phdrs,data_size}
A subsequent fix for arm64 will use this parameter to parse the vma
information from the snapshot created by dump_vma_snapshot() rather than
traversing the vma list without the mmap_lock.
Fixes: 6dd8b1a0b6cb ("arm64: mte: Dump the MTE tags in the core file")
Cc: <stable@vger.kernel.org> # 5.18.x
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Seth Jenkins <sethjenkins@google.com>
Suggested-by: Seth Jenkins <sethjenkins@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20221222181251.1345752-3-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/elfcore.c | 4 ++--
arch/ia64/kernel/elfcore.c | 4 ++--
arch/x86/um/elfcore.c | 4 ++--
fs/binfmt_elf.c | 4 ++--
fs/binfmt_elf_fdpic.c | 4 ++--
include/linux/elfcore.h | 8 ++++----
6 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index 45f0aba1d8752..f25519e283a58 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -76,7 +76,7 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
return ret;
}
-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
struct vm_area_struct *vma;
int vma_count = 0;
@@ -113,7 +113,7 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
struct vm_area_struct *vma;
size_t data_size = 0;
diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c
index 94680521fbf91..8895df1215404 100644
--- a/arch/ia64/kernel/elfcore.c
+++ b/arch/ia64/kernel/elfcore.c
@@ -7,7 +7,7 @@
#include <asm/elf.h>
-Elf64_Half elf_core_extra_phdrs(void)
+Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return GATE_EHDR->e_phnum;
}
@@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
const struct elf_phdr *const gate_phdrs =
(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 48a3eb09d9516..650cdbbdaf45e 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -7,7 +7,7 @@
#include <asm/elf.h>
-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
}
@@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
if ( vsyscall_ehdr ) {
const struct elfhdr *const ehdrp =
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index de63572a94044..9a780fafc5397 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2034,7 +2034,7 @@ static int elf_core_dump(struct coredump_params *cprm)
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
*/
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
@@ -2074,7 +2074,7 @@ static int elf_core_dump(struct coredump_params *cprm)
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 096e3520a0b10..a05eafcacfb27 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1509,7 +1509,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
tmp->next = thread_list;
thread_list = tmp;
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
@@ -1555,7 +1555,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm)
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 9ec81290e3c89..bd5560542c799 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -105,14 +105,14 @@ int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
* Dumping its extra ELF program headers includes all the other information
* a debugger needs to easily find how the gate DSO was being used.
*/
-extern Elf_Half elf_core_extra_phdrs(void);
+extern Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm);
extern int
elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
extern int
elf_core_write_extra_data(struct coredump_params *cprm);
-extern size_t elf_core_extra_data_size(void);
+extern size_t elf_core_extra_data_size(struct coredump_params *cprm);
#else
-static inline Elf_Half elf_core_extra_phdrs(void)
+static inline Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return 0;
}
@@ -127,7 +127,7 @@ static inline int elf_core_write_extra_data(struct coredump_params *cprm)
return 1;
}
-static inline size_t elf_core_extra_data_size(void)
+static inline size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
return 0;
}
--
GitLab
From 4f4c549feb4ecca95ae9abb88887b941d196f83a Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 22 Dec 2022 18:12:51 +0000
Subject: [PATCH 0393/1167] arm64: mte: Avoid the racy walk of the vma list
during core dump
The MTE coredump code in arch/arm64/kernel/elfcore.c iterates over the
vma list without the mmap_lock held. This can race with another process
or userfaultfd concurrently modifying the vma list. Change the
for_each_mte_vma macro and its callers to instead use the vma snapshot
taken by dump_vma_snapshot() and stored in the cprm object.
Fixes: 6dd8b1a0b6cb ("arm64: mte: Dump the MTE tags in the core file")
Cc: <stable@vger.kernel.org> # 5.18.x
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Seth Jenkins <sethjenkins@google.com>
Suggested-by: Seth Jenkins <sethjenkins@google.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20221222181251.1345752-4-catalin.marinas@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/elfcore.c | 56 +++++++++++++++++--------------------
1 file changed, 26 insertions(+), 30 deletions(-)
diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c
index f25519e283a58..2e94d20c4ac7a 100644
--- a/arch/arm64/kernel/elfcore.c
+++ b/arch/arm64/kernel/elfcore.c
@@ -8,28 +8,27 @@
#include <asm/cpufeature.h>
#include <asm/mte.h>
-#define for_each_mte_vma(vmi, vma) \
+#define for_each_mte_vma(cprm, i, m) \
if (system_supports_mte()) \
- for_each_vma(vmi, vma) \
- if (vma->vm_flags & VM_MTE)
+ for (i = 0, m = cprm->vma_meta; \
+ i < cprm->vma_count; \
+ i++, m = cprm->vma_meta + i) \
+ if (m->flags & VM_MTE)
-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
{
- if (vma->vm_flags & VM_DONTDUMP)
- return 0;
-
- return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+ return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
}
/* Derived from dump_user_range(); start/end must be page-aligned */
static int mte_dump_tag_range(struct coredump_params *cprm,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long len)
{
int ret = 1;
unsigned long addr;
void *tags = NULL;
- for (addr = start; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
struct page *page = get_dump_page(addr);
/*
@@ -78,11 +77,11 @@ static int mte_dump_tag_range(struct coredump_params *cprm,
Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
int vma_count = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(cprm, i, m)
vma_count++;
return vma_count;
@@ -90,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
+ int i;
+ struct core_vma_metadata *m;
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(cprm, i, m) {
struct elf_phdr phdr;
phdr.p_type = PT_AARCH64_MEMTAG_MTE;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = m->start;
phdr.p_paddr = 0;
- phdr.p_filesz = mte_vma_tag_dump_size(vma);
- phdr.p_memsz = vma->vm_end - vma->vm_start;
+ phdr.p_filesz = mte_vma_tag_dump_size(m);
+ phdr.p_memsz = m->end - m->start;
offset += phdr.p_filesz;
phdr.p_flags = 0;
phdr.p_align = 0;
@@ -115,26 +114,23 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
size_t data_size = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
- data_size += mte_vma_tag_dump_size(vma);
+ for_each_mte_vma(cprm, i, m)
+ data_size += mte_vma_tag_dump_size(m);
return data_size;
}
int elf_core_write_extra_data(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
-
- for_each_mte_vma(vmi, vma) {
- if (vma->vm_flags & VM_DONTDUMP)
- continue;
+ int i;
+ struct core_vma_metadata *m;
- if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+ for_each_mte_vma(cprm, i, m) {
+ if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
return 0;
}
--
GitLab
From decb17aeb8fa21484a0140c0696dc5a477cc5c57 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jan 2023 09:50:20 +0000
Subject: [PATCH 0394/1167] KVM: arm64: vgic: Add Apple M2 cpus to the list of
broken SEIS implementations
I really hoped that Apple had fixed their not-quite-a-vgic implementation
when moving from M1 to M2. Alas, it seems they didn't, and running
a buggy EFI version results in the vgic generating SErrors outside
of the guest and taking the host down.
Apply the same workaround as for M1. Yes, this is all a bit crap.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230103095022.3230946-2-maz@kernel.org
---
arch/arm64/include/asm/cputype.h | 4 ++++
arch/arm64/kvm/vgic/vgic-v3.c | 2 ++
2 files changed, 6 insertions(+)
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 4e8b66c74ea2b..683ca3af40848 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -124,6 +124,8 @@
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
@@ -177,6 +179,8 @@
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 826ff6f2a4e7b..2074521d4a8ce 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -616,6 +616,8 @@ static const struct midr_range broken_seis[] = {
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
{},
};
--
GitLab
From ef08c0fadd8a17ebe429b85e23952dac3263ad34 Mon Sep 17 00:00:00 2001
From: junhua huang <huang.junhua@zte.com.cn>
Date: Wed, 28 Dec 2022 09:54:12 +0800
Subject: [PATCH 0395/1167] arm64/uprobes: change the uprobe_opcode_t typedef
to fix the sparse warning
After we fixed the uprobe inst endian in aarch_be, the sparse check report
the following warning info:
sparse warnings: (new ones prefixed by >>)
>> kernel/events/uprobes.c:223:25: sparse: sparse: restricted __le32 degrades to integer
>> kernel/events/uprobes.c:574:56: sparse: sparse: incorrect type in argument 4 (different base types)
@@ expected unsigned int [addressable] [usertype] opcode @@ got restricted __le32 [usertype] @@
kernel/events/uprobes.c:574:56: sparse: expected unsigned int [addressable] [usertype] opcode
kernel/events/uprobes.c:574:56: sparse: got restricted __le32 [usertype]
>> kernel/events/uprobes.c:1483:32: sparse: sparse: incorrect type in initializer (different base types)
@@ expected unsigned int [usertype] insn @@ got restricted __le32 [usertype] @@
kernel/events/uprobes.c:1483:32: sparse: expected unsigned int [usertype] insn
kernel/events/uprobes.c:1483:32: sparse: got restricted __le32 [usertype]
use the __le32 to u32 for uprobe_opcode_t, to keep the same.
Fixes: 60f07e22a73d ("arm64:uprobe fix the uprobe SWBP_INSN in big-endian")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: junhua huang <huang.junhua@zte.com.cn>
Link: https://lore.kernel.org/r/202212280954121197626@zte.com.cn
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/uprobes.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
index ba4bff5ca6749..2b09495499c61 100644
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@@ -16,7 +16,7 @@
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;
struct arch_uprobe_task {
};
--
GitLab
From 36d7546b56a254709a38f1904231e1a93f1c5717 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jan 2023 12:39:33 +0000
Subject: [PATCH 0396/1167] MAINTAINERS: Add Zenghui Yu as a KVM/arm64 reviewer
Zenghui has been around for quite some time, and has been instrumental
in reviewing the GICv4/4.1 KVM support. I'm delighted that he's agreed
to help with the patch review in a more official capacity!
Acked-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230103123933.3234865-1-maz@kernel.org
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f61eb221415bd..551544d877a37 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11359,6 +11359,7 @@ R: James Morse <james.morse@arm.com>
R: Alexandru Elisei <alexandru.elisei@arm.com>
R: Suzuki K Poulose <suzuki.poulose@arm.com>
R: Oliver Upton <oliver.upton@linux.dev>
+R: Zenghui Yu <yuzenghui@huawei.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.linux.dev
L: kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)
--
GitLab
From 7ed906e576a782b8272727f39c68a1762ea3ef98 Mon Sep 17 00:00:00 2001
From: Alexandru Elisei <alexandru.elisei@arm.com>
Date: Tue, 3 Jan 2023 12:07:36 +0000
Subject: [PATCH 0397/1167] MAINTAINERS: Remove myself as a KVM/arm64 reviewer
Haven't done any meaningful reviews for more than a year, and it doesn't
look like I'll be able to do so in the future. Make it official and remove
myself from the KVM/arm64 "Reviewers" list.
Signed-off-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230103120736.116523-1-alexandru.elisei@arm.com
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 551544d877a37..6a0fc23455bdd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11356,7 +11356,6 @@ F: virt/kvm/*
KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
M: Marc Zyngier <maz@kernel.org>
R: James Morse <james.morse@arm.com>
-R: Alexandru Elisei <alexandru.elisei@arm.com>
R: Suzuki K Poulose <suzuki.poulose@arm.com>
R: Oliver Upton <oliver.upton@linux.dev>
R: Zenghui Yu <yuzenghui@huawei.com>
--
GitLab
From 031af50045ea97ed4386eb3751ca2c134d0fc911 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 4 Jan 2023 15:16:26 +0000
Subject: [PATCH 0398/1167] arm64: cmpxchg_double*: hazard against entire
exchange variable
The inline assembly for arm64's cmpxchg_double*() implementations use a
+Q constraint to hazard against other accesses to the memory location
being exchanged. However, the pointer passed to the constraint is a
pointer to unsigned long, and thus the hazard only applies to the first
8 bytes of the location.
GCC can take advantage of this, assuming that other portions of the
location are unchanged, leading to a number of potential problems.
This is similar to what we fixed back in commit:
fee960bed5e857eb ("arm64: xchg: hazard against entire exchange variable")
... but we forgot to adjust cmpxchg_double*() similarly at the same
time.
The same problem applies, as demonstrated with the following test:
| struct big {
| u64 lo, hi;
| } __aligned(128);
|
| unsigned long foo(struct big *b)
| {
| u64 hi_old, hi_new;
|
| hi_old = b->hi;
| cmpxchg_double_local(&b->lo, &b->hi, 0x12, 0x34, 0x56, 0x78);
| hi_new = b->hi;
|
| return hi_old ^ hi_new;
| }
... which GCC 12.1.0 compiles as:
| 0000000000000000 <foo>:
| 0: d503233f paciasp
| 4: aa0003e4 mov x4, x0
| 8: 1400000e b 40 <foo+0x40>
| c: d2800240 mov x0, #0x12 // #18
| 10: d2800681 mov x1, #0x34 // #52
| 14: aa0003e5 mov x5, x0
| 18: aa0103e6 mov x6, x1
| 1c: d2800ac2 mov x2, #0x56 // #86
| 20: d2800f03 mov x3, #0x78 // #120
| 24: 48207c82 casp x0, x1, x2, x3, [x4]
| 28: ca050000 eor x0, x0, x5
| 2c: ca060021 eor x1, x1, x6
| 30: aa010000 orr x0, x0, x1
| 34: d2800000 mov x0, #0x0 // #0 <--- BANG
| 38: d50323bf autiasp
| 3c: d65f03c0 ret
| 40: d2800240 mov x0, #0x12 // #18
| 44: d2800681 mov x1, #0x34 // #52
| 48: d2800ac2 mov x2, #0x56 // #86
| 4c: d2800f03 mov x3, #0x78 // #120
| 50: f9800091 prfm pstl1strm, [x4]
| 54: c87f1885 ldxp x5, x6, [x4]
| 58: ca0000a5 eor x5, x5, x0
| 5c: ca0100c6 eor x6, x6, x1
| 60: aa0600a6 orr x6, x5, x6
| 64: b5000066 cbnz x6, 70 <foo+0x70>
| 68: c8250c82 stxp w5, x2, x3, [x4]
| 6c: 35ffff45 cbnz w5, 54 <foo+0x54>
| 70: d2800000 mov x0, #0x0 // #0 <--- BANG
| 74: d50323bf autiasp
| 78: d65f03c0 ret
Notice that at the lines with "BANG" comments, GCC has assumed that the
higher 8 bytes are unchanged by the cmpxchg_double() call, and that
`hi_old ^ hi_new` can be reduced to a constant zero, for both LSE and
LL/SC versions of cmpxchg_double().
This patch fixes the issue by passing a pointer to __uint128_t into the
+Q constraint, ensuring that the compiler hazards against the entire 16
bytes being modified.
With this change, GCC 12.1.0 compiles the above test as:
| 0000000000000000 <foo>:
| 0: f9400407 ldr x7, [x0, #8]
| 4: d503233f paciasp
| 8: aa0003e4 mov x4, x0
| c: 1400000f b 48 <foo+0x48>
| 10: d2800240 mov x0, #0x12 // #18
| 14: d2800681 mov x1, #0x34 // #52
| 18: aa0003e5 mov x5, x0
| 1c: aa0103e6 mov x6, x1
| 20: d2800ac2 mov x2, #0x56 // #86
| 24: d2800f03 mov x3, #0x78 // #120
| 28: 48207c82 casp x0, x1, x2, x3, [x4]
| 2c: ca050000 eor x0, x0, x5
| 30: ca060021 eor x1, x1, x6
| 34: aa010000 orr x0, x0, x1
| 38: f9400480 ldr x0, [x4, #8]
| 3c: d50323bf autiasp
| 40: ca0000e0 eor x0, x7, x0
| 44: d65f03c0 ret
| 48: d2800240 mov x0, #0x12 // #18
| 4c: d2800681 mov x1, #0x34 // #52
| 50: d2800ac2 mov x2, #0x56 // #86
| 54: d2800f03 mov x3, #0x78 // #120
| 58: f9800091 prfm pstl1strm, [x4]
| 5c: c87f1885 ldxp x5, x6, [x4]
| 60: ca0000a5 eor x5, x5, x0
| 64: ca0100c6 eor x6, x6, x1
| 68: aa0600a6 orr x6, x5, x6
| 6c: b5000066 cbnz x6, 78 <foo+0x78>
| 70: c8250c82 stxp w5, x2, x3, [x4]
| 74: 35ffff45 cbnz w5, 5c <foo+0x5c>
| 78: f9400480 ldr x0, [x4, #8]
| 7c: d50323bf autiasp
| 80: ca0000e0 eor x0, x7, x0
| 84: d65f03c0 ret
... sampling the high 8 bytes before and after the cmpxchg, and
performing an EOR, as we'd expect.
For backporting, I've tested this atop linux-4.9.y with GCC 5.5.0. Note
that linux-4.9.y is oldest currently supported stable release, and
mandates GCC 5.1+. Unfortunately I couldn't get a GCC 5.1 binary to run
on my machines due to library incompatibilities.
I've also used a standalone test to check that we can use a __uint128_t
pointer in a +Q constraint at least as far back as GCC 4.8.5 and LLVM
3.9.1.
Fixes: 5284e1b4bc8a ("arm64: xchg: Implement cmpxchg_double")
Fixes: e9a4b795652f ("arm64: cmpxchg_dbl: patch in lse instructions when supported by the CPU")
Reported-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/lkml/Y6DEfQXymYVgL3oJ@boqun-archlinux/
Reported-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/Y6GXoO4qmH9OIZ5Q@hirez.programming.kicks-ass.net/
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: stable@vger.kernel.org
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20230104151626.3262137-1-mark.rutland@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/atomic_ll_sc.h | 2 +-
arch/arm64/include/asm/atomic_lse.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 0890e4f568fb7..cbb3d961123b1 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \
" cbnz %w0, 1b\n" \
" " #mb "\n" \
"2:" \
- : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \
+ : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \
: "r" (old1), "r" (old2), "r" (new1), "r" (new2) \
: cl); \
\
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 52075e93de6c0..a94d6dacc0292 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]" \
: [old1] "+&r" (x0), [old2] "+&r" (x1), \
- [v] "+Q" (*(unsigned long *)ptr) \
+ [v] "+Q" (*(__uint128_t *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
: cl); \
--
GitLab
From df875276d8c69b27e1ed242d3cee6bc23d3b7f43 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Sat, 10 Dec 2022 21:03:49 +0100
Subject: [PATCH 0399/1167] dt-bindings: interconnect: Add UFS clocks to
MSM8996 A2NoC
MSM8996 A2NoC contains a UFS master, which means the UFS hardware is
accessed every time sync_state is called within the interconnect
framework. It's all good on devices where this clock is already enabled
(most likely from the bootloader), but devices with eMMC storage are
rather unlikely to have it like that. Add the missing 2 clocks to the
binding.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> #db820c
Link: https://lore.kernel.org/r/20221210200353.418391-2-konrad.dybcio@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
.../bindings/interconnect/qcom,rpm.yaml | 24 ++++++++++++++++++-
1 file changed, 23 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml
index 4b37aa88a375b..5e6be4e79201e 100644
--- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml
+++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml
@@ -84,7 +84,6 @@ allOf:
- qcom,msm8939-pcnoc
- qcom,msm8939-snoc
- qcom,msm8996-a1noc
- - qcom,msm8996-a2noc
- qcom,msm8996-bimc
- qcom,msm8996-cnoc
- qcom,msm8996-pnoc
@@ -186,6 +185,29 @@ allOf:
required:
- power-domains
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - qcom,msm8996-a2noc
+
+ then:
+ properties:
+ clock-names:
+ items:
+ - const: bus
+ - const: bus_a
+ - const: aggre2_ufs_axi
+ - const: ufs_axi
+
+ clocks:
+ items:
+ - description: Bus Clock
+ - description: Bus A Clock
+ - description: Aggregate2 NoC UFS AXI Clock
+ - description: UFS AXI Clock
+
- if:
properties:
compatible:
--
GitLab
From 60426ff08af6a21275d9c879c0dfb09406469868 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Sat, 10 Dec 2022 21:03:50 +0100
Subject: [PATCH 0400/1167] interconnect: qcom: msm8996: Provide UFS clocks to
A2NoC
On eMMC devices the bootloader has no business enabling UFS clocks.
That results in a platform hang and hard reboot when trying to vote
on paths including MASTER_UFS and since sync_state guarantees that
it's done at boot time, this effectively prevents such devices from
booting. Fix that.
Fixes: 7add937f5222 ("interconnect: qcom: Add MSM8996 interconnect provider driver")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> #db820c
Link: https://lore.kernel.org/r/20221210200353.418391-3-konrad.dybcio@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/msm8996.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c
index c2903ae3b3bc3..7ddb1f23fb2a3 100644
--- a/drivers/interconnect/qcom/msm8996.c
+++ b/drivers/interconnect/qcom/msm8996.c
@@ -33,6 +33,13 @@ static const char * const bus_a0noc_clocks[] = {
"aggre0_noc_mpu_cfg"
};
+static const char * const bus_a2noc_clocks[] = {
+ "bus",
+ "bus_a",
+ "aggre2_ufs_axi",
+ "ufs_axi"
+};
+
static const u16 mas_a0noc_common_links[] = {
MSM8996_SLAVE_A0NOC_SNOC
};
@@ -1859,6 +1866,8 @@ static const struct qcom_icc_desc msm8996_a2noc = {
.type = QCOM_ICC_NOC,
.nodes = a2noc_nodes,
.num_nodes = ARRAY_SIZE(a2noc_nodes),
+ .clocks = bus_a2noc_clocks,
+ .num_clocks = ARRAY_SIZE(bus_a2noc_clocks),
.regmap_cfg = &msm8996_a2noc_regmap_config
};
--
GitLab
From 4be39d5d86c690c60e2afe55787fc5ec4409d0f0 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Sat, 10 Dec 2022 21:03:51 +0100
Subject: [PATCH 0401/1167] interconnect: qcom: msm8996: Fix regmap
max_register values
The device tree reg starts at BUS_BASE + QoS_OFFSET, but the regmap
configs in the ICC driver had values suggesting the reg started at
BUS_BASE. Shrink them down (where they haven't been already, so for
providers where QoS_OFFSET = 0) to make sure they stay within their
window.
Fixes: 7add937f5222 ("interconnect: qcom: Add MSM8996 interconnect provider driver")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> #db820c
Link: https://lore.kernel.org/r/20221210200353.418391-4-konrad.dybcio@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/msm8996.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c
index 7ddb1f23fb2a3..25a1a32bc611f 100644
--- a/drivers/interconnect/qcom/msm8996.c
+++ b/drivers/interconnect/qcom/msm8996.c
@@ -1813,7 +1813,7 @@ static const struct regmap_config msm8996_a0noc_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x9000,
+ .max_register = 0x6000,
.fast_io = true
};
@@ -1837,7 +1837,7 @@ static const struct regmap_config msm8996_a1noc_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x7000,
+ .max_register = 0x5000,
.fast_io = true
};
@@ -1858,7 +1858,7 @@ static const struct regmap_config msm8996_a2noc_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0xa000,
+ .max_register = 0x7000,
.fast_io = true
};
@@ -1886,7 +1886,7 @@ static const struct regmap_config msm8996_bimc_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x62000,
+ .max_register = 0x5a000,
.fast_io = true
};
@@ -1997,7 +1997,7 @@ static const struct regmap_config msm8996_mnoc_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
.val_bits = 32,
- .max_register = 0x20000,
+ .max_register = 0x1c000,
.fast_io = true
};
--
GitLab
From dd42ec8ea5b979edcebbf0ba05807d866884b567 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Sat, 10 Dec 2022 21:03:52 +0100
Subject: [PATCH 0402/1167] interconnect: qcom: rpm: Use _optional func for
provider clocks
It turned out that - very unfortunately - msm8996 needs a binding
update, adding 2 more clocks to the A2NoC node. Use the _optional
variant of devm_clk_get to make sure old DTs will still probe with
newer versions of the driver.
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> #db820c
Link: https://lore.kernel.org/r/20221210200353.418391-5-konrad.dybcio@linaro.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
drivers/interconnect/qcom/icc-rpm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c
index ba6781f54ab73..df3196f725368 100644
--- a/drivers/interconnect/qcom/icc-rpm.c
+++ b/drivers/interconnect/qcom/icc-rpm.c
@@ -488,7 +488,7 @@ int qnoc_probe(struct platform_device *pdev)
}
regmap_done:
- ret = devm_clk_bulk_get(dev, qp->num_clks, qp->bus_clks);
+ ret = devm_clk_bulk_get_optional(dev, qp->num_clks, qp->bus_clks);
if (ret)
return ret;
--
GitLab
From 0cab5b4964c7064893e6ff5e81087a9206c63908 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 27 Dec 2022 17:12:04 +0000
Subject: [PATCH 0403/1167] arm64/sme: Fix context switch for SME only systems
When refactoring fpsimd_load() to support keeping SVE enabled over syscalls
support for systems with SME but not SVE was broken. The code that selects
between loading regular FPSIMD and SVE states was guarded by using
system_supports_sve() but is also needed to handle the streaming SVE state
in SME only systems where that check will be false. Fix this by also
checking for system_supports_sme().
Fixes: a0136be443d5 ("arm64/fpsimd: Load FP state based on recorded data type")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20221223-arm64-fix-sme-only-v1-1-938d663f69e5@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/fpsimd.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index dcc81e7200d40..b6ef1af0122eb 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -385,7 +385,7 @@ static void task_fpsimd_load(void)
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
--
GitLab
From 7dde62f0687c8856b6c0660066c7ee83a6a6f033 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 27 Dec 2022 17:12:05 +0000
Subject: [PATCH 0404/1167] arm64/signal: Always accept SVE signal frames on
SME only systems
Currently we reject an attempt to restore a SVE signal frame on a system
with SME but not SVE supported. This means that it is not possible to
disable streaming mode via signal return as this is configured via the
flags in the SVE signal context. Instead accept the signal frame, we will
require it to have a vector length of 0 specified and no payload since the
task will have no SVE vector length configured.
Fixes: 85ed24dad290 ("arm64/sme: Implement streaming SVE signal handling")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20221223-arm64-fix-sme-only-v1-2-938d663f69e5@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/signal.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e0d09bf5b01b8..f90ee2dc413cd 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -281,7 +281,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
vl = task_get_sme_vl(current);
} else {
- if (!system_supports_sve())
+ /*
+ * A SME only system use SVE for streaming mode so can
+ * have a SVE formatted context with a zero VL and no
+ * payload data.
+ */
+ if (!system_supports_sve() && !system_supports_sme())
return -EINVAL;
vl = task_get_sve_vl(current);
--
GitLab
From f26cd7372160da2eba31061d7943348ab9f2c01d Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 27 Dec 2022 17:12:06 +0000
Subject: [PATCH 0405/1167] arm64/signal: Always allocate SVE signal frames on
SME only systems
Currently we only allocate space for SVE signal frames on systems that
support SVE, meaning that SME only systems do not allocate a signal frame
for streaming mode SVE state. Change the check so space is allocated if
either feature is supported.
Fixes: 85ed24dad290 ("arm64/sme: Implement streaming SVE signal handling")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20221223-arm64-fix-sme-only-v1-3-938d663f69e5@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/kernel/signal.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f90ee2dc413cd..be279fd482480 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -737,7 +737,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
if (add_all || test_thread_flag(TIF_SVE) ||
--
GitLab
From 601a27ea09a317d0fe2895df7d875381fb393041 Mon Sep 17 00:00:00 2001
From: Wengang Wang <wen.gang.wang@oracle.com>
Date: Wed, 4 Jan 2023 10:05:43 -0800
Subject: [PATCH 0406/1167] xfs: fix extent busy updating
In xfs_extent_busy_update_extent() case 6 and 7, whenever bno is modified on
extent busy, the relavent length has to be modified accordingly.
Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
fs/xfs/xfs_extent_busy.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index ad22a003f9595..f3d328e4a4408 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -236,6 +236,7 @@ xfs_extent_busy_update_extent(
*
*/
busyp->bno = fend;
+ busyp->length = bend - fend;
} else if (bbno < fbno) {
/*
* Case 8:
--
GitLab
From b2b50d572135c5c6e10c2ff79cd828d5a8141ef6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Wed, 4 Jan 2023 16:37:53 -0800
Subject: [PATCH 0407/1167] block: Remove "select SRCU"
Now that the SRCU Kconfig option is unconditionally selected, there is
no longer any point in selecting it. Therefore, remove the "select SRCU"
Kconfig statements.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/Kconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/block/Kconfig b/block/Kconfig
index 444c5ab3b67e2..5d9d9c84d5165 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -6,7 +6,6 @@ menuconfig BLOCK
bool "Enable the block layer" if EXPERT
default y
select SBITMAP
- select SRCU
help
Provide block layer support for the kernel.
--
GitLab
From cdfa92eb90f5770b26a79824ef213ebdbbd988b1 Mon Sep 17 00:00:00 2001
From: Chancel Liu <chancel.liu@nxp.com>
Date: Wed, 4 Jan 2023 10:57:54 +0800
Subject: [PATCH 0408/1167] ASoC: fsl_micfil: Correct the number of steps on SX
controls
The parameter "max" of SOC_SINGLE_SX_TLV() means the number of steps
rather than maximum value. This patch corrects the minimum value to -8
and the number of steps to 15.
Signed-off-by: Chancel Liu <chancel.liu@nxp.com>
Acked-by: Shengjiu Wang <shengjiu.wang@gmail.com>
Link: https://lore.kernel.org/r/20230104025754.3019235-1-chancel.liu@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/fsl/fsl_micfil.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c
index 7b17f152bbf3c..94341e4352b3c 100644
--- a/sound/soc/fsl/fsl_micfil.c
+++ b/sound/soc/fsl/fsl_micfil.c
@@ -315,21 +315,21 @@ static int hwvad_detected(struct snd_kcontrol *kcontrol,
static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = {
SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(1), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(2), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(3), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(4), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(5), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv),
SOC_ENUM_EXT("MICFIL Quality Select",
fsl_micfil_quality_enum,
micfil_quality_get, micfil_quality_set),
--
GitLab
From 38892ea4cefbb6ed3a91e76d3af84a1f8077d2d4 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 4 Jan 2023 18:36:27 +0900
Subject: [PATCH 0409/1167] spi: dt-bindings: Rename spi-cs-setup-ns to
spi-cs-setup-delay-ns
Other delay values follow the delay-ns naming convention, so unify the
newly introduced spi-cs-setup-ns property for consistency.
Also fix a typo while we're here.
Fixes: f6c911f3308c ("spi: dt-bindings: Introduce spi-cs-setup-ns property")
Signed-off-by: Hector Martin <marcan@marcan.st>
Link: https://lore.kernel.org/r/20230104093631.15611-2-marcan@marcan.st
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../devicetree/bindings/spi/spi-peripheral-props.yaml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
index ead2cccf658fd..9a60c0664bbe7 100644
--- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml
@@ -44,9 +44,9 @@ properties:
description:
Maximum SPI clocking speed of the device in Hz.
- spi-cs-setup-ns:
+ spi-cs-setup-delay-ns:
description:
- Delay in nanosecods to be introduced by the controller after CS is
+ Delay in nanoseconds to be introduced by the controller after CS is
asserted.
spi-rx-bus-width:
--
GitLab
From e0fe6a31cac84735939c29d1e05055d58325c6c0 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 4 Jan 2023 18:36:28 +0900
Subject: [PATCH 0410/1167] spi: Rename spi-cs-setup-ns property to
spi-cs-setup-delay-ns
As mentioned in the corresponding DT binding commit, the naming scheme
for delay properties includes "delay" in the name, so let's keep that
consistent.
Fixes: 33a2fde5f77b ("spi: Introduce spi-cs-setup-ns property")
Signed-off-by: Hector Martin <marcan@marcan.st>
Link: https://lore.kernel.org/r/20230104093631.15611-3-marcan@marcan.st
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 3cc7bb4d03dec..15f174f4e0561 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -2310,7 +2310,7 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
if (!of_property_read_u32(nc, "spi-max-frequency", &value))
spi->max_speed_hz = value;
- if (!of_property_read_u16(nc, "spi-cs-setup-ns", &cs_setup)) {
+ if (!of_property_read_u16(nc, "spi-cs-setup-delay-ns", &cs_setup)) {
spi->cs_setup.value = cs_setup;
spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS;
}
--
GitLab
From 6fea87637bf36bd285227f490132e83582ab7513 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Fri, 16 Dec 2022 17:12:53 +0800
Subject: [PATCH 0411/1167] drm/amd/pm: correct the reference clock for fan
speed(rpm) calculation
Correct the reference clock as 25Mhz for SMU13 fan speed calculation.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0.x, 6.1.x
---
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e54b760b875bf..d1f50d42288d2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1261,7 +1261,8 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu,
uint32_t speed)
{
struct amdgpu_device *adev = smu->adev;
- uint32_t tach_period, crystal_clock_freq;
+ uint32_t crystal_clock_freq = 2500;
+ uint32_t tach_period;
int ret;
if (!speed)
@@ -1271,7 +1272,6 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu,
if (ret)
return ret;
- crystal_clock_freq = amdgpu_asic_get_xclk(adev);
tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
WREG32_SOC15(THM, 0, regCG_TACH_CTRL,
REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL),
--
GitLab
From 318ca20893c19ead02845a08204c3f9249bb74cd Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 4 Jan 2023 10:45:01 +0800
Subject: [PATCH 0412/1167] drm/amd/pm: add the missing mapping for PPT feature
on SMU13.0.0 and 13.0.7
Then we are able to set a new ppt limit via the hwmon interface(power1_cap).
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0.x, 6.1.x
---
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 1 +
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 9643b21c636a9..4c20d17e7416e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -213,6 +213,7 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] =
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index 5c6c6ad011ca6..e87db7e02e8a5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -192,6 +192,7 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] =
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = {
--
GitLab
From ed21f6c3fe423b17211fa5a85cd028621a749a2a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 5 Jan 2023 10:45:36 +0100
Subject: [PATCH 0413/1167] drm/amdgpu: fix another missing fence reference in
the CS code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
drm_sched_job_add_dependency() consumes the references of the gang
members. Only triggered by mesh shaders.
Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: 1728baa7e4e6 ("drm/amdgpu: use scheduler dependencies for CS")
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Tested-by: Bert Karwatzki <spasswolf@web.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230105111703.52695-1-christian.koenig@amd.com
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 8516c814bc9b5..47763ac0d14a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1254,9 +1254,12 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
continue;
fence = &p->jobs[i]->base.s_fence->scheduled;
+ dma_fence_get(fence);
r = drm_sched_job_add_dependency(&leader->base, fence);
- if (r)
+ if (r) {
+ dma_fence_put(fence);
goto error_cleanup;
+ }
}
if (p->gang_size > 1) {
--
GitLab
From 41cc108b2451e0c65e8c9c9f6a3e103b62b60bb3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 5 Jan 2023 11:27:16 +0100
Subject: [PATCH 0414/1167] drm/amdgpu: fix missing dma_fence_put in error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
When the fence can't be added we need to drop the reference.
Suggested-by: Bert Karwatzki <spasswolf@web.de>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230105111703.52695-2-christian.koenig@amd.com
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index bac7976975bd3..dcd8c066bc1f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -391,8 +391,10 @@ int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job)
dma_fence_get(f);
r = drm_sched_job_add_dependency(&job->base, f);
- if (r)
+ if (r) {
+ dma_fence_put(f);
return r;
+ }
}
return 0;
}
--
GitLab
From e95d50d74b93a767a026f588e8de0b9718a0105e Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 5 Jan 2023 13:23:39 +0200
Subject: [PATCH 0415/1167] lib/scatterlist: Fix to merge contiguous pages into
the last SG properly
When sg_alloc_append_table_from_pages() calls to pages_are_mergeable() in
its 'sgt_append->prv' flow to check whether it can merge contiguous pages
into the last SG, it passes the page arguments in the wrong order.
The first parameter should be the next candidate page to be merged to
the last page and not the opposite.
The current code leads to a corrupted SG which resulted in OOPs and
unexpected errors when non-contiguous pages are merged wrongly.
Fix to pass the page parameters in the right order.
Fixes: 1567b49d1a40 ("lib/scatterlist: add check when merging zone device pages")
Link: https://lore.kernel.org/r/20230105112339.107969-1-yishaih@nvidia.com
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
lib/scatterlist.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index a0ad2a7959b5d..f72aa50c6654b 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -476,7 +476,7 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
/* Merge contiguous pages into the last SG */
prv_len = sgt_append->prv->length;
last_pg = sg_page(sgt_append->prv);
- while (n_pages && pages_are_mergeable(last_pg, pages[0])) {
+ while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
if (sgt_append->prv->length + PAGE_SIZE > max_segment)
break;
sgt_append->prv->length += PAGE_SIZE;
--
GitLab
From b2d473a6019ef9a54b0156ecdb2e0398c9fa6a24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@rivosinc.com>
Date: Mon, 2 Jan 2023 17:07:48 +0100
Subject: [PATCH 0416/1167] riscv, kprobes: Stricter c.jr/c.jalr decoding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
In the compressed instruction extension, c.jr, c.jalr, c.mv, and c.add
is encoded the following way (each instruction is 16b):
---+-+-----------+-----------+--
100 0 rs1[4:0]!=0 00000 10 : c.jr
100 1 rs1[4:0]!=0 00000 10 : c.jalr
100 0 rd[4:0]!=0 rs2[4:0]!=0 10 : c.mv
100 1 rd[4:0]!=0 rs2[4:0]!=0 10 : c.add
The following logic is used to decode c.jr and c.jalr:
insn & 0xf007 == 0x8002 => instruction is an c.jr
insn & 0xf007 == 0x9002 => instruction is an c.jalr
When 0xf007 is used to mask the instruction, c.mv can be incorrectly
decoded as c.jr, and c.add as c.jalr.
Correct the decoding by changing the mask from 0xf007 to 0xf07f.
Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported")
Signed-off-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20230102160748.1307289-1-bjorn@kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/kernel/probes/simulate-insn.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h
index cb6ff7dccb92e..de8474146a9b6 100644
--- a/arch/riscv/kernel/probes/simulate-insn.h
+++ b/arch/riscv/kernel/probes/simulate-insn.h
@@ -31,9 +31,9 @@ __RISCV_INSN_FUNCS(fence, 0x7f, 0x0f);
} while (0)
__RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001);
-__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002);
+__RISCV_INSN_FUNCS(c_jr, 0xf07f, 0x8002);
__RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001);
-__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002);
+__RISCV_INSN_FUNCS(c_jalr, 0xf07f, 0x9002);
__RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001);
__RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001);
__RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002);
--
GitLab
From b9b916aee6715cd7f3318af6dc360c4729417b94 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben-linux@fluff.org>
Date: Thu, 29 Dec 2022 17:05:45 +0000
Subject: [PATCH 0417/1167] riscv: uaccess: fix type of 0 variable on error in
get_user()
If the get_user(x, ptr) has x as a pointer, then the setting
of (x) = 0 is going to produce the following sparse warning,
so fix this by forcing the type of 'x' when access_ok() fails.
fs/aio.c:2073:21: warning: Using plain integer as NULL pointer
Signed-off-by: Ben Dooks <ben-linux@fluff.org>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20221229170545.718264-1-ben-linux@fluff.org
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/uaccess.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 855450bed9f52..ec0cab9fbddd0 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -165,7 +165,7 @@ do { \
might_fault(); \
access_ok(__p, sizeof(*__p)) ? \
__get_user((x), __p) : \
- ((x) = 0, -EFAULT); \
+ ((x) = (__force __typeof__(x))0, -EFAULT); \
})
#define __put_user_asm(insn, x, ptr, err) \
--
GitLab
From cdf64343f91a1225e9e3d4ce4261962cd41b4ddd Mon Sep 17 00:00:00 2001
From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Date: Fri, 23 Dec 2022 02:10:08 +0000
Subject: [PATCH 0418/1167] dt-bindings: msm: dsi-controller-main: Fix
operating-points-v2 constraint
The existing msm8916.dtsi does not depend on nor require operating points.
Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/515940/
Link: https://lore.kernel.org/r/20221223021025.1646636-2-bryan.odonoghue@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
.../devicetree/bindings/display/msm/dsi-controller-main.yaml | 1 -
1 file changed, 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
index f2c143730a551..55bfe1101d6f4 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
@@ -138,7 +138,6 @@ required:
- assigned-clocks
- assigned-clock-parents
- power-domains
- - operating-points-v2
- ports
additionalProperties: false
--
GitLab
From a6f033938beb31f893302a93f83ec0b6460c6cac Mon Sep 17 00:00:00 2001
From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Date: Fri, 23 Dec 2022 02:10:09 +0000
Subject: [PATCH 0419/1167] dt-bindings: msm: dsi-controller-main: Fix
power-domain constraint
power-domain is required for the sc7180 dispcc GDSC but not every qcom SoC
has a similar dependency for example the apq8064.
Most Qcom SoC's using mdss-dsi-ctrl seem to have the ability to
power-collapse the MDP without collapsing DSI.
For example the qcom vendor kernel commit for apq8084, msm8226, msm8916,
msm8974.
https://review.carbonrom.org/plugins/gitiles/CarbonROM/android_kernel_oneplus_msm8994/+/7b5c011a770daa2811778937ed646237a28a8694
"ARM: dts: msm: add mdss gdsc supply to dsi controller device
It is possible for the DSI controller to be active when MDP is
power collapsed. DSI controller needs to have it's own vote for
mdss gdsc to ensure that gdsc remains on in such cases."
This however doesn't appear to be the case for the apq8064 so we shouldn't
be marking power-domain as required in yaml checks.
Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/515958/
Link: https://lore.kernel.org/r/20221223021025.1646636-3-bryan.odonoghue@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
.../devicetree/bindings/display/msm/dsi-controller-main.yaml | 1 -
1 file changed, 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
index 55bfe1101d6f4..8ba61fef576a5 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
@@ -137,7 +137,6 @@ required:
- phys
- assigned-clocks
- assigned-clock-parents
- - power-domains
- ports
additionalProperties: false
--
GitLab
From 654ffe4b793b42ed6b5909daff0b91809916d94e Mon Sep 17 00:00:00 2001
From: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Date: Fri, 23 Dec 2022 02:10:10 +0000
Subject: [PATCH 0420/1167] dt-bindings: msm: dsi-controller-main: Fix
description of core clock
There's a typo in describing the core clock as an 'escape' clock. The
accurate description is 'core'.
Fixes: 4dbe55c97741 ("dt-bindings: msm: dsi: add yaml schemas for DSI bindings")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/515938/
Link: https://lore.kernel.org/r/20221223021025.1646636-4-bryan.odonoghue@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
.../devicetree/bindings/display/msm/dsi-controller-main.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
index 8ba61fef576a5..6e2fd6e9fa7f0 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml
@@ -32,7 +32,7 @@ properties:
- description: Display byte clock
- description: Display byte interface clock
- description: Display pixel clock
- - description: Display escape clock
+ - description: Display core clock
- description: Display AHB clock
- description: Display AXI clock
--
GitLab
From 00dd060ab3cf95ca6ede7853bc14397014971b5e Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 5 Jan 2023 03:47:43 +0200
Subject: [PATCH 0421/1167] drm/msm: another fix for the headless Adreno GPU
Fix another oops reproducible when rebooting the board with the Adreno
GPU working in the headless mode (e.g. iMX platforms).
Unable to handle kernel NULL pointer dereference at virtual address 00000000 when read
[00000000] *pgd=74936831, *pte=00000000, *ppte=00000000
Internal error: Oops: 17 [#1] ARM
CPU: 0 PID: 51 Comm: reboot Not tainted 6.2.0-rc1-dirty #11
Hardware name: Freescale i.MX53 (Device Tree Support)
PC is at msm_atomic_commit_tail+0x50/0x970
LR is at commit_tail+0x9c/0x188
pc : [<c06aa430>] lr : [<c067a214>] psr: 600e0013
sp : e0851d30 ip : ee4eb7eb fp : 00090acc
r10: 00000058 r9 : c2193014 r8 : c4310000
r7 : c4759380 r6 : 07bef61d r5 : 00000000 r4 : 00000000
r3 : c44cc440 r2 : 00000000 r1 : 00000000 r0 : 00000000
Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none
Control: 10c5387d Table: 74910019 DAC: 00000051
Register r0 information: NULL pointer
Register r1 information: NULL pointer
Register r2 information: NULL pointer
Register r3 information: slab kmalloc-1k start c44cc400 pointer offset 64 size 1024
Register r4 information: NULL pointer
Register r5 information: NULL pointer
Register r6 information: non-paged memory
Register r7 information: slab kmalloc-128 start c4759380 pointer offset 0 size 128
Register r8 information: slab kmalloc-2k start c4310000 pointer offset 0 size 2048
Register r9 information: non-slab/vmalloc memory
Register r10 information: non-paged memory
Register r11 information: non-paged memory
Register r12 information: non-paged memory
Process reboot (pid: 51, stack limit = 0xc80046d9)
Stack: (0xe0851d30 to 0xe0852000)
1d20: c4759380 fbd77200 000005ff 002b9c70
1d40: c4759380 c4759380 00000000 07bef61d 00000600 c0d6fe7c c2193014 00000058
1d60: 00090acc c067a214 00000000 c4759380 c4310000 00000000 c44cc854 c067a89c
1d80: 00000000 00000000 00000000 c4310468 00000000 c4759380 c4310000 c4310468
1da0: c4310470 c0643258 c4759380 00000000 00000000 c0c4ee24 00000000 c44cc810
1dc0: 00000000 c0c4ee24 00000000 c44cc810 00000000 0347d2a8 e0851e00 e0851e00
1de0: c4759380 c067ad20 c4310000 00000000 c44cc810 c27f8718 c44cc854 c067adb8
1e00: c4933000 00000002 00000001 00000000 00000000 c2130850 00000000 c2130854
1e20: c25fc488 00000000 c0ff162c 00000000 00000001 00000002 00000000 00000000
1e40: c43102c0 c43102c0 00000000 0347d2a8 c44cc810 c44cc814 c2133da8 c06d1a60
1e60: 00000000 00000000 00079028 c2012f24 fee1dead c4933000 00000058 c01431e4
1e80: 01234567 c0143a20 00000000 00000000 00000000 00000000 00000000 00000000
1ea0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1ec0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1ee0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1f00: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1f20: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1f40: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1f60: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
1f80: 00000000 00000000 00000000 0347d2a8 00000002 00000004 00000078 00000058
1fa0: c010028c c0100060 00000002 00000004 fee1dead 28121969 01234567 00079028
1fc0: 00000002 00000004 00000078 00000058 0002fdc5 00000000 00000000 00090acc
1fe0: 00000058 becc9c64 b6e97e05 b6e0e5f6 600e0030 fee1dead 00000000 00000000
msm_atomic_commit_tail from commit_tail+0x9c/0x188
commit_tail from drm_atomic_helper_commit+0x160/0x188
drm_atomic_helper_commit from drm_atomic_commit+0xac/0xe0
drm_atomic_commit from drm_atomic_helper_disable_all+0x1b0/0x1c0
drm_atomic_helper_disable_all from drm_atomic_helper_shutdown+0x88/0x140
drm_atomic_helper_shutdown from device_shutdown+0x16c/0x240
device_shutdown from kernel_restart+0x38/0x90
kernel_restart from __do_sys_reboot+0x174/0x224
__do_sys_reboot from ret_fast_syscall+0x0/0x1c
Exception stack(0xe0851fa8 to 0xe0851ff0)
1fa0: 00000002 00000004 fee1dead 28121969 01234567 00079028
1fc0: 00000002 00000004 00000078 00000058 0002fdc5 00000000 00000000 00090acc
1fe0: 00000058 becc9c64 b6e97e05 b6e0e5f6
Code: 15922088 1184421c e1500003 1afffff8 (e5953000)
---[ end trace 0000000000000000 ]---
Fixes: 0a58d2ae572a ("drm/msm: Make .remove and .shutdown HW shutdown consistent")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/516909/
Link: https://lore.kernel.org/r/20230105014743.1478110-1-dmitry.baryshkov@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
drivers/gpu/drm/msm/msm_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index cffba9ca7ec24..5737364fbb542 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1279,7 +1279,7 @@ void msm_drv_shutdown(struct platform_device *pdev)
* msm_drm_init, drm_dev->registered is used as an indicator that the
* shutdown will be successful.
*/
- if (drm && drm->registered)
+ if (drm && drm->registered && priv->kms)
drm_atomic_helper_shutdown(drm);
}
--
GitLab
From 13ef096e342b00e30b95a90c6c13eee1f0bec4c5 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 2 Jan 2023 11:02:00 +0100
Subject: [PATCH 0422/1167] drm/msm/adreno: Make adreno quirks not overwrite
each other
So far the adreno quirks have all been assigned with an OR operator,
which is problematic, because they were assigned consecutive integer
values, which makes checking them with an AND operator kind of no bueno..
Switch to using BIT(n) so that only the quirks that the programmer chose
are taken into account when evaluating info->quirks & ADRENO_QUIRK_...
Fixes: 370063ee427a ("drm/msm/adreno: Add A540 support")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Marijn Suijten <marijn.suijten@somainline.org>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/516456/
Link: https://lore.kernel.org/r/20230102100201.77286-1-konrad.dybcio@linaro.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/adreno_gpu.h | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 5d4b1c95033ff..b4f9b1343d637 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -29,11 +29,9 @@ enum {
ADRENO_FW_MAX,
};
-enum adreno_quirks {
- ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
- ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
- ADRENO_QUIRK_LMLOADKILL_DISABLE = 3,
-};
+#define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0)
+#define ADRENO_QUIRK_FAULT_DETECT_MASK BIT(1)
+#define ADRENO_QUIRK_LMLOADKILL_DISABLE BIT(2)
struct adreno_rev {
uint8_t core;
@@ -65,7 +63,7 @@ struct adreno_info {
const char *name;
const char *fw[ADRENO_FW_MAX];
uint32_t gmem;
- enum adreno_quirks quirks;
+ u64 quirks;
struct msm_gpu *(*init)(struct drm_device *dev);
const char *zapfw;
u32 inactive_period;
--
GitLab
From f4a75b5933c998e60fd812a7680e0971eb1c7cee Mon Sep 17 00:00:00 2001
From: Akhil P Oommen <quic_akhilpo@quicinc.com>
Date: Fri, 16 Dec 2022 22:33:14 +0530
Subject: [PATCH 0423/1167] drm/msm/a6xx: Avoid gx gbit halt during rpm suspend
As per the downstream driver, gx gbif halt is required only during
recovery sequence. So lets avoid it during regular rpm suspend.
Signed-off-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/515279/
Link: https://lore.kernel.org/r/20221216223253.1.Ice9c47bfeb1fddb8dc377a3491a043a3ee7fca7d@changeid
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 15 +++++++++------
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 7 +++++++
drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 +
3 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 6484b97c5344f..f3c9600221d48 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -876,7 +876,8 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu)
#define GBIF_CLIENT_HALT_MASK BIT(0)
#define GBIF_ARB_HALT_MASK BIT(1)
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu,
+ bool gx_off)
{
struct msm_gpu *gpu = &adreno_gpu->base;
@@ -889,9 +890,11 @@ static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
return;
}
- /* Halt the gx side of GBIF */
- gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
- spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ if (gx_off) {
+ /* Halt the gx side of GBIF */
+ gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
+ spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ }
/* Halt new client requests on GBIF */
gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
@@ -929,7 +932,7 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu)
/* Halt the gmu cm3 core */
gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, true);
/* Reset GPU core blocks */
gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1);
@@ -1083,7 +1086,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
return;
}
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
/* tell the GMU we want to slumber */
ret = a6xx_gmu_notify_slumber(gmu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index e87196457b9aa..33bba81d5a22b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1277,6 +1277,12 @@ static void a6xx_recover(struct msm_gpu *gpu)
if (hang_debug)
a6xx_dump(gpu);
+ /*
+ * To handle recovery specific sequences during the rpm suspend we are
+ * about to trigger
+ */
+ a6xx_gpu->hung = true;
+
/* Halt SQE first */
gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
@@ -1319,6 +1325,7 @@ static void a6xx_recover(struct msm_gpu *gpu)
mutex_unlock(&gpu->active_lock);
msm_gpu_hw_init(gpu);
+ a6xx_gpu->hung = false;
}
static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index ab853f61db632..eea2e60ce3b7b 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -32,6 +32,7 @@ struct a6xx_gpu {
void *llc_slice;
void *htw_llc_slice;
bool have_mmu500;
+ bool hung;
};
#define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
--
GitLab
From c26de7507d1f5ffa5daf6a4980ef7896889691a9 Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Thu, 5 Jan 2023 09:07:11 +0800
Subject: [PATCH 0424/1167] stmmac: dwmac-mediatek: remove the
dwmac_fix_mac_speed
In current driver, MAC will always enable 2ns delay in RGMII mode,
but that's not the correct usage.
Remove the dwmac_fix_mac_speed() in driver, and recommend "rgmii-id"
for phy-mode in device tree.
Fixes: f2d356a6ab71 ("stmmac: dwmac-mediatek: add support for mt8195")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../ethernet/stmicro/stmmac/dwmac-mediatek.c | 26 -------------------
1 file changed, 26 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index d42e1afb65213..2f7d8e4561d92 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -90,7 +90,6 @@ struct mediatek_dwmac_plat_data {
struct mediatek_dwmac_variant {
int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat);
int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat);
- void (*dwmac_fix_mac_speed)(void *priv, unsigned int speed);
/* clock ids to be requested */
const char * const *clk_list;
@@ -443,32 +442,9 @@ static int mt8195_set_delay(struct mediatek_dwmac_plat_data *plat)
return 0;
}
-static void mt8195_fix_mac_speed(void *priv, unsigned int speed)
-{
- struct mediatek_dwmac_plat_data *priv_plat = priv;
-
- if ((phy_interface_mode_is_rgmii(priv_plat->phy_mode))) {
- /* prefer 2ns fixed delay which is controlled by TXC_PHASE_CTRL,
- * when link speed is 1Gbps with RGMII interface,
- * Fall back to delay macro circuit for 10/100Mbps link speed.
- */
- if (speed == SPEED_1000)
- regmap_update_bits(priv_plat->peri_regmap,
- MT8195_PERI_ETH_CTRL0,
- MT8195_RGMII_TXC_PHASE_CTRL |
- MT8195_DLY_GTXC_ENABLE |
- MT8195_DLY_GTXC_INV |
- MT8195_DLY_GTXC_STAGES,
- MT8195_RGMII_TXC_PHASE_CTRL);
- else
- mt8195_set_delay(priv_plat);
- }
-}
-
static const struct mediatek_dwmac_variant mt8195_gmac_variant = {
.dwmac_set_phy_interface = mt8195_set_interface,
.dwmac_set_delay = mt8195_set_delay,
- .dwmac_fix_mac_speed = mt8195_fix_mac_speed,
.clk_list = mt8195_dwmac_clk_l,
.num_clks = ARRAY_SIZE(mt8195_dwmac_clk_l),
.dma_bit_mask = 35,
@@ -619,8 +595,6 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
plat->bsp_priv = priv_plat;
plat->init = mediatek_dwmac_init;
plat->clks_config = mediatek_dwmac_clks_config;
- if (priv_plat->variant->dwmac_fix_mac_speed)
- plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed;
plat->safety_feat_cfg = devm_kzalloc(&pdev->dev,
sizeof(*plat->safety_feat_cfg),
--
GitLab
From eea8ce81fbb544e3caad1a1c876ba1af467b3d3c Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Thu, 5 Jan 2023 11:42:49 +0800
Subject: [PATCH 0425/1167] net: usb: cdc_ether: add support for Thales
Cinterion PLS62-W modem
This modem has 7 interfaces, 5 of them are serial interfaces and are
driven by cdc_acm, while 2 of them are wwan interfaces and are driven
by cdc_ether:
If 0: Abstract (modem)
If 1: Abstract (modem)
If 2: Abstract (modem)
If 3: Abstract (modem)
If 4: Abstract (modem)
If 5: Ethernet Networking
If 6: Ethernet Networking
Without this change, the 2 network interfaces will be named to usb0
and usb1, our QA think the names are confusing and filed a bug on it.
After applying this change, the name will be wwan0 and wwan1, and
they could work well with modem manager.
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230105034249.10433-1-hui.wang@canonical.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/usb/cdc_ether.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 8911cd2ed5343..c140edb4b6482 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -1007,6 +1007,12 @@ static const struct usb_device_id products[] = {
USB_CDC_SUBCLASS_ETHERNET,
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&wwan_info,
+}, {
+ /* Cinterion PLS62-W modem by GEMALTO/THALES */
+ USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x005b, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET,
+ USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&wwan_info,
}, {
/* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */
USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM,
--
GitLab
From c45219cba101f32853d011da2ba46a1b2338dc4c Mon Sep 17 00:00:00 2001
From: Pierre-Olivier Mercier <nemunaire@nemunai.re>
Date: Thu, 5 Jan 2023 13:02:08 +0100
Subject: [PATCH 0426/1167] Revert "arm64: dts: meson-sm1-odroid-hc4: disable
unused USB PHY0"
This reverts commit 703e84d6615a4a95fb504c8f2e4c9426b86f3930.
USB device enumeration was not working on Odroid HC4 as both USB2 PHYs
need to be enabled. This is inherited from the GLX USB design [1].
[1]: https://lore.kernel.org/all/20170814224542.18257-1-martin.blumenstingl@googlemail.com/T/
Signed-off-by: Pierre-Olivier Mercier <nemunaire@nemunai.re>
Acked-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://lore.kernel.org/r/20230105120206.28964-1-nemunaire@nemunai.re
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
---
arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
index e3486f60645a4..a1f0c38ccadda 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts
@@ -131,10 +131,6 @@ flash@0 {
};
&usb {
- phys = <&usb2_phy1>;
- phy-names = "usb2-phy1";
-};
-
-&usb2_phy0 {
- status = "disabled";
+ phys = <&usb2_phy0>, <&usb2_phy1>;
+ phy-names = "usb2-phy0", "usb2-phy1";
};
--
GitLab
From 1a5a23b9bdf6bde0e5185ca834ff6e806cc2aaaf Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 30 Dec 2022 14:54:27 +0800
Subject: [PATCH 0427/1167] usb: fotg210-udc: fix error return code in
fotg210_udc_probe()
After commit 5f217ccd520f ("fotg210-udc: Support optional external PHY"),
the error code is re-assigned to 0 in fotg210_udc_probe(), if allocate or
map memory fails after the assignment, it can't return an error code. Set
the error code to -ENOMEM to fix this problem.
Fixes: 5f217ccd520f ("fotg210-udc: Support optional external PHY")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20221230065427.944586-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/fotg210/fotg210-udc.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c
index 66e1b7ee3346e..87cca81bf4ac9 100644
--- a/drivers/usb/fotg210/fotg210-udc.c
+++ b/drivers/usb/fotg210/fotg210-udc.c
@@ -1201,6 +1201,8 @@ int fotg210_udc_probe(struct platform_device *pdev)
dev_info(dev, "found and initialized PHY\n");
}
+ ret = -ENOMEM;
+
for (i = 0; i < FOTG210_MAX_NUM_EP; i++) {
fotg210->ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL);
if (!fotg210->ep[i])
--
GitLab
From 0688773f0710528e1ab302c3d6317e269f2e2e6e Mon Sep 17 00:00:00 2001
From: Patrick Thompson <ptf@google.com>
Date: Tue, 20 Dec 2022 15:58:26 -0500
Subject: [PATCH 0428/1167] drm: Add orientation quirk for Lenovo ideapad
D330-10IGL
Panel is 800x1280 but mounted on a detachable form factor sideways.
Signed-off-by: Patrick Thompson <ptf@google.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20221220205826.178008-1-ptf@google.com
---
drivers/gpu/drm/drm_panel_orientation_quirks.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 52d8800a8ab86..3659f0465a724 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -304,6 +304,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"),
},
.driver_data = (void *)&lcd1200x1920_rightside_up,
+ }, { /* Lenovo Ideapad D330-10IGL (HD) */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* Lenovo Yoga Book X90F / X91F / X91L */
.matches = {
/* Non exact match to match all versions */
--
GitLab
From 8a758d98dba380a7d32a98b0840ad707e3036233 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 20 Oct 2022 23:17:06 +0100
Subject: [PATCH 0429/1167] rxrpc: Stash the network namespace pointer in
rxrpc_local
Stash the network namespace pointer in the rxrpc_local struct in addition
to a pointer to the rxrpc-specific net namespace info. Use this to remove
some places where the socket is passed as a parameter.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/ar-internal.h | 10 +++++-----
net/rxrpc/call_accept.c | 2 +-
net/rxrpc/conn_client.c | 2 +-
net/rxrpc/local_object.c | 7 ++++---
net/rxrpc/peer_object.c | 23 ++++++++++-------------
5 files changed, 21 insertions(+), 23 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 18092526d3c82..9cf763c338bcd 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -283,7 +283,8 @@ struct rxrpc_local {
struct rcu_head rcu;
atomic_t active_users; /* Number of users of the local endpoint */
refcount_t ref; /* Number of references to the structure */
- struct rxrpc_net *rxnet; /* The network ns in which this resides */
+ struct net *net; /* The network namespace */
+ struct rxrpc_net *rxnet; /* Our bits in the network namespace */
struct hlist_node link;
struct socket *socket; /* my UDP socket */
struct task_struct *io_thread;
@@ -1063,12 +1064,11 @@ void rxrpc_peer_keepalive_worker(struct work_struct *);
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+ struct sockaddr_rxrpc *srx, gfp_t gfp);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t,
enum rxrpc_peer_trace);
-void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index c02401656fa98..c957e4415cdc4 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -280,7 +280,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
- rxrpc_new_incoming_peer(rx, local, peer);
+ rxrpc_new_incoming_peer(local, peer);
}
/* Now allocate and set up the connection */
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 87efa0373aed3..e4063c4f4bb24 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -378,7 +378,7 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
+ cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp);
if (!cp->peer)
goto error;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 270b63d8f37a6..c0ac2fe07ec48 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -85,7 +85,7 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
/*
* Allocate a new local endpoint.
*/
-static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
+static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
@@ -94,7 +94,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
if (local) {
refcount_set(&local->ref, 1);
atomic_set(&local->active_users, 1);
- local->rxnet = rxnet;
+ local->net = net;
+ local->rxnet = rxrpc_net(net);
INIT_HLIST_NODE(&local->link);
init_rwsem(&local->defrag_sem);
init_completion(&local->io_thread_ready);
@@ -248,7 +249,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net,
goto found;
}
- local = rxrpc_alloc_local(rxnet, srx);
+ local = rxrpc_alloc_local(net, srx);
if (!local)
goto nomem;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 4eecea2be307b..8d7a715a0bb1c 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -147,10 +147,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
* assess the MTU size for the network interface through which this peer is
* reached
*/
-static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
+static void rxrpc_assess_MTU_size(struct rxrpc_local *local,
struct rxrpc_peer *peer)
{
- struct net *net = sock_net(&rx->sk);
+ struct net *net = local->net;
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
@@ -236,11 +236,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp,
/*
* Initialise peer record.
*/
-static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
+static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer,
unsigned long hash_key)
{
peer->hash_key = hash_key;
- rxrpc_assess_MTU_size(rx, peer);
+ rxrpc_assess_MTU_size(local, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
@@ -272,8 +272,7 @@ static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
/*
* Set up a new peer.
*/
-static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
@@ -285,7 +284,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
}
_leave(" = %p", peer);
@@ -304,14 +303,13 @@ static void rxrpc_free_peer(struct rxrpc_peer *peer)
* since we've already done a search in the list from the non-reentrant context
* (the data_ready handler) that is the only place we can add new peers.
*/
-void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
- struct rxrpc_peer *peer)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
@@ -322,8 +320,7 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
/*
* obtain a remote transport endpoint for the specified address
*/
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
@@ -343,7 +340,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
- candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
+ candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
--
GitLab
From 5040011d073d3acdeb58af2b64f84e33bb03abd2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 2 Nov 2022 10:24:29 +0000
Subject: [PATCH 0430/1167] rxrpc: Make the local endpoint hold a ref on a
connected call
Make the local endpoint and it's I/O thread hold a reference on a connected
call until that call is disconnected. Without this, we're reliant on
either the AF_RXRPC socket to hold a ref (which is dropped when the call is
released) or a queued work item to hold a ref (the work item is being
replaced with the I/O thread).
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 3 +++
net/rxrpc/call_object.c | 2 ++
net/rxrpc/conn_client.c | 6 +++---
net/rxrpc/conn_object.c | 25 +++++++++++++++----------
4 files changed, 23 insertions(+), 13 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 5f9dd73895364..b526d982da7ea 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -148,6 +148,7 @@
E_(rxrpc_client_to_idle, "->Idle")
#define rxrpc_call_traces \
+ EM(rxrpc_call_get_io_thread, "GET iothread") \
EM(rxrpc_call_get_input, "GET input ") \
EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \
EM(rxrpc_call_get_notify_socket, "GET notify ") \
@@ -160,6 +161,7 @@
EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \
EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \
EM(rxrpc_call_put_discard_error, "PUT disc-err") \
+ EM(rxrpc_call_put_io_thread, "PUT iothread") \
EM(rxrpc_call_put_input, "PUT input ") \
EM(rxrpc_call_put_kernel, "PUT kernel ") \
EM(rxrpc_call_put_poke, "PUT poke ") \
@@ -173,6 +175,7 @@
EM(rxrpc_call_see_activate_client, "SEE act-clnt") \
EM(rxrpc_call_see_connect_failed, "SEE con-fail") \
EM(rxrpc_call_see_connected, "SEE connect ") \
+ EM(rxrpc_call_see_disconnected, "SEE disconn ") \
EM(rxrpc_call_see_distribute_error, "SEE dist-err") \
EM(rxrpc_call_see_input, "SEE input ") \
EM(rxrpc_call_see_release, "SEE release ") \
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 89dcf60b11587..239fc3c750790 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -453,6 +453,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
BUG();
}
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+
/* Set the channel for this call. We don't get channel_lock as we're
* only defending against the data_ready handler (which we're called
* from) and the RESPONSE packet parser (which is only really
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index e4063c4f4bb24..1edd65883c55a 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -725,8 +725,11 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+
bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
if (IS_ERR(bundle)) {
+ rxrpc_put_call(call, rxrpc_call_get_io_thread);
ret = PTR_ERR(bundle);
goto out;
}
@@ -820,7 +823,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
_enter("c=%x", call->debug_id);
spin_lock(&bundle->channel_lock);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
/* Calls that have never actually been assigned a channel can simply be
* discarded.
@@ -912,8 +914,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
out:
spin_unlock(&bundle->channel_lock);
- _leave("");
- return;
}
/*
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 3c8f83dacb2b3..2bd3f62888956 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -178,6 +178,9 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
{
struct rxrpc_connection *conn = call->conn;
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ rxrpc_see_call(call, rxrpc_call_see_disconnected);
+
call->peer->cong_ssthresh = call->cong_ssthresh;
if (!hlist_unhashed(&call->error_link)) {
@@ -186,18 +189,20 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
spin_unlock(&call->peer->lock);
}
- if (rxrpc_is_client_call(call))
- return rxrpc_disconnect_client_call(conn->bundle, call);
+ if (rxrpc_is_client_call(call)) {
+ rxrpc_disconnect_client_call(conn->bundle, call);
+ } else {
+ spin_lock(&conn->bundle->channel_lock);
+ __rxrpc_disconnect_call(conn, call);
+ spin_unlock(&conn->bundle->channel_lock);
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
+ conn->idle_timestamp = jiffies;
+ if (atomic_dec_and_test(&conn->active))
+ rxrpc_set_service_reap_timer(conn->rxnet,
+ jiffies + rxrpc_connection_expiry);
+ }
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- conn->idle_timestamp = jiffies;
- if (atomic_dec_and_test(&conn->active))
- rxrpc_set_service_reap_timer(conn->rxnet,
- jiffies + rxrpc_connection_expiry);
+ rxrpc_put_call(call, rxrpc_call_put_io_thread);
}
/*
--
GitLab
From 30df927b936b2ef21eb07dce9c141c7897609643 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Sat, 8 Oct 2022 14:33:50 +0100
Subject: [PATCH 0431/1167] rxrpc: Separate call retransmission from other conn
events
Call the rxrpc_conn_retransmit_call() directly from rxrpc_input_packet()
rather than calling it via connection event handling.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/ar-internal.h | 2 ++
net/rxrpc/conn_event.c | 34 +++++-----------------------------
net/rxrpc/io_thread.c | 2 +-
3 files changed, 8 insertions(+), 30 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 9cf763c338bcd..f3b8806e72411 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -897,6 +897,8 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *);
/*
* conn_event.c
*/
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb,
+ unsigned int channel);
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 480364bcbf855..dfd29882126f6 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -19,9 +19,9 @@
/*
* Retransmit terminal ACK or ABORT of the previous call.
*/
-static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- unsigned int channel)
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ struct sk_buff *skb,
+ unsigned int channel)
{
struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL;
struct rxrpc_channel *chan;
@@ -292,24 +292,6 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
- case RXRPC_PACKET_TYPE_BUSY:
- /* Just ignore BUSY packets for now. */
- return 0;
-
- case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
-
case RXRPC_PACKET_TYPE_CHALLENGE:
return conn->security->respond_to_challenge(conn, skb,
_abort_code);
@@ -504,18 +486,12 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
_leave(" = -ECONNABORTED [%u]", conn->state);
- return -ECONNABORTED;
+ return 0;
}
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
return 0;
@@ -526,7 +502,7 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
+ return 0;
case RXRPC_PACKET_TYPE_CHALLENGE:
case RXRPC_PACKET_TYPE_RESPONSE:
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 1ad067d66fb60..0e1a548d35f8e 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -358,7 +358,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
sp->hdr.seq,
sp->hdr.serial,
sp->hdr.flags);
- rxrpc_input_conn_packet(conn, skb);
+ rxrpc_conn_retransmit_call(conn, skb, channel);
return 0;
}
--
GitLab
From a343b174b4bdde851033996960bca5ad1394d04b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 12 Oct 2022 22:17:56 +0100
Subject: [PATCH 0432/1167] rxrpc: Only set/transmit aborts in the I/O thread
Only set the abort call completion state in the I/O thread and only
transmit ABORT packets from there. rxrpc_abort_call() can then be made to
actually send the packet.
Further, ABORT packets should only be sent if the call has been exposed to
the network (ie. at least one attempted DATA transmission has occurred for
it).
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 1 +
net/rxrpc/ar-internal.h | 7 ++++++-
net/rxrpc/call_event.c | 16 +++++++++++++---
net/rxrpc/call_object.c | 7 ++++---
net/rxrpc/input.c | 6 ++----
net/rxrpc/recvmsg.c | 2 ++
net/rxrpc/sendmsg.c | 29 ++++++++++++++++++++++-------
7 files changed, 50 insertions(+), 18 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index b526d982da7ea..c44cc01de7501 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -17,6 +17,7 @@
* Declare tracing information enums and their string mappings for display.
*/
#define rxrpc_call_poke_traces \
+ EM(rxrpc_call_poke_abort, "Abort") \
EM(rxrpc_call_poke_error, "Error") \
EM(rxrpc_call_poke_idle, "Idle") \
EM(rxrpc_call_poke_start, "Start") \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index f3b8806e72411..0cf28a56aec5d 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -625,7 +625,10 @@ struct rxrpc_call {
unsigned long events;
spinlock_t notify_lock; /* Kernel notification lock */
rwlock_t state_lock; /* lock for state transition */
- u32 abort_code; /* Local/remote abort code */
+ const char *send_abort_why; /* String indicating why the abort was sent */
+ s32 send_abort; /* Abort code to be sent */
+ short send_abort_err; /* Error to be associated with the abort */
+ s32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
enum rxrpc_call_state state; /* current state of call */
enum rxrpc_call_completion completion; /* Call completion condition */
@@ -1146,6 +1149,8 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *,
/*
* sendmsg.c
*/
+bool rxrpc_propose_abort(struct rxrpc_call *call,
+ u32 abort_code, int error, const char *why);
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index b2cf448fb02c0..b7efecf5ccfc0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -270,9 +270,11 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call)
{
struct rxrpc_txbuf *txb;
- if (rxrpc_is_client_call(call) &&
- !test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+ if (list_empty(&call->tx_sendmsg))
+ return;
rxrpc_expose_client_call(call);
+ }
while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
struct rxrpc_txbuf, call_link))) {
@@ -336,6 +338,7 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
unsigned long now, next, t;
rxrpc_serial_t ackr_serial;
bool resend = false, expired = false;
+ s32 abort_code;
rxrpc_see_call(call, rxrpc_call_see_input);
@@ -346,6 +349,14 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
if (call->state == RXRPC_CALL_COMPLETE)
goto out;
+ /* Handle abort request locklessly, vs rxrpc_propose_abort(). */
+ abort_code = smp_load_acquire(&call->send_abort);
+ if (abort_code) {
+ rxrpc_abort_call(call->send_abort_why, call, 0, call->send_abort,
+ call->send_abort_err);
+ goto out;
+ }
+
if (skb && skb->mark == RXRPC_SKB_MARK_ERROR)
goto out;
@@ -433,7 +444,6 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
} else {
rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
}
- rxrpc_send_abort_packet(call);
goto out;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 239fc3c750790..298b7c465d7ee 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -430,6 +430,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
call->state = RXRPC_CALL_SERVER_SECURING;
call->cong_tstamp = skb->tstamp;
+ __set_bit(RXRPC_CALL_EXPOSED, &call->flags);
+
spin_lock(&conn->state_lock);
switch (conn->state) {
@@ -590,7 +592,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del(&call->accept_link);
- rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKR");
rxrpc_put_call(call, rxrpc_call_put_release_sock_tba);
}
@@ -598,8 +600,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->sock_calls.next,
struct rxrpc_call, sock_link);
rxrpc_get_call(call, rxrpc_call_get_release_sock);
- rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
- rxrpc_send_abort_packet(call);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKT");
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put_release_sock);
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index d0e20e946e48d..1f03a286620d5 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -12,8 +12,7 @@
static void rxrpc_proto_abort(const char *why,
struct rxrpc_call *call, rxrpc_seq_t seq)
{
- if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG);
}
/*
@@ -1007,8 +1006,7 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
case RXRPC_CALL_COMPLETE:
break;
default:
- if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN);
trace_rxrpc_improper_term(call);
break;
}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 6ebd6440a2b7c..a4ccdc006d0fe 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -134,6 +134,8 @@ bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
write_lock(&call->state_lock);
ret = __rxrpc_abort_call(why, call, seq, abort_code, error);
write_unlock(&call->state_lock);
+ if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ rxrpc_send_abort_packet(call);
return ret;
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index cde1e65f16b45..dc3c2a834fc8b 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -17,6 +17,26 @@
#include <net/af_rxrpc.h>
#include "ar-internal.h"
+/*
+ * Propose an abort to be made in the I/O thread.
+ */
+bool rxrpc_propose_abort(struct rxrpc_call *call,
+ u32 abort_code, int error, const char *why)
+{
+ _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+
+ if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) {
+ call->send_abort_why = why;
+ call->send_abort_err = error;
+ /* Request abort locklessly vs rxrpc_input_call_event(). */
+ smp_store_release(&call->send_abort, abort_code);
+ rxrpc_poke_call(call, rxrpc_call_poke_abort);
+ return true;
+ }
+
+ return false;
+}
+
/*
* Return true if there's sufficient Tx queue space.
*/
@@ -663,9 +683,8 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
+ rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, "CMD");
ret = 0;
- if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED))
- ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else {
@@ -760,11 +779,7 @@ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
-
- aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
- if (aborted)
- rxrpc_send_abort_packet(call);
-
+ aborted = rxrpc_propose_abort(call, abort_code, error, why);
mutex_unlock(&call->user_mutex);
return aborted;
}
--
GitLab
From 03fc55adf8761c546d72798264b019c9f672c578 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 12 Oct 2022 17:01:25 +0100
Subject: [PATCH 0433/1167] rxrpc: Only disconnect calls in the I/O thread
Only perform call disconnection in the I/O thread to reduce the locking
requirement.
This is the first part of a fix for a race that exists between call
connection and call disconnection whereby the data transmission code adds
the call to the peer error distribution list after the call has been
disconnected (say by the rxrpc socket getting closed).
The fix is to complete the process of moving call connection, data
transmission and call disconnection into the I/O thread and thus forcibly
serialising them.
Note that the issue may predate the overhaul to an I/O thread model that
were included in the merge window for v6.2, but the timing is very much
changed by the change given below.
Fixes: cf37b5987508 ("rxrpc: Move DATA transmission into call processor work item")
Reported-by: syzbot+c22650d2844392afdcfd@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 1 +
net/rxrpc/call_event.c | 7 ++++++-
net/rxrpc/call_object.c | 9 +--------
net/rxrpc/input.c | 6 ------
net/rxrpc/recvmsg.c | 1 +
5 files changed, 9 insertions(+), 15 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index c44cc01de7501..eac513668e333 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -18,6 +18,7 @@
*/
#define rxrpc_call_poke_traces \
EM(rxrpc_call_poke_abort, "Abort") \
+ EM(rxrpc_call_poke_complete, "Compl") \
EM(rxrpc_call_poke_error, "Error") \
EM(rxrpc_call_poke_idle, "Idle") \
EM(rxrpc_call_poke_start, "Start") \
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index b7efecf5ccfc0..b2fc3fa686ece 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -484,8 +484,13 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
}
out:
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (call->state == RXRPC_CALL_COMPLETE) {
del_timer_sync(&call->timer);
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
+ rxrpc_disconnect_call(call);
+ if (call->security)
+ call->security->free_call_crypto(call);
+ }
if (call->acks_hard_ack != call->tx_bottom)
rxrpc_shrink_call_tx_buffer(call);
_leave("");
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 298b7c465d7ee..13aac3ca03a03 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -50,7 +50,7 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what)
struct rxrpc_local *local = call->local;
bool busy;
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) {
spin_lock_bh(&local->lock);
busy = !list_empty(&call->attend_link);
trace_rxrpc_poke_call(call, busy, what);
@@ -533,13 +533,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
call->flags, rxrpc_call_see_release);
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
-
if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags))
BUG();
rxrpc_put_call_slot(call);
- del_timer_sync(&call->timer);
/* Make sure we don't get any more notifications */
write_lock(&rx->recvmsg_lock);
@@ -572,10 +569,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
- if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
- rxrpc_disconnect_call(call);
- if (call->security)
- call->security->free_call_crypto(call);
_leave("");
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 1f03a286620d5..bb4beb4453259 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -997,8 +997,6 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb)
*/
void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
{
- struct rxrpc_connection *conn = call->conn;
-
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
@@ -1012,8 +1010,4 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
}
rxrpc_input_call_event(call, skb);
-
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index a4ccdc006d0fe..8d5fe65f5951c 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -201,6 +201,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
case RXRPC_CALL_CLIENT_RECV_REPLY:
__rxrpc_call_completed(call);
write_unlock(&call->state_lock);
+ rxrpc_poke_call(call, rxrpc_call_poke_complete);
break;
case RXRPC_CALL_SERVER_RECV_REQUEST:
--
GitLab
From f2cce89a074e6d2991dddc94f6b6ebe1576b8459 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 20 Oct 2022 09:08:34 +0100
Subject: [PATCH 0434/1167] rxrpc: Implement a mechanism to send an event
notification to a connection
Provide a means by which an event notification can be sent to a connection
through such that the I/O thread can pick it up and handle it rather than
doing it in a separate workqueue.
This is then used to move the deferred final ACK of a call into the I/O
thread rather than a separate work queue as part of the drive to do all
transmission from the I/O thread.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 5 ++---
net/rxrpc/ar-internal.h | 5 +++++
net/rxrpc/conn_event.c | 14 ++++++++++----
net/rxrpc/conn_object.c | 20 +++++++++++++++++++-
net/rxrpc/io_thread.c | 19 ++++++++++++++++++-
net/rxrpc/local_object.c | 1 +
6 files changed, 55 insertions(+), 9 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index eac513668e333..b969756f97fce 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -111,7 +111,7 @@
EM(rxrpc_conn_get_call_input, "GET inp-call") \
EM(rxrpc_conn_get_conn_input, "GET inp-conn") \
EM(rxrpc_conn_get_idle, "GET idle ") \
- EM(rxrpc_conn_get_poke, "GET poke ") \
+ EM(rxrpc_conn_get_poke_timer, "GET poke ") \
EM(rxrpc_conn_get_service_conn, "GET svc-conn") \
EM(rxrpc_conn_new_client, "NEW client ") \
EM(rxrpc_conn_new_service, "NEW service ") \
@@ -126,10 +126,9 @@
EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \
EM(rxrpc_conn_put_unbundle, "PUT unbundle") \
EM(rxrpc_conn_put_unidle, "PUT unidle ") \
+ EM(rxrpc_conn_put_work, "PUT work ") \
EM(rxrpc_conn_queue_challenge, "QUE chall ") \
- EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \
EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \
- EM(rxrpc_conn_queue_timer, "QUE timer ") \
EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \
EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \
E_(rxrpc_conn_see_work, "SEE work ")
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 0cf28a56aec5d..d82d7f36cdaa0 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -202,6 +202,7 @@ struct rxrpc_host_header {
* - max 48 bytes (struct sk_buff::cb)
*/
struct rxrpc_skb_priv {
+ struct rxrpc_connection *conn; /* Connection referred to (poke packet) */
u16 offset; /* Offset of data */
u16 len; /* Length of data */
u8 flags;
@@ -292,6 +293,7 @@ struct rxrpc_local {
struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */
struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */
struct sk_buff_head rx_queue; /* Received packets */
+ struct list_head conn_attend_q; /* Conns requiring immediate attention */
struct list_head call_attend_q; /* Calls requiring immediate attention */
struct rb_root client_bundles; /* Client connection bundles by socket params */
spinlock_t client_bundles_lock; /* Lock for client_bundles */
@@ -441,6 +443,7 @@ struct rxrpc_connection {
struct rxrpc_peer *peer; /* Remote endpoint */
struct rxrpc_net *rxnet; /* Network namespace to which call belongs */
struct key *key; /* Security details */
+ struct list_head attend_link; /* Link in local->conn_attend_q */
refcount_t ref;
atomic_t active; /* Active count for service conns */
@@ -905,6 +908,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *s
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb);
/*
* conn_object.c
@@ -912,6 +916,7 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
extern unsigned int rxrpc_connection_expiry;
extern unsigned int rxrpc_closed_conn_expiry;
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why);
struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t);
struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *,
struct sockaddr_rxrpc *,
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index dfd29882126f6..7a980a32344f1 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -412,10 +412,6 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
- /* Process delayed ACKs whose time has come. */
- if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
- rxrpc_process_delayed_final_acks(conn, false);
-
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
@@ -515,3 +511,13 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
return -EPROTO;
}
}
+
+/*
+ * Input a connection event.
+ */
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
+{
+ /* Process delayed ACKs whose time has come. */
+ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
+ rxrpc_process_delayed_final_acks(conn, false);
+}
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 2bd3f62888956..281f59e356f5d 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -23,12 +23,30 @@ static void rxrpc_clean_up_connection(struct work_struct *work);
static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
unsigned long reap_at);
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why)
+{
+ struct rxrpc_local *local = conn->local;
+ bool busy;
+
+ if (WARN_ON_ONCE(!local))
+ return;
+
+ spin_lock_bh(&local->lock);
+ busy = !list_empty(&conn->attend_link);
+ if (!busy) {
+ rxrpc_get_connection(conn, why);
+ list_add_tail(&conn->attend_link, &local->conn_attend_q);
+ }
+ spin_unlock_bh(&local->lock);
+ rxrpc_wake_up_io_thread(local);
+}
+
static void rxrpc_connection_timer(struct timer_list *timer)
{
struct rxrpc_connection *conn =
container_of(timer, struct rxrpc_connection, timer);
- rxrpc_queue_conn(conn, rxrpc_conn_queue_timer);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer);
}
/*
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 0e1a548d35f8e..46e58cf5bc96e 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -421,6 +421,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
*/
int rxrpc_io_thread(void *data)
{
+ struct rxrpc_connection *conn;
struct sk_buff_head rx_queue;
struct rxrpc_local *local = data;
struct rxrpc_call *call;
@@ -436,6 +437,20 @@ int rxrpc_io_thread(void *data)
for (;;) {
rxrpc_inc_stat(local->rxnet, stat_io_loop);
+ /* Deal with connections that want immediate attention. */
+ conn = list_first_entry_or_null(&local->conn_attend_q,
+ struct rxrpc_connection,
+ attend_link);
+ if (conn) {
+ spin_lock_bh(&local->lock);
+ list_del_init(&conn->attend_link);
+ spin_unlock_bh(&local->lock);
+
+ rxrpc_input_conn_event(conn, NULL);
+ rxrpc_put_connection(conn, rxrpc_conn_put_poke);
+ continue;
+ }
+
/* Deal with calls that want immediate attention. */
if ((call = list_first_entry_or_null(&local->call_attend_q,
struct rxrpc_call,
@@ -463,6 +478,7 @@ int rxrpc_io_thread(void *data)
rxrpc_input_error(local, skb);
rxrpc_free_skb(skb, rxrpc_skb_put_error_report);
break;
+ break;
default:
WARN_ON_ONCE(1);
rxrpc_free_skb(skb, rxrpc_skb_put_unknown);
@@ -481,7 +497,8 @@ int rxrpc_io_thread(void *data)
set_current_state(TASK_INTERRUPTIBLE);
should_stop = kthread_should_stop();
if (!skb_queue_empty(&local->rx_queue) ||
- !list_empty(&local->call_attend_q)) {
+ !list_empty(&local->call_attend_q) ||
+ !list_empty(&local->conn_attend_q)) {
__set_current_state(TASK_RUNNING);
continue;
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index c0ac2fe07ec48..8ef6cd8defa45 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -100,6 +100,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
init_rwsem(&local->defrag_sem);
init_completion(&local->io_thread_ready);
skb_queue_head_init(&local->rx_queue);
+ INIT_LIST_HEAD(&local->conn_attend_q);
INIT_LIST_HEAD(&local->call_attend_q);
local->client_bundles = RB_ROOT;
spin_lock_init(&local->client_bundles_lock);
--
GitLab
From a00ce28b1778fa3576575b43bdb17f60ded38b66 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 20 Oct 2022 09:56:36 +0100
Subject: [PATCH 0435/1167] rxrpc: Clean up connection abort
Clean up connection abort, using the connection state_lock to gate access
to change that state, and use an rxrpc_call_completion value to indicate
the difference between local and remote aborts as these can be pasted
directly into the call state.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 2 +
net/rxrpc/ar-internal.h | 46 ++++---
net/rxrpc/call_object.c | 8 +-
net/rxrpc/conn_event.c | 233 ++++++++++++-----------------------
net/rxrpc/insecure.c | 18 +--
net/rxrpc/output.c | 56 +++++++++
net/rxrpc/proc.c | 10 +-
net/rxrpc/rxkad.c | 28 ++---
8 files changed, 188 insertions(+), 213 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index b969756f97fce..222d0498d23fc 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -111,6 +111,7 @@
EM(rxrpc_conn_get_call_input, "GET inp-call") \
EM(rxrpc_conn_get_conn_input, "GET inp-conn") \
EM(rxrpc_conn_get_idle, "GET idle ") \
+ EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \
EM(rxrpc_conn_get_poke_timer, "GET poke ") \
EM(rxrpc_conn_get_service_conn, "GET svc-conn") \
EM(rxrpc_conn_new_client, "NEW client ") \
@@ -128,6 +129,7 @@
EM(rxrpc_conn_put_unidle, "PUT unidle ") \
EM(rxrpc_conn_put_work, "PUT work ") \
EM(rxrpc_conn_queue_challenge, "QUE chall ") \
+ EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \
EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \
EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \
EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index d82d7f36cdaa0..78bd6fb0bc154 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -263,13 +263,11 @@ struct rxrpc_security {
/* respond to a challenge */
int (*respond_to_challenge)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* verify a response */
int (*verify_response)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* clear connection security */
void (*clear)(struct rxrpc_connection *);
@@ -367,6 +365,18 @@ struct rxrpc_conn_parameters {
u32 security_level; /* Security level selected */
};
+/*
+ * Call completion condition (state == RXRPC_CALL_COMPLETE).
+ */
+enum rxrpc_call_completion {
+ RXRPC_CALL_SUCCEEDED, /* - Normal termination */
+ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
+ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
+ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
+ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
+ NR__RXRPC_CALL_COMPLETIONS
+};
+
/*
* Bits in the connection flags.
*/
@@ -391,6 +401,7 @@ enum rxrpc_conn_flag {
*/
enum rxrpc_conn_event {
RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */
+ RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */
};
/*
@@ -403,8 +414,7 @@ enum rxrpc_conn_proto_state {
RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */
RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */
RXRPC_CONN_SERVICE, /* Service secured connection */
- RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */
- RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */
+ RXRPC_CONN_ABORTED, /* Conn aborted */
RXRPC_CONN__NR_STATES
};
@@ -487,7 +497,8 @@ struct rxrpc_connection {
unsigned long idle_timestamp; /* Time at which last became idle */
spinlock_t state_lock; /* state-change lock */
enum rxrpc_conn_proto_state state; /* current state of connection */
- u32 abort_code; /* Abort code of connection abort */
+ enum rxrpc_call_completion completion; /* Completion condition */
+ s32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
@@ -561,18 +572,6 @@ enum rxrpc_call_state {
NR__RXRPC_CALL_STATES
};
-/*
- * Call completion condition (state == RXRPC_CALL_COMPLETE).
- */
-enum rxrpc_call_completion {
- RXRPC_CALL_SUCCEEDED, /* - Normal termination */
- RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
- RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
- RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
- RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
- NR__RXRPC_CALL_COMPLETIONS
-};
-
/*
* Call Tx congestion management modes.
*/
@@ -905,11 +904,19 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *);
*/
void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb,
unsigned int channel);
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, const char *why);
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb);
+static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn)
+{
+ /* Order reading the abort info after the state check. */
+ return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED;
+}
+
/*
* conn_object.c
*/
@@ -1059,6 +1066,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net)
int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
int rxrpc_send_abort_packet(struct rxrpc_call *);
int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *);
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn);
void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb);
void rxrpc_send_keepalive(struct rxrpc_peer *);
void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 13aac3ca03a03..666430182dfd6 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -443,14 +443,10 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
break;
- case RXRPC_CONN_REMOTELY_ABORTED:
- __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
+ case RXRPC_CONN_ABORTED:
+ __rxrpc_set_call_completion(call, conn->completion,
conn->abort_code, conn->error);
break;
- case RXRPC_CONN_LOCALLY_ABORTED:
- __rxrpc_abort_call("CON", call, 1,
- conn->abort_code, conn->error);
- break;
default:
BUG();
}
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 7a980a32344f1..753d91a9646fc 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -16,6 +16,60 @@
#include <net/ip.h>
#include "ar-internal.h"
+/*
+ * Set the completion state on an aborted connection.
+ */
+static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err,
+ enum rxrpc_call_completion compl)
+{
+ bool aborted = false;
+
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ spin_lock(&conn->state_lock);
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ conn->abort_code = abort_code;
+ conn->error = err;
+ conn->completion = compl;
+ /* Order the abort info before the state change. */
+ smp_store_release(&conn->state, RXRPC_CONN_ABORTED);
+ set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
+ set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events);
+ aborted = true;
+ }
+ spin_unlock(&conn->state_lock);
+ }
+
+ return aborted;
+}
+
+/*
+ * Mark a socket buffer to indicate that the connection it's on should be aborted.
+ */
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, const char *why)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ if (rxrpc_set_conn_aborted(conn, skb, abort_code, err,
+ RXRPC_CALL_LOCALLY_ABORTED)) {
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber,
+ sp->hdr.seq, abort_code, err);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort);
+ }
+ return -EPROTO;
+}
+
+/*
+ * Mark a connection as being remotely aborted.
+ */
+static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn,
+ struct sk_buff *skb)
+{
+ return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED,
+ RXRPC_CALL_REMOTELY_ABORTED);
+}
+
/*
* Retransmit terminal ACK or ABORT of the previous call.
*/
@@ -146,9 +200,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
/*
* pass a connection-level abort onto all calls on that connection
*/
-static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl,
- rxrpc_serial_t serial)
+static void rxrpc_abort_calls(struct rxrpc_connection *conn)
{
struct rxrpc_call *call;
int i;
@@ -161,102 +213,17 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
call = rcu_dereference_protected(
conn->channels[i].call,
lockdep_is_held(&conn->bundle->channel_lock));
- if (call) {
- if (compl == RXRPC_CALL_LOCALLY_ABORTED)
- trace_rxrpc_abort(call->debug_id,
- "CON", call->cid,
- call->call_id, 0,
- conn->abort_code,
- conn->error);
- else
- trace_rxrpc_rx_abort(call, serial,
- conn->abort_code);
- rxrpc_set_call_completion(call, compl,
+ if (call)
+ rxrpc_set_call_completion(call,
+ conn->completion,
conn->abort_code,
conn->error);
- }
}
spin_unlock(&conn->bundle->channel_lock);
_leave("");
}
-/*
- * generate a connection-level abort
- */
-static int rxrpc_abort_connection(struct rxrpc_connection *conn,
- int error, u32 abort_code)
-{
- struct rxrpc_wire_header whdr;
- struct msghdr msg;
- struct kvec iov[2];
- __be32 word;
- size_t len;
- u32 serial;
- int ret;
-
- _enter("%d,,%u,%u", conn->debug_id, error, abort_code);
-
- /* generate a connection-level abort */
- spin_lock(&conn->state_lock);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- spin_unlock(&conn->state_lock);
- _leave(" = 0 [already dead]");
- return 0;
- }
-
- conn->error = error;
- conn->abort_code = abort_code;
- conn->state = RXRPC_CONN_LOCALLY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- spin_unlock(&conn->state_lock);
-
- msg.msg_name = &conn->peer->srx.transport;
- msg.msg_namelen = conn->peer->srx.transport_len;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_flags = 0;
-
- whdr.epoch = htonl(conn->proto.epoch);
- whdr.cid = htonl(conn->proto.cid);
- whdr.callNumber = 0;
- whdr.seq = 0;
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
- whdr.flags = conn->out_clientflag;
- whdr.userStatus = 0;
- whdr.securityIndex = conn->security_ix;
- whdr._rsvd = 0;
- whdr.serviceId = htons(conn->service_id);
-
- word = htonl(conn->abort_code);
-
- iov[0].iov_base = &whdr;
- iov[0].iov_len = sizeof(whdr);
- iov[1].iov_base = &word;
- iov[1].iov_len = sizeof(word);
-
- len = iov[0].iov_len + iov[1].iov_len;
-
- serial = atomic_inc_return(&conn->serial);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
- whdr.serial = htonl(serial);
-
- ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
- if (ret < 0) {
- trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
- rxrpc_tx_point_conn_abort);
- _debug("sendmsg failed: %d", ret);
- return -EAGAIN;
- }
-
- trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
-
- conn->peer->last_tx_at = ktime_get_seconds();
-
- _leave(" = 0");
- return 0;
-}
-
/*
* mark a call as being on a now-secured channel
* - must be called with BH's disabled.
@@ -278,26 +245,22 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call)
* connection-level Rx packet processor
*/
static int rxrpc_process_event(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
int loop, ret;
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
+ if (conn->state == RXRPC_CONN_ABORTED)
return -ECONNABORTED;
- }
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_CHALLENGE:
- return conn->security->respond_to_challenge(conn, skb,
- _abort_code);
+ return conn->security->respond_to_challenge(conn, skb);
case RXRPC_PACKET_TYPE_RESPONSE:
- ret = conn->security->verify_response(conn, skb, _abort_code);
+ ret = conn->security->verify_response(conn, skb);
if (ret < 0)
return ret;
@@ -336,26 +299,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
*/
static void rxrpc_secure_connection(struct rxrpc_connection *conn)
{
- u32 abort_code;
- int ret;
-
- _enter("{%d}", conn->debug_id);
-
- ASSERT(conn->security_ix != 0);
-
- if (conn->security->issue_challenge(conn) < 0) {
- abort_code = RX_CALL_DEAD;
- ret = -ENOMEM;
- goto abort;
- }
-
- _leave("");
- return;
-
-abort:
- _debug("abort %d, %d", ret, abort_code);
- rxrpc_abort_connection(conn, ret, abort_code);
- _leave(" [aborted]");
+ if (conn->security->issue_challenge(conn) < 0)
+ rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, "OOM");
}
/*
@@ -406,7 +351,6 @@ void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn, bool force)
static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
{
struct sk_buff *skb;
- u32 abort_code = RX_PROTOCOL_ERROR;
int ret;
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
@@ -416,33 +360,18 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_see_conn_work);
- ret = rxrpc_process_event(conn, skb, &abort_code);
+ ret = rxrpc_process_event(conn, skb);
switch (ret) {
- case -EPROTO:
- case -EKEYEXPIRED:
- case -EKEYREJECTED:
- goto protocol_error;
case -ENOMEM:
case -EAGAIN:
- goto requeue_and_leave;
- case -ECONNABORTED:
+ skb_queue_head(&conn->rx_queue, skb);
+ rxrpc_queue_conn(conn, rxrpc_conn_queue_retry_work);
+ break;
default:
rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
break;
}
}
-
- return;
-
-requeue_and_leave:
- skb_queue_head(&conn->rx_queue, skb);
- return;
-
-protocol_error:
- if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
- goto requeue_and_leave;
- rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
- return;
}
void rxrpc_process_connection(struct work_struct *work)
@@ -480,28 +409,25 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
- return 0;
- }
-
- _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
-
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
return 0;
case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return 0;
+ if (rxrpc_is_conn_aborted(conn))
+ return true;
+ rxrpc_input_conn_abort(conn, skb);
+ rxrpc_abort_calls(conn);
+ return true;
case RXRPC_PACKET_TYPE_CHALLENGE:
case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_is_conn_aborted(conn)) {
+ if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED)
+ rxrpc_send_conn_abort(conn);
+ return true;
+ }
rxrpc_post_packet_to_conn(conn, skb);
return 0;
@@ -517,6 +443,9 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
*/
void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
{
+ if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
+ rxrpc_abort_calls(conn);
+
/* Process delayed ACKs whose time has come. */
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn, false);
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index 0eb8471bfc536..29dcc7d3f51a7 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -43,25 +43,15 @@ static void none_free_call_crypto(struct rxrpc_call *call)
}
static int none_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("chall_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN");
}
static int none_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("resp_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN");
}
static void none_clear(struct rxrpc_connection *conn)
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 3d8c9f830ee09..8a5ff2c9e0612 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -544,6 +544,62 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
goto done;
}
+/*
+ * Transmit a connection-level abort.
+ */
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
+{
+ struct rxrpc_wire_header whdr;
+ struct msghdr msg;
+ struct kvec iov[2];
+ __be32 word;
+ size_t len;
+ u32 serial;
+ int ret;
+
+ msg.msg_name = &conn->peer->srx.transport;
+ msg.msg_namelen = conn->peer->srx.transport_len;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = 0;
+
+ whdr.epoch = htonl(conn->proto.epoch);
+ whdr.cid = htonl(conn->proto.cid);
+ whdr.callNumber = 0;
+ whdr.seq = 0;
+ whdr.type = RXRPC_PACKET_TYPE_ABORT;
+ whdr.flags = conn->out_clientflag;
+ whdr.userStatus = 0;
+ whdr.securityIndex = conn->security_ix;
+ whdr._rsvd = 0;
+ whdr.serviceId = htons(conn->service_id);
+
+ word = htonl(conn->abort_code);
+
+ iov[0].iov_base = &whdr;
+ iov[0].iov_len = sizeof(whdr);
+ iov[1].iov_base = &word;
+ iov[1].iov_len = sizeof(word);
+
+ len = iov[0].iov_len + iov[1].iov_len;
+
+ serial = atomic_inc_return(&conn->serial);
+ whdr.serial = htonl(serial);
+
+ iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
+ ret = do_udp_sendmsg(conn->local->socket, &msg, len);
+ if (ret < 0) {
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_point_conn_abort);
+ _debug("sendmsg failed: %d", ret);
+ return;
+ }
+
+ trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
+
+ conn->peer->last_tx_at = ktime_get_seconds();
+}
+
/*
* Reject a packet through the local endpoint.
*/
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 3a59591ec0615..63947cce40483 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -17,8 +17,7 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
[RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ",
[RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ",
[RXRPC_CONN_SERVICE] = "SvSecure",
- [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort",
- [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort",
+ [RXRPC_CONN_ABORTED] = "Aborted ",
};
/*
@@ -143,6 +142,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
{
struct rxrpc_connection *conn;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ const char *state;
char lbuff[50], rbuff[50];
if (v == &rxnet->conn_proc_list) {
@@ -163,9 +163,11 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
}
sprintf(lbuff, "%pISpc", &conn->local->srx.transport);
-
sprintf(rbuff, "%pISpc", &conn->peer->srx.transport);
print:
+ state = rxrpc_is_conn_aborted(conn) ?
+ rxrpc_call_completions[conn->completion] :
+ rxrpc_conn_states[conn->state];
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %s %3u %3d"
" %s %08x %08x %08x %08x %08x %08x %08x\n",
@@ -176,7 +178,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
rxrpc_conn_is_service(conn) ? "Svc" : "Clt",
refcount_read(&conn->ref),
atomic_read(&conn->active),
- rxrpc_conn_states[conn->state],
+ state,
key_serial(conn->key),
atomic_read(&conn->serial),
conn->hi_serial,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index d1233720e05f2..5d2fbc6ec3cf1 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -821,8 +821,7 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn,
* respond to a challenge packet
*/
static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
const struct rxrpc_key_token *token;
struct rxkad_challenge challenge;
@@ -898,7 +897,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
ret = -EPROTO;
other_error:
- *_abort_code = abort_code;
+ rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK");
return ret;
}
@@ -910,8 +909,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
struct sk_buff *skb,
void *ticket, size_t ticket_len,
struct rxrpc_crypt *_session_key,
- time64_t *_expiry,
- u32 *_abort_code)
+ time64_t *_expiry)
{
struct skcipher_request *req;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -1042,8 +1040,7 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
abort_code = RXKADBADTICKET;
ret = -EPROTO;
other_error:
- *_abort_code = abort_code;
- return ret;
+ return rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK");
temporary_error:
return ret;
}
@@ -1086,8 +1083,7 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn,
* verify a response
*/
static int rxkad_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxkad_response *response;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -1115,11 +1111,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
abort_code = RXKADNOAUTH;
break;
}
- trace_rxrpc_abort(0, "SVK",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- abort_code, PTR_ERR(server_key));
- *_abort_code = abort_code;
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, abort_code,
+ PTR_ERR(server_key), "RXK");
}
ret = -ENOMEM;
@@ -1168,7 +1161,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
goto temporary_error_free_ticket;
ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
- &session_key, &expiry, _abort_code);
+ &session_key, &expiry);
if (ret < 0)
goto temporary_error_free_ticket;
@@ -1246,10 +1239,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
kfree(ticket);
protocol_error:
kfree(response);
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
key_put(server_key);
- *_abort_code = abort_code;
- return -EPROTO;
+ trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+ return rxrpc_abort_conn(conn, skb, abort_code, -EPROTO, "RXK");
temporary_error_free_ticket:
kfree(ticket);
--
GitLab
From 57af281e5389b6fefedb3685f86847cbb0055f75 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 6 Oct 2022 21:45:42 +0100
Subject: [PATCH 0436/1167] rxrpc: Tidy up abort generation infrastructure
Tidy up the abort generation infrastructure in the following ways:
(1) Create an enum and string mapping table to list the reasons an abort
might be generated in tracing.
(2) Replace the 3-char string with the values from (1) in the places that
use that to log the abort source. This gets rid of a memcpy() in the
tracepoint.
(3) Subsume the rxrpc_rx_eproto tracepoint with the rxrpc_abort tracepoint
and use values from (1) to indicate the trace reason.
(4) Always make a call to an abort function at the point of the abort
rather than stashing the values into variables and using goto to get
to a place where it reported. The C optimiser will collapse the calls
together as appropriate. The abort functions return a value that can
be returned directly if appropriate.
Note that this extends into afs also at the points where that generates an
abort. To aid with this, the afs sources need to #define
RXRPC_TRACE_ONLY_DEFINE_ENUMS before including the rxrpc tracing header
because they don't have access to the rxrpc internal structures that some
of the tracepoints make use of.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
fs/afs/cmservice.c | 6 +-
fs/afs/rxrpc.c | 23 ++-
include/net/af_rxrpc.h | 3 +-
include/trace/events/rxrpc.h | 140 +++++++++++----
net/rxrpc/ar-internal.h | 51 +++---
net/rxrpc/call_accept.c | 43 +++--
net/rxrpc/call_event.c | 13 +-
net/rxrpc/call_object.c | 6 +-
net/rxrpc/conn_event.c | 19 +--
net/rxrpc/input.c | 65 ++++---
net/rxrpc/insecure.c | 6 +-
net/rxrpc/io_thread.c | 163 ++++++++----------
net/rxrpc/recvmsg.c | 18 +-
net/rxrpc/rxkad.c | 321 +++++++++++++++--------------------
net/rxrpc/rxperf.c | 17 +-
net/rxrpc/security.c | 14 +-
net/rxrpc/sendmsg.c | 20 ++-
17 files changed, 484 insertions(+), 444 deletions(-)
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 7dcd59693a0c2..d4ddb20d67320 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -13,6 +13,8 @@
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
static int afs_deliver_cb_init_call_back_state(struct afs_call *);
static int afs_deliver_cb_init_call_back_state3(struct afs_call *);
@@ -191,7 +193,7 @@ static void afs_cm_destructor(struct afs_call *call)
* Abort a service call from within an action function.
*/
static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error,
- const char *why)
+ enum rxrpc_abort_reason why)
{
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
abort_code, error, why);
@@ -469,7 +471,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
afs_send_empty_reply(call);
else
- afs_abort_service_call(call, 1, 1, "K-1");
+ afs_abort_service_call(call, 1, 1, afs_abort_probeuuid_negative);
afs_put_call(call);
_leave("");
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index c62939e5ea1f0..bd3830bc67006 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -13,6 +13,8 @@
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
struct workqueue_struct *afs_async_calls;
@@ -397,7 +399,8 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
error_do_abort:
if (ret != -ECONNABORTED) {
rxrpc_kernel_abort_call(call->net->socket, rxcall,
- RX_USER_ABORT, ret, "KSD");
+ RX_USER_ABORT, ret,
+ afs_abort_send_data_error);
} else {
len = 0;
iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0);
@@ -527,7 +530,8 @@ static void afs_deliver_to_call(struct afs_call *call)
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KIV");
+ abort_code, ret,
+ afs_abort_op_not_supported);
goto local_abort;
case -EIO:
pr_err("kAFS: Call %u in bad state %u\n",
@@ -542,12 +546,14 @@ static void afs_deliver_to_call(struct afs_call *call)
if (state != AFS_CALL_CL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KUM");
+ abort_code, ret,
+ afs_abort_unmarshal_error);
goto local_abort;
default:
abort_code = RX_CALL_DEAD;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KER");
+ abort_code, ret,
+ afs_abort_general_error);
goto local_abort;
}
}
@@ -619,7 +625,8 @@ long afs_wait_for_call_to_complete(struct afs_call *call,
/* Kill off the call if it's still live. */
_debug("call interrupted");
if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- RX_USER_ABORT, -EINTR, "KWI"))
+ RX_USER_ABORT, -EINTR,
+ afs_abort_interrupted))
afs_set_call_complete(call, -EINTR, 0);
}
}
@@ -836,7 +843,8 @@ void afs_send_empty_reply(struct afs_call *call)
case -ENOMEM:
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
fallthrough;
default:
_leave(" [error]");
@@ -878,7 +886,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
if (n == -ENOMEM) {
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
}
_leave(" [error]");
}
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index d5a5ae9263804..ba717eac0229a 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -15,6 +15,7 @@ struct key;
struct sock;
struct socket;
struct rxrpc_call;
+enum rxrpc_abort_reason;
enum rxrpc_interruptibility {
RXRPC_INTERRUPTIBLE, /* Call is interruptible */
@@ -55,7 +56,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
struct iov_iter *, size_t *, bool, u32 *, u16 *);
bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
- u32, int, const char *);
+ u32, int, enum rxrpc_abort_reason);
void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *);
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 222d0498d23fc..caeabd50e049c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -16,6 +16,104 @@
/*
* Declare tracing information enums and their string mappings for display.
*/
+#define rxrpc_abort_reasons \
+ /* AFS errors */ \
+ EM(afs_abort_general_error, "afs-error") \
+ EM(afs_abort_interrupted, "afs-intr") \
+ EM(afs_abort_oom, "afs-oom") \
+ EM(afs_abort_op_not_supported, "afs-op-notsupp") \
+ EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \
+ EM(afs_abort_send_data_error, "afs-send-data") \
+ EM(afs_abort_unmarshal_error, "afs-unmarshal") \
+ /* rxperf errors */ \
+ EM(rxperf_abort_general_error, "rxperf-error") \
+ EM(rxperf_abort_oom, "rxperf-oom") \
+ EM(rxperf_abort_op_not_supported, "rxperf-op-notsupp") \
+ EM(rxperf_abort_unmarshal_error, "rxperf-unmarshal") \
+ /* RxKAD security errors */ \
+ EM(rxkad_abort_1_short_check, "rxkad1-short-check") \
+ EM(rxkad_abort_1_short_data, "rxkad1-short-data") \
+ EM(rxkad_abort_1_short_encdata, "rxkad1-short-encdata") \
+ EM(rxkad_abort_1_short_header, "rxkad1-short-hdr") \
+ EM(rxkad_abort_2_short_check, "rxkad2-short-check") \
+ EM(rxkad_abort_2_short_data, "rxkad2-short-data") \
+ EM(rxkad_abort_2_short_header, "rxkad2-short-hdr") \
+ EM(rxkad_abort_2_short_len, "rxkad2-short-len") \
+ EM(rxkad_abort_bad_checksum, "rxkad2-bad-cksum") \
+ EM(rxkad_abort_chall_key_expired, "rxkad-chall-key-exp") \
+ EM(rxkad_abort_chall_level, "rxkad-chall-level") \
+ EM(rxkad_abort_chall_no_key, "rxkad-chall-nokey") \
+ EM(rxkad_abort_chall_short, "rxkad-chall-short") \
+ EM(rxkad_abort_chall_version, "rxkad-chall-version") \
+ EM(rxkad_abort_resp_bad_callid, "rxkad-resp-bad-callid") \
+ EM(rxkad_abort_resp_bad_checksum, "rxkad-resp-bad-cksum") \
+ EM(rxkad_abort_resp_bad_param, "rxkad-resp-bad-param") \
+ EM(rxkad_abort_resp_call_ctr, "rxkad-resp-call-ctr") \
+ EM(rxkad_abort_resp_call_state, "rxkad-resp-call-state") \
+ EM(rxkad_abort_resp_key_expired, "rxkad-resp-key-exp") \
+ EM(rxkad_abort_resp_key_rejected, "rxkad-resp-key-rej") \
+ EM(rxkad_abort_resp_level, "rxkad-resp-level") \
+ EM(rxkad_abort_resp_nokey, "rxkad-resp-nokey") \
+ EM(rxkad_abort_resp_ooseq, "rxkad-resp-ooseq") \
+ EM(rxkad_abort_resp_short, "rxkad-resp-short") \
+ EM(rxkad_abort_resp_short_tkt, "rxkad-resp-short-tkt") \
+ EM(rxkad_abort_resp_tkt_aname, "rxkad-resp-tk-aname") \
+ EM(rxkad_abort_resp_tkt_expired, "rxkad-resp-tk-exp") \
+ EM(rxkad_abort_resp_tkt_future, "rxkad-resp-tk-future") \
+ EM(rxkad_abort_resp_tkt_inst, "rxkad-resp-tk-inst") \
+ EM(rxkad_abort_resp_tkt_len, "rxkad-resp-tk-len") \
+ EM(rxkad_abort_resp_tkt_realm, "rxkad-resp-tk-realm") \
+ EM(rxkad_abort_resp_tkt_short, "rxkad-resp-tk-short") \
+ EM(rxkad_abort_resp_tkt_sinst, "rxkad-resp-tk-sinst") \
+ EM(rxkad_abort_resp_tkt_sname, "rxkad-resp-tk-sname") \
+ EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \
+ EM(rxkad_abort_resp_version, "rxkad-resp-version") \
+ /* rxrpc errors */ \
+ EM(rxrpc_abort_call_improper_term, "call-improper-term") \
+ EM(rxrpc_abort_call_reset, "call-reset") \
+ EM(rxrpc_abort_call_sendmsg, "call-sendmsg") \
+ EM(rxrpc_abort_call_sock_release, "call-sock-rel") \
+ EM(rxrpc_abort_call_sock_release_tba, "call-sock-rel-tba") \
+ EM(rxrpc_abort_call_timeout, "call-timeout") \
+ EM(rxrpc_abort_no_service_key, "no-serv-key") \
+ EM(rxrpc_abort_nomem, "nomem") \
+ EM(rxrpc_abort_service_not_offered, "serv-not-offered") \
+ EM(rxrpc_abort_shut_down, "shut-down") \
+ EM(rxrpc_abort_unsupported_security, "unsup-sec") \
+ EM(rxrpc_badmsg_bad_abort, "bad-abort") \
+ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \
+ EM(rxrpc_badmsg_short_ack, "short-ack") \
+ EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \
+ EM(rxrpc_badmsg_short_hdr, "short-hdr") \
+ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \
+ EM(rxrpc_badmsg_zero_call, "zero-call") \
+ EM(rxrpc_badmsg_zero_seq, "zero-seq") \
+ EM(rxrpc_badmsg_zero_service, "zero-service") \
+ EM(rxrpc_eproto_ackr_outside_window, "ackr-out-win") \
+ EM(rxrpc_eproto_ackr_sack_overflow, "ackr-sack-over") \
+ EM(rxrpc_eproto_ackr_short_sack, "ackr-short-sack") \
+ EM(rxrpc_eproto_ackr_zero, "ackr-zero") \
+ EM(rxrpc_eproto_bad_upgrade, "bad-upgrade") \
+ EM(rxrpc_eproto_data_after_last, "data-after-last") \
+ EM(rxrpc_eproto_different_last, "diff-last") \
+ EM(rxrpc_eproto_early_reply, "early-reply") \
+ EM(rxrpc_eproto_improper_term, "improper-term") \
+ EM(rxrpc_eproto_no_client_call, "no-cl-call") \
+ EM(rxrpc_eproto_no_client_conn, "no-cl-conn") \
+ EM(rxrpc_eproto_no_service_call, "no-sv-call") \
+ EM(rxrpc_eproto_reupgrade, "re-upgrade") \
+ EM(rxrpc_eproto_rxnull_challenge, "rxnull-chall") \
+ EM(rxrpc_eproto_rxnull_response, "rxnull-resp") \
+ EM(rxrpc_eproto_tx_rot_last, "tx-rot-last") \
+ EM(rxrpc_eproto_unexpected_ack, "unex-ack") \
+ EM(rxrpc_eproto_unexpected_ackall, "unex-ackall") \
+ EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end") \
+ EM(rxrpc_eproto_unexpected_reply, "unex-reply") \
+ EM(rxrpc_eproto_wrong_security, "wrong-sec") \
+ EM(rxrpc_recvmsg_excess_data, "recvmsg-excess") \
+ EM(rxrpc_recvmsg_short_data, "recvmsg-short") \
+ E_(rxrpc_sendmsg_late_send, "sendmsg-late")
+
#define rxrpc_call_poke_traces \
EM(rxrpc_call_poke_abort, "Abort") \
EM(rxrpc_call_poke_complete, "Compl") \
@@ -382,6 +480,7 @@
#define EM(a, b) a,
#define E_(a, b) a
+enum rxrpc_abort_reason { rxrpc_abort_reasons } __mode(byte);
enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte);
enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte);
enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte);
@@ -410,9 +509,13 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte);
*/
#undef EM
#undef E_
+
+#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS
+
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define E_(a, b) TRACE_DEFINE_ENUM(a);
+rxrpc_abort_reasons;
rxrpc_bundle_traces;
rxrpc_call_poke_traces;
rxrpc_call_traces;
@@ -663,14 +766,14 @@ TRACE_EVENT(rxrpc_rx_done,
);
TRACE_EVENT(rxrpc_abort,
- TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
- rxrpc_seq_t seq, int abort_code, int error),
+ TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why,
+ u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error),
TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
TP_STRUCT__entry(
__field(unsigned int, call_nr )
- __array(char, why, 4 )
+ __field(enum rxrpc_abort_reason, why )
__field(u32, cid )
__field(u32, call_id )
__field(rxrpc_seq_t, seq )
@@ -679,8 +782,8 @@ TRACE_EVENT(rxrpc_abort,
),
TP_fast_assign(
- memcpy(__entry->why, why, 4);
__entry->call_nr = call_nr;
+ __entry->why = why;
__entry->cid = cid;
__entry->call_id = call_id;
__entry->abort_code = abort_code;
@@ -691,7 +794,8 @@ TRACE_EVENT(rxrpc_abort,
TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
__entry->call_nr,
__entry->cid, __entry->call_id, __entry->seq,
- __entry->abort_code, __entry->error, __entry->why)
+ __entry->abort_code, __entry->error,
+ __print_symbolic(__entry->why, rxrpc_abort_reasons))
);
TRACE_EVENT(rxrpc_call_complete,
@@ -1527,30 +1631,6 @@ TRACE_EVENT(rxrpc_improper_term,
__entry->abort_code)
);
-TRACE_EVENT(rxrpc_rx_eproto,
- TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
- const char *why),
-
- TP_ARGS(call, serial, why),
-
- TP_STRUCT__entry(
- __field(unsigned int, call )
- __field(rxrpc_serial_t, serial )
- __field(const char *, why )
- ),
-
- TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
- __entry->serial = serial;
- __entry->why = why;
- ),
-
- TP_printk("c=%08x EPROTO %08x %s",
- __entry->call,
- __entry->serial,
- __entry->why)
- );
-
TRACE_EVENT(rxrpc_connect_call,
TP_PROTO(struct rxrpc_call *call),
@@ -1848,6 +1928,8 @@ TRACE_EVENT(rxrpc_call_poked,
#undef EM
#undef E_
+
+#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 78bd6fb0bc154..120ce3ccbb227 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -627,9 +627,10 @@ struct rxrpc_call {
unsigned long events;
spinlock_t notify_lock; /* Kernel notification lock */
rwlock_t state_lock; /* lock for state transition */
- const char *send_abort_why; /* String indicating why the abort was sent */
+ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */
s32 send_abort; /* Abort code to be sent */
short send_abort_err; /* Error to be associated with the abort */
+ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */
s32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
enum rxrpc_call_state state; /* current state of call */
@@ -818,9 +819,11 @@ extern struct workqueue_struct *rxrpc_workqueue;
*/
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
-int rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *,
- struct rxrpc_connection *, struct sockaddr_rxrpc *,
- struct sk_buff *);
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
@@ -840,7 +843,7 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call,
unsigned long now,
enum rxrpc_timer_trace why);
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
/*
* call_object.c
@@ -905,10 +908,10 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *);
void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb,
unsigned int channel);
int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
- s32 abort_code, int err, const char *why);
+ s32 abort_code, int err, enum rxrpc_abort_reason why);
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb);
static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn)
@@ -979,12 +982,19 @@ void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *);
*/
int rxrpc_encap_rcv(struct sock *, struct sk_buff *);
void rxrpc_error_report(struct sock *);
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err);
int rxrpc_io_thread(void *data);
static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local)
{
wake_up_process(local->io_thread);
}
+static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO);
+}
+
/*
* insecure.c
*/
@@ -1108,29 +1118,26 @@ bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion
bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
bool __rxrpc_call_completed(struct rxrpc_call *);
bool rxrpc_call_completed(struct rxrpc_call *);
-bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
-bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
+bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
* Abort a call due to a protocol error.
*/
-static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
- struct sk_buff *skb,
- const char *eproto_why,
- const char *why,
- u32 abort_code)
+static inline int rxrpc_abort_eproto(struct rxrpc_call *call,
+ struct sk_buff *skb,
+ s32 abort_code,
+ enum rxrpc_abort_reason why)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why);
- return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO);
+ rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why);
+ return -EPROTO;
}
-#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \
- __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \
- (abort_why), (abort_code))
-
/*
* rtt.c
*/
@@ -1162,8 +1169,8 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *,
/*
* sendmsg.c
*/
-bool rxrpc_propose_abort(struct rxrpc_call *call,
- u32 abort_code, int error, const char *why);
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why);
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index c957e4415cdc4..a132d486dea0d 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -326,11 +326,11 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
* If we want to report an error, we mark the skb with the packet type and
* abort code and return false.
*/
-int rxrpc_new_incoming_call(struct rxrpc_local *local,
- struct rxrpc_peer *peer,
- struct rxrpc_connection *conn,
- struct sockaddr_rxrpc *peer_srx,
- struct sk_buff *skb)
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb)
{
const struct rxrpc_security *sec = NULL;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -339,10 +339,9 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local,
_enter("");
- /* Don't set up a call for anything other than the first DATA packet. */
- if (sp->hdr.seq != 1 ||
- sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
- return 0; /* Just discard */
+ /* Don't set up a call for anything other than a DATA packet. */
+ if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call);
rcu_read_lock();
@@ -363,16 +362,14 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local,
if (!conn) {
sec = rxrpc_get_incoming_security(rx, skb);
if (!sec)
- goto reject;
+ goto unsupported_security;
}
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
- trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
- sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_shut_down,
+ RX_INVALID_OPERATION, -ESHUTDOWN);
goto no_call;
}
@@ -413,22 +410,24 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local,
_leave(" = %p{%d}", call, call->debug_id);
rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
+ return true;
unsupported_service:
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->priority = RX_INVALID_OPERATION;
- goto reject;
+ rcu_read_unlock();
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EOPNOTSUPP);
+unsupported_security:
+ rcu_read_unlock();
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
no_call:
spin_unlock(&rx->incoming_lock);
-reject:
rcu_read_unlock();
_leave(" = f [%u]", skb->mark);
- return -EPROTO;
+ return false;
discard:
rcu_read_unlock();
- return 0;
+ return true;
}
/*
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index b2fc3fa686ece..695aeb70d1a6b 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -333,7 +333,7 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call)
/*
* Handle retransmission and deferred ACK/abort generation.
*/
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
{
unsigned long now, next, t;
rxrpc_serial_t ackr_serial;
@@ -352,8 +352,8 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
/* Handle abort request locklessly, vs rxrpc_propose_abort(). */
abort_code = smp_load_acquire(&call->send_abort);
if (abort_code) {
- rxrpc_abort_call(call->send_abort_why, call, 0, call->send_abort,
- call->send_abort_err);
+ rxrpc_abort_call(call, 0, call->send_abort, call->send_abort_err,
+ call->send_abort_why);
goto out;
}
@@ -440,9 +440,11 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
(int)call->conn->hi_serial - (int)call->rx_serial > 0) {
trace_rxrpc_call_reset(call);
- rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_reset);
} else {
- rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
+ rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME,
+ rxrpc_abort_call_timeout);
}
goto out;
}
@@ -494,4 +496,5 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
if (call->acks_hard_ack != call->tx_bottom)
rxrpc_shrink_call_tx_buffer(call);
_leave("");
+ return true;
}
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 666430182dfd6..705f6e26cc75e 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -581,7 +581,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del(&call->accept_link);
- rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKR");
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release_tba);
rxrpc_put_call(call, rxrpc_call_put_release_sock_tba);
}
@@ -589,7 +590,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
call = list_entry(rx->sock_calls.next,
struct rxrpc_call, sock_link);
rxrpc_get_call(call, rxrpc_call_get_release_sock);
- rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, "SKT");
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put_release_sock);
}
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 753d91a9646fc..485d7f0fed2cb 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -47,7 +47,7 @@ static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff
* Mark a socket buffer to indicate that the connection it's on should be aborted.
*/
int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
- s32 abort_code, int err, const char *why)
+ s32 abort_code, int err, enum rxrpc_abort_reason why)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -288,8 +288,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
return 0;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
+ WARN_ON_ONCE(1);
return -EPROTO;
}
}
@@ -300,7 +299,8 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
static void rxrpc_secure_connection(struct rxrpc_connection *conn)
{
if (conn->security->issue_challenge(conn) < 0)
- rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, "OOM");
+ rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM,
+ rxrpc_abort_nomem);
}
/*
@@ -405,14 +405,14 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
/*
* Input a connection-level packet.
*/
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
- return 0;
+ return true;
case RXRPC_PACKET_TYPE_ABORT:
if (rxrpc_is_conn_aborted(conn))
@@ -429,12 +429,11 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
return true;
}
rxrpc_post_packet_to_conn(conn, skb);
- return 0;
+ return true;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
- return -EPROTO;
+ WARN_ON_ONCE(1);
+ return true;
}
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index bb4beb4453259..bd69ff2d90826 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -9,10 +9,10 @@
#include "ar-internal.h"
-static void rxrpc_proto_abort(const char *why,
- struct rxrpc_call *call, rxrpc_seq_t seq)
+static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq,
+ enum rxrpc_abort_reason why)
{
- rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG);
+ rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why);
}
/*
@@ -249,8 +249,8 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
* This occurs when we get an ACKALL packet, the first DATA packet of a reply,
* or a final ACK packet.
*/
-static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
- const char *abort_why)
+static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
+ enum rxrpc_abort_reason abort_why)
{
unsigned int state;
@@ -283,13 +283,12 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
else
trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
_leave(" = ok");
- return true;
+ return;
bad_state:
write_unlock(&call->state_lock);
kdebug("end_tx %s", rxrpc_call_states[call->state]);
- rxrpc_proto_abort(abort_why, call, call->tx_top);
- return false;
+ rxrpc_proto_abort(call, call->tx_top, abort_why);
}
/*
@@ -311,11 +310,13 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
if (!rxrpc_rotate_tx_window(call, top, &summary)) {
- rxrpc_proto_abort("TXL", call, top);
+ rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply);
return false;
}
}
- return rxrpc_end_tx_phase(call, true, "ETD");
+
+ rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply);
+ return true;
}
static void rxrpc_input_update_ack_window(struct rxrpc_call *call,
@@ -365,17 +366,14 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb,
if (last) {
if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq + 1 != wtop) {
- rxrpc_proto_abort("LSN", call, seq);
- return;
- }
+ seq + 1 != wtop)
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last);
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
after_eq(seq, wtop)) {
pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n",
call->debug_id, seq, window, wtop, wlimit);
- rxrpc_proto_abort("LSA", call, seq);
- return;
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last);
}
}
@@ -583,7 +581,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
goto out_notify;
if (!rxrpc_input_split_jumbo(call, skb)) {
- rxrpc_proto_abort("VLD", call, sp->hdr.seq);
+ rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo);
goto out_notify;
}
skb = NULL;
@@ -764,7 +762,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
offset = sizeof(struct rxrpc_wire_header);
if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0)
- return rxrpc_proto_abort("XAK", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack);
offset += sizeof(ack);
ack_serial = sp->hdr.serial;
@@ -844,7 +842,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
ioffset = offset + nr_acks + 3;
if (skb->len >= ioffset + sizeof(info) &&
skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0)
- return rxrpc_proto_abort("XAI", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info);
if (nr_acks > 0)
skb_condense(skb);
@@ -867,7 +865,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
rxrpc_input_ackinfo(call, skb, &info);
if (first_soft_ack == 0)
- return rxrpc_proto_abort("AK0", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
/* Ignore ACKs unless we are or have just been transmitting. */
switch (READ_ONCE(call->state)) {
@@ -882,20 +880,20 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
if (before(hard_ack, call->acks_hard_ack) ||
after(hard_ack, call->tx_top))
- return rxrpc_proto_abort("AKW", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window);
if (nr_acks > call->tx_top - hard_ack)
- return rxrpc_proto_abort("AKN", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow);
if (after(hard_ack, call->acks_hard_ack)) {
if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
- rxrpc_end_tx_phase(call, false, "ETA");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack);
return;
}
}
if (nr_acks > 0) {
if (offset > (int)skb->len - nr_acks)
- return rxrpc_proto_abort("XSA", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
nr_acks, &summary);
}
@@ -917,7 +915,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb)
struct rxrpc_ack_summary summary = { 0 };
if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
- rxrpc_end_tx_phase(call, false, "ETL");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall);
}
/*
@@ -962,27 +960,23 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb)
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
- rxrpc_input_data(call, skb);
- break;
+ return rxrpc_input_data(call, skb);
case RXRPC_PACKET_TYPE_ACK:
- rxrpc_input_ack(call, skb);
- break;
+ return rxrpc_input_ack(call, skb);
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets from the server; the retry and
* lifespan timers will take care of business. BUSY packets
* from the client don't make sense.
*/
- break;
+ return;
case RXRPC_PACKET_TYPE_ABORT:
- rxrpc_input_abort(call, skb);
- break;
+ return rxrpc_input_abort(call, skb);
case RXRPC_PACKET_TYPE_ACKALL:
- rxrpc_input_ackall(call, skb);
- break;
+ return rxrpc_input_ackall(call, skb);
default:
break;
@@ -1004,7 +998,8 @@ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
case RXRPC_CALL_COMPLETE:
break;
default:
- rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN,
+ rxrpc_eproto_improper_term);
trace_rxrpc_improper_term(call);
break;
}
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index 29dcc7d3f51a7..34353b6e584bc 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -45,13 +45,15 @@ static void none_free_call_crypto(struct rxrpc_call *call)
static int none_respond_to_challenge(struct rxrpc_connection *conn,
struct sk_buff *skb)
{
- return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN");
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_challenge);
}
static int none_verify_response(struct rxrpc_connection *conn,
struct sk_buff *skb)
{
- return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, "RXN");
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_response);
}
static void none_clear(struct rxrpc_connection *conn)
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 46e58cf5bc96e..33fd2394c8b3b 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -66,10 +66,32 @@ void rxrpc_error_report(struct sock *sk)
rcu_read_unlock();
}
+/*
+ * Directly produce an abort from a packet.
+ */
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ abort_code, err);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = abort_code;
+ return false;
+}
+
+static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG);
+}
+
+#define just_discard true
+
/*
* Process event packets targeted at a local endpoint.
*/
-static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
+static bool rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
char v;
@@ -81,22 +103,21 @@ static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
if (v == 0)
rxrpc_send_version_request(local, &sp->hdr, skb);
}
+
+ return true;
}
/*
* Extract the wire header from a packet and translate the byte order.
*/
-static noinline
-int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
+static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp,
+ struct sk_buff *skb)
{
struct rxrpc_wire_header whdr;
/* dig out the RxRPC connection details */
- if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) {
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_hdr"));
- return -EBADMSG;
- }
+ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_short_hdr);
memset(sp, 0, sizeof(*sp));
sp->hdr.epoch = ntohl(whdr.epoch);
@@ -110,7 +131,7 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
sp->hdr.securityIndex = whdr.securityIndex;
sp->hdr._rsvd = ntohs(whdr._rsvd);
sp->hdr.serviceId = ntohs(whdr.serviceId);
- return 0;
+ return true;
}
/*
@@ -130,28 +151,28 @@ static bool rxrpc_extract_abort(struct sk_buff *skb)
/*
* Process packets received on the local endpoint
*/
-static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
+static bool rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
{
struct rxrpc_connection *conn;
struct sockaddr_rxrpc peer_srx;
struct rxrpc_skb_priv *sp;
struct rxrpc_peer *peer = NULL;
struct sk_buff *skb = *_skb;
- int ret = 0;
+ bool ret = false;
skb_pull(skb, sizeof(struct udphdr));
sp = rxrpc_skb(skb);
/* dig out the RxRPC connection details */
- if (rxrpc_extract_header(sp, skb) < 0)
- goto bad_message;
+ if (!rxrpc_extract_header(sp, skb))
+ return just_discard;
if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
static int lose;
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
- return 0;
+ return just_discard;
}
}
@@ -160,28 +181,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (rxrpc_to_client(sp))
- return 0;
- rxrpc_input_version(local, skb);
- return 0;
+ return just_discard;
+ return rxrpc_input_version(local, skb);
case RXRPC_PACKET_TYPE_BUSY:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
fallthrough;
case RXRPC_PACKET_TYPE_ACK:
case RXRPC_PACKET_TYPE_ACKALL:
if (sp->hdr.callNumber == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
break;
case RXRPC_PACKET_TYPE_ABORT:
if (!rxrpc_extract_abort(skb))
- return 0; /* Just discard if malformed */
+ return just_discard; /* Just discard if malformed */
break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0 ||
- sp->hdr.seq == 0)
- goto bad_message;
+ if (sp->hdr.callNumber == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
+ if (sp->hdr.seq == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_seq);
/* Unshare the packet so that it can be modified for in-place
* decryption.
@@ -191,7 +212,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
if (!skb) {
rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem);
*_skb = NULL;
- return 0;
+ return just_discard;
}
if (skb != *_skb) {
@@ -205,28 +226,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
case RXRPC_PACKET_TYPE_CHALLENGE:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
break;
case RXRPC_PACKET_TYPE_RESPONSE:
if (rxrpc_to_client(sp))
- return 0;
+ return just_discard;
break;
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
- return 0;
+ return just_discard;
default:
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_unsupported_packet);
}
if (sp->hdr.serviceId == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_service);
if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0))
- return true; /* Unsupported address type - discard. */
+ return just_discard; /* Unsupported address type. */
if (peer_srx.transport.family != local->srx.transport.family &&
(peer_srx.transport.family == AF_INET &&
@@ -234,7 +255,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
peer_srx.transport.family,
local->srx.transport.family);
- return true; /* Wrong address type - discard. */
+ return just_discard; /* Wrong address type. */
}
if (rxrpc_to_client(sp)) {
@@ -242,12 +263,8 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb);
conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input);
rcu_read_unlock();
- if (!conn) {
- trace_rxrpc_abort(0, "NCC", sp->hdr.cid,
- sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- goto protocol_error;
- }
+ if (!conn)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_conn);
ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb);
rxrpc_put_connection(conn, rxrpc_conn_put_call_input);
@@ -280,19 +297,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb);
rxrpc_put_peer(peer, rxrpc_peer_put_input);
- if (ret < 0)
- goto reject_packet;
- return 0;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(local, skb);
- return 0;
+ return ret;
}
/*
@@ -306,21 +311,23 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
unsigned int channel;
+ bool ret;
if (sp->hdr.securityIndex != conn->security_ix)
- goto wrong_security;
+ return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security,
+ RXKADINCONSISTENCY, -EBADMSG);
if (sp->hdr.serviceId != conn->service_id) {
int old_id;
if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags))
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_reupgrade);
+
old_id = cmpxchg(&conn->service_id, conn->orig_service_id,
sp->hdr.serviceId);
-
if (old_id != conn->orig_service_id &&
old_id != sp->hdr.serviceId)
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_bad_upgrade);
}
if (after(sp->hdr.serial, conn->hi_serial))
@@ -336,19 +343,19 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
/* Ignore really old calls */
if (sp->hdr.callNumber < chan->last_call)
- return 0;
+ return just_discard;
if (sp->hdr.callNumber == chan->last_call) {
if (chan->call ||
sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
- return 0;
+ return just_discard;
/* For the previous service call, if completed successfully, we
* discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
chan->last_type == RXRPC_PACKET_TYPE_ACK)
- return 0;
+ return just_discard;
/* But otherwise we need to retransmit the final packet from
* data cached in the connection record.
@@ -359,7 +366,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
sp->hdr.serial,
sp->hdr.flags);
rxrpc_conn_retransmit_call(conn, skb, channel);
- return 0;
+ return just_discard;
}
rcu_read_lock();
@@ -370,7 +377,8 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
if (sp->hdr.callNumber > chan->call_id) {
if (rxrpc_to_client(sp)) {
rxrpc_put_call(call, rxrpc_call_put_input);
- goto reject_packet;
+ return rxrpc_protocol_error(skb,
+ rxrpc_eproto_unexpected_implicit_end);
}
if (call) {
@@ -382,38 +390,14 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
if (!call) {
if (rxrpc_to_client(sp))
- goto bad_message;
- if (rxrpc_new_incoming_call(conn->local, conn->peer, conn,
- peer_srx, skb) == 0)
- return 0;
- goto reject_packet;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_call);
+ return rxrpc_new_incoming_call(conn->local, conn->peer, conn,
+ peer_srx, skb);
}
- rxrpc_input_call_event(call, skb);
+ ret = rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
-
-wrong_security:
- trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- skb->priority = RXKADINCONSISTENCY;
- goto post_abort;
-
-reupgrade:
- trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
- goto protocol_error;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
-post_abort:
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(conn->local, skb);
- return 0;
+ return ret;
}
/*
@@ -470,7 +454,8 @@ int rxrpc_io_thread(void *data)
switch (skb->mark) {
case RXRPC_SKB_MARK_PACKET:
skb->priority = 0;
- rxrpc_input_packet(local, &skb);
+ if (!rxrpc_input_packet(local, &skb))
+ rxrpc_reject_packet(local, skb);
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_free_skb(skb, rxrpc_skb_put_input);
break;
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 8d5fe65f5951c..59b521b82aec3 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -117,8 +117,8 @@ bool rxrpc_call_completed(struct rxrpc_call *call)
/*
* Record that a call is locally aborted.
*/
-bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
+bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
abort_code, error);
@@ -126,13 +126,13 @@ bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
abort_code, error);
}
-bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
bool ret;
write_lock(&call->state_lock);
- ret = __rxrpc_abort_call(why, call, seq, abort_code, error);
+ ret = __rxrpc_abort_call(call, seq, abort_code, error, why);
write_unlock(&call->state_lock);
if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags))
rxrpc_send_abort_packet(call);
@@ -642,11 +642,15 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
return ret;
short_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_short_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EBADMSG);
ret = -EBADMSG;
goto out;
excess_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_excess_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EMSGSIZE);
ret = -EMSGSIZE;
goto out;
call_complete:
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 5d2fbc6ec3cf1..e52cb8058156f 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -411,18 +411,15 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist sg[16];
- bool aborted;
u32 data_size, buf;
u16 check;
int ret;
_enter("");
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
@@ -442,11 +439,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
skcipher_request_zero(req);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_encdata);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
@@ -456,26 +451,16 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
-
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_check);
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
@@ -490,18 +475,15 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist _sg[4], *sg;
- bool aborted;
u32 data_size, buf;
u16 check;
int nsg, ret;
_enter(",{%d}", sp->len);
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
@@ -513,7 +495,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
} else {
sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO);
if (!sg)
- goto nomem;
+ return -ENOMEM;
}
sg_init_table(sg, nsg);
@@ -537,11 +519,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
kfree(sg);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_len);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
@@ -551,30 +531,17 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_check);
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
-
-nomem:
- _leave(" = -ENOMEM");
- return -ENOMEM;
}
/*
@@ -590,7 +557,6 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
__be32 buf[2];
} crypto __aligned(8);
rxrpc_seq_t seq = sp->hdr.seq;
- bool aborted;
int ret;
u16 cksum;
u32 x, y;
@@ -627,9 +593,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
cksum = 1; /* zero checksums are not permitted */
if (cksum != sp->hdr.cksum) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK",
- RXKADSEALEDINCON);
- goto protocol_error;
+ ret = rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_bad_checksum);
+ goto out;
}
switch (call->conn->security_level) {
@@ -647,13 +613,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
break;
}
+out:
skcipher_request_free(req);
return ret;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
@@ -827,27 +789,24 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
struct rxkad_challenge challenge;
struct rxkad_response *resp;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- const char *eproto;
- u32 version, nonce, min_level, abort_code;
- int ret;
+ u32 version, nonce, min_level;
+ int ret = -EPROTO;
_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
- eproto = tracepoint_string("chall_no_key");
- abort_code = RX_PROTOCOL_ERROR;
if (!conn->key)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxkad_abort_chall_no_key);
- abort_code = RXKADEXPIRED;
ret = key_validate(conn->key);
if (ret < 0)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_chall_key_expired);
- eproto = tracepoint_string("chall_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&challenge, sizeof(challenge)) < 0)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_chall_short);
version = ntohl(challenge.version);
nonce = ntohl(challenge.nonce);
@@ -855,15 +814,13 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level);
- eproto = tracepoint_string("chall_ver");
- abort_code = RXKADINCONSISTENCY;
if (version != RXKAD_VERSION)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_chall_version);
- abort_code = RXKADLEVELFAIL;
- ret = -EACCES;
if (conn->security_level < min_level)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES,
+ rxkad_abort_chall_level);
token = conn->key->payload.data[0];
@@ -892,13 +849,6 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad);
kfree(resp);
return ret;
-
-protocol_error:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- ret = -EPROTO;
-other_error:
- rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK");
- return ret;
}
/*
@@ -912,16 +862,12 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
time64_t *_expiry)
{
struct skcipher_request *req;
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv, key;
struct scatterlist sg[1];
struct in_addr addr;
unsigned int life;
- const char *eproto;
time64_t issue, now;
bool little_endian;
- int ret;
- u32 abort_code;
u8 *p, *q, *name, *end;
_enter("{%d},{%x}", conn->debug_id, key_serial(server_key));
@@ -933,10 +879,9 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
memcpy(&iv, &server_key->payload.data[2], sizeof(iv));
- ret = -ENOMEM;
req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS);
if (!req)
- goto temporary_error;
+ return -ENOMEM;
sg_init_one(&sg[0], ticket, ticket_len);
skcipher_request_set_callback(req, 0, NULL, NULL);
@@ -947,18 +892,21 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
p = ticket;
end = p + ticket_len;
-#define Z(field) \
- ({ \
- u8 *__str = p; \
- eproto = tracepoint_string("rxkad_bad_"#field); \
- q = memchr(p, 0, end - p); \
- if (!q || q - p > (field##_SZ)) \
- goto bad_ticket; \
- for (; p < q; p++) \
- if (!isprint(*p)) \
- goto bad_ticket; \
- p++; \
- __str; \
+#define Z(field, fieldl) \
+ ({ \
+ u8 *__str = p; \
+ q = memchr(p, 0, end - p); \
+ if (!q || q - p > field##_SZ) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ for (; p < q; p++) \
+ if (!isprint(*p)) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ p++; \
+ __str; \
})
/* extract the ticket flags */
@@ -967,20 +915,20 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
p++;
/* extract the authentication name */
- name = Z(ANAME);
+ name = Z(ANAME, aname);
_debug("KIV ANAME: %s", name);
/* extract the principal's instance */
- name = Z(INST);
+ name = Z(INST, inst);
_debug("KIV INST : %s", name);
/* extract the principal's authentication domain */
- name = Z(REALM);
+ name = Z(REALM, realm);
_debug("KIV REALM: %s", name);
- eproto = tracepoint_string("rxkad_bad_len");
if (end - p < 4 + 8 + 4 + 2)
- goto bad_ticket;
+ return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO,
+ rxkad_abort_resp_tkt_short);
/* get the IPv4 address of the entity that requested the ticket */
memcpy(&addr, p, sizeof(addr));
@@ -1012,37 +960,23 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
_debug("KIV ISSUE: %llx [%llx]", issue, now);
/* check the ticket is in date */
- if (issue > now) {
- abort_code = RXKADNOAUTH;
- ret = -EKEYREJECTED;
- goto other_error;
- }
-
- if (issue < now - life) {
- abort_code = RXKADEXPIRED;
- ret = -EKEYEXPIRED;
- goto other_error;
- }
+ if (issue > now)
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, -EKEYREJECTED,
+ rxkad_abort_resp_tkt_future);
+ if (issue < now - life)
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, -EKEYEXPIRED,
+ rxkad_abort_resp_tkt_expired);
*_expiry = issue + life;
/* get the service name */
- name = Z(SNAME);
+ name = Z(SNAME, sname);
_debug("KIV SNAME: %s", name);
/* get the service instance name */
- name = Z(INST);
+ name = Z(INST, sinst);
_debug("KIV SINST: %s", name);
return 0;
-
-bad_ticket:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- abort_code = RXKADBADTICKET;
- ret = -EPROTO;
-other_error:
- return rxrpc_abort_conn(conn, skb, abort_code, ret, "RXK");
-temporary_error:
- return ret;
}
/*
@@ -1089,10 +1023,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
struct key *server_key;
- const char *eproto;
time64_t expiry;
void *ticket;
- u32 abort_code, version, kvno, ticket_len, level;
+ u32 version, kvno, ticket_len, level;
__be32 csum;
int ret, i;
@@ -1100,19 +1033,18 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
server_key = rxrpc_look_up_server_security(conn, skb, 0, 0);
if (IS_ERR(server_key)) {
- switch (PTR_ERR(server_key)) {
+ ret = PTR_ERR(server_key);
+ switch (ret) {
case -ENOKEY:
- abort_code = RXKADUNKNOWNKEY;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, ret,
+ rxkad_abort_resp_nokey);
case -EKEYEXPIRED:
- abort_code = RXKADEXPIRED;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_resp_key_expired);
default:
- abort_code = RXKADNOAUTH;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, ret,
+ rxkad_abort_resp_key_rejected);
}
- return rxrpc_abort_conn(conn, skb, abort_code,
- PTR_ERR(server_key), "RXK");
}
ret = -ENOMEM;
@@ -1120,11 +1052,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
if (!response)
goto temporary_error;
- eproto = tracepoint_string("rxkad_rsp_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
- response, sizeof(*response)) < 0)
+ response, sizeof(*response)) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short);
goto protocol_error;
+ }
version = ntohl(response->version);
ticket_len = ntohl(response->ticket_len);
@@ -1132,20 +1065,23 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len);
- eproto = tracepoint_string("rxkad_rsp_ver");
- abort_code = RXKADINCONSISTENCY;
- if (version != RXKAD_VERSION)
+ if (version != RXKAD_VERSION) {
+ rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_resp_version);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_tktlen");
- abort_code = RXKADTICKETLEN;
- if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN)
+ if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) {
+ rxrpc_abort_conn(conn, skb, RXKADTICKETLEN, -EPROTO,
+ rxkad_abort_resp_tkt_len);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_unkkey");
- abort_code = RXKADUNKNOWNKEY;
- if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5)
+ if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) {
+ rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, -EPROTO,
+ rxkad_abort_resp_unknown_tkt);
goto protocol_error;
+ }
/* extract the kerberos ticket and decrypt and decode it */
ret = -ENOMEM;
@@ -1153,12 +1089,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
if (!ticket)
goto temporary_error_free_resp;
- eproto = tracepoint_string("rxkad_tkt_short");
- abort_code = RXKADPACKETSHORT;
- ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
- ticket, ticket_len);
- if (ret < 0)
- goto temporary_error_free_ticket;
+ if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
+ ticket, ticket_len) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short_tkt);
+ goto protocol_error;
+ }
ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
&session_key, &expiry);
@@ -1169,56 +1105,66 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
* response */
rxkad_decrypt_response(conn, response, &session_key);
- eproto = tracepoint_string("rxkad_rsp_param");
- abort_code = RXKADSEALEDINCON;
- if (ntohl(response->encrypted.epoch) != conn->proto.epoch)
- goto protocol_error_free;
- if (ntohl(response->encrypted.cid) != conn->proto.cid)
- goto protocol_error_free;
- if (ntohl(response->encrypted.securityIndex) != conn->security_ix)
+ if (ntohl(response->encrypted.epoch) != conn->proto.epoch ||
+ ntohl(response->encrypted.cid) != conn->proto.cid ||
+ ntohl(response->encrypted.securityIndex) != conn->security_ix) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_param);
goto protocol_error_free;
+ }
+
csum = response->encrypted.checksum;
response->encrypted.checksum = 0;
rxkad_calc_response_checksum(response);
- eproto = tracepoint_string("rxkad_rsp_csum");
- if (response->encrypted.checksum != csum)
+ if (response->encrypted.checksum != csum) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_checksum);
goto protocol_error_free;
+ }
spin_lock(&conn->bundle->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
struct rxrpc_call *call;
u32 call_id = ntohl(response->encrypted.call_id[i]);
- eproto = tracepoint_string("rxkad_rsp_callid");
- if (call_id > INT_MAX)
+ if (call_id > INT_MAX) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_callid);
goto protocol_error_unlock;
+ }
- eproto = tracepoint_string("rxkad_rsp_callctr");
- if (call_id < conn->channels[i].call_counter)
+ if (call_id < conn->channels[i].call_counter) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_ctr);
goto protocol_error_unlock;
+ }
- eproto = tracepoint_string("rxkad_rsp_callst");
if (call_id > conn->channels[i].call_counter) {
call = rcu_dereference_protected(
conn->channels[i].call,
lockdep_is_held(&conn->bundle->channel_lock));
- if (call && call->state < RXRPC_CALL_COMPLETE)
+ if (call && call->state < RXRPC_CALL_COMPLETE) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_state);
goto protocol_error_unlock;
+ }
conn->channels[i].call_counter = call_id;
}
}
spin_unlock(&conn->bundle->channel_lock);
- eproto = tracepoint_string("rxkad_rsp_seq");
- abort_code = RXKADOUTOFSEQUENCE;
- if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1)
+ if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) {
+ rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO,
+ rxkad_abort_resp_ooseq);
goto protocol_error_free;
+ }
- eproto = tracepoint_string("rxkad_rsp_level");
- abort_code = RXKADLEVELFAIL;
level = ntohl(response->encrypted.level);
- if (level > RXRPC_SECURITY_ENCRYPT)
+ if (level > RXRPC_SECURITY_ENCRYPT) {
+ rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EPROTO,
+ rxkad_abort_resp_level);
goto protocol_error_free;
+ }
conn->security_level = level;
/* create a key to hold the security data and expiration time - after
@@ -1240,8 +1186,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
protocol_error:
kfree(response);
key_put(server_key);
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- return rxrpc_abort_conn(conn, skb, abort_code, -EPROTO, "RXK");
+ return -EPROTO;
temporary_error_free_ticket:
kfree(ticket);
diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c
index d33a109e846c1..16dcabb71ebe1 100644
--- a/net/rxrpc/rxperf.c
+++ b/net/rxrpc/rxperf.c
@@ -10,6 +10,8 @@
#include <linux/slab.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
MODULE_DESCRIPTION("rxperf test server (afs)");
MODULE_AUTHOR("Red Hat, Inc.");
@@ -307,12 +309,14 @@ static void rxperf_deliver_to_call(struct work_struct *work)
case -EOPNOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GOP");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -ENOTSUPP:
abort_code = RX_USER_ABORT;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GUA");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -EIO:
pr_err("Call %u in bad state %u\n",
@@ -324,11 +328,13 @@ static void rxperf_deliver_to_call(struct work_struct *work)
case -ENOMEM:
case -EFAULT:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_UNMARSHAL, ret, "GUM");
+ RXGEN_SS_UNMARSHAL, ret,
+ rxperf_abort_unmarshal_error);
goto call_complete;
default:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RX_CALL_DEAD, ret, "GER");
+ RX_CALL_DEAD, ret,
+ rxperf_abort_general_error);
goto call_complete;
}
}
@@ -523,7 +529,8 @@ static int rxperf_process_call(struct rxperf_call *call)
if (n == -ENOMEM)
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "GOM");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ rxperf_abort_oom);
return n;
}
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index ab968f65a4900..78af14694618d 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -144,21 +144,15 @@ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx,
sec = rxrpc_security_lookup(sp->hdr.securityIndex);
if (!sec) {
- trace_rxrpc_abort(0, "SVS",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
return NULL;
}
if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
!rx->securities) {
- trace_rxrpc_abort(0, "SVR",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = sec->no_key_abort;
+ rxrpc_direct_abort(skb, rxrpc_abort_no_service_key,
+ sec->no_key_abort, -EKEYREJECTED);
return NULL;
}
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index dc3c2a834fc8b..d67808b659f13 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -20,14 +20,15 @@
/*
* Propose an abort to be made in the I/O thread.
*/
-bool rxrpc_propose_abort(struct rxrpc_call *call,
- u32 abort_code, int error, const char *why)
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why)
{
- _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) {
call->send_abort_why = why;
call->send_abort_err = error;
+ call->send_abort_seq = 0;
/* Request abort locklessly vs rxrpc_input_call_event(). */
smp_store_release(&call->send_abort, abort_code);
rxrpc_poke_call(call, rxrpc_call_poke_abort);
@@ -683,7 +684,8 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
- rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, "CMD");
+ rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED,
+ rxrpc_abort_call_sendmsg);
ret = 0;
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
@@ -748,7 +750,9 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
break;
default:
/* Request phase complete for this client call */
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EPROTO);
ret = -EPROTO;
break;
}
@@ -766,17 +770,17 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data);
* @call: The call to be aborted
* @abort_code: The abort code to stick into the ABORT packet
* @error: Local error value
- * @why: 3-char string indicating why.
+ * @why: Indication as to why.
*
* Allow a kernel service to abort a call, if it's still in an abortable state
* and return true if the call was aborted, false if it was already complete.
*/
bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
- u32 abort_code, int error, const char *why)
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
bool aborted;
- _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
aborted = rxrpc_propose_abort(call, abort_code, error, why);
--
GitLab
From f06cb29189361353e9ed12df936c8e1d7f69b730 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 20 Oct 2022 22:58:56 +0100
Subject: [PATCH 0437/1167] rxrpc: Make the set of connection IDs per local
endpoint
Make the set of connection IDs per local endpoint so that endpoints don't
cause each other's connections to get dismissed.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/af_rxrpc.c | 8 --------
net/rxrpc/ar-internal.h | 5 +++--
net/rxrpc/conn_client.c | 44 +++++++++++++++++-----------------------
net/rxrpc/conn_object.c | 6 +++---
net/rxrpc/local_object.c | 10 +++++++++
5 files changed, 35 insertions(+), 38 deletions(-)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 7ea576f6ba4bc..6f6a6b77ee846 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -957,16 +957,9 @@ static const struct net_proto_family rxrpc_family_ops = {
static int __init af_rxrpc_init(void)
{
int ret = -1;
- unsigned int tmp;
BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb));
- get_random_bytes(&tmp, sizeof(tmp));
- tmp &= 0x3fffffff;
- if (tmp == 0)
- tmp = 1;
- idr_set_cursor(&rxrpc_client_conn_ids, tmp);
-
ret = -ENOMEM;
rxrpc_call_jar = kmem_cache_create(
"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
@@ -1062,7 +1055,6 @@ static void __exit af_rxrpc_exit(void)
* are released.
*/
rcu_barrier();
- rxrpc_destroy_client_conn_ids();
destroy_workqueue(rxrpc_workqueue);
rxrpc_exit_security();
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 120ce3ccbb227..e9ab06100a211 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -300,6 +300,8 @@ struct rxrpc_local {
int debug_id; /* debug ID for printks */
bool dead;
bool service_closed; /* Service socket closed */
+ struct idr conn_ids; /* List of connection IDs */
+ spinlock_t conn_lock; /* Lock for client connection pool */
struct sockaddr_rxrpc srx; /* local address */
};
@@ -887,9 +889,8 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
extern unsigned int rxrpc_reap_client_connections;
extern unsigned long rxrpc_conn_idle_client_expiry;
extern unsigned long rxrpc_conn_idle_client_fast_expiry;
-extern struct idr rxrpc_client_conn_ids;
-void rxrpc_destroy_client_conn_ids(void);
+void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local);
struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 1edd65883c55a..59ce5c08cf574 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -34,12 +34,6 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900;
__read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
__read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
-/*
- * We use machine-unique IDs for our client connections.
- */
-DEFINE_IDR(rxrpc_client_conn_ids);
-static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
-
static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
/*
@@ -51,65 +45,65 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn,
gfp_t gfp)
{
- struct rxrpc_net *rxnet = conn->rxnet;
+ struct rxrpc_local *local = conn->local;
int id;
_enter("");
idr_preload(gfp);
- spin_lock(&rxrpc_conn_id_lock);
+ spin_lock(&local->conn_lock);
- id = idr_alloc_cyclic(&rxrpc_client_conn_ids, conn,
+ id = idr_alloc_cyclic(&local->conn_ids, conn,
1, 0x40000000, GFP_NOWAIT);
if (id < 0)
goto error;
- spin_unlock(&rxrpc_conn_id_lock);
+ spin_unlock(&local->conn_lock);
idr_preload_end();
- conn->proto.epoch = rxnet->epoch;
+ conn->proto.epoch = local->rxnet->epoch;
conn->proto.cid = id << RXRPC_CIDSHIFT;
set_bit(RXRPC_CONN_HAS_IDR, &conn->flags);
_leave(" [CID %x]", conn->proto.cid);
return 0;
error:
- spin_unlock(&rxrpc_conn_id_lock);
+ spin_unlock(&local->conn_lock);
idr_preload_end();
_leave(" = %d", id);
return id;
}
/*
- * Release a connection ID for a client connection from the global pool.
+ * Release a connection ID for a client connection.
*/
-static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn)
+static void rxrpc_put_client_connection_id(struct rxrpc_local *local,
+ struct rxrpc_connection *conn)
{
if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) {
- spin_lock(&rxrpc_conn_id_lock);
- idr_remove(&rxrpc_client_conn_ids,
- conn->proto.cid >> RXRPC_CIDSHIFT);
- spin_unlock(&rxrpc_conn_id_lock);
+ spin_lock(&local->conn_lock);
+ idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT);
+ spin_unlock(&local->conn_lock);
}
}
/*
* Destroy the client connection ID tree.
*/
-void rxrpc_destroy_client_conn_ids(void)
+void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
int id;
- if (!idr_is_empty(&rxrpc_client_conn_ids)) {
- idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) {
+ if (!idr_is_empty(&local->conn_ids)) {
+ idr_for_each_entry(&local->conn_ids, conn, id) {
pr_err("AF_RXRPC: Leaked client conn %p {%d}\n",
conn, refcount_read(&conn->ref));
}
BUG();
}
- idr_destroy(&rxrpc_client_conn_ids);
+ idr_destroy(&local->conn_ids);
}
/*
@@ -225,7 +219,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
return conn;
error_1:
- rxrpc_put_client_connection_id(conn);
+ rxrpc_put_client_connection_id(bundle->local, conn);
error_0:
kfree(conn);
_leave(" = %d", ret);
@@ -257,7 +251,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
* times the maximum number of client conns away from the current
* allocation point to try and keep the IDs concentrated.
*/
- id_cursor = idr_get_cursor(&rxrpc_client_conn_ids);
+ id_cursor = idr_get_cursor(&conn->local->conn_ids);
id = conn->proto.cid >> RXRPC_CIDSHIFT;
distance = id - id_cursor;
if (distance < 0)
@@ -982,7 +976,7 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
atomic_dec(&rxnet->nr_client_conns);
- rxrpc_put_client_connection_id(conn);
+ rxrpc_put_client_connection_id(local, conn);
}
/*
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 281f59e356f5d..2e3f0a222e1b4 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -100,10 +100,10 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo
_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
- /* Look up client connections by connection ID alone as their IDs are
- * unique for this machine.
+ /* Look up client connections by connection ID alone as their
+ * IDs are unique for this machine.
*/
- conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
+ conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
if (!conn || refcount_read(&conn->ref) == 0) {
_debug("no conn");
goto not_found;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 8ef6cd8defa45..ca8b3ee68b597 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -89,6 +89,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
+ u32 tmp;
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
@@ -109,6 +110,14 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
local->srx.srx_service = 0;
+ idr_init(&local->conn_ids);
+ get_random_bytes(&tmp, sizeof(tmp));
+ tmp &= 0x3fffffff;
+ if (tmp == 0)
+ tmp = 1;
+ idr_set_cursor(&local->conn_ids, tmp);
+ spin_lock_init(&local->conn_lock);
+
trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1);
}
@@ -409,6 +418,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local)
* local endpoint.
*/
rxrpc_purge_queue(&local->rx_queue);
+ rxrpc_destroy_client_conn_ids(local);
}
/*
--
GitLab
From 2953d3b8d8fd1188034c54862b74402b0b846695 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 21 Oct 2022 08:54:03 +0100
Subject: [PATCH 0438/1167] rxrpc: Offload the completion of service conn
security to the I/O thread
Offload the completion of the challenge/response cycle on a service
connection to the I/O thread. After the RESPONSE packet has been
successfully decrypted and verified by the work queue, offloading the
changing of the call states to the I/O thread makes iteration over the
conn's channel list simpler.
Do this by marking the RESPONSE skbuff and putting it onto the receive
queue for the I/O thread to collect. We put it on the front of the queue
as we've already received the packet for it.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 2 ++
net/rxrpc/ar-internal.h | 1 +
net/rxrpc/conn_event.c | 46 +++++++++++++++++++++++++-----------
net/rxrpc/io_thread.c | 5 ++++
4 files changed, 40 insertions(+), 14 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index caeabd50e049c..85671f4a77de1 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -126,6 +126,7 @@
#define rxrpc_skb_traces \
EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \
EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \
+ EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \
EM(rxrpc_skb_get_conn_work, "GET conn-work") \
EM(rxrpc_skb_get_local_work, "GET locl-work") \
EM(rxrpc_skb_get_reject_work, "GET rej-work ") \
@@ -135,6 +136,7 @@
EM(rxrpc_skb_new_error_report, "NEW error-rpt") \
EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \
EM(rxrpc_skb_new_unshared, "NEW unshared ") \
+ EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \
EM(rxrpc_skb_put_conn_work, "PUT conn-work") \
EM(rxrpc_skb_put_error_report, "PUT error-rep") \
EM(rxrpc_skb_put_input, "PUT input ") \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e9ab06100a211..e508ec221b75e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -38,6 +38,7 @@ struct rxrpc_txbuf;
enum rxrpc_skb_mark {
RXRPC_SKB_MARK_PACKET, /* Received packet */
RXRPC_SKB_MARK_ERROR, /* Error notification */
+ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */
RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */
RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */
};
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 485d7f0fed2cb..b2042702ca9aa 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -248,7 +248,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- int loop, ret;
+ int ret;
if (conn->state == RXRPC_CONN_ABORTED)
return -ECONNABORTED;
@@ -269,22 +269,21 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
if (ret < 0)
return ret;
- spin_lock(&conn->bundle->channel_lock);
spin_lock(&conn->state_lock);
-
- if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
+ if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING)
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
- for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
- rxrpc_call_is_secure(
- rcu_dereference_protected(
- conn->channels[loop].call,
- lockdep_is_held(&conn->bundle->channel_lock)));
- } else {
- spin_unlock(&conn->state_lock);
- }
+ spin_unlock(&conn->state_lock);
- spin_unlock(&conn->bundle->channel_lock);
+ if (conn->state == RXRPC_CONN_SERVICE) {
+ /* Offload call state flipping to the I/O thread. As
+ * we've already received the packet, put it on the
+ * front of the queue.
+ */
+ skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
+ rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
+ skb_queue_head(&conn->local->rx_queue, skb);
+ rxrpc_wake_up_io_thread(conn->local);
+ }
return 0;
default:
@@ -442,9 +441,28 @@ bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
*/
void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
{
+ unsigned int loop;
+
if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
rxrpc_abort_calls(conn);
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ if (conn->state != RXRPC_CONN_SERVICE)
+ break;
+
+ spin_lock(&conn->bundle->channel_lock);
+
+ for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+ rxrpc_call_is_secure(
+ rcu_dereference_protected(
+ conn->channels[loop].call,
+ lockdep_is_held(&conn->bundle->channel_lock)));
+
+ spin_unlock(&conn->bundle->channel_lock);
+ break;
+ }
+
/* Process delayed ACKs whose time has come. */
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn, false);
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 33fd2394c8b3b..751139b3c1ac9 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -451,6 +451,7 @@ int rxrpc_io_thread(void *data)
/* Process received packets and errors. */
if ((skb = __skb_dequeue(&rx_queue))) {
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
switch (skb->mark) {
case RXRPC_SKB_MARK_PACKET:
skb->priority = 0;
@@ -463,6 +464,10 @@ int rxrpc_io_thread(void *data)
rxrpc_input_error(local, skb);
rxrpc_free_skb(skb, rxrpc_skb_put_error_report);
break;
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ rxrpc_input_conn_event(sp->conn, skb);
+ rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke);
+ rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured);
break;
default:
WARN_ON_ONCE(1);
--
GitLab
From 1bab27af6b88b5c811f99de4812b5590f20d1cb7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 21 Oct 2022 09:30:23 +0100
Subject: [PATCH 0439/1167] rxrpc: Set up a connection bundle from a call, not
rxrpc_conn_parameters
Use the information now stored in struct rxrpc_call to configure the
connection bundle and thence the connection, rather than using the
rxrpc_conn_parameters struct.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 3 +-
net/rxrpc/af_rxrpc.c | 1 -
net/rxrpc/ar-internal.h | 8 +--
net/rxrpc/call_object.c | 4 +-
net/rxrpc/conn_client.c | 132 ++++++++++++++++++-----------------
net/rxrpc/conn_object.c | 2 +-
net/rxrpc/sendmsg.c | 1 -
7 files changed, 76 insertions(+), 75 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 85671f4a77de1..e2f6b79d55170 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -178,7 +178,6 @@
#define rxrpc_peer_traces \
EM(rxrpc_peer_free, "FREE ") \
EM(rxrpc_peer_get_accept, "GET accept ") \
- EM(rxrpc_peer_get_activate_call, "GET act-call") \
EM(rxrpc_peer_get_bundle, "GET bundle ") \
EM(rxrpc_peer_get_client_conn, "GET cln-conn") \
EM(rxrpc_peer_get_input, "GET input ") \
@@ -191,7 +190,6 @@
EM(rxrpc_peer_put_bundle, "PUT bundle ") \
EM(rxrpc_peer_put_call, "PUT call ") \
EM(rxrpc_peer_put_conn, "PUT conn ") \
- EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \
EM(rxrpc_peer_put_input, "PUT input ") \
EM(rxrpc_peer_put_input_error, "PUT inpt-err") \
E_(rxrpc_peer_put_keepalive, "PUT keepaliv")
@@ -201,6 +199,7 @@
EM(rxrpc_bundle_get_client_call, "GET clt-call") \
EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \
EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \
+ EM(rxrpc_bundle_put_call, "PUT call ") \
EM(rxrpc_bundle_put_conn, "PUT conn ") \
EM(rxrpc_bundle_put_discard, "PUT discard ") \
E_(rxrpc_bundle_new, "NEW ")
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 6f6a6b77ee846..f4e1ffff2ba41 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -328,7 +328,6 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
mutex_unlock(&call->user_mutex);
}
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p", call);
return call;
}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e508ec221b75e..2740c63331140 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -360,7 +360,6 @@ struct rxrpc_conn_proto {
struct rxrpc_conn_parameters {
struct rxrpc_local *local; /* Representation of local endpoint */
- struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
@@ -428,6 +427,7 @@ struct rxrpc_bundle {
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
+ const struct rxrpc_security *security; /* applied security module */
refcount_t ref;
atomic_t active; /* Number of active users */
unsigned int debug_id;
@@ -593,6 +593,7 @@ enum rxrpc_congest_mode {
struct rxrpc_call {
struct rcu_head rcu;
struct rxrpc_connection *conn; /* connection carrying call */
+ struct rxrpc_bundle *bundle; /* Connection bundle to use */
struct rxrpc_peer *peer; /* Peer record for remote address */
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_sock __rcu *socket; /* socket responsible */
@@ -894,11 +895,10 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry;
void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local);
struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
-int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
- struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
- gfp_t);
+int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace);
void rxrpc_discard_expired_client_conns(struct work_struct *);
void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 705f6e26cc75e..835e9781afc6c 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -365,7 +365,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
+ ret = rxrpc_connect_call(call, gfp);
if (ret < 0)
goto error_attached_to_socket;
@@ -663,6 +663,8 @@ static void rxrpc_destroy_call(struct work_struct *work)
rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned);
rxrpc_put_connection(call->conn, rxrpc_conn_put_call);
+ rxrpc_deactivate_bundle(call->bundle);
+ rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call);
rxrpc_put_peer(call->peer, rxrpc_peer_put_call);
rxrpc_put_local(call->local, rxrpc_local_put_call);
call_rcu(&call->rcu, rxrpc_rcu_free_call);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 59ce5c08cf574..c0db7722571e3 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -34,7 +34,10 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900;
__read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
__read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
+static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle)
+{
+ atomic_inc(&bundle->active);
+}
/*
* Get a connection ID and epoch for a client connection from the global pool.
@@ -109,20 +112,21 @@ void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
/*
* Allocate a connection bundle.
*/
-static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
+static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
gfp_t gfp)
{
struct rxrpc_bundle *bundle;
bundle = kzalloc(sizeof(*bundle), gfp);
if (bundle) {
- bundle->local = cp->local;
- bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle);
- bundle->key = cp->key;
- bundle->exclusive = cp->exclusive;
- bundle->upgrade = cp->upgrade;
- bundle->service_id = cp->service_id;
- bundle->security_level = cp->security_level;
+ bundle->local = call->local;
+ bundle->peer = rxrpc_get_peer(call->peer, rxrpc_peer_get_bundle);
+ bundle->key = key_get(call->key);
+ bundle->security = call->security;
+ bundle->exclusive = test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags);
+ bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
+ bundle->service_id = call->dest_srx.srx_service;
+ bundle->security_level = call->security_level;
refcount_set(&bundle->ref, 1);
atomic_set(&bundle->active, 1);
spin_lock_init(&bundle->channel_lock);
@@ -146,19 +150,23 @@ static void rxrpc_free_bundle(struct rxrpc_bundle *bundle)
{
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free);
rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle);
+ key_put(bundle->key);
kfree(bundle);
}
void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why)
{
- unsigned int id = bundle->debug_id;
+ unsigned int id;
bool dead;
int r;
- dead = __refcount_dec_and_test(&bundle->ref, &r);
- trace_rxrpc_bundle(id, r - 1, why);
- if (dead)
- rxrpc_free_bundle(bundle);
+ if (bundle) {
+ id = bundle->debug_id;
+ dead = __refcount_dec_and_test(&bundle->ref, &r);
+ trace_rxrpc_bundle(id, r - 1, why);
+ if (dead)
+ rxrpc_free_bundle(bundle);
+ }
}
/*
@@ -272,20 +280,23 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
* Look up the conn bundle that matches the connection parameters, adding it if
* it doesn't yet exist.
*/
-static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp,
- gfp_t gfp)
+static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
{
static atomic_t rxrpc_bundle_id;
struct rxrpc_bundle *bundle, *candidate;
- struct rxrpc_local *local = cp->local;
+ struct rxrpc_local *local = call->local;
struct rb_node *p, **pp, *parent;
long diff;
+ bool upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
_enter("{%px,%x,%u,%u}",
- cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade);
+ call->peer, key_serial(call->key), call->security_level,
+ upgrade);
- if (cp->exclusive)
- return rxrpc_alloc_bundle(cp, gfp);
+ if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) {
+ call->bundle = rxrpc_alloc_bundle(call, gfp);
+ return call->bundle;
+ }
/* First, see if the bundle is already there. */
_debug("search 1");
@@ -294,11 +305,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
while (p) {
bundle = rb_entry(p, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
p = p->rb_left;
@@ -311,9 +322,9 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
_debug("not found");
/* It wasn't. We need to add one. */
- candidate = rxrpc_alloc_bundle(cp, gfp);
+ candidate = rxrpc_alloc_bundle(call, gfp);
if (!candidate)
- return NULL;
+ return ERR_PTR(-ENOMEM);
_debug("search 2");
spin_lock(&local->client_bundles_lock);
@@ -323,11 +334,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
parent = *pp;
bundle = rb_entry(parent, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
pp = &(*pp)->rb_left;
@@ -341,19 +352,19 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
rb_link_node(&candidate->local_node, parent, pp);
rb_insert_color(&candidate->local_node, &local->client_bundles);
- rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
+ call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [new]", candidate->debug_id);
- return candidate;
+ _leave(" = B=%u [new]", call->bundle->debug_id);
+ return call->bundle;
found_bundle_free:
rxrpc_free_bundle(candidate);
found_bundle:
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
- atomic_inc(&bundle->active);
+ call->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
+ rxrpc_activate_bundle(bundle);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [found]", bundle->debug_id);
- return bundle;
+ _leave(" = B=%u [found]", call->bundle->debug_id);
+ return call->bundle;
}
/*
@@ -362,31 +373,25 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c
* If we return with a connection, the call will be on its waiting list. It's
* left to the caller to assign a channel and wake up the call.
*/
-static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
+static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_call *call, gfp_t gfp)
{
struct rxrpc_bundle *bundle;
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- cp->peer = rxrpc_lookup_peer(cp->local, srx, gfp);
- if (!cp->peer)
+ call->peer = rxrpc_lookup_peer(call->local, &call->dest_srx, gfp);
+ if (!call->peer)
goto error;
call->tx_last_sent = ktime_get_real();
- call->cong_ssthresh = cp->peer->cong_ssthresh;
+ call->cong_ssthresh = call->peer->cong_ssthresh;
if (call->cong_cwnd >= call->cong_ssthresh)
call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
else
call->cong_mode = RXRPC_CALL_SLOW_START;
- if (cp->upgrade)
- __set_bit(RXRPC_CALL_UPGRADE, &call->flags);
/* Find the client connection bundle. */
- bundle = rxrpc_look_up_bundle(cp, gfp);
+ bundle = rxrpc_look_up_bundle(call, gfp);
if (!bundle)
goto error;
@@ -449,7 +454,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
if (old)
trace_rxrpc_client(old, -1, rxrpc_client_replace);
candidate->bundle_shift = shift;
- atomic_inc(&bundle->active);
+ rxrpc_activate_bundle(bundle);
bundle->conns[i] = candidate;
for (j = 0; j < RXRPC_MAXCALLS; j++)
set_bit(shift + j, &bundle->avail_chans);
@@ -541,7 +546,6 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
rxrpc_see_call(call, rxrpc_call_see_activate_client);
list_del_init(&call->chan_wait_link);
- call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call);
call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call);
call->cid = conn->proto.cid | channel;
call->call_id = call_id;
@@ -705,14 +709,11 @@ static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
* find a connection for a call
* - called in process context with IRQs enabled
*/
-int rxrpc_connect_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
+int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
{
struct rxrpc_bundle *bundle;
- struct rxrpc_net *rxnet = cp->local->rxnet;
+ struct rxrpc_local *local = call->local;
+ struct rxrpc_net *rxnet = local->rxnet;
int ret = 0;
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
@@ -721,7 +722,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
rxrpc_get_call(call, rxrpc_call_get_io_thread);
- bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
+ bundle = rxrpc_prep_call(call, gfp);
if (IS_ERR(bundle)) {
rxrpc_put_call(call, rxrpc_call_get_io_thread);
ret = PTR_ERR(bundle);
@@ -738,9 +739,6 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
/* Paired with the write barrier in rxrpc_activate_one_channel(). */
smp_rmb();
-out_put_bundle:
- rxrpc_deactivate_bundle(bundle);
- rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call);
out:
_leave(" = %d", ret);
return ret;
@@ -758,7 +756,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
rxrpc_disconnect_client_call(bundle, call);
- goto out_put_bundle;
+ goto out;
}
/*
@@ -945,11 +943,15 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
/*
* Drop the active count on a bundle.
*/
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
{
- struct rxrpc_local *local = bundle->local;
+ struct rxrpc_local *local;
bool need_put = false;
+ if (!bundle)
+ return;
+
+ local = bundle->local;
if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) {
if (!bundle->exclusive) {
_debug("erase bundle");
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 2e3f0a222e1b4..2a7d5378300cc 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -208,7 +208,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
}
if (rxrpc_is_client_call(call)) {
- rxrpc_disconnect_client_call(conn->bundle, call);
+ rxrpc_disconnect_client_call(call->bundle, call);
} else {
spin_lock(&conn->bundle->channel_lock);
__rxrpc_disconnect_call(conn, call);
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index d67808b659f13..2a003c3a9897e 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -564,7 +564,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
atomic_inc_return(&rxrpc_debug_id));
/* The socket is now unlocked */
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p\n", call);
return call;
}
--
GitLab
From 0b9bb322f13d486d5b8630264ccbfb4794bb43a9 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 27 Oct 2022 00:16:55 +0100
Subject: [PATCH 0440/1167] rxrpc: Split out the call state changing functions
into their own file
Split out the functions that change the state of an rxrpc call into their
own file. The idea being to remove anything to do with changing the state
of a call directly from the rxrpc sendmsg() and recvmsg() paths and have
all that done in the I/O thread only, with the ultimate aim of removing the
state lock entirely. Moving the code out of sendmsg.c and recvmsg.c makes
that easier to manage.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/Makefile | 1 +
net/rxrpc/ar-internal.h | 26 ++++++++----
net/rxrpc/call_state.c | 89 +++++++++++++++++++++++++++++++++++++++++
net/rxrpc/recvmsg.c | 81 -------------------------------------
4 files changed, 108 insertions(+), 89 deletions(-)
create mode 100644 net/rxrpc/call_state.c
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index e76d3459d78ee..ac5caf5a48e16 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -10,6 +10,7 @@ rxrpc-y := \
call_accept.o \
call_event.o \
call_object.o \
+ call_state.o \
conn_client.o \
conn_event.o \
conn_object.o \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 2740c63331140..203e0354d86bb 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -885,6 +885,24 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
return !rxrpc_is_service_call(call);
}
+/*
+ * call_state.c
+ */
+bool __rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error);
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error);
+bool __rxrpc_call_completed(struct rxrpc_call *call);
+bool rxrpc_call_completed(struct rxrpc_call *call);
+bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
+
/*
* conn_client.c
*/
@@ -1116,14 +1134,6 @@ extern const struct seq_operations rxrpc_local_seq_ops;
* recvmsg.c
*/
void rxrpc_notify_socket(struct rxrpc_call *);
-bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool __rxrpc_call_completed(struct rxrpc_call *);
-bool rxrpc_call_completed(struct rxrpc_call *);
-bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why);
-bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c
new file mode 100644
index 0000000000000..8fbb2112ed7e2
--- /dev/null
+++ b/net/rxrpc/call_state.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Call state changing functions.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include "ar-internal.h"
+
+/*
+ * Transition a call to the complete state.
+ */
+bool __rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error)
+{
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ call->abort_code = abort_code;
+ call->error = error;
+ call->completion = compl;
+ call->state = RXRPC_CALL_COMPLETE;
+ trace_rxrpc_call_complete(call);
+ wake_up(&call->waitq);
+ rxrpc_notify_socket(call);
+ return true;
+ }
+ return false;
+}
+
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error)
+{
+ bool ret = false;
+
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ write_lock(&call->state_lock);
+ ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
+ write_unlock(&call->state_lock);
+ }
+ return ret;
+}
+
+/*
+ * Record that a call successfully completed.
+ */
+bool __rxrpc_call_completed(struct rxrpc_call *call)
+{
+ return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
+}
+
+bool rxrpc_call_completed(struct rxrpc_call *call)
+{
+ bool ret = false;
+
+ if (call->state < RXRPC_CALL_COMPLETE) {
+ write_lock(&call->state_lock);
+ ret = __rxrpc_call_completed(call);
+ write_unlock(&call->state_lock);
+ }
+ return ret;
+}
+
+/*
+ * Record that a call is locally aborted.
+ */
+bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
+{
+ trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
+ abort_code, error);
+ return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
+ abort_code, error);
+}
+
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
+{
+ bool ret;
+
+ write_lock(&call->state_lock);
+ ret = __rxrpc_abort_call(call, seq, abort_code, error, why);
+ write_unlock(&call->state_lock);
+ if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ rxrpc_send_abort_packet(call);
+ return ret;
+}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 59b521b82aec3..ff08f917ecda2 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -58,87 +58,6 @@ void rxrpc_notify_socket(struct rxrpc_call *call)
_leave("");
}
-/*
- * Transition a call to the complete state.
- */
-bool __rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- if (call->state < RXRPC_CALL_COMPLETE) {
- call->abort_code = abort_code;
- call->error = error;
- call->completion = compl;
- call->state = RXRPC_CALL_COMPLETE;
- trace_rxrpc_call_complete(call);
- wake_up(&call->waitq);
- rxrpc_notify_socket(call);
- return true;
- }
- return false;
-}
-
-bool rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call successfully completed.
- */
-bool __rxrpc_call_completed(struct rxrpc_call *call)
-{
- return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
-}
-
-bool rxrpc_call_completed(struct rxrpc_call *call)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call is locally aborted.
- */
-bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why)
-{
- trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
- abort_code, error);
- return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
- abort_code, error);
-}
-
-bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why)
-{
- bool ret;
-
- write_lock(&call->state_lock);
- ret = __rxrpc_abort_call(call, seq, abort_code, error, why);
- write_unlock(&call->state_lock);
- if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags))
- rxrpc_send_abort_packet(call);
- return ret;
-}
-
/*
* Pass a call terminating message to userspace.
*/
--
GitLab
From d41b3f5b96881809c73f86e3ca436c9426610b7a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 19 Dec 2022 15:32:32 +0000
Subject: [PATCH 0441/1167] rxrpc: Wrap accesses to get call state to put the
barrier in one place
Wrap accesses to get the state of a call from outside of the I/O thread in
a single place so that the barrier needed to order wrt the error code and
abort code is in just that place.
Also use a barrier when setting the call state and again when reading the
call state such that the auxiliary completion info (error code, abort code)
can be read without taking a read lock on the call state lock.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/af_rxrpc.c | 2 +-
net/rxrpc/ar-internal.h | 16 ++++++++++++++++
net/rxrpc/call_state.c | 3 ++-
net/rxrpc/recvmsg.c | 12 ++++++------
net/rxrpc/sendmsg.c | 29 +++++++++++++----------------
5 files changed, 38 insertions(+), 24 deletions(-)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index f4e1ffff2ba41..61c30d0f67356 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -379,7 +379,7 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
bool rxrpc_kernel_check_life(const struct socket *sock,
const struct rxrpc_call *call)
{
- return call->state != RXRPC_CALL_COMPLETE;
+ return !rxrpc_call_is_complete(call);
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 203e0354d86bb..9e992487649c4 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -903,6 +903,22 @@ bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
u32 abort_code, int error, enum rxrpc_abort_reason why);
+static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call)
+{
+ /* Order read ->state before read ->error. */
+ return smp_load_acquire(&call->state);
+}
+
+static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
+
+static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call)
+{
+ return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED;
+}
+
/*
* conn_client.c
*/
diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c
index 8fbb2112ed7e2..649fb9e5d1af5 100644
--- a/net/rxrpc/call_state.c
+++ b/net/rxrpc/call_state.c
@@ -19,7 +19,8 @@ bool __rxrpc_set_call_completion(struct rxrpc_call *call,
call->abort_code = abort_code;
call->error = error;
call->completion = compl;
- call->state = RXRPC_CALL_COMPLETE;
+ /* Allow reader of completion state to operate locklessly */
+ smp_store_release(&call->state, RXRPC_CALL_COMPLETE);
trace_rxrpc_call_complete(call);
wake_up(&call->waitq);
rxrpc_notify_socket(call);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index ff08f917ecda2..7bf36a8839ecc 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -89,7 +89,7 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
break;
default:
- pr_err("Invalid terminal call state %u\n", call->state);
+ pr_err("Invalid terminal call state %u\n", call->completion);
BUG();
break;
}
@@ -111,7 +111,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
- if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY)
+ if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY)
rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
write_lock(&call->state_lock);
@@ -210,7 +210,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
rx_pkt_offset = call->rx_pkt_offset;
rx_pkt_len = call->rx_pkt_len;
- if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) {
+ if (rxrpc_call_state(call) >= RXRPC_CALL_SERVER_ACK_REQUEST) {
seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
ret = 1;
goto done;
@@ -416,7 +416,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
msg->msg_namelen = len;
}
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
@@ -436,7 +436,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
if (ret < 0)
goto error_unlock_call;
- if (call->state == RXRPC_CALL_COMPLETE) {
+ if (rxrpc_call_is_complete(call)) {
ret = rxrpc_recvmsg_term(call, msg);
if (ret < 0)
goto error_unlock_call;
@@ -516,7 +516,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
mutex_lock(&call->user_mutex);
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 2a003c3a9897e..f0b5822f3e04c 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -25,7 +25,7 @@ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
{
_enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
- if (!call->send_abort && call->state < RXRPC_CALL_COMPLETE) {
+ if (!call->send_abort && !rxrpc_call_is_complete(call)) {
call->send_abort_why = why;
call->send_abort_err = error;
call->send_abort_seq = 0;
@@ -60,7 +60,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (signal_pending(current))
@@ -95,7 +95,7 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
if (rxrpc_check_tx_space(call, &tx_win))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (timeout == 0 &&
@@ -124,7 +124,7 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
@@ -273,7 +273,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
ret = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto maybe_error;
- state = READ_ONCE(call->state);
+ state = rxrpc_call_state(call);
ret = -ESHUTDOWN;
if (state >= RXRPC_CALL_COMPLETE)
goto maybe_error;
@@ -350,7 +350,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
/* check for the far side aborting the call or a network error
* occurring */
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto call_terminated;
/* add the packet to the send queue if it's now full */
@@ -375,12 +375,9 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
success:
ret = copied;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) {
- read_lock(&call->state_lock);
- if (call->error < 0)
- ret = call->error;
- read_unlock(&call->state_lock);
- }
+ if (rxrpc_call_is_complete(call) &&
+ call->error < 0)
+ ret = call->error;
out:
call->tx_pending = txb;
_leave(" = %d", ret);
@@ -618,10 +615,10 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
return PTR_ERR(call);
/* ... and we have the call lock. */
ret = 0;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto out_put_unlock;
} else {
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_UNINITIALISED:
case RXRPC_CALL_CLIENT_AWAIT_CONN:
case RXRPC_CALL_SERVER_PREALLOC:
@@ -675,7 +672,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
break;
}
- state = READ_ONCE(call->state);
+ state = rxrpc_call_state(call);
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, state, call->conn);
@@ -735,7 +732,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
case RXRPC_CALL_SERVER_SEND_REPLY:
--
GitLab
From 2d689424b6184535890c251f937ccf815fde9cd2 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 11 Nov 2022 08:35:36 +0000
Subject: [PATCH 0442/1167] rxrpc: Move call state changes from sendmsg to I/O
thread
Move all the call state changes that are made in rxrpc_sendmsg() to the I/O
thread. This is a step towards removing the call state lock.
This requires the switch to the RXRPC_CALL_CLIENT_AWAIT_REPLY and
RXRPC_CALL_SERVER_SEND_REPLY states to be done when the last packet is
decanted from ->tx_sendmsg to ->tx_buffer in the I/O thread, not when it is
added to ->tx_sendmsg by sendmsg().
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
Documentation/networking/rxrpc.rst | 4 +-
net/rxrpc/call_event.c | 50 +++++++++++++++++++++-
net/rxrpc/sendmsg.c | 69 ++++++------------------------
3 files changed, 63 insertions(+), 60 deletions(-)
diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index 39494a6ea739c..e1af54424192b 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -880,8 +880,8 @@ The kernel interface functions are as follows:
notify_end_rx can be NULL or it can be used to specify a function to be
called when the call changes state to end the Tx phase. This function is
- called with the call-state spinlock held to prevent any reply or final ACK
- from being delivered first.
+ called with a spinlock held to prevent the last DATA packet from being
+ transmitted until the function returns.
(#) Receive data from a call::
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 695aeb70d1a6b..2e3c01060d59a 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -251,6 +251,50 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
_leave("");
}
+/*
+ * Start transmitting the reply to a service. This cancels the need to ACK the
+ * request if we haven't yet done so.
+ */
+static void rxrpc_begin_service_reply(struct rxrpc_call *call)
+{
+ unsigned long now;
+
+ write_lock(&call->state_lock);
+
+ if (call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
+ now = jiffies;
+ call->state = RXRPC_CALL_SERVER_SEND_REPLY;
+ WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
+ if (call->ackr_reason == RXRPC_ACK_DELAY)
+ call->ackr_reason = 0;
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
+ }
+
+ write_unlock(&call->state_lock);
+}
+
+/*
+ * Close the transmission phase. After this point there is no more data to be
+ * transmitted in the call.
+ */
+static void rxrpc_close_tx_phase(struct rxrpc_call *call)
+{
+ _debug("________awaiting reply/ACK__________");
+
+ write_lock(&call->state_lock);
+ switch (call->state) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ break;
+ case RXRPC_CALL_SERVER_SEND_REPLY:
+ call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
+ break;
+ default:
+ break;
+ }
+ write_unlock(&call->state_lock);
+}
+
static bool rxrpc_tx_window_has_space(struct rxrpc_call *call)
{
unsigned int winsize = min_t(unsigned int, call->tx_winsize,
@@ -285,6 +329,9 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call)
call->tx_top = txb->seq;
list_add_tail(&txb->call_link, &call->tx_buffer);
+ if (txb->wire.flags & RXRPC_LAST_PACKET)
+ rxrpc_close_tx_phase(call);
+
rxrpc_transmit_one(call, txb);
if (!rxrpc_tx_window_has_space(call))
@@ -298,12 +345,11 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call)
case RXRPC_CALL_SERVER_ACK_REQUEST:
if (list_empty(&call->tx_sendmsg))
return;
+ rxrpc_begin_service_reply(call);
fallthrough;
case RXRPC_CALL_SERVER_SEND_REPLY:
- case RXRPC_CALL_SERVER_AWAIT_ACK:
case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (!rxrpc_tx_window_has_space(call))
return;
if (list_empty(&call->tx_sendmsg)) {
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index f0b5822f3e04c..0428528abbf49 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -189,7 +189,6 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
struct rxrpc_txbuf *txb,
rxrpc_notify_end_tx_t notify_end_tx)
{
- unsigned long now;
rxrpc_seq_t seq = txb->seq;
bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke;
@@ -212,36 +211,10 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
poke = list_empty(&call->tx_sendmsg);
list_add_tail(&txb->call_link, &call->tx_sendmsg);
call->tx_prepared = seq;
+ if (last)
+ rxrpc_notify_end_tx(rx, call, notify_end_tx);
spin_unlock(&call->tx_lock);
- if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
- _debug("________awaiting reply/ACK__________");
- write_lock(&call->state_lock);
- switch (call->state) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- call->state = RXRPC_CALL_SERVER_SEND_REPLY;
- now = jiffies;
- WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
- if (call->ackr_reason == RXRPC_ACK_DELAY)
- call->ackr_reason = 0;
- trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
- if (!last)
- break;
- fallthrough;
- case RXRPC_CALL_SERVER_SEND_REPLY:
- call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- default:
- break;
- }
- write_unlock(&call->state_lock);
- }
-
if (poke)
rxrpc_poke_call(call, rxrpc_call_poke_start);
}
@@ -280,8 +253,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
ret = -EPROTO;
if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- state != RXRPC_CALL_SERVER_SEND_REPLY)
+ state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ /* Request phase complete for this client call */
+ trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EPROTO);
goto maybe_error;
+ }
ret = -EMSGSIZE;
if (call->tx_total_len != -1) {
@@ -573,7 +551,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
__releases(&rx->sk.sk_lock.slock)
{
- enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
bool dropped_lock = false;
@@ -672,11 +649,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
break;
}
- state = rxrpc_call_state(call);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, state, call->conn);
-
- if (state >= RXRPC_CALL_COMPLETE) {
+ if (rxrpc_call_is_complete(call)) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
@@ -722,7 +695,7 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
bool dropped_lock = false;
int ret;
- _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+ _enter("{%d},", call->debug_id);
ASSERTCMP(msg->msg_name, ==, NULL);
ASSERTCMP(msg->msg_control, ==, NULL);
@@ -732,26 +705,10 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
- switch (rxrpc_call_state(call)) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- case RXRPC_CALL_SERVER_SEND_REPLY:
- ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
- notify_end_tx, &dropped_lock);
- break;
- case RXRPC_CALL_COMPLETE:
- read_lock(&call->state_lock);
+ ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
+ notify_end_tx, &dropped_lock);
+ if (ret == -ESHUTDOWN)
ret = call->error;
- read_unlock(&call->state_lock);
- break;
- default:
- /* Request phase complete for this client call */
- trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
- call->cid, call->call_id, call->rx_consumed,
- 0, -EPROTO);
- ret = -EPROTO;
- break;
- }
if (!dropped_lock)
mutex_unlock(&call->user_mutex);
--
GitLab
From 93368b6bd58ac49d804fdc9ab041a6dc89ebf1cc Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 26 Oct 2022 23:43:00 +0100
Subject: [PATCH 0443/1167] rxrpc: Move call state changes from recvmsg to I/O
thread
Move the call state changes that are made in rxrpc_recvmsg() to the I/O
thread. This means that, thenceforth, only the I/O thread does this and
the call state lock can be removed.
This requires the Rx phase to be ended when the last packet is received,
not when it is processed.
Since this now changes the rxrpc call state to SUCCEEDED before we've
consumed all the data from it, rxrpc_kernel_check_life() mustn't say the
call is dead until the recvmsg queue is empty (unless the call has failed).
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
fs/afs/rxrpc.c | 1 +
net/rxrpc/af_rxrpc.c | 10 ++-
net/rxrpc/ar-internal.h | 3 +-
net/rxrpc/input.c | 38 ++++++++-
net/rxrpc/recvmsg.c | 168 +++++++++++++++-------------------------
5 files changed, 109 insertions(+), 111 deletions(-)
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index bd3830bc67006..7817e2b860e5e 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -909,6 +909,7 @@ int afs_extract_data(struct afs_call *call, bool want_more)
ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
&call->iov_len, want_more, &remote_abort,
&call->service_id);
+ trace_afs_receive_data(call, call->iter, want_more, ret);
if (ret == 0 || ret == -EAGAIN)
return ret;
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 61c30d0f67356..cf200e4e0eae1 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -373,13 +373,17 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
* @sock: The socket the call is on
* @call: The call to check
*
- * Allow a kernel service to find out whether a call is still alive -
- * ie. whether it has completed.
+ * Allow a kernel service to find out whether a call is still alive - whether
+ * it has completed successfully and all received data has been consumed.
*/
bool rxrpc_kernel_check_life(const struct socket *sock,
const struct rxrpc_call *call)
{
- return !rxrpc_call_is_complete(call);
+ if (!rxrpc_call_is_complete(call))
+ return true;
+ if (call->completion != RXRPC_CALL_SUCCEEDED)
+ return false;
+ return !skb_queue_empty(&call->recvmsg_queue);
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 9e992487649c4..8612734397361 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -545,7 +545,8 @@ enum rxrpc_call_flag {
RXRPC_CALL_KERNEL, /* The call was made by the kernel */
RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */
RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */
- RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */
+ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */
+ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */
};
/*
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index bd69ff2d90826..6eb21425f41fe 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -319,6 +319,41 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
return true;
}
+/*
+ * End the packet reception phase.
+ */
+static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
+{
+ rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
+
+ _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
+
+ trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
+
+ if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY)
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
+
+ write_lock(&call->state_lock);
+
+ switch (call->state) {
+ case RXRPC_CALL_CLIENT_RECV_REPLY:
+ __rxrpc_call_completed(call);
+ write_unlock(&call->state_lock);
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST:
+ call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
+ call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
+ write_unlock(&call->state_lock);
+ rxrpc_propose_delay_ACK(call, serial,
+ rxrpc_propose_ack_processing_op);
+ break;
+ default:
+ write_unlock(&call->state_lock);
+ break;
+ }
+}
+
static void rxrpc_input_update_ack_window(struct rxrpc_call *call,
rxrpc_seq_t window, rxrpc_seq_t wtop)
{
@@ -337,8 +372,9 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb,
__skb_queue_tail(&call->recvmsg_queue, skb);
rxrpc_input_update_ack_window(call, window, wtop);
-
trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq);
+ if (last)
+ rxrpc_end_rx_phase(call, sp->hdr.serial);
}
/*
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 7bf36a8839ecc..dd54ceee7bcc8 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -100,42 +100,6 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
return ret;
}
-/*
- * End the packet reception phase.
- */
-static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
-{
- rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
-
- _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
-
- trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
-
- if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY)
- rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
-
- write_lock(&call->state_lock);
-
- switch (call->state) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- rxrpc_poke_call(call, rxrpc_call_poke_complete);
- break;
-
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
- call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
- write_unlock(&call->state_lock);
- rxrpc_propose_delay_ACK(call, serial,
- rxrpc_propose_ack_processing_op);
- break;
- default:
- write_unlock(&call->state_lock);
- break;
- }
-}
-
/*
* Discard a packet we've used up and advance the Rx window by one.
*/
@@ -166,10 +130,9 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate,
serial, call->rx_consumed);
- if (last) {
- rxrpc_end_rx_phase(call, serial);
- return;
- }
+
+ if (last)
+ set_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags);
/* Check to see if there's an ACK that needs sending. */
acked = atomic_add_return(call->rx_consumed - old_consumed,
@@ -194,7 +157,8 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb)
/*
* Deliver messages to a call. This keeps processing packets until the buffer
* is filled and we find either more DATA (returns 0) or the end of the DATA
- * (returns 1). If more packets are required, it returns -EAGAIN.
+ * (returns 1). If more packets are required, it returns -EAGAIN and if the
+ * call has failed it returns -EIO.
*/
static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, struct iov_iter *iter,
@@ -210,7 +174,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
rx_pkt_offset = call->rx_pkt_offset;
rx_pkt_len = call->rx_pkt_len;
- if (rxrpc_call_state(call) >= RXRPC_CALL_SERVER_ACK_REQUEST) {
+ if (rxrpc_call_has_failed(call)) {
+ seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
+ ret = -EIO;
+ goto done;
+ }
+
+ if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) {
seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
ret = 1;
goto done;
@@ -234,14 +204,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
if (rx_pkt_offset == 0) {
ret2 = rxrpc_verify_data(call, skb);
- rx_pkt_offset = sp->offset;
- rx_pkt_len = sp->len;
trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq,
- rx_pkt_offset, rx_pkt_len, ret2);
+ sp->offset, sp->len, ret2);
if (ret2 < 0) {
+ kdebug("verify = %d", ret2);
ret = ret2;
goto out;
}
+ rx_pkt_offset = sp->offset;
+ rx_pkt_len = sp->len;
} else {
trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq,
rx_pkt_offset, rx_pkt_len, 0);
@@ -416,36 +387,36 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
msg->msg_namelen = len;
}
- switch (rxrpc_call_state(call)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
- flags, &copied);
- if (ret == -EAGAIN)
- ret = 0;
-
- if (!skb_queue_empty(&call->recvmsg_queue))
- rxrpc_notify_socket(call);
- break;
- default:
+ ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
+ flags, &copied);
+ if (ret == -EAGAIN)
ret = 0;
- break;
- }
-
+ if (ret == -EIO)
+ goto call_failed;
if (ret < 0)
goto error_unlock_call;
- if (rxrpc_call_is_complete(call)) {
- ret = rxrpc_recvmsg_term(call, msg);
- if (ret < 0)
- goto error_unlock_call;
- if (!(flags & MSG_PEEK))
- rxrpc_release_call(rx, call);
- msg->msg_flags |= MSG_EOR;
- ret = 1;
- }
+ if (rxrpc_call_is_complete(call) &&
+ skb_queue_empty(&call->recvmsg_queue))
+ goto call_complete;
+ if (rxrpc_call_has_failed(call))
+ goto call_failed;
+ rxrpc_notify_socket(call);
+ goto not_yet_complete;
+
+call_failed:
+ rxrpc_purge_queue(&call->recvmsg_queue);
+call_complete:
+ ret = rxrpc_recvmsg_term(call, msg);
+ if (ret < 0)
+ goto error_unlock_call;
+ if (!(flags & MSG_PEEK))
+ rxrpc_release_call(rx, call);
+ msg->msg_flags |= MSG_EOR;
+ ret = 1;
+
+not_yet_complete:
if (ret == 0)
msg->msg_flags |= MSG_MORE;
else
@@ -508,49 +479,34 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
size_t offset = 0;
int ret;
- _enter("{%d,%s},%zu,%d",
- call->debug_id, rxrpc_call_states[call->state],
- *_len, want_more);
-
- ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING);
+ _enter("{%d},%zu,%d", call->debug_id, *_len, want_more);
mutex_lock(&call->user_mutex);
- switch (rxrpc_call_state(call)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
- *_len, 0, &offset);
- *_len -= offset;
- if (ret < 0)
- goto out;
-
- /* We can only reach here with a partially full buffer if we
- * have reached the end of the data. We must otherwise have a
- * full buffer or have been given -EAGAIN.
- */
- if (ret == 1) {
- if (iov_iter_count(iter) > 0)
- goto short_data;
- if (!want_more)
- goto read_phase_complete;
- ret = 0;
- goto out;
- }
-
- if (!want_more)
- goto excess_data;
+ ret = rxrpc_recvmsg_data(sock, call, NULL, iter, *_len, 0, &offset);
+ *_len -= offset;
+ if (ret == -EIO)
+ goto call_failed;
+ if (ret < 0)
goto out;
- case RXRPC_CALL_COMPLETE:
- goto call_complete;
-
- default:
- ret = -EINPROGRESS;
+ /* We can only reach here with a partially full buffer if we have
+ * reached the end of the data. We must otherwise have a full buffer
+ * or have been given -EAGAIN.
+ */
+ if (ret == 1) {
+ if (iov_iter_count(iter) > 0)
+ goto short_data;
+ if (!want_more)
+ goto read_phase_complete;
+ ret = 0;
goto out;
}
+ if (!want_more)
+ goto excess_data;
+ goto out;
+
read_phase_complete:
ret = 1;
out:
@@ -572,7 +528,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
0, -EMSGSIZE);
ret = -EMSGSIZE;
goto out;
-call_complete:
+call_failed:
*_abort = call->abort_code;
ret = call->error;
if (call->completion == RXRPC_CALL_SUCCEEDED) {
--
GitLab
From 96b4059f43ce69e9c590f77d6ce3e99888d5cfe6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 27 Oct 2022 11:25:55 +0100
Subject: [PATCH 0444/1167] rxrpc: Remove call->state_lock
All the setters of call->state are now in the I/O thread and thus the state
lock is now unnecessary.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/ar-internal.h | 33 +++++++++-----
net/rxrpc/call_accept.c | 2 +-
net/rxrpc/call_event.c | 42 ++++++++----------
net/rxrpc/call_object.c | 30 ++++++-------
net/rxrpc/call_state.c | 87 ++++++++++++++-----------------------
net/rxrpc/conn_client.c | 10 ++---
net/rxrpc/conn_event.c | 11 ++---
net/rxrpc/input.c | 96 ++++++++++++++++++-----------------------
net/rxrpc/output.c | 4 +-
net/rxrpc/proc.c | 6 ++-
net/rxrpc/rxkad.c | 2 +-
net/rxrpc/sendmsg.c | 3 --
12 files changed, 142 insertions(+), 184 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 8612734397361..751b1903fd6e1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -631,14 +631,13 @@ struct rxrpc_call {
unsigned long flags;
unsigned long events;
spinlock_t notify_lock; /* Kernel notification lock */
- rwlock_t state_lock; /* lock for state transition */
unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */
s32 send_abort; /* Abort code to be sent */
short send_abort_err; /* Error to be associated with the abort */
rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */
s32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
- enum rxrpc_call_state state; /* current state of call */
+ enum rxrpc_call_state _state; /* Current state of call (needs barrier) */
enum rxrpc_call_completion completion; /* Call completion condition */
refcount_t ref;
u8 security_ix; /* Security type */
@@ -889,25 +888,37 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
/*
* call_state.c
*/
-bool __rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error);
bool rxrpc_set_call_completion(struct rxrpc_call *call,
enum rxrpc_call_completion compl,
u32 abort_code,
int error);
-bool __rxrpc_call_completed(struct rxrpc_call *call);
bool rxrpc_call_completed(struct rxrpc_call *call);
-bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why);
bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
u32 abort_code, int error, enum rxrpc_abort_reason why);
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error);
+
+static inline void rxrpc_set_call_state(struct rxrpc_call *call,
+ enum rxrpc_call_state state)
+{
+ /* Order write of completion info before write of ->state. */
+ smp_store_release(&call->_state, state);
+}
+
+static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call)
+{
+ return call->_state; /* Only inside I/O thread */
+}
+
+static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call)
{
- /* Order read ->state before read ->error. */
- return smp_load_acquire(&call->state);
+ /* Order read ->state before read of completion info. */
+ return smp_load_acquire(&call->_state);
}
static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call)
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a132d486dea0d..3fbf2fcaaf9e2 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -99,7 +99,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
- call->state = RXRPC_CALL_SERVER_PREALLOC;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC);
__set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 2e3c01060d59a..1abdef15debce 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -257,20 +257,13 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb)
*/
static void rxrpc_begin_service_reply(struct rxrpc_call *call)
{
- unsigned long now;
-
- write_lock(&call->state_lock);
-
- if (call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
- now = jiffies;
- call->state = RXRPC_CALL_SERVER_SEND_REPLY;
- WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
- if (call->ackr_reason == RXRPC_ACK_DELAY)
- call->ackr_reason = 0;
- trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
- }
+ unsigned long now = jiffies;
- write_unlock(&call->state_lock);
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY);
+ WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
+ if (call->ackr_reason == RXRPC_ACK_DELAY)
+ call->ackr_reason = 0;
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
}
/*
@@ -281,18 +274,16 @@ static void rxrpc_close_tx_phase(struct rxrpc_call *call)
{
_debug("________awaiting reply/ACK__________");
- write_lock(&call->state_lock);
- switch (call->state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
break;
case RXRPC_CALL_SERVER_SEND_REPLY:
- call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK);
break;
default:
break;
}
- write_unlock(&call->state_lock);
}
static bool rxrpc_tx_window_has_space(struct rxrpc_call *call)
@@ -341,7 +332,7 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call)
static void rxrpc_transmit_some_data(struct rxrpc_call *call)
{
- switch (call->state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_ACK_REQUEST:
if (list_empty(&call->tx_sendmsg))
return;
@@ -390,9 +381,10 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
//printk("\n--------------------\n");
_enter("{%d,%s,%lx}",
- call->debug_id, rxrpc_call_states[call->state], call->events);
+ call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)],
+ call->events);
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
goto out;
/* Handle abort request locklessly, vs rxrpc_propose_abort(). */
@@ -415,7 +407,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
}
t = READ_ONCE(call->expect_req_by);
- if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST &&
+ if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST &&
time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
expired = true;
@@ -499,7 +491,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
rxrpc_propose_ack_ping_for_lost_ack);
- if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY)
+ if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY)
rxrpc_resend(call, NULL);
if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags))
@@ -511,7 +503,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
rxrpc_propose_ack_input_data);
/* Make sure the timer is restarted */
- if (call->state != RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
next = call->expect_rx_by;
#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
@@ -532,7 +524,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
}
out:
- if (call->state == RXRPC_CALL_COMPLETE) {
+ if (__rxrpc_call_is_complete(call)) {
del_timer_sync(&call->timer);
if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
rxrpc_disconnect_call(call);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 835e9781afc6c..c94161acf3c41 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -69,7 +69,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t)
_enter("%d", call->debug_id);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
trace_rxrpc_timer_expired(call, jiffies);
rxrpc_poke_call(call, rxrpc_call_poke_timer);
}
@@ -162,7 +162,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->notify_lock);
spin_lock_init(&call->tx_lock);
- rwlock_init(&call->state_lock);
refcount_set(&call->ref, 1);
call->debug_id = debug_id;
call->tx_total_len = -1;
@@ -211,7 +210,6 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
now = ktime_get_real();
call->acks_latest_ts = now;
call->cong_tstamp = now;
- call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
call->dest_srx = *srx;
call->interruptibility = p->interruptibility;
call->tx_total_len = p->tx_total_len;
@@ -227,11 +225,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
ret = rxrpc_init_client_call_security(call);
if (ret < 0) {
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
rxrpc_put_call(call, rxrpc_call_put_discard_error);
return ERR_PTR(ret);
}
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN);
+
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
p->user_call_ID, rxrpc_call_new_client);
@@ -384,8 +384,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
error_dup_user_ID:
write_unlock(&rx->call_lock);
release_sock(&rx->sk);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, -EEXIST);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0,
rxrpc_call_see_userid_exists);
rxrpc_release_call(rx, call);
@@ -403,8 +402,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret,
rxrpc_call_see_connect_failed);
set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, ret);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
_leave(" = c=%08x [err]", call->debug_id);
return call;
}
@@ -427,25 +425,25 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
call->call_id = sp->hdr.callNumber;
call->dest_srx.srx_service = sp->hdr.serviceId;
call->cid = sp->hdr.cid;
- call->state = RXRPC_CALL_SERVER_SECURING;
call->cong_tstamp = skb->tstamp;
__set_bit(RXRPC_CALL_EXPOSED, &call->flags);
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE_UNSECURED:
case RXRPC_CONN_SERVICE_CHALLENGING:
- call->state = RXRPC_CALL_SERVER_SECURING;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
break;
case RXRPC_CONN_SERVICE:
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
break;
case RXRPC_CONN_ABORTED:
- __rxrpc_set_call_completion(call, conn->completion,
- conn->abort_code, conn->error);
+ rxrpc_set_call_completion(call, conn->completion,
+ conn->abort_code, conn->error);
break;
default:
BUG();
@@ -614,7 +612,7 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
dead = __refcount_dec_and_test(&call->ref, &r);
trace_rxrpc_call(debug_id, r - 1, 0, why);
if (dead) {
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
if (!list_empty(&call->link)) {
spin_lock(&rxnet->call_lock);
@@ -677,7 +675,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
{
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
del_timer(&call->timer);
@@ -715,7 +713,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
call, refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[__rxrpc_call_state(call)],
call->flags, call->events);
spin_unlock(&rxnet->call_lock);
diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c
index 649fb9e5d1af5..27dc1242b7125 100644
--- a/net/rxrpc/call_state.c
+++ b/net/rxrpc/call_state.c
@@ -10,81 +10,60 @@
/*
* Transition a call to the complete state.
*/
-bool __rxrpc_set_call_completion(struct rxrpc_call *call,
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
enum rxrpc_call_completion compl,
u32 abort_code,
int error)
{
- if (call->state < RXRPC_CALL_COMPLETE) {
- call->abort_code = abort_code;
- call->error = error;
- call->completion = compl;
- /* Allow reader of completion state to operate locklessly */
- smp_store_release(&call->state, RXRPC_CALL_COMPLETE);
- trace_rxrpc_call_complete(call);
- wake_up(&call->waitq);
- rxrpc_notify_socket(call);
- return true;
- }
- return false;
-}
-
-bool rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- bool ret = false;
+ if (__rxrpc_call_state(call) == RXRPC_CALL_COMPLETE)
+ return false;
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
- write_unlock(&call->state_lock);
- }
- return ret;
+ call->abort_code = abort_code;
+ call->error = error;
+ call->completion = compl;
+ /* Allow reader of completion state to operate locklessly */
+ rxrpc_set_call_state(call, RXRPC_CALL_COMPLETE);
+ trace_rxrpc_call_complete(call);
+ wake_up(&call->waitq);
+ rxrpc_notify_socket(call);
+ return true;
}
/*
* Record that a call successfully completed.
*/
-bool __rxrpc_call_completed(struct rxrpc_call *call)
-{
- return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
-}
-
bool rxrpc_call_completed(struct rxrpc_call *call)
{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- }
- return ret;
+ return rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
}
/*
* Record that a call is locally aborted.
*/
-bool __rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why)
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
abort_code, error);
- return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
- abort_code, error);
+ if (!rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
+ abort_code, error))
+ return false;
+ if (test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ rxrpc_send_abort_packet(call);
+ return true;
}
-bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
- u32 abort_code, int error, enum rxrpc_abort_reason why)
+/*
+ * Record that a call errored out before even getting off the ground, thereby
+ * setting the state to allow it to be destroyed.
+ */
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error)
{
- bool ret;
-
- write_lock(&call->state_lock);
- ret = __rxrpc_abort_call(call, seq, abort_code, error, why);
- write_unlock(&call->state_lock);
- if (ret && test_bit(RXRPC_CALL_EXPOSED, &call->flags))
- rxrpc_send_abort_packet(call);
- return ret;
+ call->abort_code = RX_CALL_DEAD;
+ call->error = error;
+ call->completion = compl;
+ call->_state = RXRPC_CALL_COMPLETE;
+ trace_rxrpc_call_complete(call);
+ __set_bit(RXRPC_CALL_RELEASED, &call->flags);
}
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index c0db7722571e3..8b5ea68dc47e7 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -553,9 +553,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
trace_rxrpc_connect_call(call);
- write_lock(&call->state_lock);
- call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
- write_unlock(&call->state_lock);
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
/* Paired with the read barrier in rxrpc_connect_call(). This orders
* cid and epoch in the connection wrt to call_id without the need to
@@ -687,7 +685,7 @@ static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
set_current_state(TASK_UNINTERRUPTIBLE);
break;
}
- if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
break;
if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
@@ -729,7 +727,7 @@ int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
goto out;
}
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) {
+ if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_CONN) {
ret = rxrpc_wait_for_channel(bundle, call, gfp);
if (ret < 0)
goto wait_failed;
@@ -748,7 +746,7 @@ int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
list_del_init(&call->chan_wait_link);
spin_unlock(&bundle->channel_lock);
- if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) {
ret = 0;
goto granted_channel;
}
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b2042702ca9aa..8d0b9ff0a5e15 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -230,14 +230,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn)
*/
static void rxrpc_call_is_secure(struct rxrpc_call *call)
{
- _enter("%p", call);
- if (call) {
- write_lock(&call->state_lock);
- if (call->state == RXRPC_CALL_SERVER_SECURING) {
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- rxrpc_notify_socket(call);
- }
- write_unlock(&call->state_lock);
+ if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) {
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
+ rxrpc_notify_socket(call);
}
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 6eb21425f41fe..367927a998815 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -184,7 +184,7 @@ void rxrpc_congestion_degrade(struct rxrpc_call *call)
if (call->cong_mode != RXRPC_CALL_SLOW_START &&
call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE)
return;
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
+ if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY)
return;
rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8));
@@ -252,43 +252,31 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to,
static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
enum rxrpc_abort_reason abort_why)
{
- unsigned int state;
-
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
- write_lock(&call->state_lock);
-
- state = call->state;
- switch (state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
- if (reply_begun)
- call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
- else
- call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ if (reply_begun) {
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
+ break;
+ }
+
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
- __rxrpc_call_completed(call);
- state = call->state;
+ rxrpc_call_completed(call);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
break;
default:
- goto bad_state;
+ kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]);
+ rxrpc_proto_abort(call, call->tx_top, abort_why);
+ break;
}
-
- write_unlock(&call->state_lock);
- if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
- trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
- else
- trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
- _leave(" = ok");
- return;
-
-bad_state:
- write_unlock(&call->state_lock);
- kdebug("end_tx %s", rxrpc_call_states[call->state]);
- rxrpc_proto_abort(call, call->tx_top, abort_why);
}
/*
@@ -303,7 +291,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call)
if (call->ackr_reason) {
now = jiffies;
timo = now + MAX_JIFFY_OFFSET;
- WRITE_ONCE(call->resend_at, timo);
+
WRITE_ONCE(call->delay_ack_at, timo);
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
@@ -326,30 +314,23 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
{
rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
- _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
+ _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]);
trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
- if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_RECV_REPLY)
- rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
-
- write_lock(&call->state_lock);
-
- switch (call->state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
- __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
+ rxrpc_call_completed(call);
break;
case RXRPC_CALL_SERVER_RECV_REQUEST:
- call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST);
call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
- write_unlock(&call->state_lock);
- rxrpc_propose_delay_ACK(call, serial,
- rxrpc_propose_ack_processing_op);
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op);
break;
+
default:
- write_unlock(&call->state_lock);
break;
}
}
@@ -583,7 +564,6 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb
static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- enum rxrpc_call_state state;
rxrpc_serial_t serial = sp->hdr.serial;
rxrpc_seq_t seq0 = sp->hdr.seq;
@@ -591,11 +571,20 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
atomic64_read(&call->ackr_window), call->rx_highest_seq,
skb->len, seq0);
- state = READ_ONCE(call->state);
- if (state >= RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
return;
- if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ case RXRPC_CALL_CLIENT_AWAIT_REPLY:
+ /* Received data implicitly ACKs all of the request
+ * packets we sent when we're acting as a client.
+ */
+ if (!rxrpc_receiving_reply(call))
+ goto out_notify;
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST: {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
@@ -606,15 +595,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
rxrpc_reduce_call_timer(call, expect_req_by, now,
rxrpc_timer_set_for_idle);
}
+ break;
}
- /* Received data implicitly ACKs all of the request packets we sent
- * when we're acting as a client.
- */
- if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
- state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
- !rxrpc_receiving_reply(call))
- goto out_notify;
+ default:
+ break;
+ }
if (!rxrpc_input_split_jumbo(call, skb)) {
rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo);
@@ -904,7 +890,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
/* Ignore ACKs unless we are or have just been transmitting. */
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
@@ -1027,7 +1013,7 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb)
*/
void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
{
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
fallthrough;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 8a5ff2c9e0612..a9746be296347 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -261,7 +261,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
rxrpc_tx_point_call_ack);
rxrpc_tx_backoff(call, ret);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
if (ret < 0)
rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
rxrpc_set_keepalive(call);
@@ -723,7 +723,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
static inline void rxrpc_instant_resend(struct rxrpc_call *call,
struct rxrpc_txbuf *txb)
{
- if (call->state < RXRPC_CALL_COMPLETE)
+ if (!__rxrpc_call_is_complete(call))
kdebug("resend");
}
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 63947cce40483..c39ef94602ed7 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -50,6 +50,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
struct rxrpc_local *local;
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ enum rxrpc_call_state state;
unsigned long timeout = 0;
rxrpc_seq_t acks_hard_ack;
char lbuff[50], rbuff[50];
@@ -74,7 +75,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
sprintf(rbuff, "%pISpc", &call->dest_srx.transport);
- if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
+ state = rxrpc_call_state(call);
+ if (state != RXRPC_CALL_SERVER_PREALLOC) {
timeout = READ_ONCE(call->expect_rx_by);
timeout -= jiffies;
}
@@ -91,7 +93,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
call->call_id,
rxrpc_is_service_call(call) ? "Svc" : "Clt",
refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[state],
call->abort_code,
call->debug_id,
acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack,
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index e52cb8058156f..dfb01e7b90fbb 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1143,7 +1143,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
call = rcu_dereference_protected(
conn->channels[i].call,
lockdep_is_held(&conn->bundle->channel_lock));
- if (call && call->state < RXRPC_CALL_COMPLETE) {
+ if (call && !__rxrpc_call_is_complete(call)) {
rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
rxkad_abort_resp_call_state);
goto protocol_error_unlock;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 0428528abbf49..a5d0005b7ce52 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -702,9 +702,6 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
mutex_lock(&call->user_mutex);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, call->state, call->conn);
-
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
notify_end_tx, &dropped_lock);
if (ret == -ESHUTDOWN)
--
GitLab
From 0d6bf319bc5aba4535bb46e1b607973688a2248a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 2 Nov 2022 16:46:13 +0000
Subject: [PATCH 0445/1167] rxrpc: Move the client conn cache management to the
I/O thread
Move the management of the client connection cache to the I/O thread rather
than managing it from the namespace as an aggregate across all the local
endpoints within the namespace.
This will allow a load of locking to be got rid of in a future patch as
only the I/O thread will be looking at the this.
The downside is that the total number of cached connections on the system
can get higher because the limit is now per-local rather than per-netns.
We can, however, keep the number of client conns in use across the entire
netfs and use that to reduce the expiration time of idle connection.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/ar-internal.h | 17 ++++----
net/rxrpc/conn_client.c | 92 ++++++++++++++--------------------------
net/rxrpc/conn_object.c | 1 -
net/rxrpc/io_thread.c | 4 ++
net/rxrpc/local_object.c | 17 ++++++++
net/rxrpc/net_ns.c | 17 --------
6 files changed, 62 insertions(+), 86 deletions(-)
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 751b1903fd6e1..de84061a54472 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -76,13 +76,7 @@ struct rxrpc_net {
bool live;
- bool kill_all_client_conns;
atomic_t nr_client_conns;
- spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
- struct mutex client_conn_discard_lock; /* Prevent multiple discarders */
- struct list_head idle_client_conns;
- struct work_struct client_conn_reaper;
- struct timer_list client_conn_reap_timer;
struct hlist_head local_endpoints;
struct mutex local_mutex; /* Lock for ->local_endpoints */
@@ -294,8 +288,16 @@ struct rxrpc_local {
struct sk_buff_head rx_queue; /* Received packets */
struct list_head conn_attend_q; /* Conns requiring immediate attention */
struct list_head call_attend_q; /* Calls requiring immediate attention */
+
struct rb_root client_bundles; /* Client connection bundles by socket params */
spinlock_t client_bundles_lock; /* Lock for client_bundles */
+ bool kill_all_client_conns;
+ spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
+ struct list_head idle_client_conns;
+ struct timer_list client_conn_reap_timer;
+ unsigned long client_conn_flags;
+#define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */
+
spinlock_t lock; /* access lock */
rwlock_t services_lock; /* lock for services list */
int debug_id; /* debug ID for printks */
@@ -946,8 +948,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace);
-void rxrpc_discard_expired_client_conns(struct work_struct *);
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local);
void rxrpc_clean_up_local_conns(struct rxrpc_local *);
/*
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 8b5ea68dc47e7..ebb43f65ebc51 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -578,17 +578,17 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
*/
static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
{
- struct rxrpc_net *rxnet = bundle->local->rxnet;
+ struct rxrpc_local *local = bundle->local;
bool drop_ref;
if (!list_empty(&conn->cache_link)) {
drop_ref = false;
- spin_lock(&rxnet->client_conn_cache_lock);
+ spin_lock(&local->client_conn_cache_lock);
if (!list_empty(&conn->cache_link)) {
list_del_init(&conn->cache_link);
drop_ref = true;
}
- spin_unlock(&rxnet->client_conn_cache_lock);
+ spin_unlock(&local->client_conn_cache_lock);
if (drop_ref)
rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
}
@@ -710,14 +710,10 @@ static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
{
struct rxrpc_bundle *bundle;
- struct rxrpc_local *local = call->local;
- struct rxrpc_net *rxnet = local->rxnet;
int ret = 0;
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
- rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
-
rxrpc_get_call(call, rxrpc_call_get_io_thread);
bundle = rxrpc_prep_call(call, gfp);
@@ -787,14 +783,14 @@ void rxrpc_expose_client_call(struct rxrpc_call *call)
/*
* Set the reap timer.
*/
-static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
+static void rxrpc_set_client_reap_timer(struct rxrpc_local *local)
{
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
unsigned long now = jiffies;
unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
- if (rxnet->live)
- timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+ if (local->rxnet->live)
+ timer_reduce(&local->client_conn_reap_timer, reap_at);
}
}
@@ -805,7 +801,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan = NULL;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
+ struct rxrpc_local *local = bundle->local;
unsigned int channel;
bool may_reuse;
u32 cid;
@@ -895,11 +891,11 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
conn->idle_timestamp = jiffies;
rxrpc_get_connection(conn, rxrpc_conn_get_idle);
- spin_lock(&rxnet->client_conn_cache_lock);
- list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
- spin_unlock(&rxnet->client_conn_cache_lock);
+ spin_lock(&local->client_conn_cache_lock);
+ list_move_tail(&conn->cache_link, &local->idle_client_conns);
+ spin_unlock(&local->client_conn_cache_lock);
- rxrpc_set_client_reap_timer(rxnet);
+ rxrpc_set_client_reap_timer(local);
}
out:
@@ -986,42 +982,34 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
* This may be called from conn setup or from a work item so cannot be
* considered non-reentrant.
*/
-void rxrpc_discard_expired_client_conns(struct work_struct *work)
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet =
- container_of(work, struct rxrpc_net, client_conn_reaper);
unsigned long expiry, conn_expires_at, now;
unsigned int nr_conns;
_enter("");
- if (list_empty(&rxnet->idle_client_conns)) {
+ if (list_empty(&local->idle_client_conns)) {
_leave(" [empty]");
return;
}
- /* Don't double up on the discarding */
- if (!mutex_trylock(&rxnet->client_conn_discard_lock)) {
- _leave(" [already]");
- return;
- }
-
/* We keep an estimate of what the number of conns ought to be after
* we've discarded some so that we don't overdo the discarding.
*/
- nr_conns = atomic_read(&rxnet->nr_client_conns);
+ nr_conns = atomic_read(&local->rxnet->nr_client_conns);
next:
- spin_lock(&rxnet->client_conn_cache_lock);
+ spin_lock(&local->client_conn_cache_lock);
- if (list_empty(&rxnet->idle_client_conns))
+ if (list_empty(&local->idle_client_conns))
goto out;
- conn = list_entry(rxnet->idle_client_conns.next,
+ conn = list_entry(local->idle_client_conns.next,
struct rxrpc_connection, cache_link);
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
/* If the number of connections is over the reap limit, we
* expedite discard by reducing the expiry timeout. We must,
* however, have at least a short grace period to be able to do
@@ -1044,7 +1032,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
trace_rxrpc_client(conn, -1, rxrpc_client_discard);
list_del_init(&conn->cache_link);
- spin_unlock(&rxnet->client_conn_cache_lock);
+ spin_unlock(&local->client_conn_cache_lock);
rxrpc_unbundle_conn(conn);
/* Drop the ->cache_link ref */
@@ -1062,32 +1050,11 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
* then things get messier.
*/
_debug("not yet");
- if (!rxnet->kill_all_client_conns)
- timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at);
+ if (!local->kill_all_client_conns)
+ timer_reduce(&local->client_conn_reap_timer, conn_expires_at);
out:
- spin_unlock(&rxnet->client_conn_cache_lock);
- mutex_unlock(&rxnet->client_conn_discard_lock);
- _leave("");
-}
-
-/*
- * Preemptively destroy all the client connection records rather than waiting
- * for them to time out
- */
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet)
-{
- _enter("");
-
- spin_lock(&rxnet->client_conn_cache_lock);
- rxnet->kill_all_client_conns = true;
- spin_unlock(&rxnet->client_conn_cache_lock);
-
- del_timer_sync(&rxnet->client_conn_reap_timer);
-
- if (!rxrpc_queue_work(&rxnet->client_conn_reaper))
- _debug("destroy: queue failed");
-
+ spin_unlock(&local->client_conn_cache_lock);
_leave("");
}
@@ -1097,14 +1064,19 @@ void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet)
void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
{
struct rxrpc_connection *conn, *tmp;
- struct rxrpc_net *rxnet = local->rxnet;
LIST_HEAD(graveyard);
_enter("");
- spin_lock(&rxnet->client_conn_cache_lock);
+ spin_lock(&local->client_conn_cache_lock);
+ local->kill_all_client_conns = true;
+ spin_unlock(&local->client_conn_cache_lock);
+
+ del_timer_sync(&local->client_conn_reap_timer);
+
+ spin_lock(&local->client_conn_cache_lock);
- list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
+ list_for_each_entry_safe(conn, tmp, &local->idle_client_conns,
cache_link) {
if (conn->local == local) {
atomic_dec(&conn->active);
@@ -1113,7 +1085,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
}
}
- spin_unlock(&rxnet->client_conn_cache_lock);
+ spin_unlock(&local->client_conn_cache_lock);
while (!list_empty(&graveyard)) {
conn = list_entry(graveyard.next,
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 2a7d5378300cc..3d8c1dc6a82ae 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -470,7 +470,6 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet)
_enter("");
atomic_dec(&rxnet->nr_conns);
- rxrpc_destroy_all_client_connections(rxnet);
del_timer_sync(&rxnet->service_conn_reap_timer);
rxrpc_queue_work(&rxnet->service_conn_reaper);
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index 751139b3c1ac9..a299cc34c1403 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -435,6 +435,10 @@ int rxrpc_io_thread(void *data)
continue;
}
+ if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags))
+ rxrpc_discard_expired_client_conns(local);
+
/* Deal with calls that want immediate attention. */
if ((call = list_first_entry_or_null(&local->call_attend_q,
struct rxrpc_call,
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index ca8b3ee68b597..9bc8d08ca12cf 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -82,6 +82,16 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
}
}
+static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
+{
+ struct rxrpc_local *local =
+ container_of(timer, struct rxrpc_local, client_conn_reap_timer);
+
+ if (local->kill_all_client_conns &&
+ test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags))
+ rxrpc_wake_up_io_thread(local);
+}
+
/*
* Allocate a new local endpoint.
*/
@@ -103,8 +113,15 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
skb_queue_head_init(&local->rx_queue);
INIT_LIST_HEAD(&local->conn_attend_q);
INIT_LIST_HEAD(&local->call_attend_q);
+
local->client_bundles = RB_ROOT;
spin_lock_init(&local->client_bundles_lock);
+ local->kill_all_client_conns = false;
+ spin_lock_init(&local->client_conn_cache_lock);
+ INIT_LIST_HEAD(&local->idle_client_conns);
+ timer_setup(&local->client_conn_reap_timer,
+ rxrpc_client_conn_reap_timeout, 0);
+
spin_lock_init(&local->lock);
rwlock_init(&local->services_lock);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index 5905530e2f33b..a0319c040c25d 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -10,15 +10,6 @@
unsigned int rxrpc_net_id;
-static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
-{
- struct rxrpc_net *rxnet =
- container_of(timer, struct rxrpc_net, client_conn_reap_timer);
-
- if (rxnet->live)
- rxrpc_queue_work(&rxnet->client_conn_reaper);
-}
-
static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
@@ -63,14 +54,6 @@ static __net_init int rxrpc_init_net(struct net *net)
rxrpc_service_conn_reap_timeout, 0);
atomic_set(&rxnet->nr_client_conns, 0);
- rxnet->kill_all_client_conns = false;
- spin_lock_init(&rxnet->client_conn_cache_lock);
- mutex_init(&rxnet->client_conn_discard_lock);
- INIT_LIST_HEAD(&rxnet->idle_client_conns);
- INIT_WORK(&rxnet->client_conn_reaper,
- rxrpc_discard_expired_client_conns);
- timer_setup(&rxnet->client_conn_reap_timer,
- rxrpc_client_conn_reap_timeout, 0);
INIT_HLIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
--
GitLab
From 9d35d880e0e4a3ab32d8c12f9e4d76198aadd42d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 19 Oct 2022 09:45:43 +0100
Subject: [PATCH 0446/1167] rxrpc: Move client call connection to the I/O
thread
Move the connection setup of client calls to the I/O thread so that a whole
load of locking and barrierage can be eliminated. This necessitates the
app thread waiting for connection to complete before it can begin
encrypting data.
This also completes the fix for a race that exists between call connection
and call disconnection whereby the data transmission code adds the call to
the peer error distribution list after the call has been disconnected (say
by the rxrpc socket getting closed).
The fix is to complete the process of moving call connection, data
transmission and call disconnection into the I/O thread and thus forcibly
serialising them.
Note that the issue may predate the overhaul to an I/O thread model that
were included in the merge window for v6.2, but the timing is very much
changed by the change given below.
Fixes: cf37b5987508 ("rxrpc: Move DATA transmission into call processor work item")
Reported-by: syzbot+c22650d2844392afdcfd@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
---
include/trace/events/rxrpc.h | 5 +-
net/rxrpc/ar-internal.h | 22 +-
net/rxrpc/call_object.c | 58 +++-
net/rxrpc/call_state.c | 2 +-
net/rxrpc/conn_client.c | 533 ++++++++---------------------------
net/rxrpc/conn_event.c | 49 +---
net/rxrpc/conn_object.c | 19 +-
net/rxrpc/conn_service.c | 1 -
net/rxrpc/io_thread.c | 13 +-
net/rxrpc/local_object.c | 6 +-
net/rxrpc/proc.c | 1 +
net/rxrpc/rxkad.c | 21 +-
net/rxrpc/security.c | 33 +--
net/rxrpc/sendmsg.c | 64 +++++
14 files changed, 297 insertions(+), 530 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index e2f6b79d55170..283db0ea3db4b 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -218,7 +218,6 @@
EM(rxrpc_conn_put_call, "PUT call ") \
EM(rxrpc_conn_put_call_input, "PUT inp-call") \
EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \
- EM(rxrpc_conn_put_discard, "PUT discard ") \
EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \
EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \
EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \
@@ -240,12 +239,11 @@
EM(rxrpc_client_chan_activate, "ChActv") \
EM(rxrpc_client_chan_disconnect, "ChDisc") \
EM(rxrpc_client_chan_pass, "ChPass") \
- EM(rxrpc_client_chan_wait_failed, "ChWtFl") \
EM(rxrpc_client_cleanup, "Clean ") \
EM(rxrpc_client_discard, "Discar") \
- EM(rxrpc_client_duplicate, "Duplic") \
EM(rxrpc_client_exposed, "Expose") \
EM(rxrpc_client_replace, "Replac") \
+ EM(rxrpc_client_queue_new_call, "Q-Call") \
EM(rxrpc_client_to_active, "->Actv") \
E_(rxrpc_client_to_idle, "->Idle")
@@ -273,6 +271,7 @@
EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \
EM(rxrpc_call_put_unnotify, "PUT unnotify") \
EM(rxrpc_call_put_userid_exists, "PUT u-exists") \
+ EM(rxrpc_call_put_userid, "PUT user-id ") \
EM(rxrpc_call_see_accept, "SEE accept ") \
EM(rxrpc_call_see_activate_client, "SEE act-clnt") \
EM(rxrpc_call_see_connect_failed, "SEE con-fail") \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index de84061a54472..007258538beeb 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -292,7 +292,6 @@ struct rxrpc_local {
struct rb_root client_bundles; /* Client connection bundles by socket params */
spinlock_t client_bundles_lock; /* Lock for client_bundles */
bool kill_all_client_conns;
- spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
struct list_head idle_client_conns;
struct timer_list client_conn_reap_timer;
unsigned long client_conn_flags;
@@ -304,7 +303,8 @@ struct rxrpc_local {
bool dead;
bool service_closed; /* Service socket closed */
struct idr conn_ids; /* List of connection IDs */
- spinlock_t conn_lock; /* Lock for client connection pool */
+ struct list_head new_client_calls; /* Newly created client calls need connection */
+ spinlock_t client_call_lock; /* Lock for ->new_client_calls */
struct sockaddr_rxrpc srx; /* local address */
};
@@ -385,7 +385,6 @@ enum rxrpc_call_completion {
* Bits in the connection flags.
*/
enum rxrpc_conn_flag {
- RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */
RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */
RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */
RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */
@@ -413,6 +412,7 @@ enum rxrpc_conn_event {
*/
enum rxrpc_conn_proto_state {
RXRPC_CONN_UNUSED, /* Connection not yet attempted */
+ RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */
RXRPC_CONN_CLIENT, /* Client connection */
RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */
RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */
@@ -436,11 +436,9 @@ struct rxrpc_bundle {
u32 security_level; /* Security level selected */
u16 service_id; /* Service ID for this connection */
bool try_upgrade; /* True if the bundle is attempting upgrade */
- bool alloc_conn; /* True if someone's getting a conn */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
- short alloc_error; /* Error from last conn allocation */
- spinlock_t channel_lock;
+ unsigned short alloc_error; /* Error from last conn allocation */
struct rb_node local_node; /* Node in local->client_conns */
struct list_head waiting_calls; /* Calls waiting for channels */
unsigned long avail_chans; /* Mask of available channels */
@@ -468,7 +466,7 @@ struct rxrpc_connection {
unsigned char act_chans; /* Mask of active channels */
struct rxrpc_channel {
unsigned long final_ack_at; /* Time at which to issue final ACK */
- struct rxrpc_call __rcu *call; /* Active call */
+ struct rxrpc_call *call; /* Active call */
unsigned int call_debug_id; /* call->debug_id */
u32 call_id; /* ID of current call */
u32 call_counter; /* Call ID counter */
@@ -489,6 +487,7 @@ struct rxrpc_connection {
struct list_head link; /* link in master connection list */
struct sk_buff_head rx_queue; /* received conn-level packets */
+ struct mutex security_lock; /* Lock for security management */
const struct rxrpc_security *security; /* applied security module */
union {
struct {
@@ -619,7 +618,7 @@ struct rxrpc_call {
struct work_struct destroyer; /* In-process-context destroyer */
rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */
struct list_head link; /* link in master call list */
- struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */
+ struct list_head wait_link; /* Link in local->new_client_calls */
struct hlist_node error_link; /* link in error distribution list */
struct list_head accept_link; /* Link in rx->acceptq */
struct list_head recvmsg_link; /* Link in rx->recvmsg_q */
@@ -866,6 +865,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
struct sockaddr_rxrpc *,
struct rxrpc_call_params *, gfp_t,
unsigned int);
+void rxrpc_start_call_timer(struct rxrpc_call *call);
void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *,
struct sk_buff *);
void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *);
@@ -905,6 +905,7 @@ static inline void rxrpc_set_call_state(struct rxrpc_call *call,
{
/* Order write of completion info before write of ->state. */
smp_store_release(&call->_state, state);
+ wake_up(&call->waitq);
}
static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call)
@@ -940,10 +941,11 @@ extern unsigned int rxrpc_reap_client_connections;
extern unsigned long rxrpc_conn_idle_client_expiry;
extern unsigned long rxrpc_conn_idle_client_fast_expiry;
-void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local);
+void rxrpc_purge_client_connections(struct rxrpc_local *local);
struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
-int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp);
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp);
+void rxrpc_connect_client_calls(struct rxrpc_local *local);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index c94161acf3c41..3ded5a24627c5 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -150,7 +150,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
timer_setup(&call->timer, rxrpc_call_timer_expired, 0);
INIT_WORK(&call->destroyer, rxrpc_destroy_call);
INIT_LIST_HEAD(&call->link);
- INIT_LIST_HEAD(&call->chan_wait_link);
+ INIT_LIST_HEAD(&call->wait_link);
INIT_LIST_HEAD(&call->accept_link);
INIT_LIST_HEAD(&call->recvmsg_link);
INIT_LIST_HEAD(&call->sock_link);
@@ -242,7 +242,7 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
/*
* Initiate the call ack/resend/expiry timer.
*/
-static void rxrpc_start_call_timer(struct rxrpc_call *call)
+void rxrpc_start_call_timer(struct rxrpc_call *call)
{
unsigned long now = jiffies;
unsigned long j = now + MAX_JIFFY_OFFSET;
@@ -286,6 +286,39 @@ static void rxrpc_put_call_slot(struct rxrpc_call *call)
up(limiter);
}
+/*
+ * Start the process of connecting a call. We obtain a peer and a connection
+ * bundle, but the actual association of a call with a connection is offloaded
+ * to the I/O thread to simplify locking.
+ */
+static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
+{
+ struct rxrpc_local *local = call->local;
+ int ret = 0;
+
+ _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+
+ call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp);
+ if (!call->peer)
+ goto error;
+
+ ret = rxrpc_look_up_bundle(call, gfp);
+ if (ret < 0)
+ goto error;
+
+ trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call);
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+ spin_lock(&local->client_call_lock);
+ list_add_tail(&call->wait_link, &local->new_client_calls);
+ spin_unlock(&local->client_call_lock);
+ rxrpc_wake_up_io_thread(local);
+ return 0;
+
+error:
+ __set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ return ret;
+}
+
/*
* Set up a call for the given parameters.
* - Called with the socket lock held, which it must release.
@@ -369,10 +402,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
if (ret < 0)
goto error_attached_to_socket;
- rxrpc_see_call(call, rxrpc_call_see_connected);
-
- rxrpc_start_call_timer(call);
-
_leave(" = %p [new]", call);
return call;
@@ -387,22 +416,20 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0,
rxrpc_call_see_userid_exists);
- rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_userid_exists);
_leave(" = -EEXIST");
return ERR_PTR(-EEXIST);
/* We got an error, but the call is attached to the socket and is in
- * need of release. However, we might now race with recvmsg() when
- * completing the call queues it. Return 0 from sys_sendmsg() and
+ * need of release. However, we might now race with recvmsg() when it
+ * completion notifies the socket. Return 0 from sys_sendmsg() and
* leave the error to recvmsg() to deal with.
*/
error_attached_to_socket:
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret,
rxrpc_call_see_connect_failed);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
+ rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
_leave(" = c=%08x [err]", call->debug_id);
return call;
}
@@ -460,7 +487,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
chan = sp->hdr.cid & RXRPC_CHANNELMASK;
conn->channels[chan].call_counter = call->call_id;
conn->channels[chan].call_id = call->call_id;
- rcu_assign_pointer(conn->channels[chan].call, call);
+ conn->channels[chan].call = call;
spin_unlock(&conn->state_lock);
spin_lock(&conn->peer->lock);
@@ -520,7 +547,7 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call)
void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
{
struct rxrpc_connection *conn = call->conn;
- bool put = false;
+ bool put = false, putu = false;
_enter("{%d,%d}", call->debug_id, refcount_read(&call->ref));
@@ -555,7 +582,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
rb_erase(&call->sock_node, &rx->calls);
memset(&call->sock_node, 0xdd, sizeof(call->sock_node));
- rxrpc_put_call(call, rxrpc_call_put_userid_exists);
+ putu = true;
}
list_del(&call->sock_link);
@@ -563,6 +590,9 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
+ if (putu)
+ rxrpc_put_call(call, rxrpc_call_put_userid);
+
_leave("");
}
diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c
index 27dc1242b7125..6afb54373ebbf 100644
--- a/net/rxrpc/call_state.c
+++ b/net/rxrpc/call_state.c
@@ -65,5 +65,5 @@ void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion comp
call->completion = compl;
call->_state = RXRPC_CALL_COMPLETE;
trace_rxrpc_call_complete(call);
- __set_bit(RXRPC_CALL_RELEASED, &call->flags);
+ WARN_ON_ONCE(__test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags));
}
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index ebb43f65ebc51..981ca5b98bcb9 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -39,61 +39,19 @@ static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle)
atomic_inc(&bundle->active);
}
-/*
- * Get a connection ID and epoch for a client connection from the global pool.
- * The connection struct pointer is then recorded in the idr radix tree. The
- * epoch doesn't change until the client is rebooted (or, at least, unless the
- * module is unloaded).
- */
-static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn,
- gfp_t gfp)
-{
- struct rxrpc_local *local = conn->local;
- int id;
-
- _enter("");
-
- idr_preload(gfp);
- spin_lock(&local->conn_lock);
-
- id = idr_alloc_cyclic(&local->conn_ids, conn,
- 1, 0x40000000, GFP_NOWAIT);
- if (id < 0)
- goto error;
-
- spin_unlock(&local->conn_lock);
- idr_preload_end();
-
- conn->proto.epoch = local->rxnet->epoch;
- conn->proto.cid = id << RXRPC_CIDSHIFT;
- set_bit(RXRPC_CONN_HAS_IDR, &conn->flags);
- _leave(" [CID %x]", conn->proto.cid);
- return 0;
-
-error:
- spin_unlock(&local->conn_lock);
- idr_preload_end();
- _leave(" = %d", id);
- return id;
-}
-
/*
* Release a connection ID for a client connection.
*/
static void rxrpc_put_client_connection_id(struct rxrpc_local *local,
struct rxrpc_connection *conn)
{
- if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) {
- spin_lock(&local->conn_lock);
- idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT);
- spin_unlock(&local->conn_lock);
- }
+ idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT);
}
/*
* Destroy the client connection ID tree.
*/
-void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
+static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
int id;
@@ -129,7 +87,6 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
bundle->security_level = call->security_level;
refcount_set(&bundle->ref, 1);
atomic_set(&bundle->active, 1);
- spin_lock_init(&bundle->channel_lock);
INIT_LIST_HEAD(&bundle->waiting_calls);
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new);
}
@@ -169,69 +126,68 @@ void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why)
}
}
+/*
+ * Get rid of outstanding client connection preallocations when a local
+ * endpoint is destroyed.
+ */
+void rxrpc_purge_client_connections(struct rxrpc_local *local)
+{
+ rxrpc_destroy_client_conn_ids(local);
+}
+
/*
* Allocate a client connection.
*/
static struct rxrpc_connection *
-rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
+rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
- int ret;
+ struct rxrpc_local *local = bundle->local;
+ struct rxrpc_net *rxnet = local->rxnet;
+ int id;
_enter("");
- conn = rxrpc_alloc_connection(rxnet, gfp);
- if (!conn) {
- _leave(" = -ENOMEM");
+ conn = rxrpc_alloc_connection(rxnet, GFP_ATOMIC | __GFP_NOWARN);
+ if (!conn)
return ERR_PTR(-ENOMEM);
+
+ id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (id < 0) {
+ kfree(conn);
+ return ERR_PTR(id);
}
refcount_set(&conn->ref, 1);
- conn->bundle = bundle;
- conn->local = bundle->local;
- conn->peer = bundle->peer;
- conn->key = bundle->key;
+ conn->proto.cid = id << RXRPC_CIDSHIFT;
+ conn->proto.epoch = local->rxnet->epoch;
+ conn->out_clientflag = RXRPC_CLIENT_INITIATED;
+ conn->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
+ conn->local = rxrpc_get_local(bundle->local, rxrpc_local_get_client_conn);
+ conn->peer = rxrpc_get_peer(bundle->peer, rxrpc_peer_get_client_conn);
+ conn->key = key_get(bundle->key);
+ conn->security = bundle->security;
conn->exclusive = bundle->exclusive;
conn->upgrade = bundle->upgrade;
conn->orig_service_id = bundle->service_id;
conn->security_level = bundle->security_level;
- conn->out_clientflag = RXRPC_CLIENT_INITIATED;
- conn->state = RXRPC_CONN_CLIENT;
+ conn->state = RXRPC_CONN_CLIENT_UNSECURED;
conn->service_id = conn->orig_service_id;
- ret = rxrpc_get_client_connection_id(conn, gfp);
- if (ret < 0)
- goto error_0;
-
- ret = rxrpc_init_client_conn_security(conn);
- if (ret < 0)
- goto error_1;
+ if (conn->security == &rxrpc_no_security)
+ conn->state = RXRPC_CONN_CLIENT;
atomic_inc(&rxnet->nr_conns);
write_lock(&rxnet->conn_lock);
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
write_unlock(&rxnet->conn_lock);
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
- rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn);
- rxrpc_get_local(conn->local, rxrpc_local_get_client_conn);
- key_get(conn->key);
-
- trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref),
- rxrpc_conn_new_client);
+ rxrpc_see_connection(conn, rxrpc_conn_new_client);
atomic_inc(&rxnet->nr_client_conns);
trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
- _leave(" = %p", conn);
return conn;
-
-error_1:
- rxrpc_put_client_connection_id(bundle->local, conn);
-error_0:
- kfree(conn);
- _leave(" = %d", ret);
- return ERR_PTR(ret);
}
/*
@@ -249,7 +205,8 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
goto dont_reuse;
- if (conn->state != RXRPC_CONN_CLIENT ||
+ if ((conn->state != RXRPC_CONN_CLIENT_UNSECURED &&
+ conn->state != RXRPC_CONN_CLIENT) ||
conn->proto.epoch != rxnet->epoch)
goto mark_dont_reuse;
@@ -280,7 +237,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
* Look up the conn bundle that matches the connection parameters, adding it if
* it doesn't yet exist.
*/
-static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
{
static atomic_t rxrpc_bundle_id;
struct rxrpc_bundle *bundle, *candidate;
@@ -295,7 +252,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t
if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) {
call->bundle = rxrpc_alloc_bundle(call, gfp);
- return call->bundle;
+ return call->bundle ? 0 : -ENOMEM;
}
/* First, see if the bundle is already there. */
@@ -324,7 +281,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t
/* It wasn't. We need to add one. */
candidate = rxrpc_alloc_bundle(call, gfp);
if (!candidate)
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
_debug("search 2");
spin_lock(&local->client_bundles_lock);
@@ -355,7 +312,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t
call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
spin_unlock(&local->client_bundles_lock);
_leave(" = B=%u [new]", call->bundle->debug_id);
- return call->bundle;
+ return 0;
found_bundle_free:
rxrpc_free_bundle(candidate);
@@ -364,160 +321,77 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t
rxrpc_activate_bundle(bundle);
spin_unlock(&local->client_bundles_lock);
_leave(" = B=%u [found]", call->bundle->debug_id);
- return call->bundle;
-}
-
-/*
- * Create or find a client bundle to use for a call.
- *
- * If we return with a connection, the call will be on its waiting list. It's
- * left to the caller to assign a channel and wake up the call.
- */
-static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_call *call, gfp_t gfp)
-{
- struct rxrpc_bundle *bundle;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- call->peer = rxrpc_lookup_peer(call->local, &call->dest_srx, gfp);
- if (!call->peer)
- goto error;
-
- call->tx_last_sent = ktime_get_real();
- call->cong_ssthresh = call->peer->cong_ssthresh;
- if (call->cong_cwnd >= call->cong_ssthresh)
- call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
- else
- call->cong_mode = RXRPC_CALL_SLOW_START;
-
- /* Find the client connection bundle. */
- bundle = rxrpc_look_up_bundle(call, gfp);
- if (!bundle)
- goto error;
-
- /* Get this call queued. Someone else may activate it whilst we're
- * lining up a new connection, but that's fine.
- */
- spin_lock(&bundle->channel_lock);
- list_add_tail(&call->chan_wait_link, &bundle->waiting_calls);
- spin_unlock(&bundle->channel_lock);
-
- _leave(" = [B=%x]", bundle->debug_id);
- return bundle;
-
-error:
- _leave(" = -ENOMEM");
- return ERR_PTR(-ENOMEM);
+ return 0;
}
/*
* Allocate a new connection and add it into a bundle.
*/
-static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
- __releases(bundle->channel_lock)
+static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle,
+ unsigned int slot)
{
- struct rxrpc_connection *candidate = NULL, *old = NULL;
- bool conflict;
- int i;
-
- _enter("");
-
- conflict = bundle->alloc_conn;
- if (!conflict)
- bundle->alloc_conn = true;
- spin_unlock(&bundle->channel_lock);
- if (conflict) {
- _leave(" [conf]");
- return;
- }
-
- candidate = rxrpc_alloc_client_connection(bundle, gfp);
-
- spin_lock(&bundle->channel_lock);
- bundle->alloc_conn = false;
+ struct rxrpc_connection *conn, *old;
+ unsigned int shift = slot * RXRPC_MAXCALLS;
+ unsigned int i;
- if (IS_ERR(candidate)) {
- bundle->alloc_error = PTR_ERR(candidate);
- spin_unlock(&bundle->channel_lock);
- _leave(" [err %ld]", PTR_ERR(candidate));
- return;
+ old = bundle->conns[slot];
+ if (old) {
+ bundle->conns[slot] = NULL;
+ trace_rxrpc_client(old, -1, rxrpc_client_replace);
+ rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
}
- bundle->alloc_error = 0;
-
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
- unsigned int shift = i * RXRPC_MAXCALLS;
- int j;
-
- old = bundle->conns[i];
- if (!rxrpc_may_reuse_conn(old)) {
- if (old)
- trace_rxrpc_client(old, -1, rxrpc_client_replace);
- candidate->bundle_shift = shift;
- rxrpc_activate_bundle(bundle);
- bundle->conns[i] = candidate;
- for (j = 0; j < RXRPC_MAXCALLS; j++)
- set_bit(shift + j, &bundle->avail_chans);
- candidate = NULL;
- break;
- }
-
- old = NULL;
+ conn = rxrpc_alloc_client_connection(bundle);
+ if (IS_ERR(conn)) {
+ bundle->alloc_error = PTR_ERR(conn);
+ return false;
}
- spin_unlock(&bundle->channel_lock);
-
- if (candidate) {
- _debug("discard C=%x", candidate->debug_id);
- trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
- rxrpc_put_connection(candidate, rxrpc_conn_put_discard);
- }
-
- rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
- _leave("");
+ rxrpc_activate_bundle(bundle);
+ conn->bundle_shift = shift;
+ bundle->conns[slot] = conn;
+ for (i = 0; i < RXRPC_MAXCALLS; i++)
+ set_bit(shift + i, &bundle->avail_chans);
+ return true;
}
/*
* Add a connection to a bundle if there are no usable connections or we have
* connections waiting for extra capacity.
*/
-static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp)
+static bool rxrpc_bundle_has_space(struct rxrpc_bundle *bundle)
{
- struct rxrpc_call *call;
- int i, usable;
+ int slot = -1, i, usable;
_enter("");
- spin_lock(&bundle->channel_lock);
+ bundle->alloc_error = 0;
/* See if there are any usable connections. */
usable = 0;
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+ for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
if (rxrpc_may_reuse_conn(bundle->conns[i]))
usable++;
-
- if (!usable && !list_empty(&bundle->waiting_calls)) {
- call = list_first_entry(&bundle->waiting_calls,
- struct rxrpc_call, chan_wait_link);
- if (test_bit(RXRPC_CALL_UPGRADE, &call->flags))
- bundle->try_upgrade = true;
+ else if (slot == -1)
+ slot = i;
}
+ if (!usable && bundle->upgrade)
+ bundle->try_upgrade = true;
+
if (!usable)
goto alloc_conn;
if (!bundle->avail_chans &&
!bundle->try_upgrade &&
- !list_empty(&bundle->waiting_calls) &&
usable < ARRAY_SIZE(bundle->conns))
goto alloc_conn;
- spin_unlock(&bundle->channel_lock);
_leave("");
- return;
+ return usable;
alloc_conn:
- return rxrpc_add_conn_to_bundle(bundle, gfp);
+ return slot >= 0 ? rxrpc_add_conn_to_bundle(bundle, slot) : false;
}
/*
@@ -531,11 +405,13 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
struct rxrpc_channel *chan = &conn->channels[channel];
struct rxrpc_bundle *bundle = conn->bundle;
struct rxrpc_call *call = list_entry(bundle->waiting_calls.next,
- struct rxrpc_call, chan_wait_link);
+ struct rxrpc_call, wait_link);
u32 call_id = chan->call_counter + 1;
_enter("C=%x,%u", conn->debug_id, channel);
+ list_del_init(&call->wait_link);
+
trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
/* Cancel the final ACK on the previous call if it hasn't been sent yet
@@ -545,65 +421,50 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
clear_bit(conn->bundle_shift + channel, &bundle->avail_chans);
rxrpc_see_call(call, rxrpc_call_see_activate_client);
- list_del_init(&call->chan_wait_link);
call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call);
call->cid = conn->proto.cid | channel;
call->call_id = call_id;
call->dest_srx.srx_service = conn->service_id;
-
- trace_rxrpc_connect_call(call);
-
- rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
-
- /* Paired with the read barrier in rxrpc_connect_call(). This orders
- * cid and epoch in the connection wrt to call_id without the need to
- * take the channel_lock.
- *
- * We provisionally assign a callNumber at this point, but we don't
- * confirm it until the call is about to be exposed.
- *
- * TODO: Pair with a barrier in the data_ready handler when that looks
- * at the call ID through a connection channel.
- */
- smp_wmb();
+ call->cong_ssthresh = call->peer->cong_ssthresh;
+ if (call->cong_cwnd >= call->cong_ssthresh)
+ call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
+ else
+ call->cong_mode = RXRPC_CALL_SLOW_START;
chan->call_id = call_id;
chan->call_debug_id = call->debug_id;
- rcu_assign_pointer(chan->call, call);
+ chan->call = call;
+
+ rxrpc_see_call(call, rxrpc_call_see_connected);
+ trace_rxrpc_connect_call(call);
+ call->tx_last_sent = ktime_get_real();
+ rxrpc_start_call_timer(call);
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
wake_up(&call->waitq);
}
/*
* Remove a connection from the idle list if it's on it.
*/
-static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
+static void rxrpc_unidle_conn(struct rxrpc_connection *conn)
{
- struct rxrpc_local *local = bundle->local;
- bool drop_ref;
-
if (!list_empty(&conn->cache_link)) {
- drop_ref = false;
- spin_lock(&local->client_conn_cache_lock);
- if (!list_empty(&conn->cache_link)) {
- list_del_init(&conn->cache_link);
- drop_ref = true;
- }
- spin_unlock(&local->client_conn_cache_lock);
- if (drop_ref)
- rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
+ list_del_init(&conn->cache_link);
+ rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
}
}
/*
- * Assign channels and callNumbers to waiting calls with channel_lock
- * held by caller.
+ * Assign channels and callNumbers to waiting calls.
*/
-static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
+static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
unsigned long avail, mask;
unsigned int channel, slot;
+ trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
+
if (bundle->try_upgrade)
mask = 1;
else
@@ -623,7 +484,7 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
if (bundle->try_upgrade)
set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
- rxrpc_unidle_conn(bundle, conn);
+ rxrpc_unidle_conn(conn);
channel &= (RXRPC_MAXCALLS - 1);
conn->act_chans |= 1 << channel;
@@ -632,125 +493,24 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
}
/*
- * Assign channels and callNumbers to waiting calls.
- */
-static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
-{
- _enter("B=%x", bundle->debug_id);
-
- trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
-
- if (!bundle->avail_chans)
- return;
-
- spin_lock(&bundle->channel_lock);
- rxrpc_activate_channels_locked(bundle);
- spin_unlock(&bundle->channel_lock);
- _leave("");
-}
-
-/*
- * Wait for a callNumber and a channel to be granted to a call.
- */
-static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
- struct rxrpc_call *call, gfp_t gfp)
-{
- DECLARE_WAITQUEUE(myself, current);
- int ret = 0;
-
- _enter("%d", call->debug_id);
-
- if (!gfpflags_allow_blocking(gfp)) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error ?: -EAGAIN;
- goto out;
- }
-
- add_wait_queue_exclusive(&call->waitq, &myself);
- for (;;) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error;
- if (ret < 0)
- break;
-
- switch (call->interruptibility) {
- case RXRPC_INTERRUPTIBLE:
- case RXRPC_PREINTERRUPTIBLE:
- set_current_state(TASK_INTERRUPTIBLE);
- break;
- case RXRPC_UNINTERRUPTIBLE:
- default:
- set_current_state(TASK_UNINTERRUPTIBLE);
- break;
- }
- if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
- break;
- if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
- call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
- signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- schedule();
- }
- remove_wait_queue(&call->waitq, &myself);
- __set_current_state(TASK_RUNNING);
-
-out:
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
- * find a connection for a call
- * - called in process context with IRQs enabled
+ * Connect waiting channels (called from the I/O thread).
*/
-int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
+void rxrpc_connect_client_calls(struct rxrpc_local *local)
{
- struct rxrpc_bundle *bundle;
- int ret = 0;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- rxrpc_get_call(call, rxrpc_call_get_io_thread);
-
- bundle = rxrpc_prep_call(call, gfp);
- if (IS_ERR(bundle)) {
- rxrpc_put_call(call, rxrpc_call_get_io_thread);
- ret = PTR_ERR(bundle);
- goto out;
- }
-
- if (rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = rxrpc_wait_for_channel(bundle, call, gfp);
- if (ret < 0)
- goto wait_failed;
- }
-
-granted_channel:
- /* Paired with the write barrier in rxrpc_activate_one_channel(). */
- smp_rmb();
+ struct rxrpc_call *call;
-out:
- _leave(" = %d", ret);
- return ret;
+ while ((call = list_first_entry_or_null(&local->new_client_calls,
+ struct rxrpc_call, wait_link))
+ ) {
+ struct rxrpc_bundle *bundle = call->bundle;
-wait_failed:
- spin_lock(&bundle->channel_lock);
- list_del_init(&call->chan_wait_link);
- spin_unlock(&bundle->channel_lock);
+ spin_lock(&local->client_call_lock);
+ list_move_tail(&call->wait_link, &bundle->waiting_calls);
+ spin_unlock(&local->client_call_lock);
- if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = 0;
- goto granted_channel;
+ if (rxrpc_bundle_has_space(bundle))
+ rxrpc_activate_channels(bundle);
}
-
- trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
- rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
- rxrpc_disconnect_client_call(bundle, call);
- goto out;
}
/*
@@ -808,8 +568,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
_enter("c=%x", call->debug_id);
- spin_lock(&bundle->channel_lock);
-
/* Calls that have never actually been assigned a channel can simply be
* discarded.
*/
@@ -818,8 +576,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
_debug("call is waiting");
ASSERTCMP(call->call_id, ==, 0);
ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags));
- list_del_init(&call->chan_wait_link);
- goto out;
+ list_del_init(&call->wait_link);
+ return;
}
cid = call->cid;
@@ -827,10 +585,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
chan = &conn->channels[channel];
trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
- if (rcu_access_pointer(chan->call) != call) {
- spin_unlock(&bundle->channel_lock);
- BUG();
- }
+ if (WARN_ON(chan->call != call))
+ return;
may_reuse = rxrpc_may_reuse_conn(conn);
@@ -851,16 +607,15 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
bundle->try_upgrade = false;
if (may_reuse)
- rxrpc_activate_channels_locked(bundle);
+ rxrpc_activate_channels(bundle);
}
-
}
/* See if we can pass the channel directly to another call. */
if (may_reuse && !list_empty(&bundle->waiting_calls)) {
trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
rxrpc_activate_one_channel(conn, channel);
- goto out;
+ return;
}
/* Schedule the final ACK to be transmitted in a short while so that it
@@ -878,7 +633,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
}
/* Deactivate the channel. */
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans);
conn->act_chans &= ~(1 << channel);
@@ -891,15 +646,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call
conn->idle_timestamp = jiffies;
rxrpc_get_connection(conn, rxrpc_conn_get_idle);
- spin_lock(&local->client_conn_cache_lock);
list_move_tail(&conn->cache_link, &local->idle_client_conns);
- spin_unlock(&local->client_conn_cache_lock);
rxrpc_set_client_reap_timer(local);
}
-
-out:
- spin_unlock(&bundle->channel_lock);
}
/*
@@ -909,7 +659,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
{
struct rxrpc_bundle *bundle = conn->bundle;
unsigned int bindex;
- bool need_drop = false;
int i;
_enter("C=%x", conn->debug_id);
@@ -917,18 +666,13 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn, true);
- spin_lock(&bundle->channel_lock);
bindex = conn->bundle_shift / RXRPC_MAXCALLS;
if (bundle->conns[bindex] == conn) {
_debug("clear slot %u", bindex);
bundle->conns[bindex] = NULL;
for (i = 0; i < RXRPC_MAXCALLS; i++)
clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
- need_drop = true;
- }
- spin_unlock(&bundle->channel_lock);
-
- if (need_drop) {
+ rxrpc_put_client_connection_id(bundle->local, conn);
rxrpc_deactivate_bundle(bundle);
rxrpc_put_connection(conn, rxrpc_conn_put_unbundle);
}
@@ -990,24 +734,16 @@ void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
_enter("");
- if (list_empty(&local->idle_client_conns)) {
- _leave(" [empty]");
- return;
- }
-
/* We keep an estimate of what the number of conns ought to be after
* we've discarded some so that we don't overdo the discarding.
*/
nr_conns = atomic_read(&local->rxnet->nr_client_conns);
next:
- spin_lock(&local->client_conn_cache_lock);
-
- if (list_empty(&local->idle_client_conns))
- goto out;
-
- conn = list_entry(local->idle_client_conns.next,
- struct rxrpc_connection, cache_link);
+ conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link);
+ if (!conn)
+ return;
if (!local->kill_all_client_conns) {
/* If the number of connections is over the reap limit, we
@@ -1032,8 +768,6 @@ void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
trace_rxrpc_client(conn, -1, rxrpc_client_discard);
list_del_init(&conn->cache_link);
- spin_unlock(&local->client_conn_cache_lock);
-
rxrpc_unbundle_conn(conn);
/* Drop the ->cache_link ref */
rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle);
@@ -1053,8 +787,6 @@ void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
if (!local->kill_all_client_conns)
timer_reduce(&local->client_conn_reap_timer, conn_expires_at);
-out:
- spin_unlock(&local->client_conn_cache_lock);
_leave("");
}
@@ -1063,34 +795,19 @@ void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
*/
void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
{
- struct rxrpc_connection *conn, *tmp;
- LIST_HEAD(graveyard);
+ struct rxrpc_connection *conn;
_enter("");
- spin_lock(&local->client_conn_cache_lock);
local->kill_all_client_conns = true;
- spin_unlock(&local->client_conn_cache_lock);
del_timer_sync(&local->client_conn_reap_timer);
- spin_lock(&local->client_conn_cache_lock);
-
- list_for_each_entry_safe(conn, tmp, &local->idle_client_conns,
- cache_link) {
- if (conn->local == local) {
- atomic_dec(&conn->active);
- trace_rxrpc_client(conn, -1, rxrpc_client_discard);
- list_move(&conn->cache_link, &graveyard);
- }
- }
-
- spin_unlock(&local->client_conn_cache_lock);
-
- while (!list_empty(&graveyard)) {
- conn = list_entry(graveyard.next,
- struct rxrpc_connection, cache_link);
+ while ((conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link))) {
list_del_init(&conn->cache_link);
+ atomic_dec(&conn->active);
+ trace_rxrpc_client(conn, -1, rxrpc_client_discard);
rxrpc_unbundle_conn(conn);
rxrpc_put_connection(conn, rxrpc_conn_put_local_dead);
}
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 8d0b9ff0a5e15..44414e724415e 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -100,9 +100,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
/* If the last call got moved on whilst we were waiting to run, just
* ignore this packet.
*/
- call_id = READ_ONCE(chan->last_call);
- /* Sync with __rxrpc_disconnect_call() */
- smp_rmb();
+ call_id = chan->last_call;
if (skb && call_id != sp->hdr.callNumber)
return;
@@ -119,9 +117,12 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
iov[2].iov_base = &ack_info;
iov[2].iov_len = sizeof(ack_info);
+ serial = atomic_inc_return(&conn->serial);
+
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(conn->proto.cid | channel);
pkt.whdr.callNumber = htonl(call_id);
+ pkt.whdr.serial = htonl(serial);
pkt.whdr.seq = 0;
pkt.whdr.type = chan->last_type;
pkt.whdr.flags = conn->out_clientflag;
@@ -158,31 +159,15 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
iov[0].iov_len += sizeof(pkt.ack);
len += sizeof(pkt.ack) + 3 + sizeof(ack_info);
ioc = 3;
- break;
-
- default:
- return;
- }
-
- /* Resync with __rxrpc_disconnect_call() and check that the last call
- * didn't get advanced whilst we were filling out the packets.
- */
- smp_rmb();
- if (READ_ONCE(chan->last_call) != call_id)
- return;
-
- serial = atomic_inc_return(&conn->serial);
- pkt.whdr.serial = htonl(serial);
- switch (chan->last_type) {
- case RXRPC_PACKET_TYPE_ABORT:
- break;
- case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
ntohl(pkt.ack.firstPacket),
ntohl(pkt.ack.serial),
pkt.ack.reason, 0);
break;
+
+ default:
+ return;
}
ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len);
@@ -207,12 +192,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn)
_enter("{%d},%x", conn->debug_id, conn->abort_code);
- spin_lock(&conn->bundle->channel_lock);
-
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
+ call = conn->channels[i].call;
if (call)
rxrpc_set_call_completion(call,
conn->completion,
@@ -220,7 +201,6 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn)
conn->error);
}
- spin_unlock(&conn->bundle->channel_lock);
_leave("");
}
@@ -316,9 +296,7 @@ void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn, bool force)
if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags))
continue;
- smp_rmb(); /* vs rxrpc_disconnect_client_call */
- ack_at = READ_ONCE(chan->final_ack_at);
-
+ ack_at = chan->final_ack_at;
if (time_before(j, ack_at) && !force) {
if (time_before(ack_at, next_j)) {
next_j = ack_at;
@@ -446,15 +424,8 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
if (conn->state != RXRPC_CONN_SERVICE)
break;
- spin_lock(&conn->bundle->channel_lock);
-
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
- rxrpc_call_is_secure(
- rcu_dereference_protected(
- conn->channels[loop].call,
- lockdep_is_held(&conn->bundle->channel_lock)));
-
- spin_unlock(&conn->bundle->channel_lock);
+ rxrpc_call_is_secure(conn->channels[loop].call);
break;
}
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 3d8c1dc6a82ae..ac85d4644a3c3 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -67,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet,
INIT_WORK(&conn->destructor, rxrpc_clean_up_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
+ mutex_init(&conn->security_lock);
skb_queue_head_init(&conn->rx_queue);
conn->rxnet = rxnet;
conn->security = &rxrpc_no_security;
@@ -157,7 +158,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
_enter("%d,%x", conn->debug_id, call->cid);
- if (rcu_access_pointer(chan->call) == call) {
+ if (chan->call == call) {
/* Save the result of the call so that we can repeat it if necessary
* through the channel, whilst disposing of the actual call record.
*/
@@ -177,12 +178,9 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
break;
}
- /* Sync with rxrpc_conn_retransmit(). */
- smp_wmb();
chan->last_call = chan->call_id;
chan->call_id = chan->call_counter;
-
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
}
_leave("");
@@ -210,10 +208,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
if (rxrpc_is_client_call(call)) {
rxrpc_disconnect_client_call(call->bundle, call);
} else {
- spin_lock(&conn->bundle->channel_lock);
__rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
-
conn->idle_timestamp = jiffies;
if (atomic_dec_and_test(&conn->active))
rxrpc_set_service_reap_timer(conn->rxnet,
@@ -316,10 +311,10 @@ static void rxrpc_clean_up_connection(struct work_struct *work)
container_of(work, struct rxrpc_connection, destructor);
struct rxrpc_net *rxnet = conn->rxnet;
- ASSERT(!rcu_access_pointer(conn->channels[0].call) &&
- !rcu_access_pointer(conn->channels[1].call) &&
- !rcu_access_pointer(conn->channels[2].call) &&
- !rcu_access_pointer(conn->channels[3].call));
+ ASSERT(!conn->channels[0].call &&
+ !conn->channels[1].call &&
+ !conn->channels[2].call &&
+ !conn->channels[3].call);
ASSERT(list_empty(&conn->cache_link));
del_timer_sync(&conn->timer);
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index 2a55a88b2a5b7..f30323de82bd1 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -11,7 +11,6 @@
static struct rxrpc_bundle rxrpc_service_dummy_bundle = {
.ref = REFCOUNT_INIT(1),
.debug_id = UINT_MAX,
- .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock),
};
/*
diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c
index a299cc34c1403..9e9dfb2fc559b 100644
--- a/net/rxrpc/io_thread.c
+++ b/net/rxrpc/io_thread.c
@@ -369,10 +369,7 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn,
return just_discard;
}
- rcu_read_lock();
- call = rxrpc_try_get_call(rcu_dereference(chan->call),
- rxrpc_call_get_input);
- rcu_read_unlock();
+ call = rxrpc_try_get_call(chan->call, rxrpc_call_get_input);
if (sp->hdr.callNumber > chan->call_id) {
if (rxrpc_to_client(sp)) {
@@ -453,6 +450,9 @@ int rxrpc_io_thread(void *data)
continue;
}
+ if (!list_empty(&local->new_client_calls))
+ rxrpc_connect_client_calls(local);
+
/* Process received packets and errors. */
if ((skb = __skb_dequeue(&rx_queue))) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -492,7 +492,10 @@ int rxrpc_io_thread(void *data)
should_stop = kthread_should_stop();
if (!skb_queue_empty(&local->rx_queue) ||
!list_empty(&local->call_attend_q) ||
- !list_empty(&local->conn_attend_q)) {
+ !list_empty(&local->conn_attend_q) ||
+ !list_empty(&local->new_client_calls) ||
+ test_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags)) {
__set_current_state(TASK_RUNNING);
continue;
}
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 9bc8d08ca12cf..b8eaca5d9f221 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -117,7 +117,6 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
local->client_bundles = RB_ROOT;
spin_lock_init(&local->client_bundles_lock);
local->kill_all_client_conns = false;
- spin_lock_init(&local->client_conn_cache_lock);
INIT_LIST_HEAD(&local->idle_client_conns);
timer_setup(&local->client_conn_reap_timer,
rxrpc_client_conn_reap_timeout, 0);
@@ -133,7 +132,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
if (tmp == 0)
tmp = 1;
idr_set_cursor(&local->conn_ids, tmp);
- spin_lock_init(&local->conn_lock);
+ INIT_LIST_HEAD(&local->new_client_calls);
+ spin_lock_init(&local->client_call_lock);
trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1);
}
@@ -435,7 +435,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local)
* local endpoint.
*/
rxrpc_purge_queue(&local->rx_queue);
- rxrpc_destroy_client_conn_ids(local);
+ rxrpc_purge_client_connections(local);
}
/*
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index c39ef94602ed7..750158a085cdd 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -12,6 +12,7 @@
static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
[RXRPC_CONN_UNUSED] = "Unused ",
+ [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ",
[RXRPC_CONN_CLIENT] = "Client ",
[RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc",
[RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ",
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index dfb01e7b90fbb..1bf571a66e020 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -1122,36 +1122,31 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
goto protocol_error_free;
}
- spin_lock(&conn->bundle->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- struct rxrpc_call *call;
u32 call_id = ntohl(response->encrypted.call_id[i]);
+ u32 counter = READ_ONCE(conn->channels[i].call_counter);
if (call_id > INT_MAX) {
rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
rxkad_abort_resp_bad_callid);
- goto protocol_error_unlock;
+ goto protocol_error_free;
}
- if (call_id < conn->channels[i].call_counter) {
+ if (call_id < counter) {
rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
rxkad_abort_resp_call_ctr);
- goto protocol_error_unlock;
+ goto protocol_error_free;
}
- if (call_id > conn->channels[i].call_counter) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
- if (call && !__rxrpc_call_is_complete(call)) {
+ if (call_id > counter) {
+ if (conn->channels[i].call) {
rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
rxkad_abort_resp_call_state);
- goto protocol_error_unlock;
+ goto protocol_error_free;
}
conn->channels[i].call_counter = call_id;
}
}
- spin_unlock(&conn->bundle->channel_lock);
if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) {
rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO,
@@ -1179,8 +1174,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
_leave(" = 0");
return 0;
-protocol_error_unlock:
- spin_unlock(&conn->bundle->channel_lock);
protocol_error_free:
kfree(ticket);
protocol_error:
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index 78af14694618d..cd66634dffe69 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -97,38 +97,31 @@ int rxrpc_init_client_call_security(struct rxrpc_call *call)
*/
int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
{
- const struct rxrpc_security *sec;
struct rxrpc_key_token *token;
struct key *key = conn->key;
- int ret;
+ int ret = 0;
_enter("{%d},{%x}", conn->debug_id, key_serial(key));
- if (!key)
- return 0;
-
- ret = key_validate(key);
- if (ret < 0)
- return ret;
-
for (token = key->payload.data[0]; token; token = token->next) {
- sec = rxrpc_security_lookup(token->security_index);
- if (sec)
+ if (token->security_index == conn->security->security_index)
goto found;
}
return -EKEYREJECTED;
found:
- conn->security = sec;
-
- ret = conn->security->init_connection_security(conn, token);
- if (ret < 0) {
- conn->security = &rxrpc_no_security;
- return ret;
+ mutex_lock(&conn->security_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = conn->security->init_connection_security(conn, token);
+ if (ret == 0) {
+ spin_lock(&conn->state_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED)
+ conn->state = RXRPC_CONN_CLIENT;
+ spin_unlock(&conn->state_lock);
+ }
}
-
- _leave(" = 0");
- return 0;
+ mutex_unlock(&conn->security_lock);
+ return ret;
}
/*
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index a5d0005b7ce52..da49fcf1c4567 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -38,6 +38,60 @@ bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
return false;
}
+/*
+ * Wait for a call to become connected. Interruption here doesn't cause the
+ * call to be aborted.
+ */
+static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo)
+{
+ DECLARE_WAITQUEUE(myself, current);
+ int ret = 0;
+
+ _enter("%d", call->debug_id);
+
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+ return call->error;
+
+ add_wait_queue_exclusive(&call->waitq, &myself);
+
+ for (;;) {
+ ret = call->error;
+ if (ret < 0)
+ break;
+
+ switch (call->interruptibility) {
+ case RXRPC_INTERRUPTIBLE:
+ case RXRPC_PREINTERRUPTIBLE:
+ set_current_state(TASK_INTERRUPTIBLE);
+ break;
+ case RXRPC_UNINTERRUPTIBLE:
+ default:
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ break;
+ }
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+ ret = call->error;
+ break;
+ }
+ if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+ call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+ signal_pending(current)) {
+ ret = sock_intr_errno(*timeo);
+ break;
+ }
+ *timeo = schedule_timeout(*timeo);
+ }
+
+ remove_wait_queue(&call->waitq, &myself);
+ __set_current_state(TASK_RUNNING);
+
+ if (ret == 0 && rxrpc_call_is_complete(call))
+ ret = call->error;
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
/*
* Return true if there's sufficient Tx queue space.
*/
@@ -239,6 +293,16 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ ret = rxrpc_wait_to_be_connected(call, &timeo);
+ if (ret < 0)
+ return ret;
+
+ if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = rxrpc_init_client_conn_security(call->conn);
+ if (ret < 0)
+ return ret;
+ }
+
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
--
GitLab
From c244c092f1ed2acfb5af3d3da81e22367d3dd733 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Thu, 5 Jan 2023 06:02:51 +0000
Subject: [PATCH 0447/1167] tipc: fix unexpected link reset due to discovery
messages
This unexpected behavior is observed:
node 1 | node 2
------ | ------
link is established | link is established
reboot | link is reset
up | send discovery message
receive discovery message |
link is established | link is established
send discovery message |
| receive discovery message
| link is reset (unexpected)
| send reset message
link is reset |
It is due to delayed re-discovery as described in function
tipc_node_check_dest(): "this link endpoint has already reset
and re-established contact with the peer, before receiving a
discovery message from that node."
However, commit 598411d70f85 has changed the condition for calling
tipc_node_link_down() which was the acceptance of new media address.
This commit fixes this by restoring the old and correct behavior.
Fixes: 598411d70f85 ("tipc: make resetting of links non-atomic")
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/tipc/node.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 49ddc484c4fe7..5e000fde80676 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1179,8 +1179,9 @@ void tipc_node_check_dest(struct net *net, u32 addr,
bool addr_match = false;
bool sign_match = false;
bool link_up = false;
+ bool link_is_reset = false;
bool accept_addr = false;
- bool reset = true;
+ bool reset = false;
char *if_name;
unsigned long intv;
u16 session;
@@ -1200,14 +1201,14 @@ void tipc_node_check_dest(struct net *net, u32 addr,
/* Prepare to validate requesting node's signature and media address */
l = le->link;
link_up = l && tipc_link_is_up(l);
+ link_is_reset = l && tipc_link_is_reset(l);
addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr));
sign_match = (signature == n->signature);
/* These three flags give us eight permutations: */
if (sign_match && addr_match && link_up) {
- /* All is fine. Do nothing. */
- reset = false;
+ /* All is fine. Ignore requests. */
/* Peer node is not a container/local namespace */
if (!n->peer_hash_mix)
n->peer_hash_mix = hash_mixes;
@@ -1232,6 +1233,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
*/
accept_addr = true;
*respond = true;
+ reset = true;
} else if (!sign_match && addr_match && link_up) {
/* Peer node rebooted. Two possibilities:
* - Delayed re-discovery; this link endpoint has already
@@ -1263,6 +1265,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
n->signature = signature;
accept_addr = true;
*respond = true;
+ reset = true;
}
if (!accept_addr)
@@ -1291,6 +1294,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
+ link_is_reset = tipc_link_is_reset(l);
le->link = l;
n->link_cnt++;
tipc_node_calculate_timer(n, l);
@@ -1303,7 +1307,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
tipc_node_write_unlock(n);
- if (reset && l && !tipc_link_is_reset(l))
+ if (reset && !link_is_reset)
tipc_node_link_down(n, b->identity, false);
tipc_node_put(n);
}
--
GitLab
From 83c7423d1eb6806d13c521d1002cc1a012111719 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 21 Dec 2022 17:45:51 +0100
Subject: [PATCH 0448/1167] udf: Fix extension of the last extent in the file
When extending the last extent in the file within the last block, we
wrongly computed the length of the last extent. This is mostly a
cosmetical problem since the extent does not contain any data and the
length will be fixed up by following operations but still.
Fixes: 1f3868f06855 ("udf: Fix extending file within last block")
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/udf/inode.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 1d7c2a812fc19..f3e988928d1d8 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -595,7 +595,7 @@ static void udf_do_extend_final_block(struct inode *inode,
*/
if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK))
return;
- added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen;
+ added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
last_ext->extLength += added_bytes;
UDF_I(inode)->i_lenExtents += added_bytes;
--
GitLab
From 23970a1c9475b305770fd37bebfec7a10f263787 Mon Sep 17 00:00:00 2001
From: Tom Rix <trix@redhat.com>
Date: Fri, 30 Dec 2022 12:53:41 -0500
Subject: [PATCH 0449/1167] udf: initialize newblock to 0
The clang build reports this error
fs/udf/inode.c:805:6: error: variable 'newblock' is used uninitialized whenever 'if' condition is true [-Werror,-Wsometimes-uninitialized]
if (*err < 0)
^~~~~~~~
newblock is never set before error handling jump.
Initialize newblock to 0 and remove redundant settings.
Fixes: d8b39db5fab8 ("udf: Handle error when adding extent to a file")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Message-Id: <20221230175341.1629734-1-trix@redhat.com>
---
fs/udf/inode.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index f3e988928d1d8..34e416327dd4e 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -684,7 +684,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
struct kernel_lb_addr eloc, tmpeloc;
int c = 1;
loff_t lbcount = 0, b_off = 0;
- udf_pblk_t newblocknum, newblock;
+ udf_pblk_t newblocknum, newblock = 0;
sector_t offset = 0;
int8_t etype;
struct udf_inode_info *iinfo = UDF_I(inode);
@@ -787,7 +787,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len);
if (ret < 0) {
*err = ret;
- newblock = 0;
goto out_free;
}
c = 0;
@@ -852,7 +851,6 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
goal, err);
if (!newblocknum) {
*err = -ENOSPC;
- newblock = 0;
goto out_free;
}
if (isBeyondEOF)
--
GitLab
From 2a33ad4a0ba5a527b92aeef9a313aefec197fe28 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Mon, 2 Jan 2023 22:00:42 +0530
Subject: [PATCH 0450/1167] HID: amd_sfh: Fix warning unwind goto
Return directly instead of using existing goto will not cleanup
previously allocated resources. Hence replace return with goto
to fix warning unwind goto which cleanups previously allocated
resources.
Fixes: 93ce5e0231d7 ("HID: amd_sfh: Implement SFH1.1 functionality")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/amd-sfh-hid/amd_sfh_client.c | 2 +-
drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
index ab125f79408f2..1fb0f7105fb21 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
@@ -282,7 +282,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
mp2_ops->start(privdata, info);
status = amd_sfh_wait_for_response
(privdata, cl_data->sensor_idx[i], SENSOR_ENABLED);
diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
index 4da2f9f62aba3..a1d6e08fab7d4 100644
--- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
+++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c
@@ -160,7 +160,7 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata)
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
writel(0, privdata->mmio + AMD_P2C_MSG(0));
mp2_ops->start(privdata, info);
--
GitLab
From e498a04443240c15c3c857165f7b652b87f4fd96 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 3 Jan 2023 13:17:46 +0100
Subject: [PATCH 0451/1167] usb: dwc3: xilinx: include linux/gpio/consumer.h
The newly added gpio consumer calls cause a build failure in configurations
that fail to include the right header implicitly:
drivers/usb/dwc3/dwc3-xilinx.c: In function 'dwc3_xlnx_init_zynqmp':
drivers/usb/dwc3/dwc3-xilinx.c:207:22: error: implicit declaration of function 'devm_gpiod_get_optional'; did you mean 'devm_clk_get_optional'? [-Werror=implicit-function-declaration]
207 | reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
| ^~~~~~~~~~~~~~~~~~~~~~~
| devm_clk_get_optional
Fixes: ca05b38252d7 ("usb: dwc3: xilinx: Add gpio-reset support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230103121755.956027-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/dwc3/dwc3-xilinx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
index 8607d4c23283c..0745e9f11b2ef 100644
--- a/drivers/usb/dwc3/dwc3-xilinx.c
+++ b/drivers/usb/dwc3/dwc3-xilinx.c
@@ -13,6 +13,7 @@
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
#include <linux/of_gpio.h>
#include <linux/of_platform.h>
#include <linux/pm_runtime.h>
--
GitLab
From c4e3ef5685393c5051b52cf1e94b8891d49793ab Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Thu, 8 Dec 2022 16:50:35 -0800
Subject: [PATCH 0452/1167] usb: dwc3: gadget: Ignore End Transfer delay on
teardown
If we delay sending End Transfer for Setup TRB to be prepared, we need
to check if the End Transfer was in preparation for a driver
teardown/soft-disconnect. In those cases, just send the End Transfer
command without delay.
In the case of soft-disconnect, there's a very small chance the command
may not go through immediately. But should it happen, the Setup TRB will
be prepared during the polling of the controller halted state, allowing
the command to go through then.
In the case of disabling endpoint due to reconfiguration (e.g.
set_interface(alt-setting) or usb reset), then it's driven by the host.
Typically the host wouldn't immediately cancel the control request and
send another control transfer to trigger the End Transfer command
timeout.
Fixes: 4db0fbb60136 ("usb: dwc3: gadget: Don't delay End Transfer on delayed_status")
Cc: stable@vger.kernel.org
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/f1617a323e190b9cc408fb8b65456e32b5814113.1670546756.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/dwc3/gadget.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 789976567f9f0..89dcfac01235f 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1727,6 +1727,7 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int
else if (!ret)
dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
+ dep->flags &= ~DWC3_EP_DELAY_STOP;
return ret;
}
@@ -3732,8 +3733,10 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE)
return;
+ if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP))
+ return;
+
if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
- (dep->flags & DWC3_EP_DELAY_STOP) ||
(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
return;
--
GitLab
From 0d4d52361b6c29bf771acd4fa461f06d78fb2fac Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Tue, 3 Jan 2023 15:11:07 +0100
Subject: [PATCH 0453/1167] s390/debug: add _ASM_S390_ prefix to header guard
Using DEBUG_H without a prefix is very generic and inconsistent with
other header guards in arch/s390/include/asm. In fact it collides with
the same name in the ath9k wireless driver though that depends on !S390
via disabled wireless support. Let's just use a consistent header guard
name and prevent possible future trouble.
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/include/asm/debug.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h
index 77f24262c25c1..ac665b9670c5d 100644
--- a/arch/s390/include/asm/debug.h
+++ b/arch/s390/include/asm/debug.h
@@ -4,8 +4,8 @@
*
* Copyright IBM Corp. 1999, 2020
*/
-#ifndef DEBUG_H
-#define DEBUG_H
+#ifndef _ASM_S390_DEBUG_H
+#define _ASM_S390_DEBUG_H
#include <linux/string.h>
#include <linux/spinlock.h>
@@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas);
#endif /* MODULE */
-#endif /* DEBUG_H */
+#endif /* _ASM_S390_DEBUG_H */
--
GitLab
From 45d619bdaf799196d702a9ae464b07066d6db2f9 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Wed, 7 Dec 2022 17:15:19 +0100
Subject: [PATCH 0454/1167] s390: expicitly align _edata and _end symbols on
page boundary
Symbols _edata and _end in the linker script are the
only unaligned expicitly on page boundary. Although
_end is aligned implicitly by BSS_SECTION macro that
is still inconsistent and could lead to a bug if a tool
or function would assume that _edata is as aligned as
others.
For example, vmem_map_init() function does not align
symbols _etext, _einittext etc. Should these symbols
be unaligned as well, the size of ranges to update
were short on one page.
Instead of fixing every occurrence of this kind in the
code and external tools just force the alignment on
these two symbols.
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/kernel/vmlinux.lds.S | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 5ea3830af0ccf..f81d96710595a 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -79,6 +79,7 @@ SECTIONS
_end_amode31_refs = .;
}
+ . = ALIGN(PAGE_SIZE);
_edata = .; /* End of data section */
/* will be freed after init */
@@ -193,6 +194,7 @@ SECTIONS
BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE)
+ . = ALIGN(PAGE_SIZE);
_end = . ;
/*
--
GitLab
From a494398bde273143c2352dd373cad8211f7d94b2 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Thu, 5 Jan 2023 12:13:06 +0900
Subject: [PATCH 0455/1167] s390: define RUNTIME_DISCARD_EXIT to fix link error
with GNU ld < 2.36
Nathan Chancellor reports that the s390 vmlinux fails to link with
GNU ld < 2.36 since commit 99cb0d917ffa ("arch: fix broken BuildID
for arm64 and riscv").
It happens for defconfig, or more specifically for CONFIG_EXPOLINE=y.
$ s390x-linux-gnu-ld --version | head -n1
GNU ld (GNU Binutils for Debian) 2.35.2
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- allnoconfig
$ ./scripts/config -e CONFIG_EXPOLINE
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu- olddefconfig
$ make -s ARCH=s390 CROSS_COMPILE=s390x-linux-gnu-
`.exit.text' referenced in section `.s390_return_reg' of drivers/base/dd.o: defined in discarded section `.exit.text' of drivers/base/dd.o
make[1]: *** [scripts/Makefile.vmlinux:34: vmlinux] Error 1
make: *** [Makefile:1252: vmlinux] Error 2
arch/s390/kernel/vmlinux.lds.S wants to keep EXIT_TEXT:
.exit.text : {
EXIT_TEXT
}
But, at the same time, EXIT_TEXT is thrown away by DISCARD because
s390 does not define RUNTIME_DISCARD_EXIT.
I still do not understand why the latter wins after 99cb0d917ffa,
but defining RUNTIME_DISCARD_EXIT seems correct because the comment
line in arch/s390/kernel/vmlinux.lds.S says:
/*
* .exit.text is discarded at runtime, not link time,
* to deal with references from __bug_table
*/
Nathan also found that binutils commit 21401fc7bf67 ("Duplicate output
sections in scripts") cured this issue, so we cannot reproduce it with
binutils 2.36+, but it is better to not rely on it.
Fixes: 99cb0d917ffa ("arch: fix broken BuildID for arm64 and riscv")
Link: https://lore.kernel.org/all/Y7Jal56f6UBh1abE@dev-arch.thelio-3990X/
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Link: https://lore.kernel.org/r/20230105031306.1455409-1-masahiroy@kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/kernel/vmlinux.lds.S | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index f81d96710595a..cbf9c1b0beda4 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -17,6 +17,8 @@
/* Handle ro_after_init data on our own. */
#define RO_AFTER_INIT_DATA
+#define RUNTIME_DISCARD_EXIT
+
#define EMITS_PT_NOTE
#include <asm-generic/vmlinux.lds.h>
--
GitLab
From f3dc61cde80d48751999c4cb46daf3b2185e6895 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 25 Nov 2022 10:18:26 +0000
Subject: [PATCH 0456/1167] firmware/psci: Fix MEM_PROTECT_RANGE function
numbers
PSCI v1.1 offers 32-bit and 64-bit variants of the MEM_PROTECT_RANGE
call using function identifier 20.
Fix the incorrect definitions of the MEM_PROTECT_CHECK_RANGE calls in
the PSCI UAPI header.
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Fixes: 3137f2e60098 ("firmware/psci: Add debugfs support to ease debugging")
Acked-by: Marc Zyngier <maz@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20221125101826.22404-1-will@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
include/uapi/linux/psci.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
index 3511095c2702b..42a40ad3fb622 100644
--- a/include/uapi/linux/psci.h
+++ b/include/uapi/linux/psci.h
@@ -58,7 +58,7 @@
#define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18)
#define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19)
-#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19)
+#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20)
#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12)
#define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13)
@@ -67,7 +67,7 @@
#define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17)
#define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18)
-#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19)
+#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20)
/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
--
GitLab
From cef139299fd86098c6e3dbd389d1d0b2462d7710 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 5 Jan 2023 09:08:34 +0000
Subject: [PATCH 0457/1167] firmware/psci: Don't register with debugfs if PSCI
isn't available
Contrary to popular belief, PSCI is not a universal property of an
ARM/arm64 system. There is a garden variety of systems out there
that don't (or even cannot) implement it.
I'm the first one deplore such a situation, but hey...
On such systems, a "cat /sys/kernel/debug/psci" results in
fireworks, as no invocation callback is registered.
Check for the invoke_psci_fn and psci_ops.get_version pointers
before registering with the debugfs subsystem, avoiding the
issue altogether.
Fixes: 3137f2e60098 ("firmware/psci: Add debugfs support to ease debugging")
Reported-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Ulf Hansson <ulf.hansson@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Hector Martin <marcan@marcan.st>
Acked-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20230105090834.630238-1-maz@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/firmware/psci/psci.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c
index e7bcfca4159f6..447ee4ea5c903 100644
--- a/drivers/firmware/psci/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -440,6 +440,9 @@ static const struct file_operations psci_debugfs_ops = {
static int __init psci_debugfs_init(void)
{
+ if (!invoke_psci_fn || !psci_ops.get_version)
+ return 0;
+
return PTR_ERR_OR_ZERO(debugfs_create_file("psci", 0444, NULL, NULL,
&psci_debugfs_ops));
}
--
GitLab
From 5db568e748f6fb7d0d2e1bff4c2698ad4f50b982 Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Mon, 2 Jan 2023 11:46:51 +0530
Subject: [PATCH 0458/1167] arm64: errata: Workaround possible Cortex-A715
[ESR|FAR]_ELx corruption
If a Cortex-A715 cpu sees a page mapping permissions change from executable
to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers, on the
next instruction abort caused by permission fault.
Only user-space does executable to non-executable permission transition via
mprotect() system call which calls ptep_modify_prot_start() and ptep_modify
_prot_commit() helpers, while changing the page mapping. The platform code
can override these helpers via __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION.
Work around the problem via doing a break-before-make TLB invalidation, for
all executable user space mappings, that go through mprotect() system call.
This overrides ptep_modify_prot_start() and ptep_modify_prot_commit(), via
defining HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION on the platform thus giving
an opportunity to intercept user space exec mappings, and do the necessary
TLB invalidation. Similar interceptions are also implemented for HugeTLB.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20230102061651.34745-1-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
Documentation/arm64/silicon-errata.rst | 2 ++
arch/arm64/Kconfig | 16 ++++++++++++++++
arch/arm64/include/asm/hugetlb.h | 9 +++++++++
arch/arm64/include/asm/pgtable.h | 9 +++++++++
arch/arm64/kernel/cpu_errata.c | 7 +++++++
arch/arm64/mm/hugetlbpage.c | 21 +++++++++++++++++++++
arch/arm64/mm/mmu.c | 21 +++++++++++++++++++++
arch/arm64/tools/cpucaps | 1 +
8 files changed, 86 insertions(+)
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 808ade4cc008a..ec5f889d76819 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -120,6 +120,8 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 03934808b2ed0..cf6d1cd8b6dc5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -972,6 +972,22 @@ config ARM64_ERRATUM_2457168
If unsure, say Y.
+config ARM64_ERRATUM_2645198
+ bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+ If a Cortex-A715 cpu sees a page mapping permissions change from executable
+ to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+ next instruction abort caused by permission fault.
+
+ Only user-space does executable to non-executable permission transition via
+ mprotect() system call. Workaround the problem by doing a break-before-make
+ TLB invalidation, for all changes to executable user space mappings.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index d20f5da2d76fa..6a4a1ab8eb238 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);
void __init arm64_hugetlb_cma_reserve(void);
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
+
#include <asm-generic/hugetlb.h>
#endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 780973a6cbb61..02ed5c0adf97a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1093,6 +1093,15 @@ static inline bool pud_sect_supported(void)
}
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 89ac00084f38a..307faa2b4395e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+ {
+ .desc = "ARM erratum 2645198",
+ .capability = ARM64_WORKAROUND_2645198,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+ },
+#endif
#ifdef CONFIG_ARM64_ERRATUM_2077057
{
.desc = "ARM erratum 2077057",
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 35e9a468d13e6..95364e8bdc194 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
{
return __hugetlb_valid_size(size);
}
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return huge_ptep_clear_flush(vma, addr, ptep);
+ }
+ return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 14c87e8d69d83..d77c9f56b7b43 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void)
}
early_initcall(prevent_bootmem_remove_init);
#endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return ptep_clear_flush(vma, addr, ptep);
+ }
+ return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index a86ee376920a0..dfeb2c51e2573 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -71,6 +71,7 @@ WORKAROUND_2038923
WORKAROUND_2064142
WORKAROUND_2077057
WORKAROUND_2457168
+WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
--
GitLab
From d3178e8a434b58678d99257c0387810a24042fb6 Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Wed, 4 Jan 2023 09:47:09 +0800
Subject: [PATCH 0459/1167] bpf: Skip invalid kfunc call in backtrack_insn
The verifier skips invalid kfunc call in check_kfunc_call(), which
would be captured in fixup_kfunc_call() if such insn is not eliminated
by dead code elimination. However, this can lead to the following
warning in backtrack_insn(), also see [1]:
------------[ cut here ]------------
verifier backtracking bug
WARNING: CPU: 6 PID: 8646 at kernel/bpf/verifier.c:2756 backtrack_insn
kernel/bpf/verifier.c:2756
__mark_chain_precision kernel/bpf/verifier.c:3065
mark_chain_precision kernel/bpf/verifier.c:3165
adjust_reg_min_max_vals kernel/bpf/verifier.c:10715
check_alu_op kernel/bpf/verifier.c:10928
do_check kernel/bpf/verifier.c:13821 [inline]
do_check_common kernel/bpf/verifier.c:16289
[...]
So make backtracking conservative with this by returning ENOTSUPP.
[1] https://lore.kernel.org/bpf/CACkBjsaXNceR8ZjkLG=dT3P=4A8SBsg0Z5h5PWLryF5=ghKq=g@mail.gmail.com/
Reported-by: syzbot+4da3ff23081bafe74fc2@syzkaller.appspotmail.com
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20230104014709.9375-1-sunhao.th@gmail.com
---
kernel/bpf/verifier.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 85f96c1e9f62f..c4c0985daac02 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2748,6 +2748,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
*/
if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
return -ENOTSUPP;
+ /* kfunc with imm==0 is invalid and fixup_kfunc_call will
+ * catch this error later. Make backtracking conservative
+ * with ENOTSUPP.
+ */
+ if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
+ return -ENOTSUPP;
/* regular helper call sets R0 */
*reg_mask &= ~1;
if (*reg_mask & 0x3f) {
--
GitLab
From 26658868354963afbff672ad6f7a85c44c311975 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan@gerhold.net>
Date: Thu, 29 Dec 2022 16:16:47 +0100
Subject: [PATCH 0460/1167] dt-bindings: soc: qcom: apr: Make
qcom,protection-domain optional again
The protection domain functionality exists only in SoCs starting from
MSM8998 [1], while the APR bindings are also used on older platforms.
Commit 41288c305836 ("ASoC: dt-bindings: qcom,apr: Split services to
shared schema") made the "qcom,protection-domain" required but it
should remain optional to avoid dtbs_check warnings on older platforms,
e.g.:
arch/arm64/boot/dts/qcom/apq8096-db820c.dtb:
apr: service@3: 'qcom,protection-domain' is a required property
From schema: Documentation/devicetree/bindings/soc/qcom/qcom,apr.yaml
[1]: https://lore.kernel.org/all/20200312120842.21991-1-sibis@codeaurora.org/
Fixes: 41288c305836 ("ASoC: dt-bindings: qcom,apr: Split services to shared schema")
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221229151648.19839-2-stephan@gerhold.net
---
.../devicetree/bindings/soc/qcom/qcom,apr-services.yaml | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml
index 290555426c39c..bdf482db32aac 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml
@@ -39,8 +39,8 @@ properties:
qcom,protection-domain:
$ref: /schemas/types.yaml#/definitions/string-array
description: |
- Protection domain service name and path for APR service
- possible values are::
+ Protection domain service name and path for APR service (if supported).
+ Possible values are::
"avs/audio", "msm/adsp/audio_pd".
"kernel/elf_loader", "msm/modem/wlan_pd".
"tms/servreg", "msm/adsp/audio_pd".
@@ -49,6 +49,5 @@ properties:
required:
- reg
- - qcom,protection-domain
additionalProperties: true
--
GitLab
From 599d41fb8ea8bd2a99ca9525dd69405020e43dda Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan@gerhold.net>
Date: Thu, 29 Dec 2022 16:16:48 +0100
Subject: [PATCH 0461/1167] soc: qcom: apr: Make qcom,protection-domain
optional again
APR should not fail if the service device tree node does not have
the qcom,protection-domain property, since this functionality does
not exist on older platforms such as MSM8916 and MSM8996.
Ignore -EINVAL (returned when the property does not exist) to fix
a regression on 6.2-rc1 that prevents audio from working:
qcom,apr remoteproc0:smd-edge.apr_audio_svc.-1.-1:
Failed to read second value of qcom,protection-domain
qcom,apr remoteproc0:smd-edge.apr_audio_svc.-1.-1:
Failed to add apr 3 svc
Fixes: 6d7860f5750d ("soc: qcom: apr: Add check for idr_alloc and of_property_read_string_index")
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221229151648.19839-3-stephan@gerhold.net
---
drivers/soc/qcom/apr.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c
index cd44f17dad3d0..d51abb462ae5d 100644
--- a/drivers/soc/qcom/apr.c
+++ b/drivers/soc/qcom/apr.c
@@ -461,9 +461,10 @@ static int apr_add_device(struct device *dev, struct device_node *np,
goto out;
}
+ /* Protection domain is optional, it does not exist on older platforms */
ret = of_property_read_string_index(np, "qcom,protection-domain",
1, &adev->service_path);
- if (ret < 0) {
+ if (ret < 0 && ret != -EINVAL) {
dev_err(dev, "Failed to read second value of qcom,protection-domain\n");
goto out;
}
--
GitLab
From 0b3a551fa58b4da941efeb209b3770868e2eddd7 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 5 Jan 2023 14:55:56 -0500
Subject: [PATCH 0462/1167] nfsd: fix handling of cached open files in
nfsd4_open codepath
Commit fb70bf124b05 ("NFSD: Instantiate a struct file when creating a
regular NFSv4 file") added the ability to cache an open fd over a
compound. There are a couple of problems with the way this currently
works:
It's racy, as a newly-created nfsd_file can end up with its PENDING bit
cleared while the nf is hashed, and the nf_file pointer is still zeroed
out. Other tasks can find it in this state and they expect to see a
valid nf_file, and can oops if nf_file is NULL.
Also, there is no guarantee that we'll end up creating a new nfsd_file
if one is already in the hash. If an extant entry is in the hash with a
valid nf_file, nfs4_get_vfs_file will clobber its nf_file pointer with
the value of op_file and the old nf_file will leak.
Fix both issues by making a new nfsd_file_acquirei_opened variant that
takes an optional file pointer. If one is present when this is called,
we'll take a new reference to it instead of trying to open the file. If
the nfsd_file already has a valid nf_file, we'll just ignore the
optional file and pass the nfsd_file back as-is.
Also rework the tracepoints a bit to allow for an "opened" variant and
don't try to avoid counting acquisitions in the case where we already
have a cached open file.
Fixes: fb70bf124b05 ("NFSD: Instantiate a struct file when creating a regular NFSv4 file")
Cc: Trond Myklebust <trondmy@hammerspace.com>
Reported-by: Stanislav Saner <ssaner@redhat.com>
Reported-and-Tested-by: Ruben Vestergaard <rubenv@drcmr.dk>
Reported-and-Tested-by: Torkil Svensgaard <torkil@drcmr.dk>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/filecache.c | 40 ++++++++++++++++++----------------
fs/nfsd/filecache.h | 5 +++--
fs/nfsd/nfs4state.c | 16 ++++----------
fs/nfsd/trace.h | 52 ++++++++++++---------------------------------
4 files changed, 42 insertions(+), 71 deletions(-)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 45b2c9e3f6360..0ef0703490144 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -1071,8 +1071,8 @@ nfsd_file_is_cached(struct inode *inode)
static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf,
- bool open, bool want_gc)
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf, bool want_gc)
{
struct nfsd_file_lookup_key key = {
.type = NFSD_FILE_KEY_FULL,
@@ -1147,8 +1147,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
out:
if (status == nfs_ok) {
- if (open)
- this_cpu_inc(nfsd_file_acquisitions);
+ this_cpu_inc(nfsd_file_acquisitions);
*pnf = nf;
} else {
if (refcount_dec_and_test(&nf->nf_ref))
@@ -1158,20 +1157,23 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
out_status:
put_cred(key.cred);
- if (open)
- trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
+ trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
return status;
open_file:
trace_nfsd_file_alloc(nf);
nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
if (nf->nf_mark) {
- if (open) {
+ if (file) {
+ get_file(file);
+ nf->nf_file = file;
+ status = nfs_ok;
+ trace_nfsd_file_opened(nf, status);
+ } else {
status = nfsd_open_verified(rqstp, fhp, may_flags,
&nf->nf_file);
trace_nfsd_file_open(nf, status);
- } else
- status = nfs_ok;
+ }
} else
status = nfserr_jukebox;
/*
@@ -1207,7 +1209,7 @@ __be32
nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
}
/**
@@ -1228,28 +1230,30 @@ __be32
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
}
/**
- * nfsd_file_create - Get a struct nfsd_file, do not open
+ * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file
* @rqstp: the RPC transaction being executed
* @fhp: the NFS filehandle of the file just created
* @may_flags: NFSD_MAY_ settings for the file
+ * @file: cached, already-open file (may be NULL)
* @pnf: OUT: new or found "struct nfsd_file" object
*
- * The nfsd_file_object returned by this API is reference-counted
- * but not garbage-collected. The object is released immediately
- * one RCU grace period after the final nfsd_file_put().
+ * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist,
+ * and @file is non-NULL, use it to instantiate a new nfsd_file instead of
+ * opening a new one.
*
* Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
* network byte order is returned.
*/
__be32
-nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf)
+nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
}
/*
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index b7efb2c3ddb18..41516a4263ea5 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -60,7 +60,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
-__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **nfp);
int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
#endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e1e85c21f12bc..313f666d53578 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5262,18 +5262,10 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
- if (!open->op_filp) {
- status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- } else {
- status = nfsd_file_create(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- nf->nf_file = open->op_filp;
- open->op_filp = NULL;
- trace_nfsd_file_create(rqstp, access, nf);
- }
+ status = nfsd_file_acquire_opened(rqstp, cur_fh, access,
+ open->op_filp, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index c852ae8eaf371..8f9c82d9e075b 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -981,43 +981,6 @@ TRACE_EVENT(nfsd_file_acquire,
)
);
-TRACE_EVENT(nfsd_file_create,
- TP_PROTO(
- const struct svc_rqst *rqstp,
- unsigned int may_flags,
- const struct nfsd_file *nf
- ),
-
- TP_ARGS(rqstp, may_flags, nf),
-
- TP_STRUCT__entry(
- __field(const void *, nf_inode)
- __field(const void *, nf_file)
- __field(unsigned long, may_flags)
- __field(unsigned long, nf_flags)
- __field(unsigned long, nf_may)
- __field(unsigned int, nf_ref)
- __field(u32, xid)
- ),
-
- TP_fast_assign(
- __entry->nf_inode = nf->nf_inode;
- __entry->nf_file = nf->nf_file;
- __entry->may_flags = may_flags;
- __entry->nf_flags = nf->nf_flags;
- __entry->nf_may = nf->nf_may;
- __entry->nf_ref = refcount_read(&nf->nf_ref);
- __entry->xid = be32_to_cpu(rqstp->rq_xid);
- ),
-
- TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
- __entry->xid, __entry->nf_inode,
- show_nfsd_may_flags(__entry->may_flags),
- __entry->nf_ref, show_nf_flags(__entry->nf_flags),
- show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
- )
-);
-
TRACE_EVENT(nfsd_file_insert_err,
TP_PROTO(
const struct svc_rqst *rqstp,
@@ -1079,8 +1042,8 @@ TRACE_EVENT(nfsd_file_cons_err,
)
);
-TRACE_EVENT(nfsd_file_open,
- TP_PROTO(struct nfsd_file *nf, __be32 status),
+DECLARE_EVENT_CLASS(nfsd_file_open_class,
+ TP_PROTO(const struct nfsd_file *nf, __be32 status),
TP_ARGS(nf, status),
TP_STRUCT__entry(
__field(void *, nf_inode) /* cannot be dereferenced */
@@ -1104,6 +1067,17 @@ TRACE_EVENT(nfsd_file_open,
__entry->nf_file)
)
+#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \
+DEFINE_EVENT(nfsd_file_open_class, name, \
+ TP_PROTO( \
+ const struct nfsd_file *nf, \
+ __be32 status \
+ ), \
+ TP_ARGS(nf, status))
+
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open);
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened);
+
TRACE_EVENT(nfsd_file_is_cached,
TP_PROTO(
const struct inode *inode,
--
GitLab
From 7827c81f0248e3c2f40d438b020f3d222f002171 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 6 Jan 2023 12:43:37 -0500
Subject: [PATCH 0463/1167] Revert "SUNRPC: Use RMW bitops in single-threaded
hot paths"
The premise that "Once an svc thread is scheduled and executing an
RPC, no other processes will touch svc_rqst::rq_flags" is false.
svc_xprt_enqueue() examines the RQ_BUSY flag in scheduled nfsd
threads when determining which thread to wake up next.
Found via KCSAN.
Fixes: 28df0988815f ("SUNRPC: Use RMW bitops in single-threaded hot paths")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs4proc.c | 7 +++----
fs/nfsd/nfs4xdr.c | 2 +-
net/sunrpc/auth_gss/svcauth_gss.c | 4 ++--
net/sunrpc/svc.c | 6 +++---
net/sunrpc/svc_xprt.c | 2 +-
net/sunrpc/svcsock.c | 8 ++++----
net/sunrpc/xprtrdma/svc_rdma_transport.c | 2 +-
7 files changed, 15 insertions(+), 16 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index bd880d55f565b..9b81d012666e2 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -937,7 +937,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* the client wants us to do more in this compound:
*/
if (!nfsd4_last_compound_op(rqstp))
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
@@ -2607,12 +2607,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
cstate->minorversion = args->minorversion;
fh_init(current_fh, NFS4_FHSIZE);
fh_init(save_fh, NFS4_FHSIZE);
-
/*
* Don't use the deferral mechanism for NFSv4; compounds make it
* too hard to avoid non-idempotency problems.
*/
- __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
/*
* According to RFC3010, this takes precedence over all other errors.
@@ -2734,7 +2733,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
out:
cstate->status = status;
/* Reset deferral mechanism for RPC deferrals */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
return rpc_success;
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ebb4d02a42ce6..97edb32be77f1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2523,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
return true;
}
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 148bb0a7fa5b4..acb822b23af1b 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -923,7 +923,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g
* rejecting the server-computed MIC in this somewhat rare case,
* do not use splice with the GSS integrity service.
*/
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Did we already verify the signature on the original pass through? */
if (rqstp->rq_deferred)
@@ -990,7 +990,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs
int pad, remaining_len, offset;
u32 rseqno;
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
priv_len = svc_getnl(&buf->head[0]);
if (rqstp->rq_deferred) {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 8f1b596db33fc..b1da586c44765 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1243,10 +1243,10 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
goto err_short_len;
/* Will be turned off by GSS integrity and privacy services */
- __set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Will be turned off only when NFSv4 Sessions are used */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
- __clear_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_DROPME, &rqstp->rq_flags);
svc_putu32(resv, rqstp->rq_xid);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 2106003645a78..c2ce125380080 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -1238,7 +1238,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req)
trace_svc_defer(rqstp);
svc_xprt_get(rqstp->rq_xprt);
dr->xprt = rqstp->rq_xprt;
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
dr->handle.revisit = svc_revisit;
return &dr->handle;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 2fc98fea59b46..e833103f46291 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -298,9 +298,9 @@ static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs)
static void svc_sock_secure_port(struct svc_rqst *rqstp)
{
if (svc_port_is_privileged(svc_addr(rqstp)))
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
else
- __clear_bit(RQ_SECURE, &rqstp->rq_flags);
+ clear_bit(RQ_SECURE, &rqstp->rq_flags);
}
/*
@@ -1008,9 +1008,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
- __set_bit(RQ_LOCAL, &rqstp->rq_flags);
+ set_bit(RQ_LOCAL, &rqstp->rq_flags);
else
- __clear_bit(RQ_LOCAL, &rqstp->rq_flags);
+ clear_bit(RQ_LOCAL, &rqstp->rq_flags);
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
calldir = p[1];
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 199fa012f18a8..94b20fb471356 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -602,7 +602,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt)
static void svc_rdma_secure_port(struct svc_rqst *rqstp)
{
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
}
static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)
--
GitLab
From ec64efc4966edf19fa1bc398a26bddfbadc1605f Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 5 Dec 2022 17:44:59 +0000
Subject: [PATCH 0464/1167] dt-bindings: riscv: fix underscore requirement for
multi-letter extensions
The RISC-V ISA Manual allows the first multi-letter extension to avoid
a leading underscore. Underscores are only required between multi-letter
extensions.
The dt-binding does not validate that a multi-letter extension is
canonically ordered, as that'd need an even worse regex than is here,
but it should not fail validation for valid ISA strings.
Allow the first multi-letter extension to appear immediately after
the single-letter extensions.
Link: https://github.com/riscv/riscv-isa-manual/releases/tag/riscv-unpriv-pdf-from-asciidoc-15112022 # Chapter 29.5
Fixes: 299824e68bd0 ("dt-bindings: riscv: add new riscv,isa strings for emulators")
Acked-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20221205174459.60195-2-conor@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
Documentation/devicetree/bindings/riscv/cpus.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index 90a7cabf58feb..97659bb718119 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -80,7 +80,7 @@ properties:
insensitive, letters in the riscv,isa string must be all
lowercase to simplify parsing.
$ref: "/schemas/types.yaml#/definitions/string"
- pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$
+ pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
# RISC-V requires 'timebase-frequency' in /cpus, so disallow it here
timebase-frequency: false
--
GitLab
From a943385aa80151c6b2611d3a1cf8338af2b257a1 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 5 Dec 2022 17:45:00 +0000
Subject: [PATCH 0465/1167] dt-bindings: riscv: fix single letter canonical
order
I used the wikipedia table for ordering extensions when updating the
pattern here in commit 299824e68bd0 ("dt-bindings: riscv: add new
riscv,isa strings for emulators").
Unfortunately that table did not match canonical order, as defined by
the RISC-V ISA Manual, which defines extension ordering in (what is
currently) Table 41, "Standard ISA extension names". Fix things up by
re-sorting v (vector) and adding p (packed-simd) & j (dynamic
languages). The e (reduced integer) and g (general) extensions are still
intentionally left out.
Link: https://github.com/riscv/riscv-isa-manual/releases/tag/riscv-unpriv-pdf-from-asciidoc-15112022 # Chapter 29.5
Fixes: 299824e68bd0 ("dt-bindings: riscv: add new riscv,isa strings for emulators")
Acked-by: Guo Ren <guoren@kernel.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/20221205174459.60195-3-conor@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
Documentation/devicetree/bindings/riscv/cpus.yaml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index 97659bb718119..d4148418350c6 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -80,7 +80,7 @@ properties:
insensitive, letters in the riscv,isa string must be all
lowercase to simplify parsing.
$ref: "/schemas/types.yaml#/definitions/string"
- pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
+ pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$
# RISC-V requires 'timebase-frequency' in /cpus, so disallow it here
timebase-frequency: false
--
GitLab
From 0283189e8f3d0917e2ac399688df85211f48447b Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Wed, 4 Jan 2023 10:47:39 -0700
Subject: [PATCH 0466/1167] docs: Fix the docs build with Sphinx 6.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Sphinx 6.0 removed the execfile_() function, which we use as part of the
configuration process. They *did* warn us... Just open-code the
functionality as is done in Sphinx itself.
Tested (using SPHINX_CONF, since this code is only executed with an
alternative config file) on various Sphinx versions from 2.5 through 6.0.
Reported-by: Martin Liška <mliska@suse.cz>
Cc: stable@vger.kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
Documentation/sphinx/load_config.py | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py
index eeb394b39e2cc..8b416bfd75ac1 100644
--- a/Documentation/sphinx/load_config.py
+++ b/Documentation/sphinx/load_config.py
@@ -3,7 +3,7 @@
import os
import sys
-from sphinx.util.pycompat import execfile_
+from sphinx.util.osutil import fs_encoding
# ------------------------------------------------------------------------------
def loadConfig(namespace):
@@ -48,7 +48,9 @@ def loadConfig(namespace):
sys.stdout.write("load additional sphinx-config: %s\n" % config_file)
config = namespace.copy()
config['__file__'] = config_file
- execfile_(config_file, config)
+ with open(config_file, 'rb') as f:
+ code = compile(f.read(), fs_encoding, 'exec')
+ exec(code, config)
del config['__file__']
namespace.update(config)
else:
--
GitLab
From 31abfdda65279a860b10a98038135501e4fc00a1 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Wed, 4 Jan 2023 13:59:16 -0700
Subject: [PATCH 0467/1167] docs: Deprecate use of Sphinx < 2.4.x
The Sphinx 2.4 release is three years old, and it is becoming increasingly
difficult to even find a system with an sufficiently archaic Python
installation that can run versions older than that. I can no longer test
changes against anything prior to 2.4.x.
Move toward raising our minimum Sphinx requirement to 2.4.x so we can
delete some older support code and claim to support a range of versions
that we can actually test.
In the absence of screams, the actual removal of support can happen later
in 2023.
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
Documentation/conf.py | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/Documentation/conf.py b/Documentation/conf.py
index a5c45df0bd839..44899be7b2cca 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -31,6 +31,12 @@ def have_command(cmd):
# Get Sphinx version
major, minor, patch = sphinx.version_info[:3]
+#
+# Warn about older versions that we don't want to support for much
+# longer.
+#
+if (major < 2) or (major == 2 and minor < 4):
+ print('WARNING: support for Sphinx < 2.4 will be removed soon.')
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
--
GitLab
From a3d81bc1eaef48e34dd0b9b48eefed9e02a06451 Mon Sep 17 00:00:00 2001
From: Hao Sun <sunhao.th@gmail.com>
Date: Fri, 6 Jan 2023 16:48:38 +0800
Subject: [PATCH 0468/1167] bpf: Skip task with pid=1 in send_signal_common()
The following kernel panic can be triggered when a task with pid=1 attaches
a prog that attempts to send killing signal to itself, also see [1] for more
details:
Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
CPU: 3 PID: 1 Comm: systemd Not tainted 6.1.0-09652-g59fe41b5255f #148
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0x100/0x178 lib/dump_stack.c:106
panic+0x2c4/0x60f kernel/panic.c:275
do_exit.cold+0x63/0xe4 kernel/exit.c:789
do_group_exit+0xd4/0x2a0 kernel/exit.c:950
get_signal+0x2460/0x2600 kernel/signal.c:2858
arch_do_signal_or_restart+0x78/0x5d0 arch/x86/kernel/signal.c:306
exit_to_user_mode_loop kernel/entry/common.c:168 [inline]
exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203
__syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline]
syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296
do_syscall_64+0x44/0xb0 arch/x86/entry/common.c:86
entry_SYSCALL_64_after_hwframe+0x63/0xcd
So skip task with pid=1 in bpf_send_signal_common() to avoid the panic.
[1] https://lore.kernel.org/bpf/20221222043507.33037-1-sunhao.th@gmail.com
Signed-off-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20230106084838.12690-1-sunhao.th@gmail.com
---
kernel/trace/bpf_trace.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3bbd3f0c810c8..f47274de012b5 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -848,6 +848,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
return -EPERM;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
+ /* Task should not be pid=1 to avoid kernel panic. */
+ if (unlikely(is_global_init(current)))
+ return -EPERM;
if (irqs_disabled()) {
/* Do an early check on signal validity. Otherwise,
--
GitLab
From cb7a95af78d29442b8294683eca4897544b8ef46 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 4 Jan 2023 11:06:28 -0800
Subject: [PATCH 0469/1167] hfs/hfsplus: avoid WARN_ON() for sanity check, use
proper error handling
Commit 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check") fixed
a build warning by turning a comment into a WARN_ON(), but it turns out
that syzbot then complains because it can trigger said warning with a
corrupted hfs image.
The warning actually does warn about a bad situation, but we are much
better off just handling it as the error it is. So rather than warn
about us doing bad things, stop doing the bad things and return -EIO.
While at it, also fix a memory leak that was introduced by an earlier
fix for a similar syzbot warning situation, and add a check for one case
that historically wasn't handled at all (ie neither comment nor
subsequent WARN_ON).
Reported-by: syzbot+7bb7cd3595533513a9e7@syzkaller.appspotmail.com
Fixes: 55d1cbbbb29e ("hfs/hfsplus: use WARN_ON for sanity check")
Fixes: 8d824e69d9f3 ("hfs: fix OOB Read in __hfs_brec_find")
Link: https://lore.kernel.org/lkml/000000000000dbce4e05f170f289@google.com/
Tested-by: Michael Schmitz <schmitzmic@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Viacheslav Dubeyko <slava@dubeyko.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
fs/hfs/inode.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 9c329a365e750..3a155c1d810ef 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -458,15 +458,16 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
/* panic? */
return -EIO;
+ res = -EIO;
if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN)
- return -EIO;
+ goto out;
fd.search_key->cat = HFS_I(main_inode)->cat_key;
if (hfs_brec_find(&fd))
- /* panic? */
goto out;
if (S_ISDIR(main_inode->i_mode)) {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir));
+ if (fd.entrylength < sizeof(struct hfs_cat_dir))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
if (rec.type != HFS_CDR_DIR ||
@@ -479,6 +480,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
} else if (HFS_IS_RSRC(inode)) {
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
hfs_inode_write_fork(inode, rec.file.RExtRec,
@@ -486,7 +489,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
} else {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file));
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
if (rec.type != HFS_CDR_FIL ||
@@ -503,9 +507,10 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc)
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
}
+ res = 0;
out:
hfs_find_exit(&fd);
- return 0;
+ return res;
}
static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
--
GitLab
From 1382999aa0548a171a272ca817f6c38e797c458c Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Fri, 6 Jan 2023 04:01:56 +0100
Subject: [PATCH 0470/1167] tpm: Allow system suspend to continue when TPM
suspend fails
TPM 1 is sometimes broken across system suspends, due to races or
locking issues or something else that haven't been diagnosed or fixed
yet, most likely having to do with concurrent reads from the TPM's
hardware random number generator driver. These issues prevent the system
from actually suspending, with errors like:
tpm tpm0: A TPM error (28) occurred continue selftest
...
tpm tpm0: A TPM error (28) occurred attempting get random
...
tpm tpm0: Error (28) sending savestate before suspend
tpm_tis 00:08: PM: __pnp_bus_suspend(): tpm_pm_suspend+0x0/0x80 returns 28
tpm_tis 00:08: PM: dpm_run_callback(): pnp_bus_suspend+0x0/0x10 returns 28
tpm_tis 00:08: PM: failed to suspend: error 28
PM: Some devices failed to suspend, or early wake event detected
This issue was partially fixed by 23393c646142 ("char: tpm: Protect
tpm_pm_suspend with locks"), in a last minute 6.1 commit that Linus took
directly because the TPM maintainers weren't available. However, it
seems like this just addresses the most common cases of the bug, rather
than addressing it entirely. So there are more things to fix still,
apparently.
In lieu of actually fixing the underlying bug, just allow system suspend
to continue, so that laptops still go to sleep fine. Later, this can be
reverted when the real bug is fixed.
Link: https://lore.kernel.org/lkml/7cbe96cf-e0b5-ba63-d1b4-f63d2e826efa@suse.cz/
Cc: stable@vger.kernel.org # 6.1+
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Luigi Semenzato <semenzato@chromium.org>
Cc: Peter Huewe <peterhuewe@gmx.de>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Johannes Altmanninger <aclopte@gmail.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
drivers/char/tpm/tpm-interface.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index d69905233aff2..7e513b7718320 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -412,7 +412,9 @@ int tpm_pm_suspend(struct device *dev)
}
suspended:
- return rc;
+ if (rc)
+ dev_err(dev, "Ignoring error %d while suspending\n", rc);
+ return 0;
}
EXPORT_SYMBOL_GPL(tpm_pm_suspend);
--
GitLab
From b4e9b8763e417db31c7088103cc557d55cb7a8f5 Mon Sep 17 00:00:00 2001
From: Angela Czubak <aczubak@marvell.com>
Date: Thu, 5 Jan 2023 21:31:07 +0530
Subject: [PATCH 0471/1167] octeontx2-af: Fix LMAC config in
cgx_lmac_rx_tx_enable
PF netdev can request AF to enable or disable reception and transmission
on assigned CGX::LMAC. The current code instead of disabling or enabling
'reception and transmission' also disables/enable the LMAC. This patch
fixes this issue.
Fixes: 1435f66a28b4 ("octeontx2-af: CGX Rx/Tx enable/disable mbox handlers")
Signed-off-by: Angela Czubak <aczubak@marvell.com>
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230105160107.17638-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 4 ++--
drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 1 -
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index b2b71fe80d61c..724df6398bbe2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -774,9 +774,9 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable)
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
if (enable)
- cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN;
+ cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN;
else
- cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN);
+ cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN);
cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
return 0;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index fb2d37676d84e..5a20d93004c71 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -26,7 +26,6 @@
#define CMR_P2X_SEL_SHIFT 59ULL
#define CMR_P2X_SEL_NIX0 1ULL
#define CMR_P2X_SEL_NIX1 2ULL
-#define CMR_EN BIT_ULL(55)
#define DATA_PKT_TX_EN BIT_ULL(53)
#define DATA_PKT_RX_EN BIT_ULL(54)
#define CGX_LMAC_TYPE_SHIFT 40
--
GitLab
From 4414c1f5c7a375eaa108676a56e12cc8234eb647 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Fri, 6 Jan 2023 23:30:57 -0800
Subject: [PATCH 0472/1167] xtensa: drop unused members of struct thread_struct
bad_vaddr, bad_uaddr and error_code fields are set but never read by the
xtensa arch-specific code. Drop them. Also drop the commented out info
field.
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
arch/xtensa/include/asm/processor.h | 9 ---------
arch/xtensa/kernel/traps.c | 2 --
arch/xtensa/mm/fault.c | 4 ----
3 files changed, 15 deletions(-)
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 228e4dff5fb2d..a6d09fe048311 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -154,11 +154,6 @@ struct thread_struct {
unsigned long ra; /* kernel's a0: return address and window call size */
unsigned long sp; /* kernel's a1: stack pointer */
- /* struct xtensa_cpuinfo info; */
-
- unsigned long bad_vaddr; /* last user fault */
- unsigned long bad_uaddr; /* last kernel fault accessing user space */
- unsigned long error_code;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK];
struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK];
@@ -176,10 +171,6 @@ struct thread_struct {
{ \
ra: 0, \
sp: sizeof(init_stack) + (long) &init_stack, \
- /*info: {0}, */ \
- bad_vaddr: 0, \
- bad_uaddr: 0, \
- error_code: 0, \
}
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 0c25e035ff107..cd98366a9b238 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs)
__die_if_kernel("Unhandled unaligned exception in kernel",
regs, SIGKILL);
- current->thread.bad_vaddr = regs->excvaddr;
- current->thread.error_code = -3;
pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
"(pid = %d, pc = %#010lx)\n",
regs->excvaddr, current->comm,
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 8c781b05c0bdd..faf7cf35a0ee3 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -206,8 +206,6 @@ void do_page_fault(struct pt_regs *regs)
bad_area:
mmap_read_unlock(mm);
if (user_mode(regs)) {
- current->thread.bad_vaddr = address;
- current->thread.error_code = is_write;
force_sig_fault(SIGSEGV, code, (void *) address);
return;
}
@@ -232,7 +230,6 @@ void do_page_fault(struct pt_regs *regs)
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- current->thread.bad_vaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address);
/* Kernel mode? Handle exceptions or die */
@@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
if ((entry = search_exception_tables(regs->pc)) != NULL) {
pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
current->comm, regs->pc, entry->fixup);
- current->thread.bad_uaddr = address;
regs->pc = entry->fixup;
return;
}
--
GitLab
From 15a59cb0a3d6ddf2cb79f8dc3081b3130aad3767 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 5 Jan 2023 10:35:30 +0100
Subject: [PATCH 0473/1167] ALSA: hda: cs35l41: Don't return -EINVAL from
system suspend/resume
The recent commit to support the system suspend for CS35L41 caused a
regression on the models with CS35L41_EXT_BOOST_NO_VSPK_SWITC boost
type, as the suspend/resume callbacks just return -EINVAL. This is
eventually handled as a fatal error and blocks the whole system
suspend/resume.
For avoiding the problem, this patch corrects the return code from
cs35l41_system_suspend() and _resume() to 0, and replace dev_err()
with dev_err_once() for stop spamming too much.
Fixes: 88672826e2a4 ("ALSA: hda: cs35l41: Support System Suspend")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/all/e6751ac2-34f3-d13f-13db-8174fade8308@pm.me
Link: https://lore.kernel.org/r/20230105093531.16960-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/cs35l41_hda.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index 91842c0c8c74b..0a5cee7302686 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -598,8 +598,8 @@ static int cs35l41_system_suspend(struct device *dev)
dev_dbg(cs35l41->dev, "System Suspend\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Suspend not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Suspend not supported\n");
+ return 0; /* don't block the whole system suspend */
}
ret = pm_runtime_force_suspend(dev);
@@ -624,8 +624,8 @@ static int cs35l41_system_resume(struct device *dev)
dev_dbg(cs35l41->dev, "System Resume\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Resume not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Resume not supported\n");
+ return 0; /* don't block the whole system resume */
}
if (cs35l41->reset_gpio) {
--
GitLab
From ae50e2ab122cef68f46b7799fb9deffe3334f5e2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 5 Jan 2023 10:35:31 +0100
Subject: [PATCH 0474/1167] ALSA: hda: cs35l41: Check runtime suspend
capability at runtime_idle
The runtime PM core checks with runtime_idle callback whether it can
goes to the runtime suspend or not, and we can put the boost type
check there instead of runtime_suspend and _resume calls. This will
reduce the unnecessary runtime_suspend() calls.
Fixes: 1873ebd30cc8 ("ALSA: hda: cs35l41: Support Hibernation during Suspend")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20230105093531.16960-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/cs35l41_hda.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c
index 0a5cee7302686..f7815ee24f836 100644
--- a/sound/pci/hda/cs35l41_hda.c
+++ b/sound/pci/hda/cs35l41_hda.c
@@ -647,6 +647,15 @@ static int cs35l41_system_resume(struct device *dev)
return ret;
}
+static int cs35l41_runtime_idle(struct device *dev)
+{
+ struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
+
+ if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH)
+ return -EBUSY; /* suspend not supported yet on this model */
+ return 0;
+}
+
static int cs35l41_runtime_suspend(struct device *dev)
{
struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
@@ -1536,7 +1545,8 @@ void cs35l41_hda_remove(struct device *dev)
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
const struct dev_pm_ops cs35l41_hda_pm_ops = {
- RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL)
+ RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume,
+ cs35l41_runtime_idle)
SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume)
};
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41);
--
GitLab
From 42f229c350f57a8e825f7591e17cbc5c87e50235 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 6 Jan 2023 13:03:18 +0000
Subject: [PATCH 0475/1167] rxrpc: Fix incoming call setup race
An incoming call can race with rxrpc socket destruction, leading to a
leaked call. This may result in an oops when the call timer eventually
expires:
BUG: kernel NULL pointer dereference, address: 0000000000000874
RIP: 0010:_raw_spin_lock_irqsave+0x2a/0x50
Call Trace:
<IRQ>
try_to_wake_up+0x59/0x550
? __local_bh_enable_ip+0x37/0x80
? rxrpc_poke_call+0x52/0x110 [rxrpc]
? rxrpc_poke_call+0x110/0x110 [rxrpc]
? rxrpc_poke_call+0x110/0x110 [rxrpc]
call_timer_fn+0x24/0x120
with a warning in the kernel log looking something like:
rxrpc: Call 00000000ba5e571a still in use (1,SvAwtACK,1061d,0)!
incurred during rmmod of rxrpc. The 1061d is the call flags:
RECVMSG_READ_ALL, RX_HEARD, BEGAN_RX_TIMER, RX_LAST, EXPOSED,
IS_SERVICE, RELEASED
but no DISCONNECTED flag (0x800), so it's an incoming (service) call and
it's still connected.
The race appears to be that:
(1) rxrpc_new_incoming_call() consults the service struct, checks sk_state
and allocates a call - then pauses, possibly for an interrupt.
(2) rxrpc_release_sock() sets RXRPC_CLOSE, nulls the service pointer,
discards the prealloc and releases all calls attached to the socket.
(3) rxrpc_new_incoming_call() resumes, launching the new call, including
its timer and attaching it to the socket.
Fix this by read-locking local->services_lock to access the AF_RXRPC socket
providing the service rather than RCU in rxrpc_new_incoming_call().
There's no real need to use RCU here as local->services_lock is only
write-locked by the socket side in two places: when binding and when
shutting down.
Fixes: 5e6ef4f1017c ("rxrpc: Make the I/O thread take over the call and local processor work")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
---
net/rxrpc/af_rxrpc.c | 8 ++++----
net/rxrpc/ar-internal.h | 2 +-
net/rxrpc/call_accept.c | 14 +++++++-------
net/rxrpc/security.c | 6 +++---
4 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index cf200e4e0eae1..ebbd4a1c3f86e 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -155,10 +155,10 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
if (service_id) {
write_lock(&local->services_lock);
- if (rcu_access_pointer(local->service))
+ if (local->service)
goto service_in_use;
rx->local = local;
- rcu_assign_pointer(local->service, rx);
+ local->service = rx;
write_unlock(&local->services_lock);
rx->sk.sk_state = RXRPC_SERVER_BOUND;
@@ -875,9 +875,9 @@ static int rxrpc_release_sock(struct sock *sk)
sk->sk_state = RXRPC_CLOSE;
- if (rx->local && rcu_access_pointer(rx->local->service) == rx) {
+ if (rx->local && rx->local->service == rx) {
write_lock(&rx->local->services_lock);
- rcu_assign_pointer(rx->local->service, NULL);
+ rx->local->service = NULL;
write_unlock(&rx->local->services_lock);
}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 007258538beeb..433060cade038 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -283,7 +283,7 @@ struct rxrpc_local {
struct socket *socket; /* my UDP socket */
struct task_struct *io_thread;
struct completion io_thread_ready; /* Indication that the I/O thread started */
- struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */
+ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */
struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */
struct sk_buff_head rx_queue; /* Received packets */
struct list_head conn_attend_q; /* Conns requiring immediate attention */
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 3fbf2fcaaf9e2..3e8689fdc4371 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -343,13 +343,13 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local,
if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call);
- rcu_read_lock();
+ read_lock(&local->services_lock);
/* Weed out packets to services we're not offering. Packets that would
* begin a call are explicitly rejected and the rest are just
* discarded.
*/
- rx = rcu_dereference(local->service);
+ rx = local->service;
if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
sp->hdr.serviceId != rx->second_service)
) {
@@ -399,7 +399,7 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local,
spin_unlock(&conn->state_lock);
spin_unlock(&rx->incoming_lock);
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
if (hlist_unhashed(&call->error_link)) {
spin_lock(&call->peer->lock);
@@ -413,20 +413,20 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local,
return true;
unsupported_service:
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
RX_INVALID_OPERATION, -EOPNOTSUPP);
unsupported_security:
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
RX_INVALID_OPERATION, -EKEYREJECTED);
no_call:
spin_unlock(&rx->incoming_lock);
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
_leave(" = f [%u]", skb->mark);
return false;
discard:
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
return true;
}
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index cd66634dffe69..cb8dd1d3b1d49 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -178,9 +178,9 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn,
sprintf(kdesc, "%u:%u",
sp->hdr.serviceId, sp->hdr.securityIndex);
- rcu_read_lock();
+ read_lock(&conn->local->services_lock);
- rx = rcu_dereference(conn->local->service);
+ rx = conn->local->service;
if (!rx)
goto out;
@@ -202,6 +202,6 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn,
}
out:
- rcu_read_unlock();
+ read_unlock(&conn->local->services_lock);
return key;
}
--
GitLab
From ea44242bbfcde2993fb27ec7c3ad5ab5cc39e438 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 15 Dec 2022 12:09:25 +0800
Subject: [PATCH 0476/1167] scsi: hisi_sas: Fix tag freeing for reserved tags
The reserved tags were put in the lower region of the tagset in commit
f7d190a94e35 ("scsi: hisi_sas: Put reserved tags in lower region of
tagset"). However, only the allocate function was changed, freeing was not
handled. This resulted in a failure to boot:
[ 33.467345] hisi_sas_v3_hw 0000:b4:02.0: task exec: failed[-132]!
[ 33.473413] sas: Executing internal abort failed 5000000000000603 (-132)
[ 33.480088] hisi_sas_v3_hw 0000:b4:02.0: I_T nexus reset: internal abort (-132)
[ 33.657336] hisi_sas_v3_hw 0000:b4:02.0: task exec: failed[-132]!
[ 33.663403] ata7.00: failed to IDENTIFY (I/O error, err_mask=0x40)
[ 35.787344] hisi_sas_v3_hw 0000:b4:04.0: task exec: failed[-132]!
[ 35.793411] sas: Executing internal abort failed 5000000000000703 (-132)
[ 35.800084] hisi_sas_v3_hw 0000:b4:04.0: I_T nexus reset: internal abort (-132)
[ 35.977335] hisi_sas_v3_hw 0000:b4:04.0: task exec: failed[-132]!
[ 35.983403] ata10.00: failed to IDENTIFY (I/O error, err_mask=0x40)
[ 35.989643] ata10.00: revalidation failed (errno=-5)
Fixes: f7d190a94e35 ("scsi: hisi_sas: Put reserved tags in lower region of tagset")
Cc: John Garry <john.g.garry@oracle.com>
Cc: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Acked-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 41ba22f6c7f05..e9c2d306ed873 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -162,7 +162,7 @@ static void hisi_sas_slot_index_clear(struct hisi_hba *hisi_hba, int slot_idx)
static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx)
{
if (hisi_hba->hw->slot_index_alloc ||
- slot_idx >= HISI_SAS_UNRESERVED_IPTT) {
+ slot_idx < HISI_SAS_RESERVED_IPTT) {
spin_lock(&hisi_hba->lock);
hisi_sas_slot_index_clear(hisi_hba, slot_idx);
spin_unlock(&hisi_hba->lock);
--
GitLab
From a67aad57d9aee41180aff36e54cb72fe4b8d5a5a Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Wed, 21 Dec 2022 01:52:03 +0000
Subject: [PATCH 0477/1167] scsi: libsas: Grab the ATA port lock in
sas_ata_device_link_abort()
Grab the ATA port lock in sas_ata_device_link_abort() before calling
ata_link_abort() as outlined in this function's locking requirements.
Fixes: 44112922674b ("scsi: libsas: Add sas_ata_device_link_abort()")
Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/libsas/sas_ata.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 1ccce706167a5..5e80225b53082 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -889,7 +889,9 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset)
{
struct ata_port *ap = device->sata_dev.ap;
struct ata_link *link = &ap->link;
+ unsigned long flags;
+ spin_lock_irqsave(ap->lock, flags);
device->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */
device->sata_dev.fis[3] = ATA_ABORTED; /* tf error */
@@ -897,6 +899,7 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset)
if (force_reset)
link->eh_info.action |= ATA_EH_RESET;
ata_link_abort(link);
+ spin_unlock_irqrestore(ap->lock, flags);
}
EXPORT_SYMBOL_GPL(sas_ata_device_link_abort);
--
GitLab
From 7fb3ff22ad8772bbf0e3ce1ef3eb7b09f431807f Mon Sep 17 00:00:00 2001
From: Yair Podemsky <ypodemsk@redhat.com>
Date: Wed, 30 Nov 2022 14:51:21 +0200
Subject: [PATCH 0478/1167] sched/core: Fix arch_scale_freq_tick() on tickless
systems
In order for the scheduler to be frequency invariant we measure the
ratio between the maximum CPU frequency and the actual CPU frequency.
During long tickless periods of time the calculations that keep track
of that might overflow, in the function scale_freq_tick():
if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt))
goto error;
eventually forcing the kernel to disable the feature for all CPUs,
and show the warning message:
"Scheduler frequency invariance went wobbly, disabling!".
Let's avoid that by limiting the frequency invariant calculations
to CPUs with regular tick.
Fixes: e2b0d619b400 ("x86, sched: check for counters overflow in frequency invariant accounting")
Suggested-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Signed-off-by: Yair Podemsky <ypodemsk@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Acked-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Link: https://lore.kernel.org/r/20221130125121.34407-1-ypodemsk@redhat.com
---
kernel/sched/core.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 25b582b6ee5f7..965d813c28ad7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5504,7 +5504,9 @@ void scheduler_tick(void)
unsigned long thermal_pressure;
u64 resched_latency;
- arch_scale_freq_tick();
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+ arch_scale_freq_tick();
+
sched_clock_tick();
rq_lock(rq, &rf);
--
GitLab
From eaf2213ba563b2d74a1f2c13a6b258273f689802 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 7 Jan 2023 16:47:41 +0900
Subject: [PATCH 0479/1167] tomoyo: fix broken dependency on *.conf.default
If *.conf.default is updated, builtin-policy.h should be rebuilt,
but this does not work when compiled with O= option.
[Without this commit]
$ touch security/tomoyo/policy/exception_policy.conf.default
$ make O=/tmp security/tomoyo/
make[1]: Entering directory '/tmp'
GEN Makefile
CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh
DESCEND objtool
make[1]: Leaving directory '/tmp'
[With this commit]
$ touch security/tomoyo/policy/exception_policy.conf.default
$ make O=/tmp security/tomoyo/
make[1]: Entering directory '/tmp'
GEN Makefile
CALL /home/masahiro/ref/linux/scripts/checksyscalls.sh
DESCEND objtool
POLICY security/tomoyo/builtin-policy.h
CC security/tomoyo/common.o
AR security/tomoyo/built-in.a
make[1]: Leaving directory '/tmp'
$(srctree)/ is essential because $(wildcard ) does not follow VPATH.
Fixes: f02dee2d148b ("tomoyo: Do not generate empty policy files")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
security/tomoyo/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile
index cca5a3012fee2..221eaadffb09c 100644
--- a/security/tomoyo/Makefile
+++ b/security/tomoyo/Makefile
@@ -10,7 +10,7 @@ endef
quiet_cmd_policy = POLICY $@
cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@
-$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE
+$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE
$(call if_changed,policy)
$(obj)/common.o: $(obj)/builtin-policy.h
--
GitLab
From df4840c1b880136fea97a1d64724995778c2475f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 7 Jan 2023 16:47:42 +0900
Subject: [PATCH 0480/1167] tomoyo: avoid unneeded creation of builtin-policy.h
When CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING=y,
builtin-policy.h is unneeded.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
security/tomoyo/Makefile | 2 ++
1 file changed, 2 insertions(+)
diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile
index 221eaadffb09c..1b18a02ccd2e6 100644
--- a/security/tomoyo/Makefile
+++ b/security/tomoyo/Makefile
@@ -13,4 +13,6 @@ quiet_cmd_policy = POLICY $@
$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE
$(call if_changed,policy)
+ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
$(obj)/common.o: $(obj)/builtin-policy.h
+endif
--
GitLab
From c0f7ae27539fbac267384a7bfc58296ea7550d52 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@microchip.com>
Date: Mon, 26 Dec 2022 16:40:43 +0200
Subject: [PATCH 0481/1167] MAINTAINERS: Update email of Tudor Ambarus
My professional email will change and the microchip one will bounce after
mid-november of 2022.
Update the MAINTAINERS file, the YAML bindings, MODULE_AUTHOR entries and
author mentions, and add an entry in the .mailmap file.
Signed-off-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Pratyush Yadav <pratyush@kernel.org>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/linux-mtd/20221226144043.367706-1-tudor.ambarus@linaro.org
---
.mailmap | 1 +
.../bindings/crypto/atmel,at91sam9g46-aes.yaml | 2 +-
.../bindings/crypto/atmel,at91sam9g46-sha.yaml | 2 +-
.../bindings/crypto/atmel,at91sam9g46-tdes.yaml | 2 +-
.../devicetree/bindings/spi/atmel,at91rm9200-spi.yaml | 2 +-
.../devicetree/bindings/spi/atmel,quadspi.yaml | 2 +-
MAINTAINERS | 10 +++++-----
drivers/crypto/atmel-ecc.c | 4 ++--
drivers/crypto/atmel-i2c.c | 4 ++--
drivers/crypto/atmel-i2c.h | 2 +-
10 files changed, 16 insertions(+), 15 deletions(-)
diff --git a/.mailmap b/.mailmap
index ccba4cf0d8938..562f70d3b6a54 100644
--- a/.mailmap
+++ b/.mailmap
@@ -422,6 +422,7 @@ Tony Luck <tony.luck@intel.com>
TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml
index 0ccaab16dc614..0b7383b3106b5 100644
--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml
index 5163c51b4547b..ee2ffb0343251 100644
--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml
index fcc5adf03cadb..3d6ed24b1b006 100644
--- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml
+++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
index 4dd973e341e6c..6c57dd6c3a361 100644
--- a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
@@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Atmel SPI device
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
diff --git a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml
index 1d493add4053d..b0d99bc105352 100644
--- a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml
+++ b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Atmel Quad Serial Peripheral Interface (QSPI)
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f86d02cb427a..36c500e34508a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13620,7 +13620,7 @@ F: arch/microblaze/
MICROCHIP AT91 DMA DRIVERS
M: Ludovic Desroches <ludovic.desroches@microchip.com>
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: dmaengine@vger.kernel.org
S: Supported
@@ -13665,7 +13665,7 @@ F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml
F: drivers/media/platform/microchip/microchip-csi2dc.c
MICROCHIP ECC DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-crypto@vger.kernel.org
S: Maintained
F: drivers/crypto/atmel-ecc.*
@@ -13762,7 +13762,7 @@ S: Maintained
F: drivers/mmc/host/atmel-mci.c
MICROCHIP NAND DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-mtd@lists.infradead.org
S: Supported
F: Documentation/devicetree/bindings/mtd/atmel-nand.txt
@@ -13814,7 +13814,7 @@ S: Supported
F: drivers/power/reset/at91-sama5d2_shdwc.c
MICROCHIP SPI DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
S: Supported
F: drivers/spi/spi-atmel.*
@@ -19665,7 +19665,7 @@ F: drivers/clk/spear/
F: drivers/pinctrl/spear/
SPI NOR SUBSYSTEM
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
M: Pratyush Yadav <pratyush@kernel.org>
R: Michael Walle <michael@walle.cc>
L: linux-mtd@lists.infradead.org
diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index 53100fb9b07bd..12205e2b53b45 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -3,7 +3,7 @@
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/delay.h>
@@ -411,6 +411,6 @@ static void __exit atmel_ecc_exit(void)
module_init(atmel_ecc_init);
module_exit(atmel_ecc_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c
index 81ce09bedda8f..55bff1e131426 100644
--- a/drivers/crypto/atmel-i2c.c
+++ b/drivers/crypto/atmel-i2c.c
@@ -3,7 +3,7 @@
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/bitrev.h>
@@ -390,6 +390,6 @@ static void __exit atmel_i2c_exit(void)
module_init(atmel_i2c_init);
module_exit(atmel_i2c_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h
index 48929efe2a5bf..35f7857a7f7cc 100644
--- a/drivers/crypto/atmel-i2c.h
+++ b/drivers/crypto/atmel-i2c.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#ifndef __ATMEL_I2C_H__
--
GitLab
From 5304930dbae82d259bcf7e5611db7c81e7a42eff Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sat, 7 Jan 2023 10:15:35 -0500
Subject: [PATCH 0482/1167] NFSD: Use set_bit(RQ_DROPME)
The premise that "Once an svc thread is scheduled and executing an
RPC, no other processes will touch svc_rqst::rq_flags" is false.
svc_xprt_enqueue() examines the RQ_BUSY flag in scheduled nfsd
threads when determining which thread to wake up next.
Fixes: 9315564747cb ("NFSD: Use only RQ_DROPME to signal the need to drop a reply")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfsproc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a5570cf75f3fd..9744443c39652 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
@@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
--
GitLab
From 43d5f5d63699724d47f0d9e0eae516a260d232b4 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Fri, 6 Jan 2023 13:44:56 +0000
Subject: [PATCH 0483/1167] riscv: dts: sifive: fu740: fix size of pcie 32bit
memory
The 32-bit memory resource is needed for non-prefetchable memory
allocations on the PCIe bus, however with some cards (such as the
SM768) the system fails to allocate memory from this.
Checking the allocation against the datasheet, it looks like there
has been a mis-calcualation of the resource for the first memory
region (0x0060090000..0x0070ffffff) which in the data-sheet for
the fu740 (v1p2) is from 0x0060000000..0x007fffffff. Changing
this to allocate from 0x0060090000..0x007fffffff fixes the probing
issues.
Fixes: ae80d5148085 ("riscv: dts: Add PCIe support for the SiFive FU740-C000 SoC")
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: stable@vger.kernel.org
Tested-by: Ron Economos <re@w6rz.net> # from IRC
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
arch/riscv/boot/dts/sifive/fu740-c000.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
index 43bed6c0a84fe..5235fd1c9cb67 100644
--- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi
@@ -328,7 +328,7 @@ pcie@e00000000 {
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x60080000 0x0 0x60080000 0x0 0x10000>, /* I/O */
<0x82000000 0x0 0x60090000 0x0 0x60090000 0x0 0xff70000>, /* mem */
- <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x1000000>, /* mem */
+ <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x10000000>, /* mem */
<0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>; /* mem prefetchable */
num-lanes = <0x8>;
interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>;
--
GitLab
From 115d9d77bb0f9152c60b6e8646369fa7f6167593 Mon Sep 17 00:00:00 2001
From: Aaron Thompson <dev@aaront.org>
Date: Fri, 6 Jan 2023 22:22:44 +0000
Subject: [PATCH 0484/1167] mm: Always release pages to the buddy allocator in
memblock_free_late().
If CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, memblock_free_pages()
only releases pages to the buddy allocator if they are not in the
deferred range. This is correct for free pages (as defined by
for_each_free_mem_pfn_range_in_zone()) because free pages in the
deferred range will be initialized and released as part of the deferred
init process. memblock_free_pages() is called by memblock_free_late(),
which is used to free reserved ranges after memblock_free_all() has
run. All pages in reserved ranges have been initialized at that point,
and accordingly, those pages are not touched by the deferred init
process. This means that currently, if the pages that
memblock_free_late() intends to release are in the deferred range, they
will never be released to the buddy allocator. They will forever be
reserved.
In addition, memblock_free_pages() calls kmsan_memblock_free_pages(),
which is also correct for free pages but is not correct for reserved
pages. KMSAN metadata for reserved pages is initialized by
kmsan_init_shadow(), which runs shortly before memblock_free_all().
For both of these reasons, memblock_free_pages() should only be called
for free pages, and memblock_free_late() should call __free_pages_core()
directly instead.
One case where this issue can occur in the wild is EFI boot on
x86_64. The x86 EFI code reserves all EFI boot services memory ranges
via memblock_reserve() and frees them later via memblock_free_late()
(efi_reserve_boot_services() and efi_free_boot_services(),
respectively). If any of those ranges happens to fall within the
deferred init range, the pages will not be released and that memory will
be unavailable.
For example, on an Amazon EC2 t3.micro VM (1 GB) booting via EFI:
v6.2-rc2:
# grep -E 'Node|spanned|present|managed' /proc/zoneinfo
Node 0, zone DMA
spanned 4095
present 3999
managed 3840
Node 0, zone DMA32
spanned 246652
present 245868
managed 178867
v6.2-rc2 + patch:
# grep -E 'Node|spanned|present|managed' /proc/zoneinfo
Node 0, zone DMA
spanned 4095
present 3999
managed 3840
Node 0, zone DMA32
spanned 246652
present 245868
managed 222816 # +43,949 pages
Fixes: 3a80a7fa7989 ("mm: meminit: initialise a subset of struct pages if CONFIG_DEFERRED_STRUCT_PAGE_INIT is set")
Signed-off-by: Aaron Thompson <dev@aaront.org>
Link: https://lore.kernel.org/r/01010185892de53e-e379acfb-7044-4b24-b30a-e2657c1ba989-000000@us-west-2.amazonses.com
Signed-off-by: Mike Rapoport (IBM) <rppt@kernel.org>
---
mm/memblock.c | 8 +++++++-
tools/testing/memblock/internal.h | 4 ++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/mm/memblock.c b/mm/memblock.c
index d036c7861310c..685e30e6d27c5 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1640,7 +1640,13 @@ void __init memblock_free_late(phys_addr_t base, phys_addr_t size)
end = PFN_DOWN(base + size);
for (; cursor < end; cursor++) {
- memblock_free_pages(pfn_to_page(cursor), cursor, 0);
+ /*
+ * Reserved pages are always initialized by the end of
+ * memblock_free_all() (by memmap_init() and, if deferred
+ * initialization is enabled, memmap_init_reserved_pages()), so
+ * these pages can be released directly to the buddy allocator.
+ */
+ __free_pages_core(pfn_to_page(cursor), 0);
totalram_pages_inc();
}
}
diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h
index fdb7f5db73082..85973e55489e7 100644
--- a/tools/testing/memblock/internal.h
+++ b/tools/testing/memblock/internal.h
@@ -15,6 +15,10 @@ bool mirrored_kernelcore = false;
struct page {};
+void __free_pages_core(struct page *page, unsigned int order)
+{
+}
+
void memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
{
--
GitLab
From e6db6f9398dadcbc06318a133d4c44a2d3844e61 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 8 Jan 2023 10:39:17 -0700
Subject: [PATCH 0485/1167] io_uring/io-wq: only free worker if it was
allocated for creation
We have two types of task_work based creation, one is using an existing
worker to setup a new one (eg when going to sleep and we have no free
workers), and the other is allocating a new worker. Only the latter
should be freed when we cancel task_work creation for a new worker.
Fixes: af82425c6a2d ("io_uring/io-wq: free worker if task_work creation is canceled")
Reported-by: syzbot+d56ec896af3637bdb7e4@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io-wq.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 992dcd9f8c4cf..411bb2d1acd45 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1230,7 +1230,12 @@ static void io_wq_cancel_tw_create(struct io_wq *wq)
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
- kfree(worker);
+ /*
+ * Only the worker continuation helper has worker allocated and
+ * hence needs freeing.
+ */
+ if (cb->func == create_worker_cont)
+ kfree(worker);
}
}
--
GitLab
From b7bfaa761d760e72a969d116517eaa12e404c262 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 8 Jan 2023 11:49:43 -0600
Subject: [PATCH 0486/1167] Linux 6.2-rc3
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index dfba294ae7907..460716314fb3c 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
--
GitLab
From e3c9405ec56b6b0a75d993427bfc7f4194f73754 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sat, 7 Jan 2023 15:37:47 +0100
Subject: [PATCH 0487/1167] docs: kbuild: remove mention to dropped $(objtree)
feature
Commit 8d613a1d048c ("kbuild: drop $(objtree)/ prefix support
for clean-files") dropped support for prefixing with $(objtree).
Thus update the documentation to match that change.
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
Documentation/kbuild/makefiles.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 6b7368d1f5163..38bc74eaa5474 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -1042,7 +1042,7 @@ $(clean-files).
When executing "make clean", the file "crc32table.h" will be deleted.
Kbuild will assume files to be in the same relative directory as the
-Makefile, except if prefixed with $(objtree).
+Makefile.
To exclude certain files or directories from make clean, use the
$(no-clean-files) variable.
--
GitLab
From b409ea4534204d4e6da3017d8713ce338f44b489 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 8 Jan 2023 21:35:57 +0900
Subject: [PATCH 0488/1167] init/version-timestamp.c: remove unneeded #include
<linux/version.h>
The kbuild test robot detected this by 'make versioncheck'.
Fixes: 2df8220cc511 ("kbuild: build init/built-in.a just once")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
init/version-timestamp.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/init/version-timestamp.c b/init/version-timestamp.c
index 179e93bae5390..043cbf80a766d 100644
--- a/init/version-timestamp.c
+++ b/init/version-timestamp.c
@@ -2,7 +2,6 @@
#include <generated/compile.h>
#include <generated/utsrelease.h>
-#include <linux/version.h>
#include <linux/proc_ns.h>
#include <linux/refcount.h>
#include <linux/uts.h>
--
GitLab
From 49e4d04f0486117ac57a97890eb1db6d52bf82b3 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 6 Jan 2023 10:34:10 -1000
Subject: [PATCH 0489/1167] block: Drop spurious might_sleep() from
blk_put_queue()
Dan reports the following smatch detected the following:
block/blk-cgroup.c:1863 blkcg_schedule_throttle() warn: sleeping in atomic context
caused by blkcg_schedule_throttle() calling blk_put_queue() in an
non-sleepable context.
blk_put_queue() acquired might_sleep() in 63f93fd6fa57 ("block: mark
blk_put_queue as potentially blocking") which transferred the might_sleep()
from blk_free_queue().
blk_free_queue() acquired might_sleep() in e8c7d14ac6c3 ("block: revert back
to synchronous request_queue removal") while turning request_queue removal
synchronous. However, this isn't necessary as nothing in the free path
actually requires sleeping.
It's pretty unusual to require a sleeping context in a put operation and
it's not needed in the first place. Let's drop it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Dan Carpenter <error27@gmail.com>
Link: https://lkml.kernel.org/r/Y7g3L6fntnTtOm63@kili
Cc: Christoph Hellwig <hch@lst.de>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Fixes: e8c7d14ac6c3 ("block: revert back to synchronous request_queue removal") # v5.9+
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/Y7iFwjN+XzWvLv3y@slm.duckdns.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-core.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 9321767470dc5..b5098355d8b27 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -283,12 +283,9 @@ static void blk_free_queue(struct request_queue *q)
*
* Decrements the refcount of the request_queue and free it when the refcount
* reaches 0.
- *
- * Context: Can sleep.
*/
void blk_put_queue(struct request_queue *q)
{
- might_sleep();
if (refcount_dec_and_test(&q->refs))
blk_free_queue(q);
}
--
GitLab
From 37c1785609833e626d344047a84e272b7879b2c3 Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Thu, 5 Jan 2023 17:01:41 +0800
Subject: [PATCH 0490/1167] x86/xen: Remove the unused function p2m_index()
The function p2m_index is defined in the p2m.c file, but not called
elsewhere, so remove this unused function.
arch/x86/xen/p2m.c:137:24: warning: unused function 'p2m_index'.
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=3557
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://lore.kernel.org/r/20230105090141.36248-1-jiapeng.chong@linux.alibaba.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
arch/x86/xen/p2m.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 58db86f7b3846..9bdc3b656b2c4 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn)
return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
-static inline unsigned p2m_index(unsigned long pfn)
-{
- return pfn % P2M_PER_PAGE;
-}
-
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
--
GitLab
From c0dccad87cf68fc6012aec7567e354353097ec1a Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau@citrix.com>
Date: Wed, 30 Nov 2022 17:36:02 +0100
Subject: [PATCH 0491/1167] hvc/xen: lock console list traversal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The currently lockless access to the xen console list in
vtermno_to_xencons() is incorrect, as additions and removals from the
list can happen anytime, and as such the traversal of the list to get
the private console data for a given termno needs to happen with the
lock held. Note users that modify the list already do so with the
lock taken.
Adjust current lock takers to use the _irq{save,restore} helpers,
since the context in which vtermno_to_xencons() is called can have
interrupts disabled. Use the _irq{save,restore} set of helpers to
switch the current callers to disable interrupts in the locked region.
I haven't checked if existing users could instead use the _irq
variant, as I think it's safer to use _irq{save,restore} upfront.
While there switch from using list_for_each_entry_safe to
list_for_each_entry: the current entry cursor won't be removed as
part of the code in the loop body, so using the _safe variant is
pointless.
Fixes: 02e19f9c7cac ('hvc_xen: implement multiconsole support')
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/20221130163611.14686-1-roger.pau@citrix.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/tty/hvc/hvc_xen.c | 46 ++++++++++++++++++++++++---------------
1 file changed, 29 insertions(+), 17 deletions(-)
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index c879f922c716b..5bddb2f5e9318 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -52,17 +52,22 @@ static DEFINE_SPINLOCK(xencons_lock);
static struct xencons_info *vtermno_to_xencons(int vtermno)
{
- struct xencons_info *entry, *n, *ret = NULL;
+ struct xencons_info *entry, *ret = NULL;
+ unsigned long flags;
- if (list_empty(&xenconsoles))
- return NULL;
+ spin_lock_irqsave(&xencons_lock, flags);
+ if (list_empty(&xenconsoles)) {
+ spin_unlock_irqrestore(&xencons_lock, flags);
+ return NULL;
+ }
- list_for_each_entry_safe(entry, n, &xenconsoles, list) {
+ list_for_each_entry(entry, &xenconsoles, list) {
if (entry->vtermno == vtermno) {
ret = entry;
break;
}
}
+ spin_unlock_irqrestore(&xencons_lock, flags);
return ret;
}
@@ -223,7 +228,7 @@ static int xen_hvm_console_init(void)
{
int r;
uint64_t v = 0;
- unsigned long gfn;
+ unsigned long gfn, flags;
struct xencons_info *info;
if (!xen_hvm_domain())
@@ -258,9 +263,9 @@ static int xen_hvm_console_init(void)
goto err;
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
err:
@@ -283,6 +288,7 @@ static int xencons_info_pv_init(struct xencons_info *info, int vtermno)
static int xen_pv_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_pv_domain())
return -ENODEV;
@@ -299,9 +305,9 @@ static int xen_pv_console_init(void)
/* already configured */
return 0;
}
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
xencons_info_pv_init(info, HVC_COOKIE);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
@@ -309,6 +315,7 @@ static int xen_pv_console_init(void)
static int xen_initial_domain_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_initial_domain())
return -ENODEV;
@@ -323,9 +330,9 @@ static int xen_initial_domain_console_init(void)
info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false);
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
@@ -380,10 +387,12 @@ static void xencons_free(struct xencons_info *info)
static int xen_console_remove(struct xencons_info *info)
{
+ unsigned long flags;
+
xencons_disconnect_backend(info);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->xbdev != NULL)
xencons_free(info);
else {
@@ -464,6 +473,7 @@ static int xencons_probe(struct xenbus_device *dev,
{
int ret, devid;
struct xencons_info *info;
+ unsigned long flags;
devid = dev->nodename[strlen(dev->nodename) - 1] - '0';
if (devid == 0)
@@ -482,9 +492,9 @@ static int xencons_probe(struct xenbus_device *dev,
ret = xencons_connect_backend(dev, info);
if (ret < 0)
goto error;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
@@ -584,10 +594,12 @@ static int __init xen_hvc_init(void)
info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256);
if (IS_ERR(info->hvc)) {
+ unsigned long flags;
+
r = PTR_ERR(info->hvc);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
unbind_from_irqhandler(info->irq, NULL);
kfree(info);
--
GitLab
From f57034cedeb6e00256313a2a6ee67f974d709b0b Mon Sep 17 00:00:00 2001
From: Oleksii Moisieiev <Oleksii_Moisieiev@epam.com>
Date: Tue, 20 Dec 2022 14:50:13 +0000
Subject: [PATCH 0492/1167] xen/pvcalls: free active map buffer on
pvcalls_front_free_map
Data buffer for active map is allocated in alloc_active_ring and freed
in free_active_ring function, which is used only for the error
cleanup. pvcalls_front_release is calling pvcalls_front_free_map which
ends foreign access for this buffer, but doesn't free allocated pages.
Call free_active_ring to clean all allocated resources.
Signed-off-by: Oleksii Moisieiev <oleksii_moisieiev@epam.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Link: https://lore.kernel.org/r/6a762ee32dd655cbb09a4aa0e2307e8919761311.1671531297.git.oleksii_moisieiev@epam.com
Signed-off-by: Juergen Gross <jgross@suse.com>
---
drivers/xen/pvcalls-front.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
index 5328f4d35f25e..d5d589bda243d 100644
--- a/drivers/xen/pvcalls-front.c
+++ b/drivers/xen/pvcalls-front.c
@@ -225,6 +225,8 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
return IRQ_HANDLED;
}
+static void free_active_ring(struct sock_mapping *map);
+
static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
struct sock_mapping *map)
{
@@ -240,7 +242,7 @@ static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
gnttab_end_foreign_access(map->active.ring->ref[i], NULL);
gnttab_end_foreign_access(map->active.ref, NULL);
- free_page((unsigned long)map->active.ring);
+ free_active_ring(map);
kfree(map);
}
--
GitLab
From a5a36720c3f650f859f5e9535dd62d06f13f4f3b Mon Sep 17 00:00:00 2001
From: "Ivan T. Ivanov" <iivanov@suse.de>
Date: Fri, 6 Jan 2023 15:19:05 +0200
Subject: [PATCH 0493/1167] brcmfmac: Prefer DT board type over DMI board type
The introduction of support for Apple board types inadvertently changed
the precedence order, causing hybrid SMBIOS+DT platforms to look up the
firmware using the DMI information instead of the device tree compatible
to generate the board type. Revert back to the old behavior,
as affected platforms use firmwares named after the DT compatible.
Fixes: 7682de8b3351 ("wifi: brcmfmac: of: Fetch Apple properties")
[1] https://bugzilla.opensuse.org/show_bug.cgi?id=1206697#c13
Cc: stable@vger.kernel.org
Signed-off-by: Ivan T. Ivanov <iivanov@suse.de>
Reviewed-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Tested-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
index a83699de01ec3..fdd0c9abc1a10 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c
@@ -79,7 +79,8 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type,
/* Apple ARM64 platforms have their own idea of board type, passed in
* via the device tree. They also have an antenna SKU parameter
*/
- if (!of_property_read_string(np, "brcm,board-type", &prop))
+ err = of_property_read_string(np, "brcm,board-type", &prop);
+ if (!err)
settings->board_type = prop;
if (!of_property_read_string(np, "apple,antenna-sku", &prop))
@@ -87,7 +88,7 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type,
/* Set board-type to the first string of the machine compatible prop */
root = of_find_node_by_path("/");
- if (root && !settings->board_type) {
+ if (root && err) {
char *board_type;
const char *tmp;
--
GitLab
From 60ea6f00c57dae5e7ba2c52ed407cb24fdb11ebe Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Fri, 6 Jan 2023 07:25:01 -0600
Subject: [PATCH 0494/1167] net: ipa: correct IPA v4.7 IMEM offset
Commit b310de784bacd ("net: ipa: add IPA v4.7 support") was merged
despite an unresolved comment made by Konrad Dybcio. Konrad
observed that the IMEM region specified for IPA v4.7 did not match
that used downstream for the SM7225 SoC. In "lagoon.dtsi" present
in a Sony Xperia source tree, a ipa_smmu_ap node was defined with a
"qcom,additional-mapping" property that defined the IPA IMEM area
starting at offset 0x146a8000 (not 0x146a9000 that was committed).
The IPA v4.7 target system used for testing uses the SM7225 SoC, so
we'll adhere what the downstream code specifies is the address of
the IMEM region used for IPA.
Link: https://lore.kernel.org/linux-arm-msm/20221208211529.757669-1-elder@linaro.org
Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Tested-by: Luca Weiss <luca.weiss@fairphone.com>
Signed-off-by: Alex Elder <elder@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ipa/data/ipa_data-v4.7.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index 7552c400961eb..b83390c486158 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -357,7 +357,7 @@ static const struct ipa_mem ipa_mem_local_data[] = {
static const struct ipa_mem_data ipa_mem_data = {
.local_count = ARRAY_SIZE(ipa_mem_local_data),
.local = ipa_mem_local_data,
- .imem_addr = 0x146a9000,
+ .imem_addr = 0x146a8000,
.imem_size = 0x00002000,
.smem_id = 497,
.smem_size = 0x00009000,
--
GitLab
From 2ab6478d1266b522a0a6ce3697914d63529f9e7a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 5 Jan 2023 15:22:29 -0800
Subject: [PATCH 0495/1167] mlxsw: spectrum_router: Replace 0-length array with
flexible array
Zero-length arrays are deprecated[1]. Replace struct
mlxsw_sp_nexthop_group_info's "nexthops" 0-length array with a flexible
array. Detected with GCC 13, using -fstrict-flex-arrays=3:
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c: In function 'mlxsw_sp_nexthop_group_hash_obj':
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:3278:38: warning: array subscript i is outside array bounds of 'struct mlxsw_sp_nexthop[0]' [-Warray-bounds=]
3278 | val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed);
| ^~~~~~~~~~~~
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:2954:33: note: while referencing 'nexthops'
2954 | struct mlxsw_sp_nexthop nexthops[0];
| ^~~~~~~~
[1] https://www.kernel.org/doc/html/latest/process/deprecated.html#zero-length-and-one-element-arrays
Cc: Ido Schimmel <idosch@nvidia.com>
Cc: Petr Machata <petrm@nvidia.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Tested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index c22c3ac4e2a18..09e32778b012d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2951,7 +2951,7 @@ struct mlxsw_sp_nexthop_group_info {
gateway:1, /* routes using the group use a gateway */
is_resilient:1;
struct list_head list; /* member in nh_res_grp_list */
- struct mlxsw_sp_nexthop nexthops[0];
+ struct mlxsw_sp_nexthop nexthops[];
#define nh_rif nexthops[0].rif
};
--
GitLab
From 9dab880d675b9d0dd56c6428e4e8352a3339371d Mon Sep 17 00:00:00 2001
From: Minsuk Kang <linuxlovemin@yonsei.ac.kr>
Date: Fri, 6 Jan 2023 17:23:44 +0900
Subject: [PATCH 0496/1167] nfc: pn533: Wait for out_urb's completion in
pn533_usb_send_frame()
Fix a use-after-free that occurs in hcd when in_urb sent from
pn533_usb_send_frame() is completed earlier than out_urb. Its callback
frees the skb data in pn533_send_async_complete() that is used as a
transfer buffer of out_urb. Wait before sending in_urb until the
callback of out_urb is called. To modify the callback of out_urb alone,
separate the complete function of out_urb and ack_urb.
Found by a modified version of syzkaller.
BUG: KASAN: use-after-free in dummy_timer
Call Trace:
memcpy (mm/kasan/shadow.c:65)
dummy_perform_transfer (drivers/usb/gadget/udc/dummy_hcd.c:1352)
transfer (drivers/usb/gadget/udc/dummy_hcd.c:1453)
dummy_timer (drivers/usb/gadget/udc/dummy_hcd.c:1972)
arch_static_branch (arch/x86/include/asm/jump_label.h:27)
static_key_false (include/linux/jump_label.h:207)
timer_expire_exit (include/trace/events/timer.h:127)
call_timer_fn (kernel/time/timer.c:1475)
expire_timers (kernel/time/timer.c:1519)
__run_timers (kernel/time/timer.c:1790)
run_timer_softirq (kernel/time/timer.c:1803)
Fixes: c46ee38620a2 ("NFC: pn533: add NXP pn533 nfc device driver")
Signed-off-by: Minsuk Kang <linuxlovemin@yonsei.ac.kr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/nfc/pn533/usb.c | 44 ++++++++++++++++++++++++++++++++++++++---
1 file changed, 41 insertions(+), 3 deletions(-)
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index 6f71ac72012ea..ed9c5e2cf3ad4 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -153,10 +153,17 @@ static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags)
return usb_submit_urb(phy->ack_urb, flags);
}
+struct pn533_out_arg {
+ struct pn533_usb_phy *phy;
+ struct completion done;
+};
+
static int pn533_usb_send_frame(struct pn533 *dev,
struct sk_buff *out)
{
struct pn533_usb_phy *phy = dev->phy;
+ struct pn533_out_arg arg;
+ void *cntx;
int rc;
if (phy->priv == NULL)
@@ -168,10 +175,17 @@ static int pn533_usb_send_frame(struct pn533 *dev,
print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1,
out->data, out->len, false);
+ init_completion(&arg.done);
+ cntx = phy->out_urb->context;
+ phy->out_urb->context = &arg;
+
rc = usb_submit_urb(phy->out_urb, GFP_KERNEL);
if (rc)
return rc;
+ wait_for_completion(&arg.done);
+ phy->out_urb->context = cntx;
+
if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
/* request for response for sent packet directly */
rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
@@ -408,7 +422,31 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy)
return arg.rc;
}
-static void pn533_send_complete(struct urb *urb)
+static void pn533_out_complete(struct urb *urb)
+{
+ struct pn533_out_arg *arg = urb->context;
+ struct pn533_usb_phy *phy = arg->phy;
+
+ switch (urb->status) {
+ case 0:
+ break; /* success */
+ case -ECONNRESET:
+ case -ENOENT:
+ dev_dbg(&phy->udev->dev,
+ "The urb has been stopped (status %d)\n",
+ urb->status);
+ break;
+ case -ESHUTDOWN:
+ default:
+ nfc_err(&phy->udev->dev,
+ "Urb failure (status %d)\n",
+ urb->status);
+ }
+
+ complete(&arg->done);
+}
+
+static void pn533_ack_complete(struct urb *urb)
{
struct pn533_usb_phy *phy = urb->context;
@@ -496,10 +534,10 @@ static int pn533_usb_probe(struct usb_interface *interface,
usb_fill_bulk_urb(phy->out_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_out_complete, phy);
usb_fill_bulk_urb(phy->ack_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_ack_complete, phy);
switch (id->driver_info) {
case PN533_DEVICE_STD:
--
GitLab
From 7871f54e3deed68a27111dda162c4fe9b9c65f8f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 6 Jan 2023 14:25:23 +0000
Subject: [PATCH 0497/1167] gro: take care of DODGY packets
Jaroslav reported a recent throughput regression with virtio_net
caused by blamed commit.
It is unclear if DODGY GSO packets coming from user space
can be accepted by GRO engine in the future with minimal
changes, and if there is any expected gain from it.
In the meantime, make sure to detect and flush DODGY packets.
Fixes: 5eddb24901ee ("gro: add support of (hw)gro packets to gro stack")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-and-bisected-by: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: Coco Li <lixiaoyan@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/gro.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/core/gro.c b/net/core/gro.c
index fd8c6a7e8d3e2..506f83d715f87 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -505,8 +505,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
NAPI_GRO_CB(skb)->count = 1;
if (unlikely(skb_is_gso(skb))) {
NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
- /* Only support TCP at the moment. */
- if (!skb_is_gso_tcp(skb))
+ /* Only support TCP and non DODGY users. */
+ if (!skb_is_gso_tcp(skb) ||
+ (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
NAPI_GRO_CB(skb)->flush = 1;
}
--
GitLab
From 76761babaa984fce8ecd87d87a68d920f24df438 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Fri, 6 Jan 2023 21:15:07 +0100
Subject: [PATCH 0498/1167] net: lan966x: Allow to add rules in TCAM even if
not enabled
The blamed commit implemented the vcap_operations to allow to add an
entry in the TCAM. One of the callbacks is to validate the supported
keysets. If the TCAM lookup was not enabled, then this will return
failure so no entries could be added.
This doesn't make much sense, as you can enable at a later point the
TCAM. Therefore change it such to allow entries in TCAM even it is not
enabled.
Fixes: 4426b78c626d ("net: lan966x: Add port keyset config and callback interface")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c
index d8dc9fbb81e1a..a54c0426a35f3 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c
@@ -95,10 +95,7 @@ lan966x_vcap_is2_get_port_keysets(struct net_device *dev, int lookup,
bool found = false;
u32 val;
- /* Check if the port keyset selection is enabled */
val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port));
- if (!ANA_VCAP_S2_CFG_ENA_GET(val))
- return -ENOENT;
/* Collect all keysets for the port in a list */
if (l3_proto == ETH_P_ALL)
--
GitLab
From 7d6ceeb1875cc08dc3d1e558e191434d94840cd5 Mon Sep 17 00:00:00 2001
From: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Date: Sat, 7 Jan 2023 04:40:20 +0100
Subject: [PATCH 0499/1167] af_unix: selftest: Fix the size of the parameter to
connect()
Adjust size parameter in connect() to match the type of the parameter, to
fix "No such file or directory" error in selftests/net/af_unix/
test_oob_unix.c:127.
The existing code happens to work provided that the autogenerated pathname
is shorter than sizeof (struct sockaddr), which is why it hasn't been
noticed earlier.
Visible from the trace excerpt:
bind(3, {sa_family=AF_UNIX, sun_path="unix_oob_453059"}, 110) = 0
clone(child_stack=NULL, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, child_tidptr=0x7fa6a6577a10) = 453060
[pid <child>] connect(6, {sa_family=AF_UNIX, sun_path="unix_oob_45305"}, 16) = -1 ENOENT (No such file or directory)
BUG: The filename is trimmed to sizeof (struct sockaddr).
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Cc: Florian Westphal <fw@strlen.de>
Reviewed-by: Florian Westphal <fw@strlen.de>
Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Signed-off-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
tools/testing/selftests/net/af_unix/test_unix_oob.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c
index b57e91e1c3f28..532459a15067c 100644
--- a/tools/testing/selftests/net/af_unix/test_unix_oob.c
+++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c
@@ -124,7 +124,7 @@ void producer(struct sockaddr_un *consumer_addr)
wait_for_signal(pipefd[0]);
if (connect(cfd, (struct sockaddr *)consumer_addr,
- sizeof(struct sockaddr)) != 0) {
+ sizeof(*consumer_addr)) != 0) {
perror("Connect failed");
kill(0, SIGTERM);
exit(1);
--
GitLab
From 23257cfc1cb7202fd0065e9f4a6a0aac1c04c4a9 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 29 Dec 2022 14:10:30 +0200
Subject: [PATCH 0500/1167] thunderbolt: Do not call PM runtime functions in
tb_retimer_scan()
We cannot call PM runtime functions in tb_retimer_scan() because it will
also be called when retimers are scanned from userspace (happens when
there is no device connected on ChromeOS for instance) and at the same
USB4 port runtime resume hook. This leads to hang because neither can
proceed.
Fix this by runtime resuming USB4 ports in tb_scan_port() instead. This
makes sure the ports are runtime PM active when retimers are added under
it while avoiding the reported hang as well.
Reported-by: Utkarsh Patel <utkarsh.h.patel@intel.com>
Fixes: 1e56c88adecc ("thunderbolt: Runtime resume USB4 port when retimers are scanned")
Cc: stable@vger.kernel.org
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/thunderbolt/retimer.c | 17 +++--------------
drivers/thunderbolt/tb.c | 20 +++++++++++++++-----
2 files changed, 18 insertions(+), 19 deletions(-)
diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c
index 6ebe7a2886ec7..56008eb91e2e4 100644
--- a/drivers/thunderbolt/retimer.c
+++ b/drivers/thunderbolt/retimer.c
@@ -427,13 +427,6 @@ int tb_retimer_scan(struct tb_port *port, bool add)
{
u32 status[TB_MAX_RETIMER_INDEX + 1] = {};
int ret, i, last_idx = 0;
- struct usb4_port *usb4;
-
- usb4 = port->usb4;
- if (!usb4)
- return 0;
-
- pm_runtime_get_sync(&usb4->dev);
/*
* Send broadcast RT to make sure retimer indices facing this
@@ -441,7 +434,7 @@ int tb_retimer_scan(struct tb_port *port, bool add)
*/
ret = usb4_port_enumerate_retimers(port);
if (ret)
- goto out;
+ return ret;
/*
* Enable sideband channel for each retimer. We can do this
@@ -471,11 +464,11 @@ int tb_retimer_scan(struct tb_port *port, bool add)
break;
}
- ret = 0;
if (!last_idx)
- goto out;
+ return 0;
/* Add on-board retimers if they do not exist already */
+ ret = 0;
for (i = 1; i <= last_idx; i++) {
struct tb_retimer *rt;
@@ -489,10 +482,6 @@ int tb_retimer_scan(struct tb_port *port, bool add)
}
}
-out:
- pm_runtime_mark_last_busy(&usb4->dev);
- pm_runtime_put_autosuspend(&usb4->dev);
-
return ret;
}
diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c
index 4628458044270..3f1ab30c4fb15 100644
--- a/drivers/thunderbolt/tb.c
+++ b/drivers/thunderbolt/tb.c
@@ -628,11 +628,15 @@ static void tb_scan_port(struct tb_port *port)
* Downstream switch is reachable through two ports.
* Only scan on the primary port (link_nr == 0).
*/
+
+ if (port->usb4)
+ pm_runtime_get_sync(&port->usb4->dev);
+
if (tb_wait_for_port(port, false) <= 0)
- return;
+ goto out_rpm_put;
if (port->remote) {
tb_port_dbg(port, "port already has a remote\n");
- return;
+ goto out_rpm_put;
}
tb_retimer_scan(port, true);
@@ -647,12 +651,12 @@ static void tb_scan_port(struct tb_port *port)
*/
if (PTR_ERR(sw) == -EIO || PTR_ERR(sw) == -EADDRNOTAVAIL)
tb_scan_xdomain(port);
- return;
+ goto out_rpm_put;
}
if (tb_switch_configure(sw)) {
tb_switch_put(sw);
- return;
+ goto out_rpm_put;
}
/*
@@ -681,7 +685,7 @@ static void tb_scan_port(struct tb_port *port)
if (tb_switch_add(sw)) {
tb_switch_put(sw);
- return;
+ goto out_rpm_put;
}
/* Link the switches using both links if available */
@@ -733,6 +737,12 @@ static void tb_scan_port(struct tb_port *port)
tb_add_dp_resources(sw);
tb_scan_switch(sw);
+
+out_rpm_put:
+ if (port->usb4) {
+ pm_runtime_mark_last_busy(&port->usb4->dev);
+ pm_runtime_put_autosuspend(&port->usb4->dev);
+ }
}
static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel)
--
GitLab
From e8ff07fb33026c5c1bb5b81293496faba5d68059 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 20 May 2022 13:35:19 +0300
Subject: [PATCH 0501/1167] thunderbolt: Use correct function to calculate
maximum USB3 link rate
We need to take minimum of both sides of the USB3 link into consideration,
not just the downstream port. Fix this by calling tb_usb3_max_link_rate()
instead.
Fixes: 0bd680cd900c ("thunderbolt: Add USB3 bandwidth management")
Cc: stable@vger.kernel.org
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/thunderbolt/tunnel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 2c3cf7fc33571..1fc3c29b24f83 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -1275,7 +1275,7 @@ static void tb_usb3_reclaim_available_bandwidth(struct tb_tunnel *tunnel,
return;
} else if (!ret) {
/* Use maximum link rate if the link valid is not set */
- ret = usb4_usb3_port_max_link_rate(tunnel->src_port);
+ ret = tb_usb3_max_link_rate(tunnel->dst_port, tunnel->src_port);
if (ret < 0) {
tb_tunnel_warn(tunnel, "failed to read maximum link rate\n");
return;
--
GitLab
From 84ee211c83212f4d35b56e0603acdcc41f860f1b Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 8 Sep 2022 09:45:22 +0300
Subject: [PATCH 0502/1167] thunderbolt: Disable XDomain lane 1 only in
software connection manager
When firmware connection manager is in use we should not touch the lane
adapter (well or any) configuration space so do this only when we know
that the software connection manager is active.
Fixes: 8e1de7042596 ("thunderbolt: Add support for XDomain lane bonding")
Cc: stable@vger.kernel.org
Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
drivers/thunderbolt/xdomain.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
index cfa83486c9dad..3c51e47dd86b7 100644
--- a/drivers/thunderbolt/xdomain.c
+++ b/drivers/thunderbolt/xdomain.c
@@ -1419,12 +1419,19 @@ static int tb_xdomain_get_properties(struct tb_xdomain *xd)
* registered, we notify the userspace that it has changed.
*/
if (!update) {
- struct tb_port *port;
+ /*
+ * Now disable lane 1 if bonding was not enabled. Do
+ * this only if bonding was possible at the beginning
+ * (that is we are the connection manager and there are
+ * two lanes).
+ */
+ if (xd->bonding_possible) {
+ struct tb_port *port;
- /* Now disable lane 1 if bonding was not enabled */
- port = tb_port_at(xd->route, tb_xdomain_parent(xd));
- if (!port->bonded)
- tb_port_disable(port->dual_link_port);
+ port = tb_port_at(xd->route, tb_xdomain_parent(xd));
+ if (!port->bonded)
+ tb_port_disable(port->dual_link_port);
+ }
if (device_add(&xd->dev)) {
dev_err(&xd->dev, "failed to add XDomain device\n");
--
GitLab
From 74905e3de8adf0e6b5d7f455dcd32cdec13dfb6c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 9 Nov 2022 06:03:03 -0500
Subject: [PATCH 0503/1167] KVM: nSVM: clarify recalc_intercepts() wrt CR8
The mysterious comment "We only want the cr8 intercept bits of L1"
dates back to basically the introduction of nested SVM, back when
the handling of "less typical" hypervisors was very haphazard.
With the development of kvm-unit-tests for interrupt handling,
the same code grew another vmcb_clr_intercept for the interrupt
window (VINTR) vmexit, this time with a comment that is at least
decent.
It turns out however that the same comment applies to the CR8 write
intercept, which is also a "recheck if an interrupt should be
injected" intercept. The CR8 read intercept instead has not
been used by KVM for 14 years (commit 649d68643ebf, "KVM: SVM:
sync TPR value to V_TPR field in the VMCB"), so do not bother
clearing it and let one comment describe both CR8 write and VINTR
handling.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/svm/nested.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index bc9cd7086fa97..add65dd597569 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm)
c->intercepts[i] = h->intercepts[i];
if (g->int_ctl & V_INTR_MASKING_MASK) {
- /* We only want the cr8 intercept bits of L1 */
- vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
- vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
/*
- * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
- * affect any interrupt we may want to inject; therefore,
- * interrupt window vmexits are irrelevant to L0.
+ * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+ * does not affect any interrupt we may want to inject;
+ * therefore, writes to CR8 are irrelevant to L0, as are
+ * interrupt window vmexits.
*/
+ vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
vmcb_clr_intercept(c, INTERCEPT_VINTR);
}
--
GitLab
From 45e966fcca03ecdcccac7cb236e16eea38cc18af Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sat, 22 Oct 2022 04:17:53 -0400
Subject: [PATCH 0504/1167] KVM: x86: Do not return host topology information
from KVM_GET_SUPPORTED_CPUID
Passing the host topology to the guest is almost certainly wrong
and will confuse the scheduler. In addition, several fields of
these CPUID leaves vary on each processor; it is simply impossible to
return the right values from KVM_GET_SUPPORTED_CPUID in such a way that
they can be passed to KVM_SET_CPUID2.
The values that will most likely prevent confusion are all zeroes.
Userspace will have to override it anyway if it wishes to present a
specific topology to the guest.
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
Documentation/virt/kvm/api.rst | 14 ++++++++++++++
arch/x86/kvm/cpuid.c | 32 ++++++++++++++++----------------
2 files changed, 30 insertions(+), 16 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index deb494f759ed3..d8ea37dfddf42 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8310,6 +8310,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID``
It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
has enabled in-kernel emulation of the local APIC.
+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different
+versions of KVM return different values for this information and userspace
+should not rely on it. Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU. In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
Obsolete ioctls and capabilities
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b14653b61470c..596061c1610e6 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -770,16 +770,22 @@ struct kvm_cpuid_array {
int nent;
};
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+ if (array->nent >= array->maxnent)
+ return NULL;
+
+ return &array->entries[array->nent++];
+}
+
static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
u32 function, u32 index)
{
- struct kvm_cpuid_entry2 *entry;
+ struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
- if (array->nent >= array->maxnent)
+ if (!entry)
return NULL;
- entry = &array->entries[array->nent++];
-
memset(entry, 0, sizeof(*entry));
entry->function = function;
entry->index = index;
@@ -956,22 +962,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->edx = edx.full;
break;
}
- /*
- * Per Intel's SDM, the 0x1f is a superset of 0xb,
- * thus they can be handled by common code.
- */
case 0x1f:
case 0xb:
/*
- * Populate entries until the level type (ECX[15:8]) of the
- * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is
- * the starting entry, filled by the primary do_host_cpuid().
+ * No topology; a valid topology is indicated by the presence
+ * of subleaf 1.
*/
- for (i = 1; entry->ecx & 0xff00; ++i) {
- entry = do_host_cpuid(array, function, i);
- if (!entry)
- goto out;
- }
+ entry->eax = entry->ebx = entry->ecx = 0;
break;
case 0xd: {
u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
@@ -1202,6 +1199,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x8000001e:
+ /* Do not return host topology information. */
+ entry->eax = entry->ebx = entry->ecx = 0;
+ entry->edx = 0; /* reserved */
break;
case 0x8000001F:
if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
--
GitLab
From 87ca4f9efbd7cc649ff43b87970888f2812945b8 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 30 Dec 2022 23:11:19 -0500
Subject: [PATCH 0505/1167] sched/core: Fix use-after-free bug in
dup_user_cpus_ptr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Since commit 07ec77a1d4e8 ("sched: Allow task CPU affinity to be
restricted on asymmetric systems"), the setting and clearing of
user_cpus_ptr are done under pi_lock for arm64 architecture. However,
dup_user_cpus_ptr() accesses user_cpus_ptr without any lock
protection. Since sched_setaffinity() can be invoked from another
process, the process being modified may be undergoing fork() at
the same time. When racing with the clearing of user_cpus_ptr in
__set_cpus_allowed_ptr_locked(), it can lead to user-after-free and
possibly double-free in arm64 kernel.
Commit 8f9ea86fdf99 ("sched: Always preserve the user requested
cpumask") fixes this problem as user_cpus_ptr, once set, will never
be cleared in a task's lifetime. However, this bug was re-introduced
in commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
do_set_cpus_allowed()") which allows the clearing of user_cpus_ptr in
do_set_cpus_allowed(). This time, it will affect all arches.
Fix this bug by always clearing the user_cpus_ptr of the newly
cloned/forked task before the copying process starts and check the
user_cpus_ptr state of the source task under pi_lock.
Note to stable, this patch won't be applicable to stable releases.
Just copy the new dup_user_cpus_ptr() function over.
Fixes: 07ec77a1d4e8 ("sched: Allow task CPU affinity to be restricted on asymmetric systems")
Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
Reported-by: David Wang çŽ‹æ ‡ <wangbiao3@xiaomi.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20221231041120.440785-2-longman@redhat.com
---
kernel/sched/core.c | 34 +++++++++++++++++++++++++++++-----
1 file changed, 29 insertions(+), 5 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 965d813c28ad7..f9f6e5413dcf9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2612,19 +2612,43 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
int node)
{
+ cpumask_t *user_mask;
unsigned long flags;
- if (!src->user_cpus_ptr)
+ /*
+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+ * may differ by now due to racing.
+ */
+ dst->user_cpus_ptr = NULL;
+
+ /*
+ * This check is racy and losing the race is a valid situation.
+ * It is not worth the extra overhead of taking the pi_lock on
+ * every fork/clone.
+ */
+ if (data_race(!src->user_cpus_ptr))
return 0;
- dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
- if (!dst->user_cpus_ptr)
+ user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+ if (!user_mask)
return -ENOMEM;
- /* Use pi_lock to protect content of user_cpus_ptr */
+ /*
+ * Use pi_lock to protect content of user_cpus_ptr
+ *
+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+ * do_set_cpus_allowed().
+ */
raw_spin_lock_irqsave(&src->pi_lock, flags);
- cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ if (src->user_cpus_ptr) {
+ swap(dst->user_cpus_ptr, user_mask);
+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ }
raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+ if (unlikely(user_mask))
+ kfree(user_mask);
+
return 0;
}
--
GitLab
From 9a5418bc48babb313d2a62df29ebe21ce8c06c59 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 30 Dec 2022 23:11:20 -0500
Subject: [PATCH 0506/1167] sched/core: Use kfree_rcu() in
do_set_cpus_allowed()
Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
do_set_cpus_allowed()") may call kfree() if user_cpus_ptr was previously
set. Unfortunately, some of the callers of do_set_cpus_allowed()
may have pi_lock held when calling it. So the following splats may be
printed especially when running with a PREEMPT_RT kernel:
WARNING: possible circular locking dependency detected
BUG: sleeping function called from invalid context
To avoid these problems, kfree_rcu() is used instead. An internal
cpumask_rcuhead union is created for the sole purpose of facilitating
the use of kfree_rcu() to free the cpumask.
Since user_cpus_ptr is not being used in non-SMP configs, the newly
introduced alloc_user_cpus_ptr() helper will return NULL in this case
and sched_setaffinity() is modified to handle this special case.
Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221231041120.440785-3-longman@redhat.com
---
kernel/sched/core.c | 33 +++++++++++++++++++++++++++++----
1 file changed, 29 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9f6e5413dcf9..bb1ee6d7bddea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2604,9 +2604,29 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
.user_mask = NULL,
.flags = SCA_USER, /* clear the user requested mask */
};
+ union cpumask_rcuhead {
+ cpumask_t cpumask;
+ struct rcu_head rcu;
+ };
__do_set_cpus_allowed(p, &ac);
- kfree(ac.user_mask);
+
+ /*
+ * Because this is called with p->pi_lock held, it is not possible
+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+ * kfree_rcu().
+ */
+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ /*
+ * See do_set_cpus_allowed() above for the rcu_head usage.
+ */
+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+ return kmalloc_node(size, GFP_KERNEL, node);
}
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
@@ -2629,7 +2649,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
if (data_race(!src->user_cpus_ptr))
return 0;
- user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+ user_mask = alloc_user_cpus_ptr(node);
if (!user_mask)
return -ENOMEM;
@@ -3605,6 +3625,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
return false;
}
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ return NULL;
+}
+
#endif /* !CONFIG_SMP */
static void
@@ -8265,8 +8290,8 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_put_task;
- user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
- if (!user_mask) {
+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+ if (IS_ENABLED(CONFIG_SMP) && !user_mask) {
retval = -ENOMEM;
goto out_put_task;
}
--
GitLab
From 01f2ea5bcf89dbd7a6530dbce7f2fb4e327e7006 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 4 Jan 2023 12:13:46 -0800
Subject: [PATCH 0507/1167] perf/x86/cstate: Add Meteor Lake support
Meteor Lake is Intel's successor to Raptor lake. From the perspective of
Intel cstate residency counters, there is nothing changed compared with
Raptor lake.
Share adl_cstates with Raptor lake.
Update the comments for Meteor Lake.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lore.kernel.org/r/20230104201349.1451191-6-kan.liang@linux.intel.com
---
arch/x86/events/intel/cstate.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index a2834bc93149a..3019fb1926e35 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,6 +41,7 @@
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
* Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+ * MTL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
@@ -51,50 +52,50 @@
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
* Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- * ICL,TGL,RKL,ADL,RPL
+ * ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
* KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- * RPL,SPR
+ * RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
* GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- * KBL,CML,ICL,TGL,RKL,ADL,RPL
+ * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- * TNT,RKL,ADL,RPL
+ * TNT,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
*
*/
@@ -686,6 +687,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
--
GitLab
From 6887a4d3aede084bf08b70fbc9736c69fce05d7f Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 4 Jan 2023 12:13:47 -0800
Subject: [PATCH 0508/1167] perf/x86/msr: Add Meteor Lake support
Meteor Lake is Intel's successor to Raptor lake. PPERF and SMI_COUNT MSRs
are also supported.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Link: https://lore.kernel.org/r/20230104201349.1451191-7-kan.liang@linux.intel.com
---
arch/x86/events/msr.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index ecced3a52668a..074150d28fa82 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -107,6 +107,8 @@ static bool test_intel(int idx, void *data)
case INTEL_FAM6_RAPTORLAKE:
case INTEL_FAM6_RAPTORLAKE_P:
case INTEL_FAM6_RAPTORLAKE_S:
+ case INTEL_FAM6_METEORLAKE:
+ case INTEL_FAM6_METEORLAKE_L:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
--
GitLab
From 69ced4160969025821f2999ff92163ed26568f1c Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 6 Jan 2023 08:04:48 -0800
Subject: [PATCH 0509/1167] perf/x86/msr: Add Emerald Rapids
The same as Sapphire Rapids, the SMI_COUNT MSR is also supported on
Emerald Rapids. Add Emerald Rapids model.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230106160449.3566477-3-kan.liang@linux.intel.com
---
arch/x86/events/msr.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 074150d28fa82..c65d8906cbcf4 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data)
case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SAPPHIRERAPIDS_X:
+ case INTEL_FAM6_EMERALDRAPIDS_X:
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_D:
--
GitLab
From 5268a2842066c227e6ccd94bac562f1e1000244f Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 6 Jan 2023 08:04:49 -0800
Subject: [PATCH 0510/1167] perf/x86/intel/uncore: Add Emerald Rapids
From the perspective of the uncore PMU, the new Emerald Rapids is the
same as the Sapphire Rapids. The only difference is the event list,
which will be supported in the perf tool later.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230106160449.3566477-4-kan.liang@linux.intel.com
---
arch/x86/events/intel/uncore.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6f1ccc57a6921..459b1aafd4d4a 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
{},
};
--
GitLab
From 18bba1843fc7f264f58c9345d00827d082f9c558 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 9 Jan 2023 12:41:46 +0100
Subject: [PATCH 0511/1167] efi: rt-wrapper: Add missing include
Add the missing #include of asm/assembler.h, which is where the ldr_l
macro is defined.
Fixes: ff7a167961d1b97e ("arm64: efi: Execute runtime services from a dedicated stack")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
arch/arm64/kernel/efi-rt-wrapper.S | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index a00886410537d..d872d18101d83 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -4,6 +4,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
SYM_FUNC_START(__efi_rt_asm_wrapper)
stp x29, x30, [sp, #-112]!
--
GitLab
From c8c37bc514514999e62a17e95160ed9ebf75ca8d Mon Sep 17 00:00:00 2001
From: Lareine Khawaly <lareine@amazon.com>
Date: Wed, 21 Dec 2022 19:59:00 +0000
Subject: [PATCH 0512/1167] i2c: designware: use casting of u64 in clock
multiplication to avoid overflow
In functions i2c_dw_scl_lcnt() and i2c_dw_scl_hcnt() may have overflow
by depending on the values of the given parameters including the ic_clk.
For example in our use case where ic_clk is larger than one million,
multiplication of ic_clk * 4700 will result in 32 bit overflow.
Add cast of u64 to the calculation to avoid multiplication overflow, and
use the corresponding define for divide.
Fixes: 2373f6b9744d ("i2c-designware: split of i2c-designware.c into core and bus specific parts")
Signed-off-by: Lareine Khawaly <lareine@amazon.com>
Signed-off-by: Hanna Hawa <hhhawa@amazon.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-designware-common.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c
index a3240ece55b2b..581e02cc979a0 100644
--- a/drivers/i2c/busses/i2c-designware-common.c
+++ b/drivers/i2c/busses/i2c-designware-common.c
@@ -351,7 +351,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset)
*
* If your hardware is free from tHD;STA issue, try this one.
*/
- return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * tSYMBOL, MICRO) -
+ 8 + offset;
else
/*
* Conditional expression:
@@ -367,7 +368,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset)
* The reason why we need to take into account "tf" here,
* is the same as described in i2c_dw_scl_lcnt().
*/
- return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tSYMBOL + tf), MICRO) -
+ 3 + offset;
}
u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset)
@@ -383,7 +385,8 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset)
* account the fall time of SCL signal (tf). Default tf value
* should be 0.3 us, for safety.
*/
- return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset;
+ return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tLOW + tf), MICRO) -
+ 1 + offset;
}
int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev)
--
GitLab
From 75507a319876aba88932e2c7dab58b6c22d89f6b Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 19 Dec 2022 13:01:45 +0000
Subject: [PATCH 0513/1167] i2c: designware: Fix unbalanced suspended flag
Ensure that i2c_mark_adapter_suspended() is always balanced by a call to
i2c_mark_adapter_resumed().
dw_i2c_plat_resume() must always be called, so that
i2c_mark_adapter_resumed() is called. This is not compatible with
DPM_FLAG_MAY_SKIP_RESUME, so remove the flag.
Since the controller is always resumed on system resume the
dw_i2c_plat_complete() callback is redundant and has been removed.
The unbalanced suspended flag was introduced by commit c57813b8b288
("i2c: designware: Lock the adapter while setting the suspended flag")
Before that commit, the system and runtime PM used the same functions. The
DPM_FLAG_MAY_SKIP_RESUME was used to skip the system resume if the driver
had been in runtime-suspend. If system resume was skipped, the suspended
flag would be cleared by the next runtime resume. The check of the
suspended flag was _after_ the call to pm_runtime_get_sync() in
i2c_dw_xfer(). So either a system resume or a runtime resume would clear
the flag before it was checked.
Having introduced the unbalanced suspended flag with that commit, a further
commit 80704a84a9f8
("i2c: designware: Use the i2c_mark_adapter_suspended/resumed() helpers")
changed from using a local suspended flag to using the
i2c_mark_adapter_suspended/resumed() functions. These use a flag that is
checked by I2C core code before issuing the transfer to the bus driver, so
there was no opportunity for the bus driver to runtime resume itself before
the flag check.
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: c57813b8b288 ("i2c: designware: Lock the adapter while setting the suspended flag")
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-designware-platdrv.c | 20 ++------------------
1 file changed, 2 insertions(+), 18 deletions(-)
diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c
index ba043b5473936..74182db03a88b 100644
--- a/drivers/i2c/busses/i2c-designware-platdrv.c
+++ b/drivers/i2c/busses/i2c-designware-platdrv.c
@@ -351,13 +351,11 @@ static int dw_i2c_plat_probe(struct platform_device *pdev)
if (dev->flags & ACCESS_NO_IRQ_SUSPEND) {
dev_pm_set_driver_flags(&pdev->dev,
- DPM_FLAG_SMART_PREPARE |
- DPM_FLAG_MAY_SKIP_RESUME);
+ DPM_FLAG_SMART_PREPARE);
} else {
dev_pm_set_driver_flags(&pdev->dev,
DPM_FLAG_SMART_PREPARE |
- DPM_FLAG_SMART_SUSPEND |
- DPM_FLAG_MAY_SKIP_RESUME);
+ DPM_FLAG_SMART_SUSPEND);
}
device_enable_async_suspend(&pdev->dev);
@@ -419,21 +417,8 @@ static int dw_i2c_plat_prepare(struct device *dev)
*/
return !has_acpi_companion(dev);
}
-
-static void dw_i2c_plat_complete(struct device *dev)
-{
- /*
- * The device can only be in runtime suspend at this point if it has not
- * been resumed throughout the ending system suspend/resume cycle, so if
- * the platform firmware might mess up with it, request the runtime PM
- * framework to resume it.
- */
- if (pm_runtime_suspended(dev) && pm_resume_via_firmware())
- pm_request_resume(dev);
-}
#else
#define dw_i2c_plat_prepare NULL
-#define dw_i2c_plat_complete NULL
#endif
#ifdef CONFIG_PM
@@ -483,7 +468,6 @@ static int __maybe_unused dw_i2c_plat_resume(struct device *dev)
static const struct dev_pm_ops dw_i2c_dev_pm_ops = {
.prepare = dw_i2c_plat_prepare,
- .complete = dw_i2c_plat_complete,
SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume)
SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend, dw_i2c_plat_runtime_resume, NULL)
};
--
GitLab
From 80f8be7af03ffe90dc4df998b16bfa212afbdde9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 8 Jan 2023 22:47:26 +0900
Subject: [PATCH 0514/1167] tomoyo: Omit use of bin2c
bin2c was, as its name implies, introduced to convert a binary file to
C code.
However, I did not see any good reason ever for using this tool because
using the .incbin directive is much faster, and often results in simpler
code.
Most of the uses of bin2c have been killed, for example:
- 13610aa908dc ("kernel/configs: use .incbin directive to embed config_data.gz")
- 4c0f032d4963 ("s390/purgatory: Omit use of bin2c")
security/tomoyo/Makefile has even less reason for using bin2c because
the policy files are text data. So, sed is enough for converting them
to C string literals, and what is nicer, generates human-readable
builtin-policy.h.
This is the last user of bin2c. After this commit lands, bin2c will be
removed.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
[penguin-kernel: Update sed script to also escape backslash and quote ]
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
security/tomoyo/Kconfig | 1 -
security/tomoyo/Makefile | 15 ++++++++-------
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
index b9f867100a9ff..772d2ab58fd14 100644
--- a/security/tomoyo/Kconfig
+++ b/security/tomoyo/Kconfig
@@ -7,7 +7,6 @@ config SECURITY_TOMOYO
select SECURITY_PATH
select SECURITY_NETWORK
select SRCU
- select BUILD_BIN2C
default n
help
This selects TOMOYO Linux, pathname-based access control.
diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile
index 1b18a02ccd2e6..884ff155edc39 100644
--- a/security/tomoyo/Makefile
+++ b/security/tomoyo/Makefile
@@ -2,13 +2,14 @@
obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o
targets += builtin-policy.h
-define do_policy
-echo "static char tomoyo_builtin_$(1)[] __initdata ="; \
-$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \
-echo ";"
-endef
-quiet_cmd_policy = POLICY $@
- cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@
+
+quiet_cmd_policy = POLICY $@
+ cmd_policy = { \
+ $(foreach x, profile exception_policy domain_policy manager stat, \
+ printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \
+ sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null); \
+ printf '\t"";\n';) \
+ } > $@
$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE
$(call if_changed,policy)
--
GitLab
From 0cbf1ecd8c4801ec7566231491f7ad9cec31098b Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan@gerhold.net>
Date: Sat, 31 Dec 2022 12:55:06 +0100
Subject: [PATCH 0515/1167] ASoC: qcom: Fix building APQ8016 machine driver
without SOUNDWIRE
Older Qualcomm platforms like APQ8016 do not have hardware support for
SoundWire, so kernel configurations made specifically for those platforms
will usually not have CONFIG_SOUNDWIRE enabled.
Unfortunately commit 8d89cf6ff229 ("ASoC: qcom: cleanup and fix
dependency of QCOM_COMMON") breaks those kernel configurations, because
SOUNDWIRE is now a required dependency for SND_SOC_QCOM_COMMON (and in
turn also SND_SOC_APQ8016_SBC). Trying to migrate such a kernel config
silently disables SND_SOC_APQ8016_SBC and breaks audio functionality.
The soundwire helpers in common.c are only used by two of the Qualcomm
audio machine drivers, so building and requiring CONFIG_SOUNDWIRE for
all platforms is unnecessary.
There is no need to stuff all common code into a single module. Fix the
issue by moving the soundwire helpers to a separate SND_SOC_QCOM_SDW
module/option that is selected only by the machine drivers that make
use of them. This also allows reverting the imply/depends changes from
the previous fix because both SM8250 and SC8280XP already depend on
SOUNDWIRE, so the soundwire helpers will be only built if SOUNDWIRE
is really enabled.
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Fixes: 8d89cf6ff229 ("ASoC: qcom: cleanup and fix dependency of QCOM_COMMON")
Signed-off-by: Stephan Gerhold <stephan@gerhold.net>
Link: https://lore.kernel.org/r/20221231115506.82991-1-stephan@gerhold.net
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/qcom/Kconfig | 21 ++++---
sound/soc/qcom/Makefile | 2 +
sound/soc/qcom/common.c | 114 -----------------------------------
sound/soc/qcom/common.h | 10 ----
sound/soc/qcom/sc8280xp.c | 1 +
sound/soc/qcom/sdw.c | 123 ++++++++++++++++++++++++++++++++++++++
sound/soc/qcom/sdw.h | 18 ++++++
sound/soc/qcom/sm8250.c | 1 +
8 files changed, 157 insertions(+), 133 deletions(-)
create mode 100644 sound/soc/qcom/sdw.c
create mode 100644 sound/soc/qcom/sdw.h
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 96a6d4731e6fd..e7b00d1d9e99f 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -2,7 +2,6 @@
menuconfig SND_SOC_QCOM
tristate "ASoC support for QCOM platforms"
depends on ARCH_QCOM || COMPILE_TEST
- imply SND_SOC_QCOM_COMMON
help
Say Y or M if you want to add support to use audio devices
in Qualcomm Technologies SOC-based platforms.
@@ -60,14 +59,16 @@ config SND_SOC_STORM
config SND_SOC_APQ8016_SBC
tristate "SoC Audio support for APQ8016 SBC platforms"
select SND_SOC_LPASS_APQ8016
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8016 SOC-based systems.
Say Y if you want to use audio devices on MI2S.
config SND_SOC_QCOM_COMMON
- depends on SOUNDWIRE
+ tristate
+
+config SND_SOC_QCOM_SDW
tristate
config SND_SOC_QDSP6_COMMON
@@ -144,7 +145,7 @@ config SND_SOC_MSM8996
depends on QCOM_APR
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8096 SoC-based systems.
@@ -155,7 +156,7 @@ config SND_SOC_SDM845
depends on QCOM_APR && I2C && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_RT5663
select SND_SOC_MAX98927
imply SND_SOC_CROS_EC_CODEC
@@ -169,7 +170,8 @@ config SND_SOC_SM8250
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SM8250 SoC-based systems.
@@ -180,7 +182,8 @@ config SND_SOC_SC8280XP
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SC8280XP SoC-based systems.
@@ -190,7 +193,7 @@ config SND_SOC_SC7180
tristate "SoC Machine driver for SC7180 boards"
depends on I2C && GPIOLIB
depends on SOUNDWIRE || SOUNDWIRE=n
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7180
select SND_SOC_MAX98357A
select SND_SOC_RT5682_I2C
@@ -204,7 +207,7 @@ config SND_SOC_SC7180
config SND_SOC_SC7280
tristate "SoC Machine driver for SC7280 boards"
depends on I2C && SOUNDWIRE
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7280
select SND_SOC_MAX98357A
select SND_SOC_WCD938X_SDW
diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index 8b97172cf990f..254350d9dc069 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -28,6 +28,7 @@ snd-soc-sdm845-objs := sdm845.o
snd-soc-sm8250-objs := sm8250.o
snd-soc-sc8280xp-objs := sc8280xp.o
snd-soc-qcom-common-objs := common.o
+snd-soc-qcom-sdw-objs := sdw.o
obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_SND_SOC_SC8280XP) += snd-soc-sc8280xp.o
obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
obj-$(CONFIG_SND_SOC_SM8250) += snd-soc-sm8250.o
obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o
+obj-$(CONFIG_SND_SOC_QCOM_SDW) += snd-soc-qcom-sdw.o
#DSP lib
obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
index 49c74c1662a3f..96fe80241fb41 100644
--- a/sound/soc/qcom/common.c
+++ b/sound/soc/qcom/common.c
@@ -180,120 +180,6 @@ int qcom_snd_parse_of(struct snd_soc_card *card)
}
EXPORT_SYMBOL_GPL(qcom_snd_parse_of);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- int ret;
-
- if (!sruntime)
- return 0;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- break;
- default:
- return 0;
- }
-
- if (*stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
-
- ret = sdw_prepare_stream(sruntime);
- if (ret)
- return ret;
-
- /**
- * NOTE: there is a strict hw requirement about the ordering of port
- * enables and actual WSA881x PA enable. PA enable should only happen
- * after soundwire ports are enabled if not DC on the line is
- * accumulated resulting in Click/Pop Noise
- * PA enable/mute are handled as part of codec DAPM and digital mute.
- */
-
- ret = sdw_enable_stream(sruntime);
- if (ret) {
- sdw_deprepare_stream(sruntime);
- return ret;
- }
- *stream_prepared = true;
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
-
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *codec_dai;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- struct sdw_stream_runtime *sruntime;
- int i;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- for_each_rtd_codec_dais(rtd, i, codec_dai) {
- sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
- if (sruntime != ERR_PTR(-ENOTSUPP))
- *psruntime = sruntime;
- }
- break;
- }
-
- return 0;
-
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
-
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime, bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- if (sruntime && *stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
- break;
- default:
- break;
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
-
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup)
{
diff --git a/sound/soc/qcom/common.h b/sound/soc/qcom/common.h
index 3ef5bb6d12df7..d7f80ee5ae26a 100644
--- a/sound/soc/qcom/common.h
+++ b/sound/soc/qcom/common.h
@@ -5,19 +5,9 @@
#define __QCOM_SND_COMMON_H__
#include <sound/soc.h>
-#include <linux/soundwire/sdw.h>
int qcom_snd_parse_of(struct snd_soc_card *card);
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *runtime,
- bool *stream_prepared);
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime);
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared);
#endif
diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c
index ade44ad7c585a..14d9fea33d16a 100644
--- a/sound/soc/qcom/sc8280xp.c
+++ b/sound/soc/qcom/sc8280xp.c
@@ -12,6 +12,7 @@
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sc8280xp"
diff --git a/sound/soc/qcom/sdw.c b/sound/soc/qcom/sdw.c
new file mode 100644
index 0000000000000..10249519a39e5
--- /dev/null
+++ b/sound/soc/qcom/sdw.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited.
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/module.h>
+#include <sound/soc.h>
+#include "qdsp6/q6afe.h"
+#include "sdw.h"
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ int ret;
+
+ if (!sruntime)
+ return 0;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ break;
+ default:
+ return 0;
+ }
+
+ if (*stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+
+ ret = sdw_prepare_stream(sruntime);
+ if (ret)
+ return ret;
+
+ /**
+ * NOTE: there is a strict hw requirement about the ordering of port
+ * enables and actual WSA881x PA enable. PA enable should only happen
+ * after soundwire ports are enabled if not DC on the line is
+ * accumulated resulting in Click/Pop Noise
+ * PA enable/mute are handled as part of codec DAPM and digital mute.
+ */
+
+ ret = sdw_enable_stream(sruntime);
+ if (ret) {
+ sdw_deprepare_stream(sruntime);
+ return ret;
+ }
+ *stream_prepared = true;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
+
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *codec_dai;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ struct sdw_stream_runtime *sruntime;
+ int i;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ for_each_rtd_codec_dais(rtd, i, codec_dai) {
+ sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
+ if (sruntime != ERR_PTR(-ENOTSUPP))
+ *psruntime = sruntime;
+ }
+ break;
+ }
+
+ return 0;
+
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
+
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime, bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ if (sruntime && *stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/sdw.h b/sound/soc/qcom/sdw.h
new file mode 100644
index 0000000000000..d74cbb84da138
--- /dev/null
+++ b/sound/soc/qcom/sdw.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#ifndef __QCOM_SND_SDW_H__
+#define __QCOM_SND_SDW_H__
+
+#include <linux/soundwire/sdw.h>
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *runtime,
+ bool *stream_prepared);
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime);
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared);
+#endif
diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c
index 8dbe9ef41b1c9..9626a9ef78c23 100644
--- a/sound/soc/qcom/sm8250.c
+++ b/sound/soc/qcom/sm8250.c
@@ -12,6 +12,7 @@
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sm8250"
#define MI2S_BCLK_RATE 1536000
--
GitLab
From 69568267c5b624eaa86afcafbca1c4765f63e112 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Dec 2022 12:59:06 +0100
Subject: [PATCH 0516/1167] ASoC: dt-bindings: qcom,lpass-wsa-macro: correct
clocks on SM8250
SM8250 DTS uses additional "va" clock in WSA macro device node:
sm8250-sony-xperia-edo-pdx203.dtb: codec@3240000: clock-names: ['mclk', 'npl', 'macro', 'dcodec', 'va', 'fsgen'] is too long
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20221225115907.55250-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../bindings/sound/qcom,lpass-wsa-macro.yaml | 58 +++++++++++++++----
1 file changed, 47 insertions(+), 11 deletions(-)
diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml
index 2bf8d082f8f10..66cbb1f5e31a5 100644
--- a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml
+++ b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml
@@ -9,9 +9,6 @@ title: LPASS(Low Power Audio Subsystem) VA Macro audio codec
maintainers:
- Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
-allOf:
- - $ref: dai-common.yaml#
-
properties:
compatible:
enum:
@@ -30,15 +27,12 @@ properties:
const: 0
clocks:
- maxItems: 5
+ minItems: 5
+ maxItems: 6
clock-names:
- items:
- - const: mclk
- - const: npl
- - const: macro
- - const: dcodec
- - const: fsgen
+ minItems: 5
+ maxItems: 6
clock-output-names:
maxItems: 1
@@ -55,10 +49,51 @@ required:
- reg
- "#sound-dai-cells"
+allOf:
+ - $ref: dai-common.yaml#
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sc7280-lpass-wsa-macro
+ - qcom,sm8450-lpass-wsa-macro
+ - qcom,sc8280xp-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ maxItems: 5
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: fsgen
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sm8250-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ minItems: 6
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: va
+ - const: fsgen
+
unevaluatedProperties: false
examples:
- |
+ #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
#include <dt-bindings/sound/qcom,q6afe.h>
codec@3240000 {
compatible = "qcom,sm8250-lpass-wsa-macro";
@@ -69,7 +104,8 @@ examples:
<&audiocc 0>,
<&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
<&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+ <&aoncc LPASS_CDC_VA_MCLK>,
<&vamacro>;
- clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
+ clock-names = "mclk", "npl", "macro", "dcodec", "va", "fsgen";
clock-output-names = "mclk";
};
--
GitLab
From c9fb35f685b2f8a2ead98e3f1b249a1d4e9c040e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 25 Dec 2022 12:59:07 +0100
Subject: [PATCH 0517/1167] ASoC: dt-bindings: qcom,lpass-tx-macro: correct
clocks on SC7280
On SC7280 ADSP bypassed platform, there are only three clocks for TX
macro. This is already reflected in "clock-names" but not in "clocks"
property:
sc7280-herobrine-zombie-lte.dtb: codec@3220000: clocks: [[219, 8], [219, 7], [220]] is too short
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20221225115907.55250-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../devicetree/bindings/sound/qcom,lpass-tx-macro.yaml | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml
index 66431aade3b70..da5f70910da52 100644
--- a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml
+++ b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml
@@ -30,7 +30,9 @@ properties:
const: 0
clocks:
- maxItems: 5
+ oneOf:
+ - maxItems: 3
+ - maxItems: 5
clock-names:
oneOf:
--
GitLab
From f993d24a948d22710148dae2c48b8a87155f6cb9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 7 Jan 2023 01:10:23 +0900
Subject: [PATCH 0518/1167] s390: fix -Wundef warning for CONFIG_KERNEL_ZSTD
Since commit 80b6093b55e3 ("kbuild: add -Wundef to KBUILD_CPPFLAGS
for W=1 builds"), building with W=1 detects misuse of #(el)if.
$ make W=1 ARCH=s390 CROSS_COMPILE=s390x-linux-gnu-
[snip]
arch/s390/boot/decompressor.c:28:7: warning: "CONFIG_KERNEL_ZSTD" is not defined, evaluates to 0 [-Wundef]
28 | #elif CONFIG_KERNEL_ZSTD
| ^~~~~~~~~~~~~~~~~~
This issue has been hidden because arch/s390/boot/Makefile overwrites
KBUILD_CFLAGS, dropping -Wundef.
CONFIG_KERNEL_ZSTD is a bool option. #elif defined() should be used.
The line #ifdef CONFIG_KERNEL_BZIP2 is fine, but I changed it for
consistency.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Link: https://lore.kernel.org/r/20230106161024.2373602-1-masahiroy@kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/boot/decompressor.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c
index e27c2140d6206..8dcd7af2911a0 100644
--- a/arch/s390/boot/decompressor.c
+++ b/arch/s390/boot/decompressor.c
@@ -23,9 +23,9 @@
#define memmove memmove
#define memzero(s, n) memset((s), 0, (n))
-#ifdef CONFIG_KERNEL_BZIP2
+#if defined(CONFIG_KERNEL_BZIP2)
#define BOOT_HEAP_SIZE 0x400000
-#elif CONFIG_KERNEL_ZSTD
+#elif defined(CONFIG_KERNEL_ZSTD)
#define BOOT_HEAP_SIZE 0x30000
#else
#define BOOT_HEAP_SIZE 0x10000
--
GitLab
From 3a73746b267e5c6a87c9ad26f8c6a48e44da609c Mon Sep 17 00:00:00 2001
From: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Date: Tue, 20 Dec 2022 17:08:47 +0900
Subject: [PATCH 0519/1167] RDMA/rxe: Fix inaccurate constants in rxe_type_info
ibv_query_device() has reported incorrect device attributes, which are
actually not used by the device. Make the constants correspond with the
attributes shown to users.
Fixes: 3ccffe8abf2f ("RDMA/rxe: Move max_elem into rxe_type_info")
Fixes: 3225717f6dfa ("RDMA/rxe: Replace red-black trees by xarrays")
Link: https://lore.kernel.org/r/20221220080848.253785-1-matsuda-daisuke@fujitsu.com
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
drivers/infiniband/sw/rxe/rxe_pool.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index f50620f5a0a14..1151c0b5cceab 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -23,16 +23,16 @@ static const struct rxe_type_info {
.size = sizeof(struct rxe_ucontext),
.elem_offset = offsetof(struct rxe_ucontext, elem),
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_UCONTEXT,
+ .max_elem = RXE_MAX_UCONTEXT,
},
[RXE_TYPE_PD] = {
.name = "pd",
.size = sizeof(struct rxe_pd),
.elem_offset = offsetof(struct rxe_pd, elem),
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_PD,
+ .max_elem = RXE_MAX_PD,
},
[RXE_TYPE_AH] = {
.name = "ah",
@@ -40,7 +40,7 @@ static const struct rxe_type_info {
.elem_offset = offsetof(struct rxe_ah, elem),
.min_index = RXE_MIN_AH_INDEX,
.max_index = RXE_MAX_AH_INDEX,
- .max_elem = RXE_MAX_AH_INDEX - RXE_MIN_AH_INDEX + 1,
+ .max_elem = RXE_MAX_AH,
},
[RXE_TYPE_SRQ] = {
.name = "srq",
@@ -49,7 +49,7 @@ static const struct rxe_type_info {
.cleanup = rxe_srq_cleanup,
.min_index = RXE_MIN_SRQ_INDEX,
.max_index = RXE_MAX_SRQ_INDEX,
- .max_elem = RXE_MAX_SRQ_INDEX - RXE_MIN_SRQ_INDEX + 1,
+ .max_elem = RXE_MAX_SRQ,
},
[RXE_TYPE_QP] = {
.name = "qp",
@@ -58,7 +58,7 @@ static const struct rxe_type_info {
.cleanup = rxe_qp_cleanup,
.min_index = RXE_MIN_QP_INDEX,
.max_index = RXE_MAX_QP_INDEX,
- .max_elem = RXE_MAX_QP_INDEX - RXE_MIN_QP_INDEX + 1,
+ .max_elem = RXE_MAX_QP,
},
[RXE_TYPE_CQ] = {
.name = "cq",
@@ -66,8 +66,8 @@ static const struct rxe_type_info {
.elem_offset = offsetof(struct rxe_cq, elem),
.cleanup = rxe_cq_cleanup,
.min_index = 1,
- .max_index = UINT_MAX,
- .max_elem = UINT_MAX,
+ .max_index = RXE_MAX_CQ,
+ .max_elem = RXE_MAX_CQ,
},
[RXE_TYPE_MR] = {
.name = "mr",
@@ -76,7 +76,7 @@ static const struct rxe_type_info {
.cleanup = rxe_mr_cleanup,
.min_index = RXE_MIN_MR_INDEX,
.max_index = RXE_MAX_MR_INDEX,
- .max_elem = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX + 1,
+ .max_elem = RXE_MAX_MR,
},
[RXE_TYPE_MW] = {
.name = "mw",
@@ -85,7 +85,7 @@ static const struct rxe_type_info {
.cleanup = rxe_mw_cleanup,
.min_index = RXE_MIN_MW_INDEX,
.max_index = RXE_MAX_MW_INDEX,
- .max_elem = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX + 1,
+ .max_elem = RXE_MAX_MW,
},
};
--
GitLab
From 1aefe5c177c1922119afb4ee443ddd6ac3140b37 Mon Sep 17 00:00:00 2001
From: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Date: Tue, 20 Dec 2022 17:08:48 +0900
Subject: [PATCH 0520/1167] RDMA/rxe: Prevent faulty rkey generation
If you create MRs more than 0x10000 times after loading the module,
responder starts to reply NAKs for RDMA/Atomic operations because of rkey
violation detected in check_rkey(). The root cause is that rkeys are
incremented each time a new MR is created and the value overflows into the
range reserved for MWs.
This commit also increases the value of RXE_MAX_MW that has been limited
unlike other parameters.
Fixes: 0994a1bcd5f7 ("RDMA/rxe: Bump up default maximum values used via uverbs")
Link: https://lore.kernel.org/r/20221220080848.253785-2-matsuda-daisuke@fujitsu.com
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Tested-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Li Zhijian <lizhijian@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
drivers/infiniband/sw/rxe/rxe_param.h | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index a754fc902e3d1..7b41d79e72b2d 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -98,11 +98,11 @@ enum rxe_device_param {
RXE_MAX_SRQ = DEFAULT_MAX_VALUE - RXE_MIN_SRQ_INDEX,
RXE_MIN_MR_INDEX = 0x00000001,
- RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE,
- RXE_MAX_MR = DEFAULT_MAX_VALUE - RXE_MIN_MR_INDEX,
- RXE_MIN_MW_INDEX = 0x00010001,
- RXE_MAX_MW_INDEX = 0x00020000,
- RXE_MAX_MW = 0x00001000,
+ RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE >> 1,
+ RXE_MAX_MR = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX,
+ RXE_MIN_MW_INDEX = RXE_MAX_MR_INDEX + 1,
+ RXE_MAX_MW_INDEX = DEFAULT_MAX_VALUE,
+ RXE_MAX_MW = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX,
RXE_MAX_PKT_PER_ACK = 64,
--
GitLab
From 6f9aba7f0d74e8dd085f9ac11fe8f3fdd7fde4ca Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Thu, 5 Jan 2023 17:34:36 +0530
Subject: [PATCH 0521/1167] perf tests bpf prologue: Fix
bpf-script-test-prologue test compile issue with clang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
While running 'perf test' for bpf, observed that "BPF prologue
generation" test case fails to compile with clang. Logs below from
powerpc:
<stdin>:33:2: error: use of undeclared identifier 'fmode_t'
fmode_t f_mode = (fmode_t)_f_mode;
^
<stdin>:37:6: error: use of undeclared identifier 'f_mode'; did you mean '_f_mode'?
if (f_mode & FMODE_WRITE)
^~~~~~
_f_mode
<stdin>:30:60: note: '_f_mode' declared here
int bpf_func__null_lseek(void *ctx, int err, unsigned long _f_mode,
^
2 errors generated.
The test code tests/bpf-script-test-prologue.c uses fmode_t. And the
error above is for "fmode_t" which is defined in include/linux/types.h
as part of kernel build directory: "/lib/modules/<kernel_version>/build"
that comes from kernel devel [ soft link to /usr/src/<kernel_version> ].
Clang picks this header file from "-working-directory" build option that
specifies this build folder.
But the commit 14e4b9f4289aed2c ("perf trace: Raw augmented syscalls fix
libbpf 1.0+ compatibility") changed the include directory to use:
"/usr/include".
Post this change, types.h from /usr/include/ is getting picked upwhich
doesn’t contain definition of "fmode_t" and hence fails to compile.
Compilation command before this commit:
/usr/bin/clang -D__KERNEL__ -D__NR_CPUS__=72 -DLINUX_VERSION_CODE=0x50e00 -xc -I/root/lib/perf/include/bpf -nostdinc -I./arch/powerpc/include -I./arch/powerpc/include/generated -I./include -I./arch/powerpc/include/uapi -I./arch/powerpc/include/generated/uapi -I./include/uapi -I./include/generated/uapi -include ./include/linux/compiler-version.h -include ./include/linux/kconfig.h -Wno-unused-value -Wno-pointer-sign -working-directory /lib/modules/<ver>/build -c - -target bpf -g -O2 -o -
Compilation command after this commit:
/usr/bin/clang -D__KERNEL__ -D__NR_CPUS__=72 -DLINUX_VERSION_CODE=0x50e00 -xc -I/usr/include/ -nostdinc -I./arch/powerpc/include -I./arch/powerpc/include/generated -I./include -I./arch/powerpc/include/uapi -I./arch/powerpc/include/generated/uapi -I./include/uapi -I./include/generated/uapi -include ./include/linux/compiler-version.h -include ./include/linux/kconfig.h -Wno-unused-value -Wno-pointer-sign -working-directory /lib/modules/<ver>/build -c - -target bpf -g -O2 -o -
The difference is addition of -I/usr/include/ in the first line which
is causing the error. Fix this by adding typedef for "fmode_t" in the
testcase to solve the compile issue.
Fixes: 14e4b9f4289aed2c ("perf trace: Raw augmented syscalls fix libbpf 1.0+ compatibility")
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/linux-perf-users/20230105120436.92051-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/bpf-script-test-prologue.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c
index bd83d364cf30d..91778b5c6125d 100644
--- a/tools/perf/tests/bpf-script-test-prologue.c
+++ b/tools/perf/tests/bpf-script-test-prologue.c
@@ -20,6 +20,8 @@
# undef if
#endif
+typedef unsigned int __bitwise fmode_t;
+
#define FMODE_READ 0x1
#define FMODE_WRITE 0x2
--
GitLab
From 291e9da91403e0e628d7692b5ed505100e7b7706 Mon Sep 17 00:00:00 2001
From: Jaroslav Kysela <perex@perex.cz>
Date: Mon, 9 Jan 2023 15:11:33 +0100
Subject: [PATCH 0522/1167] ALSA: usb-audio: Always initialize fixed_rate in
snd_usb_find_implicit_fb_sync_format()
Handle the fallback code path, too.
Fixes: fd28941cff1c ("ALSA: usb-audio: Add new quirk FIXED_RATE for JBL Quantum810 Wireless")
BugLink: https://lore.kernel.org/alsa-devel/Y7frf3N%2FxzvESEsN@kili/
Reported-by: Dan Carpenter <error27@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20230109141133.335543-1-perex@perex.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/implicit.c | 3 ++-
sound/usb/pcm.c | 2 ++
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c
index 41ac7185b42b6..4727043fd7458 100644
--- a/sound/usb/implicit.c
+++ b/sound/usb/implicit.c
@@ -471,7 +471,7 @@ snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip,
subs = find_matching_substream(chip, stream, target->sync_ep,
target->fmt_type);
if (!subs)
- return sync_fmt;
+ goto end;
high_score = 0;
list_for_each_entry(fp, &subs->fmt_list, list) {
@@ -485,6 +485,7 @@ snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip,
}
}
+ end:
if (fixed_rate)
*fixed_rate = snd_usb_pcm_has_fixed_rate(subs);
return sync_fmt;
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index fbd4798834e5f..1f72960d0d536 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -163,6 +163,8 @@ bool snd_usb_pcm_has_fixed_rate(struct snd_usb_substream *subs)
struct snd_usb_audio *chip = subs->stream->chip;
int rate = -1;
+ if (!subs)
+ return false;
if (!(chip->quirk_flags & QUIRK_FLAG_FIXED_RATE))
return false;
list_for_each_entry(fp, &subs->fmt_list, list) {
--
GitLab
From 2ece0930ac5662bccce0ba4c59b84c98d2437200 Mon Sep 17 00:00:00 2001
From: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Date: Mon, 2 Jan 2023 22:39:55 +0530
Subject: [PATCH 0523/1167] i2c: designware-pci: Add new PCI IDs for AMD NAVI
GPU
Add additional supported PCI IDs for latest AMD NAVI GPU card which
has an integrated Type-C controller and designware I2C with PCI
interface.
Signed-off-by: Basavaraj Natikar <Basavaraj.Natikar@amd.com>
Tested-by: Sanath S <Sanath.S@amd.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-designware-pcidrv.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c
index e499f96506c52..782fe1ef3ca10 100644
--- a/drivers/i2c/busses/i2c-designware-pcidrv.c
+++ b/drivers/i2c/busses/i2c-designware-pcidrv.c
@@ -396,6 +396,8 @@ static const struct pci_device_id i2_designware_pci_ids[] = {
{ PCI_VDEVICE(ATI, 0x73a4), navi_amd },
{ PCI_VDEVICE(ATI, 0x73e4), navi_amd },
{ PCI_VDEVICE(ATI, 0x73c4), navi_amd },
+ { PCI_VDEVICE(ATI, 0x7444), navi_amd },
+ { PCI_VDEVICE(ATI, 0x7464), navi_amd },
{ 0,}
};
MODULE_DEVICE_TABLE(pci, i2_designware_pci_ids);
--
GitLab
From 78a4471fa1a76a8bef4919105de67660a89a1e9b Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Sat, 7 Jan 2023 13:32:29 +0100
Subject: [PATCH 0524/1167] i2c: mxs: suppress probe-deferral error message
During boot of I2SE Duckbill the kernel log contains a
confusing error:
Failed to request dma
This is caused by i2c-mxs tries to request a not yet available DMA
channel (-EPROBE_DEFER). So suppress this message by using
dev_err_probe().
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-mxs.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index 5af5cffc444ef..d113bed795452 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -826,8 +826,8 @@ static int mxs_i2c_probe(struct platform_device *pdev)
/* Setup the DMA */
i2c->dmach = dma_request_chan(dev, "rx-tx");
if (IS_ERR(i2c->dmach)) {
- dev_err(dev, "Failed to request dma\n");
- return PTR_ERR(i2c->dmach);
+ return dev_err_probe(dev, PTR_ERR(i2c->dmach),
+ "Failed to request dma\n");
}
platform_set_drvdata(pdev, i2c);
--
GitLab
From 476fdcdaaae7b06c780cdfc234c704107f16c529 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Fri, 23 Dec 2022 10:20:11 +0100
Subject: [PATCH 0525/1167] drm/i915: Reserve enough fence slot for
i915_vma_unbind_async
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A nested dma_resv_reserve_fences(1) will not reserve slot from the
2nd call onwards and folowing dma_resv_add_fence() might hit the
"BUG_ON(fobj->num_fences >= fobj->max_fences)" check.
I915 hit above nested dma_resv case in ttm_bo_handle_move_mem() with
async unbind:
dma_resv_reserve_fences() from --> ttm_bo_handle_move_mem()
dma_resv_reserve_fences() from --> i915_vma_unbind_async()
dma_resv_add_fence() from --> i915_vma_unbind_async()
dma_resv_add_fence() from -->ttm_bo_move_accel_cleanup()
Resolve this by adding an extra fence in i915_vma_unbind_async().
Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 2f6b90da9192 ("drm/i915: Use vma resources for async unbinding")
Cc: <stable@vger.kernel.org> # v5.18+
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221223092011.11657-1-nirmoy.das@intel.com
(cherry picked from commit 4f0755c2faf7388616109717facc5bbde6850e60)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/i915_vma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 3a33be5401ed2..135390d975b6f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -2116,7 +2116,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm)
if (!obj->mm.rsgt)
return -EBUSY;
- err = dma_resv_reserve_fences(obj->base.resv, 1);
+ err = dma_resv_reserve_fences(obj->base.resv, 2);
if (err)
return -EBUSY;
--
GitLab
From afce71ff6daa9c0f852df0727fe32c6fb107f0fa Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Tue, 3 Jan 2023 15:49:46 -0800
Subject: [PATCH 0526/1167] drm/i915: Fix potential context UAFs
gem_context_register() makes the context visible to userspace, and which
point a separate thread can trigger the I915_GEM_CONTEXT_DESTROY ioctl.
So we need to ensure that nothing uses the ctx ptr after this. And we
need to ensure that adding the ctx to the xarray is the *last* thing
that gem_context_register() does with the ctx pointer.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Fixes: eb4dedae920a ("drm/i915/gem: Delay tracking the GEM context until it is registered")
Fixes: a4c1cdd34e2c ("drm/i915/gem: Delay context creation (v3)")
Fixes: 49bd54b390c2 ("drm/i915: Track all user contexts per client")
Cc: <stable@vger.kernel.org> # v5.10+
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
[tursulin: Stable and fixes tags add/tidy.]
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230103234948.1218393-1-robdclark@gmail.com
(cherry picked from commit bed4b455cf5374e68879be56971c1da563bcd90c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_context.c | 24 +++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 7f2831efc798b..6250de9b9196c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1688,6 +1688,10 @@ void i915_gem_init__contexts(struct drm_i915_private *i915)
init_contexts(&i915->gem.contexts);
}
+/*
+ * Note that this implicitly consumes the ctx reference, by placing
+ * the ctx in the context_xa.
+ */
static void gem_context_register(struct i915_gem_context *ctx,
struct drm_i915_file_private *fpriv,
u32 id)
@@ -1703,10 +1707,6 @@ static void gem_context_register(struct i915_gem_context *ctx,
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
- /* And finally expose ourselves to userspace via the idr */
- old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
- WARN_ON(old);
-
spin_lock(&ctx->client->ctx_lock);
list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
spin_unlock(&ctx->client->ctx_lock);
@@ -1714,6 +1714,10 @@ static void gem_context_register(struct i915_gem_context *ctx,
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
+
+ /* And finally expose ourselves to userspace via the idr */
+ old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
+ WARN_ON(old);
}
int i915_gem_context_open(struct drm_i915_private *i915,
@@ -2199,14 +2203,22 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv,
if (IS_ERR(ctx))
return ctx;
+ /*
+ * One for the xarray and one for the caller. We need to grab
+ * the reference *prior* to making the ctx visble to userspace
+ * in gem_context_register(), as at any point after that
+ * userspace can try to race us with another thread destroying
+ * the context under our feet.
+ */
+ i915_gem_context_get(ctx);
+
gem_context_register(ctx, file_priv, id);
old = xa_erase(&file_priv->proto_context_xa, id);
GEM_BUG_ON(old != pc);
proto_context_close(file_priv->dev_priv, pc);
- /* One for the xarray and one for the caller */
- return i915_gem_context_get(ctx);
+ return ctx;
}
struct i915_gem_context *
--
GitLab
From 4e4ff23a35ee3a145fbc8378ecfeaab2d235cddd Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 9 Jan 2023 15:47:25 +0000
Subject: [PATCH 0527/1167] arm64/mm: Define dummy pud_user_exec() when using
2-level page-table
With only two levels of page-table, the generic 'pud_*' macros are
implemented using dummy operations in pgtable-nopmd.h. Since commit
730a11f982e6 ("arm64/mm: add pud_user_exec() check in
pud_user_accessible_page()"), pud_user_accessible_page() unconditionally
calls pud_user_exec(), which is an arm64-specific helper and therefore
isn't defined by pgtable-nopmd.h. This results in a build failure for
configurations with only two levels of page table:
arch/arm64/include/asm/pgtable.h: In function 'pud_user_accessible_page':
>> arch/arm64/include/asm/pgtable.h:870:51: error: implicit declaration of function 'pud_user_exec'; did you mean 'pmd_user_exec'? [-Werror=implicit-function-declaration]
870 | return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
| ^~~~~~~~~~~~~
| pmd_user_exec
Fix the problem by defining pud_user_exec() as pud_user() in this case.
Link: https://lore.kernel.org/r/202301080515.z6zEksU4-lkp@intel.com
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/include/asm/pgtable.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 02ed5c0adf97a..65e78999c75d7 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud)
#else
#define pud_page_paddr(pud) ({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */
/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
#define pmd_set_fixmap(addr) NULL
--
GitLab
From 68a63a412d18bd2e2577c8928139f92541afa7a6 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@arm.com>
Date: Mon, 9 Jan 2023 12:27:43 +0000
Subject: [PATCH 0528/1167] arm64: Fix build with CC=clang, CONFIG_FTRACE=y and
CONFIG_STACK_TRACER=y
commit 45bd8951806e ("arm64: Improve HAVE_DYNAMIC_FTRACE_WITH_REGS
selection for clang") fixed the build with the above combination by
splitting HAVE_DYNAMIC_FTRACE_WITH_REGS into separate checks for
Clang and GCC.
commit 26299b3f6ba2 ("ftrace: arm64: move from REGS to ARGS") added the
GCC only check "-fpatchable-function-entry=2" back in unconditionally
which breaks the build.
Remove the unconditional check, because the conditional ones were also
updated to _ARGS in the above commit, so they work correctly on their
own.
Fixes: 26299b3f6ba2 ("ftrace: arm64: move from REGS to ARGS")
Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20230109122744.1904852-1-james.clark@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
arch/arm64/Kconfig | 2 --
1 file changed, 2 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cf6d1cd8b6dc5..c5ccca26a4087 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -184,8 +184,6 @@ config ARM64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
- if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
--
GitLab
From cd2d0d45a3d2c199344305a1e8fed42347cf4bec Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Jan 2023 09:30:53 +0100
Subject: [PATCH 0529/1167] ARM: pxa: enable PXA310/PXA320 for DT-only build
After commit b5aaaa666a85 ("ARM: pxa: add Kconfig dependencies for
ATAGS based boards"), the default PXA build no longer includes support
for the board files that are considered unused.
As a side-effect of this, the PXA310 and PXA320 support is not built
into the kernel any more, even though it should work in principle as
long as the symbols are enabled. As Robert points out, there are dts
files for zylonite and cm-x300, though those have not made it into the
mainline kernel.
Link: https://lore.kernel.org/linux-arm-kernel/m2sfglh02h.fsf@free.fr/
Reported-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/mach-pxa/Kconfig | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index b90d98bae68d7..03e25af6f48c9 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -45,6 +45,8 @@ config MACH_PXA27X_DT
config MACH_PXA3XX_DT
bool "Support PXA3xx platforms from device tree"
select CPU_PXA300
+ select CPU_PXA310
+ select CPU_PXA320
select PINCTRL
select POWER_SUPPLY
select PXA3xx
--
GitLab
From 70051cffb31b5ee09096351c3b41fcae6f89de31 Mon Sep 17 00:00:00 2001
From: Jaroslav Kysela <perex@perex.cz>
Date: Mon, 9 Jan 2023 16:12:49 +0100
Subject: [PATCH 0530/1167] ALSA: control-led: use strscpy in set_led_id()
The use of strncpy() in the set_led_id() was incorrect.
The len variable should use 'min(sizeof(buf2) - 1, count)'
expression.
Use strscpy() function to simplify things and handle the error gracefully.
Fixes: a135dfb5de15 ("ALSA: led control - add sysfs kcontrol LED marking layer")
Reported-by: yang.yang29@zte.com.cn
Link: https://lore.kernel.org/alsa-devel/202301091945513559977@zte.com.cn/
Cc: <stable@vger.kernel.org>
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/core/control_led.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/sound/core/control_led.c b/sound/core/control_led.c
index f975cc85772bb..3cadd40100f3e 100644
--- a/sound/core/control_led.c
+++ b/sound/core/control_led.c
@@ -530,12 +530,11 @@ static ssize_t set_led_id(struct snd_ctl_led_card *led_card, const char *buf, si
bool attach)
{
char buf2[256], *s, *os;
- size_t len = max(sizeof(s) - 1, count);
struct snd_ctl_elem_id id;
int err;
- strncpy(buf2, buf, len);
- buf2[len] = '\0';
+ if (strscpy(buf2, buf, sizeof(buf2)) < 0)
+ return -E2BIG;
memset(&id, 0, sizeof(id));
id.iface = SNDRV_CTL_ELEM_IFACE_MIXER;
s = buf2;
--
GitLab
From cad90e5381d840cf2296aaac9b3eff71a30b7c5b Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Tue, 20 Dec 2022 20:13:23 +1000
Subject: [PATCH 0531/1167] objtool: Tolerate STT_NOTYPE symbols at end of
section
Hand-written asm often contains non-function symbols in executable
sections. _end symbols for finding the size of instruction blocks
for runtime processing is one such usage.
optprobe_template_end is one example that causes the warning:
objtool: optprobe_template_end(): can't find starting instruction
This is because the symbol happens to be at the end of the file (and
therefore end of a section in the object file).
So ignore end-of-section STT_NOTYPE symbols instead of bailing out
because an instruction can't be found. While we're here, add a more
descriptive warning for STT_FUNC symbols found at the end of a
section.
[ This also solves a PowerPC regression reported by Sathvika Vasireddy. ]
Reported-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Reported-by: Sathvika Vasireddy <sv@linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Sathvika Vasireddy <sv@linux.ibm.com>
Link: https://lore.kernel.org/r/20221220101323.3119939-1-npiggin@gmail.com
---
tools/objtool/check.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4350be739f4fa..4b7c8b33069e5 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -427,6 +427,15 @@ static int decode_instructions(struct objtool_file *file)
if (func->type != STT_NOTYPE && func->type != STT_FUNC)
continue;
+ if (func->offset == sec->sh.sh_size) {
+ /* Heuristic: likely an "end" symbol */
+ if (func->type == STT_NOTYPE)
+ continue;
+ WARN("%s(): STT_FUNC at end of section",
+ func->name);
+ return -1;
+ }
+
if (func->return_thunk || func->alias != func)
continue;
--
GitLab
From feaf75658783a919410f8c2039dbc24b6a29603d Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@linux.ibm.com>
Date: Mon, 9 Jan 2023 08:54:37 +0100
Subject: [PATCH 0532/1167] nolibc: fix fd_set type
The kernel uses unsigned long for the fd_set bitmap,
but nolibc use u32. This works fine on little endian
machines, but fails on big endian. Convert to unsigned
long to fix this.
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/types.h | 53 ++++++++++++++++++++----------------
1 file changed, 30 insertions(+), 23 deletions(-)
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
index 959997034e553..300e0ff1cd58c 100644
--- a/tools/include/nolibc/types.h
+++ b/tools/include/nolibc/types.h
@@ -89,39 +89,46 @@
#define EXIT_SUCCESS 0
#define EXIT_FAILURE 1
+#define FD_SETIDXMASK (8 * sizeof(unsigned long))
+#define FD_SETBITMASK (8 * sizeof(unsigned long)-1)
+
/* for select() */
typedef struct {
- uint32_t fd32[(FD_SETSIZE + 31) / 32];
+ unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK];
} fd_set;
-#define FD_CLR(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+#define FD_CLR(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] &= \
+ ~(1U << (__fd & FX_SETBITMASK)); \
} while (0)
-#define FD_SET(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] |= 1U << (__fd & 31); \
+#define FD_SET(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] |= \
+ 1 << (__fd & FD_SETBITMASK); \
} while (0)
-#define FD_ISSET(fd, set) ({ \
- fd_set *__set = (set); \
- int __fd = (fd); \
- int __r = 0; \
- if (__fd >= 0) \
- __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
- __r; \
+#define FD_ISSET(fd, set) ({ \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ int __r = 0; \
+ if (__fd >= 0) \
+ __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \
+1U << (__fd & FD_SET_BITMASK)); \
+ __r; \
})
-#define FD_ZERO(set) do { \
- fd_set *__set = (set); \
- int __idx; \
- for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
- __set->fd32[__idx] = 0; \
+#define FD_ZERO(set) do { \
+ fd_set *__set = (set); \
+ int __idx; \
+ int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\
+ for (__idx = 0; __idx < __size; __idx++) \
+ __set->fds[__idx] = 0; \
} while (0)
/* for poll() */
--
GitLab
From 16f5cea74179b5795af7ce359971f5128d10f80e Mon Sep 17 00:00:00 2001
From: Warner Losh <imp@bsdimp.com>
Date: Mon, 9 Jan 2023 08:54:38 +0100
Subject: [PATCH 0533/1167] tools/nolibc: Fix S_ISxxx macros
The mode field has the type encoded as an value in a field, not as a bit
mask. Mask the mode with S_IFMT instead of each type to test. Otherwise,
false positives are possible: eg S_ISDIR will return true for block
devices because S_IFDIR = 0040000 and S_IFBLK = 0060000 since mode is
masked with S_IFDIR instead of S_IFMT. These macros now match the
similar definitions in tools/include/uapi/linux/stat.h.
Signed-off-by: Warner Losh <imp@bsdimp.com>
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/types.h | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
index 300e0ff1cd58c..f1d64fca7cf05 100644
--- a/tools/include/nolibc/types.h
+++ b/tools/include/nolibc/types.h
@@ -26,13 +26,13 @@
#define S_IFSOCK 0140000
#define S_IFMT 0170000
-#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
-#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
-#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
-#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
-#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
-#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
-#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK)
/* dirent types */
#define DT_UNKNOWN 0x0
--
GitLab
From 184177c3d6e023da934761e198c281344d7dd65b Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 9 Jan 2023 08:54:39 +0100
Subject: [PATCH 0534/1167] tools/nolibc: restore mips branch ordering in the
_start block
Depending on the compiler used and the optimization options, the sbrk()
test was crashing, both on real hardware (mips-24kc) and in qemu. One
such example is kernel.org toolchain in version 11.3 optimizing at -Os.
Inspecting the sys_brk() call shows the following code:
0040047c <sys_brk>:
40047c: 24020fcd li v0,4045
400480: 27bdffe0 addiu sp,sp,-32
400484: 0000000c syscall
400488: 27bd0020 addiu sp,sp,32
40048c: 10e00001 beqz a3,400494 <sys_brk+0x18>
400490: 00021023 negu v0,v0
400494: 03e00008 jr ra
It is obviously wrong, the "negu" instruction is placed in beqz's
delayed slot, and worse, there's no nop nor instruction after the
return, so the next function's first instruction (addiu sip,sip,-32)
will also be executed as part of the delayed slot that follows the
return.
This is caused by the ".set noreorder" directive in the _start block,
that applies to the whole program. The compiler emits code without the
delayed slots and relies on the compiler to swap instructions when this
option is not set. Removing the option would require to change the
startup code in a way that wouldn't make it look like the resulting
code, which would not be easy to debug. Instead let's just save the
default ordering before changing it, and restore it at the end of the
_start block. Now the code is correct:
0040047c <sys_brk>:
40047c: 24020fcd li v0,4045
400480: 27bdffe0 addiu sp,sp,-32
400484: 0000000c syscall
400488: 10e00002 beqz a3,400494 <sys_brk+0x18>
40048c: 27bd0020 addiu sp,sp,32
400490: 00021023 negu v0,v0
400494: 03e00008 jr ra
400498: 00000000 nop
Fixes: 66b6f755ad45 ("rcutorture: Import a copy of nolibc") #5.0
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/arch-mips.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
index 5fc5b8029bff9..7380093ba9e7d 100644
--- a/tools/include/nolibc/arch-mips.h
+++ b/tools/include/nolibc/arch-mips.h
@@ -192,6 +192,7 @@ struct sys_stat_struct {
__asm__ (".section .text\n"
".weak __start\n"
".set nomips16\n"
+ ".set push\n"
".set noreorder\n"
".option pic0\n"
".ent __start\n"
@@ -210,6 +211,7 @@ __asm__ (".section .text\n"
"li $v0, 4001\n" // NR_exit == 4001
"syscall\n"
".end __start\n"
+ ".set pop\n"
"");
#endif // _NOLIBC_ARCH_MIPS_H
--
GitLab
From 55abdd1f5e1e07418bf4a46c233a92f83cb5ae97 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 9 Jan 2023 08:54:40 +0100
Subject: [PATCH 0535/1167] tools/nolibc: fix missing includes causing build
issues at -O0
After the nolibc includes were split to facilitate portability from
standard libcs, programs that include only what they need may miss
some symbols which are needed by libgcc. This is the case for raise()
which is needed by the divide by zero code in some architectures for
example.
Regardless, being able to include only the apparently needed files is
convenient.
Instead of trying to move all exported definitions to a single file,
since this can change over time, this patch takes another approach
consisting in including the nolibc header at the end of all standard
include files. This way their types and functions are already known
at the moment of inclusion, and including any single one of them is
sufficient to bring all the required ones.
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/ctype.h | 3 +++
tools/include/nolibc/errno.h | 3 +++
tools/include/nolibc/signal.h | 3 +++
tools/include/nolibc/stdio.h | 3 +++
tools/include/nolibc/stdlib.h | 3 +++
tools/include/nolibc/string.h | 3 +++
tools/include/nolibc/sys.h | 2 ++
tools/include/nolibc/time.h | 3 +++
tools/include/nolibc/types.h | 3 +++
tools/include/nolibc/unistd.h | 3 +++
10 files changed, 29 insertions(+)
diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h
index e3000b2992d7b..6f90706d06442 100644
--- a/tools/include/nolibc/ctype.h
+++ b/tools/include/nolibc/ctype.h
@@ -96,4 +96,7 @@ int ispunct(int c)
return isgraph(c) && !isalnum(c);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_CTYPE_H */
diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h
index 06893d6dfb7a6..9dc4919c769b7 100644
--- a/tools/include/nolibc/errno.h
+++ b/tools/include/nolibc/errno.h
@@ -24,4 +24,7 @@ static int errno;
*/
#define MAX_ERRNO 4095
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_ERRNO_H */
diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h
index ef47e71e2be37..137552216e469 100644
--- a/tools/include/nolibc/signal.h
+++ b/tools/include/nolibc/signal.h
@@ -19,4 +19,7 @@ int raise(int signal)
return sys_kill(sys_getpid(), signal);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_SIGNAL_H */
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
index a3cebc4bc3ac4..96ac8afc5aeed 100644
--- a/tools/include/nolibc/stdio.h
+++ b/tools/include/nolibc/stdio.h
@@ -303,4 +303,7 @@ void perror(const char *msg)
fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDIO_H */
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
index 92378c4b96605..a24000d1e8222 100644
--- a/tools/include/nolibc/stdlib.h
+++ b/tools/include/nolibc/stdlib.h
@@ -419,4 +419,7 @@ char *u64toa(uint64_t in)
return itoa_buffer;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDLIB_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index ad97c0d522b8e..0932db3817d2c 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -285,4 +285,7 @@ char *strrchr(const char *s, int c)
return (char *)ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STRING_H */
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
index ce3ee03aa6794..78473d34e27cd 100644
--- a/tools/include/nolibc/sys.h
+++ b/tools/include/nolibc/sys.h
@@ -1243,5 +1243,7 @@ ssize_t write(int fd, const void *buf, size_t count)
return ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
#endif /* _NOLIBC_SYS_H */
diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h
index d18b7661fdd71..84655361b9ad2 100644
--- a/tools/include/nolibc/time.h
+++ b/tools/include/nolibc/time.h
@@ -25,4 +25,7 @@ time_t time(time_t *tptr)
return tv.tv_sec;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TIME_H */
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
index f1d64fca7cf05..fbbc0e68c001b 100644
--- a/tools/include/nolibc/types.h
+++ b/tools/include/nolibc/types.h
@@ -209,4 +209,7 @@ struct stat {
})
#endif
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TYPES_H */
diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h
index 1c25e20ee3606..1cfcd52106a42 100644
--- a/tools/include/nolibc/unistd.h
+++ b/tools/include/nolibc/unistd.h
@@ -51,4 +51,7 @@ int tcsetpgrp(int fd, pid_t pid)
return ioctl(fd, TIOCSPGRP, &pid);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_UNISTD_H */
--
GitLab
From 1bfbe1f3e96720daf185f03d101f072d69753f88 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 9 Jan 2023 08:54:41 +0100
Subject: [PATCH 0536/1167] tools/nolibc: prevent gcc from making memset() loop
over itself
When building on ARM in thumb mode with gcc-11.3 at -O2 or -O3,
nolibc-test segfaults during the select() tests. It turns out that at
this level, gcc recognizes an opportunity for using memset() to zero
the fd_set, but it miscompiles it because it also recognizes a memset
pattern as well, and decides to call memset() from the memset() code:
000122bc <memset>:
122bc: b510 push {r4, lr}
122be: 0004 movs r4, r0
122c0: 2a00 cmp r2, #0
122c2: d003 beq.n 122cc <memset+0x10>
122c4: 23ff movs r3, #255 ; 0xff
122c6: 4019 ands r1, r3
122c8: f7ff fff8 bl 122bc <memset>
122cc: 0020 movs r0, r4
122ce: bd10 pop {r4, pc}
Simply placing an empty asm() statement inside the loop suffices to
avoid this.
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/string.h | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index 0932db3817d2c..fffdaf6ff4673 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -88,8 +88,11 @@ void *memset(void *dst, int b, size_t len)
{
char *p = dst;
- while (len--)
+ while (len--) {
+ /* prevent gcc from recognizing memset() here */
+ asm volatile("");
*(p++) = b;
+ }
return dst;
}
--
GitLab
From 00b18da4089330196906b9fe075c581c17eb726c Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 9 Jan 2023 08:54:42 +0100
Subject: [PATCH 0537/1167] tools/nolibc: fix the O_* fcntl/open macro
definitions for riscv
When RISCV port was imported in 5.2, the O_* macros were taken with
their octal value and written as-is in hex, resulting in the getdents64()
to fail in nolibc-test.
Fixes: 582e84f7b779 ("tool headers nolibc: add RISCV support") #5.2
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
tools/include/nolibc/arch-riscv.h | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
index ba04771cb3a34..a3bdd9803f8cb 100644
--- a/tools/include/nolibc/arch-riscv.h
+++ b/tools/include/nolibc/arch-riscv.h
@@ -11,13 +11,13 @@
#define O_RDONLY 0
#define O_WRONLY 1
#define O_RDWR 2
-#define O_CREAT 0x100
-#define O_EXCL 0x200
-#define O_NOCTTY 0x400
-#define O_TRUNC 0x1000
-#define O_APPEND 0x2000
-#define O_NONBLOCK 0x4000
-#define O_DIRECTORY 0x200000
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
struct sys_stat_struct {
unsigned long st_dev; /* Device. */
--
GitLab
From 29cf28235e3e57e0af01ae29db57a75f87a2ada8 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Fri, 6 Jan 2023 20:28:30 -0300
Subject: [PATCH 0538/1167] cifs: fix file info setting in
cifs_query_path_info()
We missed to set file info when CIFSSMBQPathInfo() returned 0, thus
leaving cifs_open_info_data::fi unset.
Fix this by setting cifs_open_info_data::fi when either
CIFSSMBQPathInfo() or SMBQueryInformation() succeed.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216881
Fixes: 76894f3e2f71 ("cifs: improve symlink handling for smb2+")
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb1ops.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 50480751e521c..5fe2c2f8ef417 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -562,17 +562,20 @@ static int cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls,
cifs_remap(cifs_sb));
- if (!rc)
- move_cifs_info_to_smb2(&data->fi, &fi);
*adjustTZ = true;
}
- if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) {
+ if (!rc) {
int tmprc;
int oplock = 0;
struct cifs_fid fid;
struct cifs_open_parms oparms;
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE))
+ return 0;
+
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = FILE_READ_ATTRIBUTES;
--
GitLab
From ba5d4c1596cada37793d405dd18d695cd3508902 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Fri, 6 Jan 2023 13:34:36 -0300
Subject: [PATCH 0539/1167] cifs: fix file info setting in cifs_open_file()
In cifs_open_file(), @buf must hold a pointer to a cifs_open_info_data
structure which is passed by cifs_nt_open(), so assigning @buf
directly to @fi was obviously wrong.
Fix this by passing a valid FILE_ALL_INFO structure to SMBLegacyOpen()
and CIFS_open(), and then copy the set structure to the corresponding
cifs_open_info_data::fi field with move_cifs_info_to_smb2() helper.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216889
Fixes: 76894f3e2f71 ("cifs: improve symlink handling for smb2+")
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb1ops.c | 54 ++++++++++++++++++++++++-----------------------
1 file changed, 28 insertions(+), 26 deletions(-)
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 5fe2c2f8ef417..4cb364454e130 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -719,17 +719,25 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path,
static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock,
void *buf)
{
- FILE_ALL_INFO *fi = buf;
+ struct cifs_open_info_data *data = buf;
+ FILE_ALL_INFO fi = {};
+ int rc;
if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS))
- return SMBLegacyOpen(xid, oparms->tcon, oparms->path,
- oparms->disposition,
- oparms->desired_access,
- oparms->create_options,
- &oparms->fid->netfid, oplock, fi,
- oparms->cifs_sb->local_nls,
- cifs_remap(oparms->cifs_sb));
- return CIFS_open(xid, oparms, oplock, fi);
+ rc = SMBLegacyOpen(xid, oparms->tcon, oparms->path,
+ oparms->disposition,
+ oparms->desired_access,
+ oparms->create_options,
+ &oparms->fid->netfid, oplock, &fi,
+ oparms->cifs_sb->local_nls,
+ cifs_remap(oparms->cifs_sb));
+ else
+ rc = CIFS_open(xid, oparms, oplock, &fi);
+
+ if (!rc && data)
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ return rc;
}
static void
@@ -1053,7 +1061,7 @@ cifs_make_node(unsigned int xid, struct inode *inode,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct inode *newinode = NULL;
int rc = -EPERM;
- FILE_ALL_INFO *buf = NULL;
+ struct cifs_open_info_data buf = {};
struct cifs_io_parms io_parms;
__u32 oplock = 0;
struct cifs_fid fid;
@@ -1085,14 +1093,14 @@ cifs_make_node(unsigned int xid, struct inode *inode,
cifs_sb->local_nls,
cifs_remap(cifs_sb));
if (rc)
- goto out;
+ return rc;
rc = cifs_get_inode_info_unix(&newinode, full_path,
inode->i_sb, xid);
if (rc == 0)
d_instantiate(dentry, newinode);
- goto out;
+ return rc;
}
/*
@@ -1100,19 +1108,13 @@ cifs_make_node(unsigned int xid, struct inode *inode,
* support block and char device (no socket & fifo)
*/
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
- goto out;
+ return rc;
if (!S_ISCHR(mode) && !S_ISBLK(mode))
- goto out;
+ return rc;
cifs_dbg(FYI, "sfu compat create special file\n");
- buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
- if (buf == NULL) {
- rc = -ENOMEM;
- goto out;
- }
-
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = GENERIC_WRITE;
@@ -1127,21 +1129,21 @@ cifs_make_node(unsigned int xid, struct inode *inode,
oplock = REQ_OPLOCK;
else
oplock = 0;
- rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf);
+ rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
if (rc)
- goto out;
+ return rc;
/*
* BB Do not bother to decode buf since no local inode yet to put
* timestamps in, but we can reuse it safely.
*/
- pdev = (struct win_dev *)buf;
+ pdev = (struct win_dev *)&buf.fi;
io_parms.pid = current->tgid;
io_parms.tcon = tcon;
io_parms.offset = 0;
io_parms.length = sizeof(struct win_dev);
- iov[1].iov_base = buf;
+ iov[1].iov_base = &buf.fi;
iov[1].iov_len = sizeof(struct win_dev);
if (S_ISCHR(mode)) {
memcpy(pdev->type, "IntxCHR", 8);
@@ -1160,8 +1162,8 @@ cifs_make_node(unsigned int xid, struct inode *inode,
d_drop(dentry);
/* FIXME: add code here to set EAs */
-out:
- kfree(buf);
+
+ cifs_free_open_info(&buf);
return rc;
}
--
GitLab
From 75b58cf5ce21650c1b3b88d8310f3415ce905018 Mon Sep 17 00:00:00 2001
From: Klaus Kudielka <klaus.kudielka@gmail.com>
Date: Sat, 7 Jan 2023 15:41:48 +0100
Subject: [PATCH 0540/1167] Revert "ARM: dts: armada-38x: Fix compatible string
for gpios"
This reverts commit c4de4667f15d04ef5920bacf41e514ec7d1ef03d, which causes
a regression on Turris Omnia (Armada 385): GPIO interrupts cease to work,
ending up in the DSA switch being non-functional.
The blamed commit is incorrect in the first place:
If compatible = "marvell,armadaxp-gpio", the second (address, size) pair
of the reg property must to point to the per-CPU interrupt registers
<0x18800 0x30> / <0x18840 0x30>, and not to the blink enable registers
<0x181c0 0x08> / <0x181c8 0x08>.
But even fixing that leaves the GPIO interrupts broken on the Omnia.
Furthermore:
Commit 5f79c651e81e explains very well, why the gpio-mvebu driver does not
work reliably with per-CPU interrupts.
Commit 988c8c0cd04d deprecates compatible = marvell,armadaxp-gpio for this
reason.
Fixes: c4de4667f15d ("ARM: dts: armada-38x: Fix compatible string for gpios")
Reported-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Link: https://lore.kernel.org/r/f24474e70c1a4e9692bd596ef6d97ceda9511245.camel@gmail.com/
Signed-off-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
arch/arm/boot/dts/armada-38x.dtsi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 12933eff419ff..446861b6b17b2 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -304,7 +304,7 @@ spdif_pins: spdif-pins {
};
gpio0: gpio@18100 {
- compatible = "marvell,armadaxp-gpio",
+ compatible = "marvell,armada-370-gpio",
"marvell,orion-gpio";
reg = <0x18100 0x40>, <0x181c0 0x08>;
reg-names = "gpio", "pwm";
@@ -323,7 +323,7 @@ gpio0: gpio@18100 {
};
gpio1: gpio@18140 {
- compatible = "marvell,armadaxp-gpio",
+ compatible = "marvell,armada-370-gpio",
"marvell,orion-gpio";
reg = <0x18140 0x40>, <0x181c8 0x08>;
reg-names = "gpio", "pwm";
--
GitLab
From a4d5d2ef5b1f6cddee0fec35d86404df148b9074 Mon Sep 17 00:00:00 2001
From: Klaus Kudielka <klaus.kudielka@gmail.com>
Date: Sat, 7 Jan 2023 15:41:49 +0100
Subject: [PATCH 0541/1167] Revert "ARM: dts: armada-39x: Fix compatible string
for gpios"
This reverts commit d10886a4e6f85ee18d47a1066a52168461370ded.
If compatible = "marvell,armadaxp-gpio", the reg property requires a
second (address, size) pair, which points to the per-CPU interrupt
registers <0x18800 0x30> / <0x18840 0x30>.
Furthermore:
Commit 5f79c651e81e explains very well, why the gpio-mvebu driver does not
work reliably with per-CPU interrupts.
Commit 988c8c0cd04d deprecates compatible = marvell,armadaxp-gpio for this
reason.
Signed-off-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
arch/arm/boot/dts/armada-39x.dtsi | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi
index 1e05208d9f341..9d1cac49c022f 100644
--- a/arch/arm/boot/dts/armada-39x.dtsi
+++ b/arch/arm/boot/dts/armada-39x.dtsi
@@ -213,7 +213,7 @@ nand_pins: nand-pins {
};
gpio0: gpio@18100 {
- compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio";
+ compatible = "marvell,orion-gpio";
reg = <0x18100 0x40>;
ngpios = <32>;
gpio-controller;
@@ -227,7 +227,7 @@ gpio0: gpio@18100 {
};
gpio1: gpio@18140 {
- compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio";
+ compatible = "marvell,orion-gpio";
reg = <0x18140 0x40>;
ngpios = <28>;
gpio-controller;
--
GitLab
From 2ec1b17f745b08526220f3c169d2eb9799a9be39 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 6 Jan 2023 09:39:49 -0700
Subject: [PATCH 0542/1167] cxl: fix cxl_report_and_clear() RAS UE addr
mis-assignment
'addr' that contains RAS UE register address is re-assigned to
RAS_CAP_CONTROL offset if there are multiple UE errors. Use different addr
variable to avoid the reassignment mistake.
Fixes: 2905cb5236cb ("cxl/pci: Add (hopeful) error handling support")
Reported-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/167302318779.580155.15233596744650706167.stgit@djiang5-mobl3.local
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/cxl/pci.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 33083a522fd1c..258004f34281a 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -554,8 +554,11 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
/* If multiple errors, log header points to first error from ctrl reg */
if (hweight32(status) > 1) {
- addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
- fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr)));
+ void __iomem *rcc_addr =
+ cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
+
+ fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
+ readl(rcc_addr)));
} else {
fe = status;
}
--
GitLab
From 0be7ed8e7eb15282b5d0f6fdfea884db594ea9bf Mon Sep 17 00:00:00 2001
From: Luben Tuikov <luben.tuikov@amd.com>
Date: Wed, 4 Jan 2023 17:09:02 -0500
Subject: [PATCH 0543/1167] drm/amdgpu: Fix potential NULL dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Fix potential NULL dereference, in the case when "man", the resource manager
might be NULL, when/if we print debug information.
Cc: Alex Deucher <Alexander.Deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: AMD Graphics <amd-gfx@lists.freedesktop.org>
Cc: Dan Carpenter <error27@gmail.com>
Cc: kernel test robot <lkp@intel.com>
Fixes: 7554886daa31ea ("drm/amdgpu: Fix size validation for non-exclusive domains (v4)")
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 4e684c2afc709..25a68d8888e0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev,
return true;
fail:
- DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
- man->size);
+ if (man)
+ DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+ man->size);
return false;
}
--
GitLab
From 1923bc5a56daeeabd7e9093bad2febcd6af2416a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 27 Dec 2022 15:49:17 -0600
Subject: [PATCH 0544/1167] drm/amd: Delay removal of the firmware framebuffer
Removing the firmware framebuffer from the driver means that even
if the driver doesn't support the IP blocks in a GPU it will no
longer be functional after the driver fails to initialize.
This change will ensure that unsupported IP blocks at least cause
the driver to work with the EFI framebuffer.
Cc: stable@vger.kernel.org
Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 6 ------
2 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index afe6af9c01385..2f28a8c02f641 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -36,6 +36,7 @@
#include <generated/utsrelease.h>
#include <linux/pci-p2pdma.h>
+#include <drm/drm_aperture.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_probe_helper.h>
@@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
#define AMDGPU_MAX_RETRY_LIMIT 2
#define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
+static const struct drm_driver amdgpu_kms_driver;
+
const char *amdgpu_asic_name[] = {
"TAHITI",
"PITCAIRN",
@@ -3687,6 +3690,11 @@ int amdgpu_device_init(struct amdgpu_device *adev,
if (r)
return r;
+ /* Get rid of things like offb */
+ r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
+ if (r)
+ return r;
+
/* Enable TMZ based on IP_VERSION */
amdgpu_gmc_tmz_set(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 1353ffd089882..cd4caaa295282 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -23,7 +23,6 @@
*/
#include <drm/amdgpu_drm.h>
-#include <drm/drm_aperture.h>
#include <drm/drm_drv.h>
#include <drm/drm_fbdev_generic.h>
#include <drm/drm_gem.h>
@@ -2122,11 +2121,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
}
#endif
- /* Get rid of things like offb */
- ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
- if (ret)
- return ret;
-
adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
if (IS_ERR(adev))
return PTR_ERR(adev);
--
GitLab
From 99f1a36c90a7524972be5a028424c57fa17753ee Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Fri, 6 Jan 2023 14:04:15 +0800
Subject: [PATCH 0545/1167] drm/amdgpu: Fixed bug on error when unloading
amdgpu
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Fixed bug on error when unloading amdgpu.
The error message is as follows:
[ 377.706202] kernel BUG at drivers/gpu/drm/drm_buddy.c:278!
[ 377.706215] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 377.706222] CPU: 4 PID: 8610 Comm: modprobe Tainted: G IOE 6.0.0-thomas #1
[ 377.706231] Hardware name: ASUS System Product Name/PRIME Z390-A, BIOS 2004 11/02/2021
[ 377.706238] RIP: 0010:drm_buddy_free_block+0x26/0x30 [drm_buddy]
[ 377.706264] Code: 00 00 00 90 0f 1f 44 00 00 48 8b 0e 89 c8 25 00 0c 00 00 3d 00 04 00 00 75 10 48 8b 47 18 48 d3 e0 48 01 47 28 e9 fa fe ff ff <0f> 0b 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 55 48 89 f5 53
[ 377.706282] RSP: 0018:ffffad2dc4683cb8 EFLAGS: 00010287
[ 377.706289] RAX: 0000000000000000 RBX: ffff8b1743bd5138 RCX: 0000000000000000
[ 377.706297] RDX: ffff8b1743bd5160 RSI: ffff8b1743bd5c78 RDI: ffff8b16d1b25f70
[ 377.706304] RBP: ffff8b1743bd59e0 R08: 0000000000000001 R09: 0000000000000001
[ 377.706311] R10: ffff8b16c8572400 R11: ffffad2dc4683cf0 R12: ffff8b16d1b25f70
[ 377.706318] R13: ffff8b16d1b25fd0 R14: ffff8b1743bd59c0 R15: ffff8b16d1b25f70
[ 377.706325] FS: 00007fec56c72c40(0000) GS:ffff8b1836500000(0000) knlGS:0000000000000000
[ 377.706334] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 377.706340] CR2: 00007f9b88c1ba50 CR3: 0000000110450004 CR4: 00000000003706e0
[ 377.706347] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 377.706354] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 377.706361] Call Trace:
[ 377.706365] <TASK>
[ 377.706369] drm_buddy_free_list+0x2a/0x60 [drm_buddy]
[ 377.706376] amdgpu_vram_mgr_fini+0xea/0x180 [amdgpu]
[ 377.706572] amdgpu_ttm_fini+0x12e/0x1a0 [amdgpu]
[ 377.706650] amdgpu_bo_fini+0x22/0x90 [amdgpu]
[ 377.706727] gmc_v11_0_sw_fini+0x26/0x30 [amdgpu]
[ 377.706821] amdgpu_device_fini_sw+0xa1/0x3c0 [amdgpu]
[ 377.706897] amdgpu_driver_release_kms+0x12/0x30 [amdgpu]
[ 377.706975] drm_dev_release+0x20/0x40 [drm]
[ 377.707006] release_nodes+0x35/0xb0
[ 377.707014] devres_release_all+0x8b/0xc0
[ 377.707020] device_unbind_cleanup+0xe/0x70
[ 377.707027] device_release_driver_internal+0xee/0x160
[ 377.707033] driver_detach+0x44/0x90
[ 377.707039] bus_remove_driver+0x55/0xe0
[ 377.707045] pci_unregister_driver+0x3b/0x90
[ 377.707052] amdgpu_exit+0x11/0x6c [amdgpu]
[ 377.707194] __x64_sys_delete_module+0x142/0x2b0
[ 377.707201] ? fpregs_assert_state_consistent+0x22/0x50
[ 377.707208] ? exit_to_user_mode_prepare+0x3e/0x190
[ 377.707215] do_syscall_64+0x38/0x90
[ 377.707221] entry_SYSCALL_64_after_hwframe+0x63/0xcd
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index faa12146635cf..9fa1d814508a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -882,7 +882,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
kfree(rsv);
list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
- drm_buddy_free_list(&mgr->mm, &rsv->blocks);
+ drm_buddy_free_list(&mgr->mm, &rsv->allocated);
kfree(rsv);
}
drm_buddy_fini(&mgr->mm);
--
GitLab
From f58985620f55580a07d40062c4115d8c9cf6ae27 Mon Sep 17 00:00:00 2001
From: Yuan Can <yuancan@huawei.com>
Date: Wed, 7 Dec 2022 08:55:02 +0000
Subject: [PATCH 0546/1167] ice: Fix potential memory leak in
ice_gnss_tty_write()
The ice_gnss_tty_write() return directly if the write_buf alloc failed,
leaking the cmd_buf.
Fix by free cmd_buf if write_buf alloc failed.
Fixes: d6b98c8d242a ("ice: add write functionality for GNSS TTY")
Signed-off-by: Yuan Can <yuancan@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/ice/ice_gnss.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index b5a7f246d230f..a1915551c69a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -363,6 +363,7 @@ ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count)
/* Send the data out to a hardware port */
write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL);
if (!write_buf) {
+ kfree(cmd_buf);
err = -ENOMEM;
goto exit;
}
--
GitLab
From 40543b3d9d2c13227ecd3aa90a713c201d1d7f09 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Date: Thu, 8 Dec 2022 21:35:52 +0800
Subject: [PATCH 0547/1167] ice: Add check for kzalloc
Add the check for the return value of kzalloc in order to avoid
NULL pointer dereference.
Moreover, use the goto-label to share the clean code.
Fixes: d6b98c8d242a ("ice: add write functionality for GNSS TTY")
Signed-off-by: Jiasheng Jiang <jiasheng@iscas.ac.cn>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/ice/ice_gnss.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index a1915551c69a8..43e199b5b513b 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -461,6 +461,9 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf)
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]),
GFP_KERNEL);
+ if (!pf->gnss_tty_port[i])
+ goto err_out;
+
pf->gnss_serial[i] = NULL;
tty_port_init(pf->gnss_tty_port[i]);
@@ -470,21 +473,23 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf)
err = tty_register_driver(tty_driver);
if (err) {
dev_err(dev, "Failed to register TTY driver err=%d\n", err);
-
- for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
- tty_port_destroy(pf->gnss_tty_port[i]);
- kfree(pf->gnss_tty_port[i]);
- }
- kfree(ttydrv_name);
- tty_driver_kref_put(pf->ice_gnss_tty_driver);
-
- return NULL;
+ goto err_out;
}
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++)
dev_info(dev, "%s%d registered\n", ttydrv_name, i);
return tty_driver;
+
+err_out:
+ while (i--) {
+ tty_port_destroy(pf->gnss_tty_port[i]);
+ kfree(pf->gnss_tty_port[i]);
+ }
+ kfree(ttydrv_name);
+ tty_driver_kref_put(pf->ice_gnss_tty_driver);
+
+ return NULL;
}
/**
--
GitLab
From daec8b54e9445566d003ac46e267e73755b5f55a Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Mon, 12 Dec 2022 14:59:52 +0100
Subject: [PATCH 0548/1167] ARM: footbridge: drop unnecessary inclusion
isa-rtc.c doesn't use any definition from bcd.h, remove its inclusion
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Link: https://lore.kernel.org/r/20221212135953.212303-1-alexandre.belloni@bootlin.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/mach-footbridge/isa-rtc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/arch/arm/mach-footbridge/isa-rtc.c b/arch/arm/mach-footbridge/isa-rtc.c
index b8f741a3a37ea..237b828dd2f10 100644
--- a/arch/arm/mach-footbridge/isa-rtc.c
+++ b/arch/arm/mach-footbridge/isa-rtc.c
@@ -20,7 +20,6 @@
#include <linux/init.h>
#include <linux/mc146818rtc.h>
-#include <linux/bcd.h>
#include <linux/io.h>
#include "common.h"
--
GitLab
From febb985c06cb6f5fac63598c0bffd4fd823d110d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 9 Jan 2023 14:46:10 -0700
Subject: [PATCH 0549/1167] io_uring/poll: add hash if ready poll request can't
complete inline
If we don't, then we may lose access to it completely, leading to a
request leak. This will eventually stall the ring exit process as
well.
Cc: stable@vger.kernel.org
Fixes: 49f1c68e048f ("io_uring: optimise submission side poll_refs")
Reported-and-tested-by: syzbot+6c95df01470a47fc3af4@syzkaller.appspotmail.com
Link: https://lore.kernel.org/io-uring/0000000000009f829805f1ce87b2@google.com/
Suggested-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/poll.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/io_uring/poll.c b/io_uring/poll.c
index ee7da6150ec41..cf6a70bd54e09 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -533,6 +533,14 @@ static bool io_poll_can_finish_inline(struct io_kiocb *req,
return pt->owning || io_poll_get_ownership(req);
}
+static void io_poll_add_hash(struct io_kiocb *req)
+{
+ if (req->flags & REQ_F_HASH_LOCKED)
+ io_poll_req_insert_locked(req);
+ else
+ io_poll_req_insert(req);
+}
+
/*
* Returns 0 when it's handed over for polling. The caller owns the requests if
* it returns non-zero, but otherwise should not touch it. Negative values
@@ -591,18 +599,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req,
if (mask &&
((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) {
- if (!io_poll_can_finish_inline(req, ipt))
+ if (!io_poll_can_finish_inline(req, ipt)) {
+ io_poll_add_hash(req);
return 0;
+ }
io_poll_remove_entries(req);
ipt->result_mask = mask;
/* no one else has access to the req, forget about the ref */
return 1;
}
- if (req->flags & REQ_F_HASH_LOCKED)
- io_poll_req_insert_locked(req);
- else
- io_poll_req_insert(req);
+ io_poll_add_hash(req);
if (mask && (poll->events & EPOLLET) &&
io_poll_can_finish_inline(req, ipt)) {
--
GitLab
From 5a41237ad1d4b62008f93163af1d9b1da90729d8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 9 Jan 2023 17:04:49 -0600
Subject: [PATCH 0550/1167] gcc: disable -Warray-bounds for gcc-11 too
We had already disabled this warning for gcc-12 due to bugs in the value
range analysis, but it turns out we end up having some similar problems
with gcc-11.3 too, so let's disable it there too.
Older gcc versions end up being increasingly less relevant, and
hopefully clang and newer version of gcc (ie gcc-13) end up working
reliably enough that we still get the build coverage even when we
disable this for some versions.
Link: https://lore.kernel.org/all/20221227002941.GA2691687@roeck-us.net/
Link: https://lore.kernel.org/all/D8BDBF66-E44C-45D4-9758-BAAA4F0C1998@kernel.org/
Cc: Kees Cook <kees@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
init/Kconfig | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/init/Kconfig b/init/Kconfig
index 7e5c3ddc341de..0958846b005e1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -894,13 +894,17 @@ config CC_IMPLICIT_FALLTHROUGH
default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
-# Currently, disable gcc-12 array-bounds globally.
+# Currently, disable gcc-11,12 array-bounds globally.
# We may want to target only particular configurations some day.
+config GCC11_NO_ARRAY_BOUNDS
+ def_bool y
+
config GCC12_NO_ARRAY_BOUNDS
def_bool y
config CC_NO_ARRAY_BOUNDS
bool
+ default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS
default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS
#
--
GitLab
From 52531258318ed59a2dc5a43df2eaf0eb1d65438e Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Fri, 16 Dec 2022 15:33:55 -0800
Subject: [PATCH 0551/1167] drm/virtio: Fix GEM handle creation UAF
Userspace can guess the handle value and try to race GEM object creation
with handle close, resulting in a use-after-free if we dereference the
object after dropping the handle's reference. For that reason, dropping
the handle's reference must be done *after* we are done dereferencing
the object.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Fixes: 62fb7a5e1096 ("virtio-gpu: add 3d/virgl support")
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221216233355.542197-2-robdclark@gmail.com
---
drivers/gpu/drm/virtio/virtgpu_ioctl.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 5d05093014ac3..9f4a90493aeac 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -358,10 +358,18 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data,
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */
rc->bo_handle = handle;
+
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
@@ -723,11 +731,18 @@ static int virtio_gpu_resource_create_blob_ioctl(struct drm_device *dev,
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc_blob->res_handle = bo->hw_res_handle;
rc_blob->bo_handle = handle;
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
--
GitLab
From a309c7194e8a2f8bd4539b9449917913f6c2cd50 Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Wed, 7 Dec 2022 12:29:07 -0500
Subject: [PATCH 0552/1167] drm/vmwgfx: Remove rcu locks from user resources
User resource lookups used rcu to avoid two extra atomics. Unfortunately
the rcu paths were buggy and it was easy to make the driver crash by
submitting command buffers from two different threads. Because the
lookups never show up in performance profiles replace them with a
regular spin lock which fixes the races in accesses to those shared
resources.
Fixes kernel oops'es in IGT's vmwgfx execution_buffer stress test and
seen crashes with apps using shared resources.
Fixes: e14c02e6b699 ("drm/vmwgfx: Look up objects without taking a reference")
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Martin Krastev <krastevm@vmware.com>
Reviewed-by: Maaz Mombasawala <mombasawalam@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221207172907.959037-1-zack@kde.org
---
drivers/gpu/drm/vmwgfx/ttm_object.c | 41 +-----
drivers/gpu/drm/vmwgfx/ttm_object.h | 14 --
drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 38 -----
drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 18 +--
drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 176 +++++++++++------------
drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 33 -----
6 files changed, 87 insertions(+), 233 deletions(-)
diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c
index 932b125ebf3d6..ddf8373c1d779 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_object.c
+++ b/drivers/gpu/drm/vmwgfx/ttm_object.c
@@ -254,40 +254,6 @@ void ttm_base_object_unref(struct ttm_base_object **p_base)
kref_put(&base->refcount, ttm_release_base);
}
-/**
- * ttm_base_object_noref_lookup - look up a base object without reference
- * @tfile: The struct ttm_object_file the object is registered with.
- * @key: The object handle.
- *
- * This function looks up a ttm base object and returns a pointer to it
- * without refcounting the pointer. The returned pointer is only valid
- * until ttm_base_object_noref_release() is called, and the object
- * pointed to by the returned pointer may be doomed. Any persistent usage
- * of the object requires a refcount to be taken using kref_get_unless_zero().
- * Iff this function returns successfully it needs to be paired with
- * ttm_base_object_noref_release() and no sleeping- or scheduling functions
- * may be called inbetween these function callse.
- *
- * Return: A pointer to the object if successful or NULL otherwise.
- */
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key)
-{
- struct vmwgfx_hash_item *hash;
- int ret;
-
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
- if (ret) {
- rcu_read_unlock();
- return NULL;
- }
-
- __release(RCU);
- return hlist_entry(hash, struct ttm_ref_object, hash)->obj;
-}
-EXPORT_SYMBOL(ttm_base_object_noref_lookup);
-
struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
uint64_t key)
{
@@ -295,15 +261,16 @@ struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
struct vmwgfx_hash_item *hash;
int ret;
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
+ spin_lock(&tfile->lock);
+ ret = ttm_tfile_find_ref(tfile, key, &hash);
if (likely(ret == 0)) {
base = hlist_entry(hash, struct ttm_ref_object, hash)->obj;
if (!kref_get_unless_zero(&base->refcount))
base = NULL;
}
- rcu_read_unlock();
+ spin_unlock(&tfile->lock);
+
return base;
}
diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.h b/drivers/gpu/drm/vmwgfx/ttm_object.h
index f0ebbe340ad69..8098a3846bae3 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_object.h
+++ b/drivers/gpu/drm/vmwgfx/ttm_object.h
@@ -307,18 +307,4 @@ extern int ttm_prime_handle_to_fd(struct ttm_object_file *tfile,
#define ttm_prime_object_kfree(__obj, __prime) \
kfree_rcu(__obj, __prime.base.rhead)
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key);
-
-/**
- * ttm_base_object_noref_release - release a base object pointer looked up
- * without reference
- *
- * Releases a base object pointer looked up with ttm_base_object_noref_lookup().
- */
-static inline void ttm_base_object_noref_release(void)
-{
- __acquire(RCU);
- rcu_read_unlock();
-}
#endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 321c551784a14..aa1cd5126a321 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -715,44 +715,6 @@ int vmw_user_bo_lookup(struct drm_file *filp,
return 0;
}
-/**
- * vmw_user_bo_noref_lookup - Look up a vmw user buffer object without reference
- * @filp: The TTM object file the handle is registered with.
- * @handle: The user buffer object handle.
- *
- * This function looks up a struct vmw_bo and returns a pointer to the
- * struct vmw_buffer_object it derives from without refcounting the pointer.
- * The returned pointer is only valid until vmw_user_bo_noref_release() is
- * called, and the object pointed to by the returned pointer may be doomed.
- * Any persistent usage of the object requires a refcount to be taken using
- * ttm_bo_reference_unless_doomed(). Iff this function returns successfully it
- * needs to be paired with vmw_user_bo_noref_release() and no sleeping-
- * or scheduling functions may be called in between these function calls.
- *
- * Return: A struct vmw_buffer_object pointer if successful or negative
- * error pointer on failure.
- */
-struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle)
-{
- struct vmw_buffer_object *vmw_bo;
- struct ttm_buffer_object *bo;
- struct drm_gem_object *gobj = drm_gem_object_lookup(filp, handle);
-
- if (!gobj) {
- DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
- (unsigned long)handle);
- return ERR_PTR(-ESRCH);
- }
- vmw_bo = gem_to_vmw_bo(gobj);
- bo = ttm_bo_get_unless_zero(&vmw_bo->base);
- vmw_bo = vmw_buffer_object(bo);
- drm_gem_object_put(gobj);
-
- return vmw_bo;
-}
-
-
/**
* vmw_bo_fence_single - Utility function to fence a single TTM buffer
* object without unreserving it.
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index b062b020b3782..5acbf5849b270 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -830,12 +830,7 @@ extern int vmw_user_resource_lookup_handle(
uint32_t handle,
const struct vmw_user_resource_conv *converter,
struct vmw_resource **p_res);
-extern struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv *
- converter);
+
extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
@@ -874,15 +869,6 @@ static inline bool vmw_resource_mob_attached(const struct vmw_resource *res)
return !RB_EMPTY_NODE(&res->mob_node);
}
-/**
- * vmw_user_resource_noref_release - release a user resource pointer looked up
- * without reference
- */
-static inline void vmw_user_resource_noref_release(void)
-{
- ttm_base_object_noref_release();
-}
-
/**
* Buffer object helper functions - vmwgfx_bo.c
*/
@@ -934,8 +920,6 @@ extern void vmw_bo_unmap(struct vmw_buffer_object *vbo);
extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
struct ttm_resource *mem);
extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
-extern struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle);
/**
* vmw_bo_adjust_prio - Adjust the buffer object eviction priority
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index a5379f6fb5ab1..a44d53e33cdb1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -290,20 +290,26 @@ static void vmw_execbuf_rcache_update(struct vmw_res_cache_entry *rcache,
rcache->valid_handle = 0;
}
+enum vmw_val_add_flags {
+ vmw_val_add_flag_none = 0,
+ vmw_val_add_flag_noctx = 1 << 0,
+};
+
/**
- * vmw_execbuf_res_noref_val_add - Add a resource described by an unreferenced
- * rcu-protected pointer to the validation list.
+ * vmw_execbuf_res_val_add - Add a resource to the validation list.
*
* @sw_context: Pointer to the software context.
* @res: Unreferenced rcu-protected pointer to the resource.
* @dirty: Whether to change dirty status.
+ * @flags: specifies whether to use the context or not
*
* Returns: 0 on success. Negative error code on failure. Typical error codes
* are %-EINVAL on inconsistency and %-ESRCH if the resource was doomed.
*/
-static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
+static int vmw_execbuf_res_val_add(struct vmw_sw_context *sw_context,
+ struct vmw_resource *res,
+ u32 dirty,
+ u32 flags)
{
struct vmw_private *dev_priv = res->dev_priv;
int ret;
@@ -318,24 +324,30 @@ static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context,
if (dirty)
vmw_validation_res_set_dirty(sw_context->ctx,
rcache->private, dirty);
- vmw_user_resource_noref_release();
return 0;
}
- priv_size = vmw_execbuf_res_size(dev_priv, res_type);
- ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
- dirty, (void **)&ctx_info,
- &first_usage);
- vmw_user_resource_noref_release();
- if (ret)
- return ret;
+ if ((flags & vmw_val_add_flag_noctx) != 0) {
+ ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
+ (void **)&ctx_info, NULL);
+ if (ret)
+ return ret;
- if (priv_size && first_usage) {
- ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
- ctx_info);
- if (ret) {
- VMW_DEBUG_USER("Failed first usage context setup.\n");
+ } else {
+ priv_size = vmw_execbuf_res_size(dev_priv, res_type);
+ ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
+ dirty, (void **)&ctx_info,
+ &first_usage);
+ if (ret)
return ret;
+
+ if (priv_size && first_usage) {
+ ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
+ ctx_info);
+ if (ret) {
+ VMW_DEBUG_USER("Failed first usage context setup.\n");
+ return ret;
+ }
}
}
@@ -343,43 +355,6 @@ static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context,
return 0;
}
-/**
- * vmw_execbuf_res_noctx_val_add - Add a non-context resource to the resource
- * validation list if it's not already on it
- *
- * @sw_context: Pointer to the software context.
- * @res: Pointer to the resource.
- * @dirty: Whether to change dirty status.
- *
- * Returns: Zero on success. Negative error code on failure.
- */
-static int vmw_execbuf_res_noctx_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
-{
- struct vmw_res_cache_entry *rcache;
- enum vmw_res_type res_type = vmw_res_type(res);
- void *ptr;
- int ret;
-
- rcache = &sw_context->res_cache[res_type];
- if (likely(rcache->valid && rcache->res == res)) {
- if (dirty)
- vmw_validation_res_set_dirty(sw_context->ctx,
- rcache->private, dirty);
- return 0;
- }
-
- ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
- &ptr, NULL);
- if (ret)
- return ret;
-
- vmw_execbuf_rcache_update(rcache, res, ptr);
-
- return 0;
-}
-
/**
* vmw_view_res_val_add - Add a view and the surface it's pointing to to the
* validation list
@@ -398,13 +373,13 @@ static int vmw_view_res_val_add(struct vmw_sw_context *sw_context,
* First add the resource the view is pointing to, otherwise it may be
* swapped out when the view is validated.
*/
- ret = vmw_execbuf_res_noctx_val_add(sw_context, vmw_view_srf(view),
- vmw_view_dirtying(view));
+ ret = vmw_execbuf_res_val_add(sw_context, vmw_view_srf(view),
+ vmw_view_dirtying(view), vmw_val_add_flag_noctx);
if (ret)
return ret;
- return vmw_execbuf_res_noctx_val_add(sw_context, view,
- VMW_RES_DIRTY_NONE);
+ return vmw_execbuf_res_val_add(sw_context, view, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
}
/**
@@ -475,8 +450,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
if (IS_ERR(res))
continue;
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_SET);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
}
@@ -490,9 +466,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
if (vmw_res_type(entry->res) == vmw_res_view)
ret = vmw_view_res_val_add(sw_context, entry->res);
else
- ret = vmw_execbuf_res_noctx_val_add
- (sw_context, entry->res,
- vmw_binding_dirtying(entry->bt));
+ ret = vmw_execbuf_res_val_add(sw_context, entry->res,
+ vmw_binding_dirtying(entry->bt),
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
break;
}
@@ -658,7 +634,8 @@ vmw_cmd_res_check(struct vmw_private *dev_priv,
{
struct vmw_res_cache_entry *rcache = &sw_context->res_cache[res_type];
struct vmw_resource *res;
- int ret;
+ int ret = 0;
+ bool needs_unref = false;
if (p_res)
*p_res = NULL;
@@ -683,17 +660,18 @@ vmw_cmd_res_check(struct vmw_private *dev_priv,
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
- (dev_priv, sw_context->fp->tfile, *id_loc, converter);
- if (IS_ERR(res)) {
+ ret = vmw_user_resource_lookup_handle
+ (dev_priv, sw_context->fp->tfile, *id_loc, converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find/use resource 0x%08x.\n",
(unsigned int) *id_loc);
- return PTR_ERR(res);
+ return ret;
}
+ needs_unref = true;
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, dirty);
+ ret = vmw_execbuf_res_val_add(sw_context, res, dirty, vmw_val_add_flag_none);
if (unlikely(ret != 0))
- return ret;
+ goto res_check_done;
if (rcache->valid && rcache->res == res) {
rcache->valid_handle = true;
@@ -708,7 +686,11 @@ vmw_cmd_res_check(struct vmw_private *dev_priv,
if (p_res)
*p_res = res;
- return 0;
+res_check_done:
+ if (needs_unref)
+ vmw_resource_unreference(&res);
+
+ return ret;
}
/**
@@ -1171,9 +1153,9 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use MOB buffer.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false);
@@ -1225,9 +1207,9 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use GMR region.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false);
@@ -2025,8 +2007,9 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
res = vmw_shader_lookup(vmw_context_res_man(ctx),
cmd->body.shid, cmd->body.type);
if (!IS_ERR(res)) {
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
@@ -2273,8 +2256,9 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret)
return ret;
}
@@ -2777,8 +2761,8 @@ static int vmw_cmd_dx_bind_shader(struct vmw_private *dev_priv,
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
VMW_DEBUG_USER("Error creating resource validation node.\n");
return ret;
@@ -3098,8 +3082,8 @@ static int vmw_cmd_dx_bind_streamoutput(struct vmw_private *dev_priv,
vmw_dx_streamoutput_set_size(res, cmd->body.sizeInBytes);
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
@@ -3148,8 +3132,8 @@ static int vmw_cmd_dx_set_streamoutput(struct vmw_private *dev_priv,
return 0;
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
@@ -4066,22 +4050,26 @@ static int vmw_execbuf_tie_context(struct vmw_private *dev_priv,
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
+ ret = vmw_user_resource_lookup_handle
(dev_priv, sw_context->fp->tfile, handle,
- user_context_converter);
- if (IS_ERR(res)) {
+ user_context_converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find or user DX context 0x%08x.\n",
(unsigned int) handle);
- return PTR_ERR(res);
+ return ret;
}
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, VMW_RES_DIRTY_SET);
- if (unlikely(ret != 0))
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_none);
+ if (unlikely(ret != 0)) {
+ vmw_resource_unreference(&res);
return ret;
+ }
sw_context->dx_ctx_node = vmw_execbuf_info_from_res(sw_context, res);
sw_context->man = vmw_context_res_man(res);
+ vmw_resource_unreference(&res);
return 0;
}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index f66caa540e146..c7d645e5ec7bf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -281,39 +281,6 @@ int vmw_user_resource_lookup_handle(struct vmw_private *dev_priv,
return ret;
}
-/**
- * vmw_user_resource_noref_lookup_handle - lookup a struct resource from a
- * TTM user-space handle and perform basic type checks
- *
- * @dev_priv: Pointer to a device private struct
- * @tfile: Pointer to a struct ttm_object_file identifying the caller
- * @handle: The TTM user-space handle
- * @converter: Pointer to an object describing the resource type
- *
- * If the handle can't be found or is associated with an incorrect resource
- * type, -EINVAL will be returned.
- */
-struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv
- *converter)
-{
- struct ttm_base_object *base;
-
- base = ttm_base_object_noref_lookup(tfile, handle);
- if (!base)
- return ERR_PTR(-ESRCH);
-
- if (unlikely(ttm_base_object_type(base) != converter->object_type)) {
- ttm_base_object_noref_release();
- return ERR_PTR(-EINVAL);
- }
-
- return converter->base_obj_to_res(base);
-}
-
/*
* Helper function that looks either a surface or bo.
*
--
GitLab
From 9e17f99220d111ea031b44153fdfe364b0024ff2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sat, 7 Jan 2023 19:10:04 +0200
Subject: [PATCH 0553/1167] net/sched: act_mpls: Fix warning during failed
attribute validation
The 'TCA_MPLS_LABEL' attribute is of 'NLA_U32' type, but has a
validation type of 'NLA_VALIDATE_FUNCTION'. This is an invalid
combination according to the comment above 'struct nla_policy':
"
Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN:
NLA_BINARY Validation function called for the attribute.
All other Unused - but note that it's a union
"
This can trigger the warning [1] in nla_get_range_unsigned() when
validation of the attribute fails. Despite being of 'NLA_U32' type, the
associated 'min'/'max' fields in the policy are negative as they are
aliased by the 'validate' field.
Fix by changing the attribute type to 'NLA_BINARY' which is consistent
with the above comment and all other users of NLA_POLICY_VALIDATE_FN().
As a result, move the length validation to the validation function.
No regressions in MPLS tests:
# ./tdc.py -f tc-tests/actions/mpls.json
[...]
# echo $?
0
[1]
WARNING: CPU: 0 PID: 17743 at lib/nlattr.c:118
nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117
Modules linked in:
CPU: 0 PID: 17743 Comm: syz-executor.0 Not tainted 6.1.0-rc8 #3
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.13.0-48-gd9c812dda519-prebuilt.qemu.org 04/01/2014
RIP: 0010:nla_get_range_unsigned+0x1d8/0x1e0 lib/nlattr.c:117
[...]
Call Trace:
<TASK>
__netlink_policy_dump_write_attr+0x23d/0x990 net/netlink/policy.c:310
netlink_policy_dump_write_attr+0x22/0x30 net/netlink/policy.c:411
netlink_ack_tlv_fill net/netlink/af_netlink.c:2454 [inline]
netlink_ack+0x546/0x760 net/netlink/af_netlink.c:2506
netlink_rcv_skb+0x1b7/0x240 net/netlink/af_netlink.c:2546
rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:6109
netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
netlink_unicast+0x5e9/0x6b0 net/netlink/af_netlink.c:1345
netlink_sendmsg+0x739/0x860 net/netlink/af_netlink.c:1921
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg net/socket.c:734 [inline]
____sys_sendmsg+0x38f/0x500 net/socket.c:2482
___sys_sendmsg net/socket.c:2536 [inline]
__sys_sendmsg+0x197/0x230 net/socket.c:2565
__do_sys_sendmsg net/socket.c:2574 [inline]
__se_sys_sendmsg net/socket.c:2572 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2572
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
Link: https://lore.kernel.org/netdev/CAO4mrfdmjvRUNbDyP0R03_DrD_eFCLCguz6OxZ2TYRSv0K9gxA@mail.gmail.com/
Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Reported-by: Wei Chen <harperchen1110@gmail.com>
Tested-by: Wei Chen <harperchen1110@gmail.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230107171004.608436-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/act_mpls.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index ff47ce4d39685..6b26bdb999d77 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -134,6 +134,11 @@ static int valid_label(const struct nlattr *attr,
{
const u32 *label = nla_data(attr);
+ if (nla_len(attr) != sizeof(*label)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length");
+ return -EINVAL;
+ }
+
if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) {
NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range");
return -EINVAL;
@@ -145,7 +150,8 @@ static int valid_label(const struct nlattr *attr,
static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
[TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
[TCA_MPLS_PROTO] = { .type = NLA_U16 },
- [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label),
+ [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+ valid_label),
[TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7),
[TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1),
[TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1),
--
GitLab
From ef01f4e25c1760920e2c94f1c232350277ace69b Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Fri, 6 Jan 2023 10:43:59 -0500
Subject: [PATCH 0554/1167] bpf: restore the ebpf program ID for
BPF_AUDIT_UNLOAD and PERF_BPF_EVENT_PROG_UNLOAD
When changing the ebpf program put() routines to support being called
from within IRQ context the program ID was reset to zero prior to
calling the perf event and audit UNLOAD record generators, which
resulted in problems as the ebpf program ID was bogus (always zero).
This patch addresses this problem by removing an unnecessary call to
bpf_prog_free_id() in __bpf_prog_offload_destroy() and adjusting
__bpf_prog_put() to only call bpf_prog_free_id() after audit and perf
have finished their bpf program unload tasks in
bpf_prog_put_deferred(). For the record, no one can determine, or
remember, why it was necessary to free the program ID, and remove it
from the IDR, prior to executing bpf_prog_put_deferred();
regardless, both Stanislav and Alexei agree that the approach in this
patch should be safe.
It is worth noting that when moving the bpf_prog_free_id() call, the
do_idr_lock parameter was forced to true as the ebpf devs determined
this was the correct as the do_idr_lock should always be true. The
do_idr_lock parameter will be removed in a follow-up patch, but it
was kept here to keep the patch small in an effort to ease any stable
backports.
I also modified the bpf_audit_prog() logic used to associate the
AUDIT_BPF record with other associated records, e.g. @ctx != NULL.
Instead of keying off the operation, it now keys off the execution
context, e.g. '!in_irg && !irqs_disabled()', which is much more
appropriate and should help better connect the UNLOAD operations with
the associated audit state (other audit records).
Cc: stable@vger.kernel.org
Fixes: d809e134be7a ("bpf: Prepare bpf_prog_put() to be called from irq context.")
Reported-by: Burn Alting <burn.alting@iinet.net.au>
Reported-by: Jiri Olsa <olsajiri@gmail.com>
Suggested-by: Stanislav Fomichev <sdf@google.com>
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230106154400.74211-1-paul@paul-moore.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/offload.c | 3 ---
kernel/bpf/syscall.c | 6 ++----
2 files changed, 2 insertions(+), 7 deletions(-)
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 13e4efc971e6d..190d9f9dc9870 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -216,9 +216,6 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
if (offload->dev_state)
offload->offdev->ops->destroy(prog);
- /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */
- bpf_prog_free_id(prog, true);
-
list_del_init(&offload->offloads);
kfree(offload);
prog->aux->offload = NULL;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 64131f88c5537..61bb19e81b9c8 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1972,7 +1972,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op)
return;
if (audit_enabled == AUDIT_OFF)
return;
- if (op == BPF_AUDIT_LOAD)
+ if (!in_irq() && !irqs_disabled())
ctx = audit_context();
ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF);
if (unlikely(!ab))
@@ -2067,6 +2067,7 @@ static void bpf_prog_put_deferred(struct work_struct *work)
prog = aux->prog;
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
+ bpf_prog_free_id(prog, true);
__bpf_prog_put_noref(prog, true);
}
@@ -2075,9 +2076,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
struct bpf_prog_aux *aux = prog->aux;
if (atomic64_dec_and_test(&aux->refcnt)) {
- /* bpf_prog_free_id() must be called first */
- bpf_prog_free_id(prog, do_idr_lock);
-
if (in_irq() || irqs_disabled()) {
INIT_WORK(&aux->work, bpf_prog_put_deferred);
schedule_work(&aux->work);
--
GitLab
From e7895f017b79410bf4591396a733b876dc1e0e9d Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Fri, 6 Jan 2023 10:44:00 -0500
Subject: [PATCH 0555/1167] bpf: remove the do_idr_lock parameter from
bpf_prog_free_id()
It was determined that the do_idr_lock parameter to
bpf_prog_free_id() was not necessary as it should always be true.
Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230106154400.74211-2-paul@paul-moore.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 2 +-
kernel/bpf/syscall.c | 20 ++++++--------------
2 files changed, 7 insertions(+), 15 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3de24cfb7a3de..634d37a599fa7 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1832,7 +1832,7 @@ void bpf_prog_inc(struct bpf_prog *prog);
struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
+void bpf_prog_free_id(struct bpf_prog *prog);
void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
struct btf_field *btf_record_find(const struct btf_record *rec,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 61bb19e81b9c8..ecca9366c7a6f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2001,7 +2001,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog)
return id > 0 ? 0 : id;
}
-void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
+void bpf_prog_free_id(struct bpf_prog *prog)
{
unsigned long flags;
@@ -2013,18 +2013,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
if (!prog->aux->id)
return;
- if (do_idr_lock)
- spin_lock_irqsave(&prog_idr_lock, flags);
- else
- __acquire(&prog_idr_lock);
-
+ spin_lock_irqsave(&prog_idr_lock, flags);
idr_remove(&prog_idr, prog->aux->id);
prog->aux->id = 0;
-
- if (do_idr_lock)
- spin_unlock_irqrestore(&prog_idr_lock, flags);
- else
- __release(&prog_idr_lock);
+ spin_unlock_irqrestore(&prog_idr_lock, flags);
}
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
@@ -2067,11 +2059,11 @@ static void bpf_prog_put_deferred(struct work_struct *work)
prog = aux->prog;
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
bpf_audit_prog(prog, BPF_AUDIT_UNLOAD);
- bpf_prog_free_id(prog, true);
+ bpf_prog_free_id(prog);
__bpf_prog_put_noref(prog, true);
}
-static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
+static void __bpf_prog_put(struct bpf_prog *prog)
{
struct bpf_prog_aux *aux = prog->aux;
@@ -2087,7 +2079,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
void bpf_prog_put(struct bpf_prog *prog)
{
- __bpf_prog_put(prog, true);
+ __bpf_prog_put(prog);
}
EXPORT_SYMBOL_GPL(bpf_prog_put);
--
GitLab
From 08f0adb193c008de640fde34a2e00a666c01d77c Mon Sep 17 00:00:00 2001
From: Miles Chen <miles.chen@mediatek.com>
Date: Tue, 10 Jan 2023 11:12:52 +0800
Subject: [PATCH 0556/1167] cpufreq: armada-37xx: stop using 0 as NULL pointer
Use NULL for NULL pointer to fix the following sparse warning:
drivers/cpufreq/armada-37xx-cpufreq.c:448:32: sparse: warning: Using plain integer as NULL pointer
Signed-off-by: Miles Chen <miles.chen@mediatek.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
drivers/cpufreq/armada-37xx-cpufreq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index c10fc33b29b18..b74289a95a171 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -445,7 +445,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
return -ENODEV;
}
- clk = clk_get(cpu_dev, 0);
+ clk = clk_get(cpu_dev, NULL);
if (IS_ERR(clk)) {
dev_err(cpu_dev, "Cannot get clock for CPU0\n");
return PTR_ERR(clk);
--
GitLab
From 2ea26b4de6f42b74a5f1701de41efa6bc9f12666 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 8 Jan 2023 20:37:53 +0100
Subject: [PATCH 0557/1167] Revert "r8169: disable detection of chip version
36"
This reverts commit 42666b2c452ce87894786aae05e3fad3cfc6cb59.
This chip version seems to be very rare, but it exits in consumer
devices, see linked report.
Link: https://stackoverflow.com/questions/75049473/cant-setup-a-wired-network-in-archlinux-fresh-install
Fixes: 42666b2c452c ("r8169: disable detection of chip version 36")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/42e9674c-d5d0-a65a-f578-e5c74f244739@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/realtek/r8169_main.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 24592d9725230..dadd61bccfe72 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -1996,10 +1996,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
/* 8168F family. */
{ 0x7c8, 0x488, RTL_GIGA_MAC_VER_38 },
- /* It seems this chip version never made it to
- * the wild. Let's disable detection.
- * { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
- */
+ { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
{ 0x7cf, 0x480, RTL_GIGA_MAC_VER_35 },
/* 8168E family. */
--
GitLab
From 17b3222e943701c408d6e03357967829aaea0550 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 13 Nov 2022 00:04:17 +0200
Subject: [PATCH 0558/1167] net/mlx5: DR, Fix 'stack frame size exceeds limit'
error in dr_rule
If the kernel configuration asks the compiler to check frame limit of 1K,
dr_rule_create_rule_nic exceed this limit:
"stack frame size (1184) exceeds limit (1024)"
Fixing this issue by checking configured frame limit and using the
optimization STE array only for cases with the usual 2K (or larger)
stack size warning.
Fixes: b9b81e1e9382 ("net/mlx5: DR, For short chains of STEs, avoid allocating ste_arr dynamically")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
---
.../ethernet/mellanox/mlx5/core/steering/dr_rule.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 74cbe53ee9dbb..b851141e03de3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -3,7 +3,12 @@
#include "dr_types.h"
+#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN < 2048)
+/* don't try to optimize STE allocation if the stack is too constaraining */
+#define DR_RULE_MAX_STES_OPTIMIZED 0
+#else
#define DR_RULE_MAX_STES_OPTIMIZED 5
+#endif
#define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn,
@@ -1218,10 +1223,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
mlx5dr_domain_nic_unlock(nic_dmn);
- if (unlikely(!hw_ste_arr_is_opt))
- kfree(hw_ste_arr);
-
- return 0;
+ goto out;
free_rule:
dr_rule_clean_rule_members(rule, nic_rule);
@@ -1238,6 +1240,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
free_hw_ste:
mlx5dr_domain_nic_unlock(nic_dmn);
+out:
if (unlikely(!hw_ste_arr_is_opt))
kfree(hw_ste_arr);
--
GitLab
From e0bf81bf0d3d4747c146e0bf44774d3d881d7137 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@nvidia.com>
Date: Tue, 16 Aug 2022 23:19:11 +0300
Subject: [PATCH 0559/1167] net/mlx5: check attr pointer validity before
dereferencing it
Fix attr pointer validity checks after it was already
dereferenced.
Fixes: cb0d54cbf948 ("net/mlx5e: Fix wrong source vport matching on tunnel rule")
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index e455b215c7088..75b77dd2392b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -143,7 +143,7 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
if (mlx5_esw_indir_table_decap_vport(attr))
vport = mlx5_esw_indir_table_decap_vport(attr);
- if (attr && !attr->chain && esw_attr->int_port)
+ if (!attr->chain && esw_attr && esw_attr->int_port)
metadata =
mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port);
else
--
GitLab
From 5e72f3f1c558019082cfeedeed73748f35d780c6 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@nvidia.com>
Date: Tue, 30 Aug 2022 00:32:30 +0300
Subject: [PATCH 0560/1167] net/mlx5e: TC, Keep mod hdr actions after mod hdr
alloc
When offloading TC NIC rule which has mod_hdr action, the
mod_hdr actions list is freed upon mod_hdr allocation.
In the new format of handling multi table actions and CT in
particular, the mod_hdr actions list is still relevant when
setting the pre and post rules and therefore, freeing the list
may cause adding rules which don't set the FTE_ID.
Therefore, the mod_hdr actions list needs to be kept for the
pre/post flows as well and should be left for these handler to
be freed.
Fixes: 8300f225268b ("net/mlx5e: Create new flow attr for multi table actions")
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9af2aa2922f5d..dbadaf1664879 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1301,7 +1301,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
- mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts);
if (err)
return err;
}
@@ -1359,8 +1358,10 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
}
mutex_unlock(&tc->t_lock);
- if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+ mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
mlx5e_detach_mod_hdr(priv, flow);
+ }
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
mlx5_fc_destroy(priv->mdev, attr->counter);
--
GitLab
From da2e552b469a0cd130ff70a88ccc4139da428a65 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 28 Nov 2022 19:05:47 +0200
Subject: [PATCH 0561/1167] net/mlx5: Fix command stats access after free
Command may fail while driver is reloading and can't accept FW commands
till command interface is reinitialized. Such command failure is being
logged to command stats. This results in NULL pointer access as command
stats structure is being freed and reallocated during mlx5 devlink
reload (see kernel log below).
Fix it by making command stats statically allocated on driver probe.
Kernel log:
[ 2394.808802] BUG: unable to handle kernel paging request at 000000000002a9c0
[ 2394.810610] PGD 0 P4D 0
[ 2394.811811] Oops: 0002 [#1] SMP NOPTI
...
[ 2394.815482] RIP: 0010:native_queued_spin_lock_slowpath+0x183/0x1d0
...
[ 2394.829505] Call Trace:
[ 2394.830667] _raw_spin_lock_irq+0x23/0x26
[ 2394.831858] cmd_status_err+0x55/0x110 [mlx5_core]
[ 2394.833020] mlx5_access_reg+0xe7/0x150 [mlx5_core]
[ 2394.834175] mlx5_query_port_ptys+0x78/0xa0 [mlx5_core]
[ 2394.835337] mlx5e_ethtool_get_link_ksettings+0x74/0x590 [mlx5_core]
[ 2394.836454] ? kmem_cache_alloc_trace+0x140/0x1c0
[ 2394.837562] __rh_call_get_link_ksettings+0x33/0x100
[ 2394.838663] ? __rtnl_unlock+0x25/0x50
[ 2394.839755] __ethtool_get_link_ksettings+0x72/0x150
[ 2394.840862] duplex_show+0x6e/0xc0
[ 2394.841963] dev_attr_show+0x1c/0x40
[ 2394.843048] sysfs_kf_seq_show+0x9b/0x100
[ 2394.844123] seq_read+0x153/0x410
[ 2394.845187] vfs_read+0x91/0x140
[ 2394.846226] ksys_read+0x4f/0xb0
[ 2394.847234] do_syscall_64+0x5b/0x1a0
[ 2394.848228] entry_SYSCALL_64_after_hwframe+0x65/0xca
Fixes: 34f46ae0d4b3 ("net/mlx5: Add command failures data to debugfs")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 13 ++-----------
include/linux/mlx5/driver.h | 2 +-
2 files changed, 3 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index d3ca745d107d6..c837103a9ee33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2176,15 +2176,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
return -EINVAL;
}
- cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL);
- if (!cmd->stats)
- return -ENOMEM;
-
cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
- if (!cmd->pool) {
- err = -ENOMEM;
- goto dma_pool_err;
- }
+ if (!cmd->pool)
+ return -ENOMEM;
err = alloc_cmd_page(dev, cmd);
if (err)
@@ -2268,8 +2262,6 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
err_free_pool:
dma_pool_destroy(cmd->pool);
-dma_pool_err:
- kvfree(cmd->stats);
return err;
}
@@ -2282,7 +2274,6 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
destroy_msg_cache(dev);
free_cmd_page(dev, cmd);
dma_pool_destroy(cmd->pool);
- kvfree(cmd->stats);
}
void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d476255c9a3f0..76ef2e4fde38d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -315,7 +315,7 @@ struct mlx5_cmd {
struct mlx5_cmd_debug dbg;
struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
int checksum_disabled;
- struct mlx5_cmd_stats *stats;
+ struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
};
struct mlx5_cmd_mailbox {
--
GitLab
From ab4b01bfdaa69492fb36484026b0a0f0af02d75a Mon Sep 17 00:00:00 2001
From: Roy Novich <royno@nvidia.com>
Date: Wed, 4 Jan 2023 11:16:21 +0200
Subject: [PATCH 0562/1167] net/mlx5e: Verify dev is present for fix features
ndo
The native NIC port net device instance is being used as Uplink
representor. While changing profiles private resources are not
available, fix features ndo does not check if the netdev is present.
Add driver protection to verify private resources are ready.
Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode")
Signed-off-by: Roy Novich <royno@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cff5f2e29e1e2..abcc614b6191b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4084,6 +4084,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
struct mlx5e_vlan_table *vlan;
struct mlx5e_params *params;
+ if (!netif_device_present(netdev))
+ return features;
+
vlan = mlx5e_fs_get_vlan(priv->fs);
mutex_lock(&priv->state_lock);
params = &priv->channels.params;
--
GitLab
From 806a8df7126a8c05d60411eeb81057c2a8bbe7a7 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 15 Dec 2022 13:02:38 +0200
Subject: [PATCH 0563/1167] net/mlx5e: IPoIB, Block queue count configuration
when sub interfaces are present
PKEY sub interfaces share the receive queues with the parent interface.
While setting the sub interface queue count is not supported, it is
currently possible to change the number of queues of the parent interface.
Thus we can end up with inconsistent queue sizes between the parent and its
sub interfaces.
This change disallows setting the queue count on the parent interface when
sub interfaces are present.
This is achieved by introducing an explicit reference to the parent netdev
in the mlx5i_priv of the child interface. An additional counter is also
required on the parent side to detect when sub interfaces are attached and
for proper cleanup.
The rtnl lock is taken during the ethtool op and the sub interface
ndo_init/uninit ops. There is no race here around counting the sub
interfaces, reading the sub interfaces and setting the number of
channels. The ASSERT_RTNL was added to document that.
Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../mellanox/mlx5/core/ipoib/ethtool.c | 16 +++++++-
.../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 38 +++++++++++++++++++
.../ethernet/mellanox/mlx5/core/ipoib/ipoib.h | 6 +++
.../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 9 ++---
4 files changed, 62 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index c247cca154e9c..eff92dc0927c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -90,9 +90,21 @@ static void mlx5i_get_ringparam(struct net_device *dev,
static int mlx5i_set_channels(struct net_device *dev,
struct ethtool_channels *ch)
{
- struct mlx5e_priv *priv = mlx5i_epriv(dev);
+ struct mlx5i_priv *ipriv = netdev_priv(dev);
+ struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+
+ /* rtnl lock protects from race between this ethtool op and sub
+ * interface ndo_init/uninit.
+ */
+ ASSERT_RTNL();
+ if (ipriv->num_sub_interfaces > 0) {
+ mlx5_core_warn(epriv->mdev,
+ "can't change number of channels for interfaces with sub interfaces (%u)\n",
+ ipriv->num_sub_interfaces);
+ return -EINVAL;
+ }
- return mlx5e_ethtool_set_channels(priv, ch);
+ return mlx5e_ethtool_set_channels(epriv, ch);
}
static void mlx5i_get_channels(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 2c73c8445e630..911cf4d239645 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -160,6 +160,44 @@ void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
stats->tx_dropped = sstats->tx_queue_dropped;
}
+struct net_device *mlx5i_parent_get(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+ struct net_device *parent_dev;
+ int parent_ifindex;
+
+ ipriv = priv->ppriv;
+
+ parent_ifindex = netdev->netdev_ops->ndo_get_iflink(netdev);
+ parent_dev = dev_get_by_index(dev_net(netdev), parent_ifindex);
+ if (!parent_dev)
+ return NULL;
+
+ parent_ipriv = netdev_priv(parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces++;
+
+ ipriv->parent_dev = parent_dev;
+
+ return parent_dev;
+}
+
+void mlx5i_parent_put(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+
+ ipriv = priv->ppriv;
+ parent_ipriv = netdev_priv(ipriv->parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces--;
+
+ dev_put(ipriv->parent_dev);
+}
+
int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
index 99d46fda9f82f..f3f2af972020a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h
@@ -54,9 +54,11 @@ struct mlx5i_priv {
struct rdma_netdev rn; /* keep this first */
u32 qpn;
bool sub_interface;
+ u32 num_sub_interfaces;
u32 qkey;
u16 pkey_index;
struct mlx5i_pkey_qpn_ht *qpn_htbl;
+ struct net_device *parent_dev;
char *mlx5e_priv[];
};
@@ -117,5 +119,9 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more);
void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+/* Reference management for child to parent interfaces. */
+struct net_device *mlx5i_parent_get(struct net_device *netdev);
+void mlx5i_parent_put(struct net_device *netdev);
+
#endif /* CONFIG_MLX5_CORE_IPOIB */
#endif /* __MLX5E_IPOB_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 4d9c9e49645c9..28795fb6bccc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -158,21 +158,19 @@ static int mlx5i_pkey_dev_init(struct net_device *dev)
struct mlx5e_priv *priv = mlx5i_epriv(dev);
struct mlx5i_priv *ipriv, *parent_ipriv;
struct net_device *parent_dev;
- int parent_ifindex;
ipriv = priv->ppriv;
- /* Get QPN to netdevice hash table from parent */
- parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev);
- parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex);
+ /* Link to parent */
+ parent_dev = mlx5i_parent_get(dev);
if (!parent_dev) {
mlx5_core_warn(priv->mdev, "failed to get parent device\n");
return -EINVAL;
}
+ /* Get QPN to netdevice hash table from parent */
parent_ipriv = netdev_priv(parent_dev);
ipriv->qpn_htbl = parent_ipriv->qpn_htbl;
- dev_put(parent_dev);
return mlx5i_dev_init(dev);
}
@@ -184,6 +182,7 @@ static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
static void mlx5i_pkey_dev_cleanup(struct net_device *netdev)
{
+ mlx5i_parent_put(netdev);
return mlx5i_dev_cleanup(netdev);
}
--
GitLab
From 31c70bfe58ef09fe36327ddcced9143a16e9e83d Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Fri, 25 Nov 2022 17:51:19 +0200
Subject: [PATCH 0564/1167] net/mlx5e: IPoIB, Block PKEY interfaces with less
rx queues than parent
A user is able to configure an arbitrary number of rx queues when
creating an interface via netlink. This doesn't work for child PKEY
interfaces because the child interface uses the parent receive channels.
Although the child shares the parent's receive channels, the number of
rx queues is important for the channel_stats array: the parent's rx
channel index is used to access the child's channel_stats. So the array
has to be at least as large as the parent's rx queue size for the
counting to work correctly and to prevent out of bound accesses.
This patch checks for the mentioned scenario and returns an error when
trying to create the interface. The error is propagated to the user.
Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
index 28795fb6bccc3..03e681297937f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c
@@ -168,6 +168,15 @@ static int mlx5i_pkey_dev_init(struct net_device *dev)
return -EINVAL;
}
+ if (dev->num_rx_queues < parent_dev->real_num_rx_queues) {
+ mlx5_core_warn(priv->mdev,
+ "failed to create child device with rx queues [%d] less than parent's [%d]\n",
+ dev->num_rx_queues,
+ parent_dev->real_num_rx_queues);
+ mlx5i_parent_put(dev);
+ return -EINVAL;
+ }
+
/* Get QPN to netdevice hash table from parent */
parent_ipriv = netdev_priv(parent_dev);
ipriv->qpn_htbl = parent_ipriv->qpn_htbl;
--
GitLab
From b5e23931c45a2f99f60a2f2b98a9e4d5a62a5b13 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Wed, 23 Nov 2022 16:59:13 +0200
Subject: [PATCH 0565/1167] net/mlx5e: IPoIB, Fix child PKEY interface stats on
rx path
The current code always does the accounting using the
stats from the parent interface (linked in the rq). This
doesn't work when there are child interfaces configured.
Fix this behavior by always using the stats from the child
interface priv. This will also work for parent only
interfaces: the child (netdev) and parent netdev (rq->netdev)
will point to the same thing.
Fixes: be98737a4faa ("net/mlx5e: Use dynamic per-channel allocations in stats")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index c8820ab221694..3df455f6b1685 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2419,7 +2419,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
priv = mlx5i_epriv(netdev);
tstamp = &priv->tstamp;
- stats = rq->stats;
+ stats = &priv->channel_stats[rq->ix]->rq;
flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
g = (flags_rqpn >> 28) & 3;
--
GitLab
From 2414c9b7a29d237c9c40abd62853dbc08b4ba7df Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@nvidia.com>
Date: Wed, 7 Dec 2022 11:05:02 +0000
Subject: [PATCH 0566/1167] net/mlx5e: TC, ignore match level for post meter
rules
The post meter table only matches on reg_c5. As such, the inner/outer
match levels are irrelevant for the match critieria. The cited patch only
sets the outer criteria to none, thus setting the inner match level for
encapsulated packets. This caused rules with police action on tunnel
devices to not find an existing flow group for the match criteria, thus
failing to offload the rule.
Set both the inner and outer match levels to none for post_meter rules.
Fixes: 0d8c38d44f33 ("net/mlx5e: TC, init post meter rules with branching attributes")
Signed-off-by: Oz Shlomo <ozsh@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c
index 8d7d761482d27..50b60fd009467 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c
@@ -127,6 +127,7 @@ mlx5e_post_meter_add_rule(struct mlx5e_priv *priv,
attr->counter = act_counter;
attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT;
+ attr->inner_match_level = MLX5_MATCH_NONE;
attr->outer_match_level = MLX5_MATCH_NONE;
attr->chain = 0;
attr->prio = 0;
--
GitLab
From c09502d54dc109530ccb9a8910ab286d0745f119 Mon Sep 17 00:00:00 2001
From: Oz Shlomo <ozsh@nvidia.com>
Date: Thu, 8 Dec 2022 08:31:48 +0000
Subject: [PATCH 0567/1167] net/mlx5e: TC, Restore pkt rate policing support
The offending commit removed the support for all packet rate metering.
Restore the pkt rate metering support by removing the restriction.
Fixes: 3603f26633e7 ("net/mlx5e: TC, allow meter jump control action")
Signed-off-by: Oz Shlomo <ozsh@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
index 512d431489228..c4378afdec09e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
@@ -34,12 +34,6 @@ static int police_act_validate(const struct flow_action_entry *act,
return -EOPNOTSUPP;
}
- if (act->police.rate_pkt_ps) {
- NL_SET_ERR_MSG_MOD(extack,
- "QoS offload not support packets per second");
- return -EOPNOTSUPP;
- }
-
return 0;
}
--
GitLab
From 3099d2e62f9061ed57798e68e285d35837be686f Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Sun, 8 Jan 2023 12:53:02 +0200
Subject: [PATCH 0568/1167] net/mlx5e: Fix memory leak on updating vport
counters
When updating statistics driver queries the vport's counters. On fail,
add error path releasing the allocated buffer avoiding memory leak.
Fixes: 64b68e369649 ("net/mlx5: Refactor and expand rep vport stat group")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 75b9e1528fd29..7d90e5b728548 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -191,7 +191,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep)
if (err) {
netdev_warn(priv->netdev, "vport %d error %d reading stats\n",
rep->vport, err);
- return;
+ goto out;
}
#define MLX5_GET_CTR(p, x) \
@@ -241,6 +241,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep)
rep_stats->tx_vport_rdma_multicast_bytes =
MLX5_GET_CTR(out, received_ib_multicast.octets);
+out:
kvfree(out);
}
--
GitLab
From fe91d57277eef8bb4aca05acfa337b4a51d0bba4 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Mon, 5 Dec 2022 14:26:09 -0800
Subject: [PATCH 0569/1167] net/mlx5: Fix ptp max frequency adjustment range
.max_adj of ptp_clock_info acts as an absolute value for the amount in ppb
that can be set for a single call of .adjfine. This means that a single
call to .getfine cannot be greater than .max_adj or less than -(.max_adj).
Provides correct value for max frequency adjustment value supported by
devices.
Fixes: 3d8c38af1493 ("net/mlx5e: Add PTP Hardware Clock (PHC) support")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 69cfe60c558a7..69318b1432688 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -681,7 +681,7 @@ static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
static const struct ptp_clock_info mlx5_ptp_clock_info = {
.owner = THIS_MODULE,
.name = "mlx5_ptp",
- .max_adj = 100000000,
+ .max_adj = 50000000,
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
--
GitLab
From d515d63cae2cd186acf40deaa8ef33067bb7f637 Mon Sep 17 00:00:00 2001
From: Gavin Li <gavinl@nvidia.com>
Date: Tue, 27 Dec 2022 04:54:09 +0200
Subject: [PATCH 0570/1167] net/mlx5e: Don't support encap rules with gbp
option
Previously, encap rules with gbp option would be offloaded by mistake but
driver does not support gbp option offload.
To fix this issue, check if the encap rule has gbp option and don't
offload the rule
Fixes: d8f9dfae49ce ("net: sched: allow flower to match vxlan options")
Signed-off-by: Gavin Li <gavinl@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index fd07c4cbfd1d2..1f62c702b6255 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -88,6 +88,8 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
struct udphdr *udp = (struct udphdr *)(buf);
struct vxlanhdr *vxh;
+ if (tun_key->tun_flags & TUNNEL_VXLAN_OPT)
+ return -EOPNOTSUPP;
vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
*ip_proto = IPPROTO_UDP;
--
GitLab
From cd4f186dc110a0f0b3484048b8ecd42ee006ca6d Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 15 Dec 2022 15:33:38 +0200
Subject: [PATCH 0571/1167] net/mlx5: E-switch, Coverity: overlapping copy
When a capability is set via port function caps callbacks, a memcpy() is
performed in which the source and the target are the same address, e.g.:
the copy is redundant. Hence, Remove it.
Discovered by Coverity.
Fixes: 7db98396ef45 ("net/mlx5: E-Switch, Implement devlink port function cmds to control RoCE")
Fixes: e5b9642a33be ("net/mlx5: E-Switch, Implement devlink port function cmds to control migratable")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 75b77dd2392b1..c981fa77f4398 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4143,8 +4143,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable,
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport,
@@ -4236,8 +4234,6 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable,
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap, hca_caps, roce, enable);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num,
--
GitLab
From f5e1ed04aa2ea665a796f0109091ca3f2b01024a Mon Sep 17 00:00:00 2001
From: Emeel Hakim <ehakim@nvidia.com>
Date: Wed, 14 Dec 2022 16:34:13 +0200
Subject: [PATCH 0572/1167] net/mlx5e: Fix macsec ssci attribute handling in
offload path
Currently when macsec offload is set with extended packet number (epn)
enabled, the driver wrongly deduce the short secure channel identifier
(ssci) from the salt instead of the stand alone ssci attribute as it
should, consequently creating a mismatch between the kernel and driver's
ssci values.
Fix by using the ssci value from the relevant attribute.
Fixes: 4411a6c0abd3 ("net/mlx5e: Support MACsec offload extended packet number (EPN)")
Signed-off-by: Emeel Hakim <ehakim@nvidia.com>
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/en_accel/macsec.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 9369a580743e1..cf7b3bb54c861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -62,6 +62,7 @@ struct mlx5e_macsec_sa {
u32 enc_key_id;
u32 next_pn;
sci_t sci;
+ ssci_t ssci;
salt_t salt;
struct rhash_head hash;
@@ -499,10 +500,11 @@ mlx5e_macsec_get_macsec_device_context(const struct mlx5e_macsec *macsec,
}
static void update_macsec_epn(struct mlx5e_macsec_sa *sa, const struct macsec_key *key,
- const pn_t *next_pn_halves)
+ const pn_t *next_pn_halves, ssci_t ssci)
{
struct mlx5e_macsec_epn_state *epn_state = &sa->epn_state;
+ sa->ssci = ssci;
sa->salt = key->salt;
epn_state->epn_enabled = 1;
epn_state->epn_msb = next_pn_halves->upper;
@@ -550,7 +552,8 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx)
tx_sa->assoc_num = assoc_num;
if (secy->xpn)
- update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves);
+ update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves,
+ ctx_tx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
@@ -945,7 +948,8 @@ static int mlx5e_macsec_add_rxsa(struct macsec_context *ctx)
rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id;
if (ctx->secy->xpn)
- update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves);
+ update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves,
+ ctx_rx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, ctx->secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
--
GitLab
From 9828994ac492e8e7de47fe66097b7e665328f348 Mon Sep 17 00:00:00 2001
From: Emeel Hakim <ehakim@nvidia.com>
Date: Sun, 11 Dec 2022 13:22:23 +0200
Subject: [PATCH 0573/1167] net/mlx5e: Fix macsec possible null dereference
when updating MAC security entity (SecY)
Upon updating MAC security entity (SecY) in hw offload path, the macsec
security association (SA) initialization routine is called. In case of
extended packet number (epn) is enabled the salt and ssci attributes are
retrieved using the MACsec driver rx_sa context which is unavailable when
updating a SecY property such as encoding-sa hence the null dereference.
Fix by using the provided SA to set those attributes.
Fixes: 4411a6c0abd3 ("net/mlx5e: Support MACsec offload extended packet number (EPN)")
Signed-off-by: Emeel Hakim <ehakim@nvidia.com>
Reviewed-by: Raed Salem <raeds@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/en_accel/macsec.c | 9 ++-------
1 file changed, 2 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index cf7b3bb54c861..7f6b940830b31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -359,7 +359,6 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5_macsec_obj_attrs obj_attrs;
union mlx5e_macsec_rule *macsec_rule;
- struct macsec_key *key;
int err;
obj_attrs.next_pn = sa->next_pn;
@@ -369,13 +368,9 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx,
obj_attrs.aso_pdn = macsec->aso.pdn;
obj_attrs.epn_state = sa->epn_state;
- key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key;
-
if (sa->epn_state.epn_enabled) {
- obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) :
- cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci);
-
- memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt));
+ obj_attrs.ssci = cpu_to_be32((__force u32)sa->ssci);
+ memcpy(&obj_attrs.salt, &sa->salt, sizeof(sa->salt));
}
obj_attrs.replay_window = ctx->secy->replay_window;
--
GitLab
From aa96d6aa7563ec2948195d1f5892cb7a2caa88e3 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 4 Jan 2023 18:21:49 +0900
Subject: [PATCH 0574/1167] nvme-apple: add NVME_QUIRK_IDENTIFY_CNS quirk to
fix regression
From the get-go, this driver and the ANS syslog have been complaining
about namespace identification. In 6.2-rc1, commit 811f4de0344d ("nvme:
avoid fallback to sequential scan due to transient issues") regressed
the driver by no longer allowing fallback to sequential namespace scans,
leaving us with no namespaces.
It turns out that the real problem is that this controller claiming
NVMe 1.1 compat is treating the CNS field as a binary field, as in NVMe
1.0. This already has a quirk, NVME_QUIRK_IDENTIFY_CNS, so set it for
the controller to fix all this nonsense (including other errors
triggered by other CNS commands).
Fixes: 811f4de0344d ("nvme: avoid fallback to sequential scan due to transient issues")
Fixes: 5bd2927aceba ("nvme-apple: Add initial Apple SoC NVMe driver")
Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/apple.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index e36aeb50b4edc..bf1c60edb7f9a 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1493,7 +1493,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
}
ret = nvme_init_ctrl(&anv->ctrl, anv->dev, &nvme_ctrl_ops,
- NVME_QUIRK_SKIP_CID_GEN);
+ NVME_QUIRK_SKIP_CID_GEN | NVME_QUIRK_IDENTIFY_CNS);
if (ret) {
dev_err_probe(dev, ret, "Failed to initialize nvme_ctrl");
goto put_dev;
--
GitLab
From 453116a441f0e556fe8900c99a632529e48f18c9 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 4 Jan 2023 19:16:42 +0900
Subject: [PATCH 0575/1167] nvme-pci: add NVME_QUIRK_IDENTIFY_CNS quirk to
Apple T2 controllers
This mirrors the quirk added to Apple Silicon controllers in apple.c.
These controllers do not support the Active NS ID List command and
behave identically to the SoC version judging by existing user
reports/syslogs, so will need the same fix. This quirk reverts
back to NVMe 1.0 behavior and disables the broken commands.
Fixes: 811f4de0344d ("nvme: avoid fallback to sequential scan due to transient issues")
Signed-off-by: Hector Martin <marcan@marcan.st>
Tested-by: Orlando Chamberlain <orlandoch.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index b13baccedb4a9..91f8adcf6056e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3495,7 +3495,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
NVME_QUIRK_128_BYTES_SQES |
NVME_QUIRK_SHARED_TAGS |
- NVME_QUIRK_SKIP_CID_GEN },
+ NVME_QUIRK_SKIP_CID_GEN |
+ NVME_QUIRK_IDENTIFY_CNS },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ 0, }
};
--
GitLab
From 09113abfb6ba981cb7cb4960b230251afd8966dc Mon Sep 17 00:00:00 2001
From: Tong Zhang <ztong0001@gmail.com>
Date: Thu, 29 Dec 2022 10:37:31 -0800
Subject: [PATCH 0576/1167] nvme-pci: fix error handling in nvme_pci_enable()
There are two issues in nvme_pci_enable():
1) If pci_alloc_irq_vectors() fails, device is left enabled. Fix this by
adding a goto disable statement.
2) nvme_pci_configure_admin_queue could return -ENODEV, in this case,
we will need to free IRQ properly. Otherwise the following warning
could be triggered:
[ 5.286752] WARNING: CPU: 0 PID: 33 at kernel/irq/irqdomain.c:253 irq_domain_remove+0x12d/0x140
[ 5.290547] Call Trace:
[ 5.290626] <TASK>
[ 5.290695] msi_remove_device_irq_domain+0xc9/0xf0
[ 5.290843] msi_device_data_release+0x15/0x80
[ 5.290978] release_nodes+0x58/0x90
[ 5.293788] WARNING: CPU: 0 PID: 33 at kernel/irq/msi.c:276 msi_device_data_release+0x76/0x80
[ 5.297573] Call Trace:
[ 5.297651] <TASK>
[ 5.297719] release_nodes+0x58/0x90
[ 5.297831] devres_release_all+0xef/0x140
[ 5.298339] device_unbind_cleanup+0x11/0xc0
[ 5.298479] really_probe+0x296/0x320
Fixes: a6ee7f19ebfd ("nvme-pci: call nvme_pci_configure_admin_queue from nvme_pci_enable")
Co-developed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Tong Zhang <ztong0001@gmail.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 91f8adcf6056e..a2553b7d9bb8e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2533,7 +2533,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
*/
result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (result < 0)
- return result;
+ goto disable;
dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
@@ -2586,8 +2586,13 @@ static int nvme_pci_enable(struct nvme_dev *dev)
pci_enable_pcie_error_reporting(pdev);
pci_save_state(pdev);
- return nvme_pci_configure_admin_queue(dev);
+ result = nvme_pci_configure_admin_queue(dev);
+ if (result)
+ goto free_irq;
+ return result;
+ free_irq:
+ pci_free_irq_vectors(pdev);
disable:
pci_disable_device(pdev);
return result;
--
GitLab
From 2fa1dc8637b5f3397f22b2771f8a4fb8712c10dc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 8 Jan 2023 07:45:30 +0100
Subject: [PATCH 0577/1167] nvme: remove __nvme_ioctl
Open code __nvme_ioctl in the two callers to make future changes that
pass down additional paramters in the ioctl path easier.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
drivers/nvme/host/ioctl.c | 18 ++++++++----------
1 file changed, 8 insertions(+), 10 deletions(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index a8639919237e6..c12b7c445fc0b 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -695,28 +695,26 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
}
}
-static int __nvme_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *arg,
- fmode_t mode)
-{
- if (is_ctrl_ioctl(cmd))
- return nvme_ctrl_ioctl(ns->ctrl, cmd, arg, mode);
- return nvme_ns_ioctl(ns, cmd, arg, mode);
-}
-
int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
+ void __user *argp = (void __user *)arg;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, mode);
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode);
+ return nvme_ns_ioctl(ns, cmd, argp, mode);
}
long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns =
container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev);
+ void __user *argp = (void __user *)arg;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, file->f_mode);
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode);
+ return nvme_ns_ioctl(ns, cmd, argp, file->f_mode);
}
static int nvme_uring_cmd_checks(unsigned int issue_flags)
--
GitLab
From 7b7fdb8e2dbc15ad4e81a328f1c60d1691c6d6be Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 8 Jan 2023 07:53:03 +0100
Subject: [PATCH 0578/1167] nvme: replace the "bool vec" arguments with flags
in the ioctl path
To prepare for passing down more information, replace the boolean
vec argument with a more extensible flags one.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
drivers/nvme/host/ioctl.c | 53 +++++++++++++++++++++------------------
1 file changed, 28 insertions(+), 25 deletions(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index c12b7c445fc0b..999ebc1b70005 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -8,6 +8,10 @@
#include <linux/io_uring.h>
#include "nvme.h"
+enum {
+ NVME_IOCTL_VEC = (1 << 0),
+};
+
static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
fmode_t mode)
{
@@ -150,7 +154,7 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
static int nvme_map_user_request(struct request *req, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
- bool vec)
+ unsigned int flags)
{
struct request_queue *q = req->q;
struct nvme_ns *ns = q->queuedata;
@@ -163,7 +167,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
struct iov_iter iter;
/* fixedbufs is only for non-vectored io */
- if (WARN_ON_ONCE(vec))
+ if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
return -EINVAL;
ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
rq_data_dir(req), &iter, ioucmd);
@@ -172,8 +176,8 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL);
} else {
ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer),
- bufflen, GFP_KERNEL, vec, 0, 0,
- rq_data_dir(req));
+ bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0,
+ 0, rq_data_dir(req));
}
if (ret)
@@ -203,9 +207,9 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
}
static int nvme_submit_user_cmd(struct request_queue *q,
- struct nvme_command *cmd, u64 ubuffer,
- unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u64 *result, unsigned timeout, bool vec)
+ struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
+ void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+ u64 *result, unsigned timeout, unsigned int flags)
{
struct nvme_ctrl *ctrl;
struct request *req;
@@ -221,7 +225,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
req->timeout = timeout;
if (ubuffer && bufflen) {
ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
- meta_len, meta_seed, &meta, NULL, vec);
+ meta_len, meta_seed, &meta, NULL, flags);
if (ret)
return ret;
}
@@ -304,10 +308,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
c.rw.apptag = cpu_to_le16(io.apptag);
c.rw.appmask = cpu_to_le16(io.appmask);
- return nvme_submit_user_cmd(ns->queue, &c,
- io.addr, length,
- metadata, meta_len, lower_32_bits(io.slba), NULL, 0,
- false);
+ return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
+ meta_len, lower_32_bits(io.slba), NULL, 0, 0);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
@@ -360,9 +362,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &result, timeout, false);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &result, timeout, 0);
if (status >= 0) {
if (put_user(result, &ucmd->result))
@@ -373,8 +374,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
}
static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd64 __user *ucmd, bool vec,
- fmode_t mode)
+ struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd64 cmd;
struct nvme_command c;
@@ -408,9 +409,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &cmd.result, timeout, vec);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &cmd.result, timeout, flags);
if (status >= 0) {
if (put_user(cmd.result, &ucmd->result))
@@ -643,7 +643,7 @@ static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd,
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp, mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, mode);
default:
return sed_ioctl(ctrl->opal_dev, cmd, argp);
}
@@ -670,6 +670,8 @@ struct nvme_user_io32 {
static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
void __user *argp, fmode_t mode)
{
+ unsigned int flags = 0;
+
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
@@ -686,10 +688,11 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
#endif
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, argp);
- case NVME_IOCTL_IO64_CMD:
- return nvme_user_cmd64(ns->ctrl, ns, argp, false, mode);
case NVME_IOCTL_IO64_CMD_VEC:
- return nvme_user_cmd64(ns->ctrl, ns, argp, true, mode);
+ flags |= NVME_IOCTL_VEC;
+ fallthrough;
+ case NVME_IOCTL_IO64_CMD:
+ return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode);
default:
return -ENOTTY;
}
@@ -962,7 +965,7 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd,
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp, file->f_mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, file->f_mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp, file->f_mode);
case NVME_IOCTL_RESET:
--
GitLab
From 313c08c72ee7f87c54e34baec5cc4f4005e8800d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 8 Jan 2023 07:56:54 +0100
Subject: [PATCH 0579/1167] nvme: don't allow unprivileged passthrough on
partitions
Passthrough commands can always access the entire device, and thus
submitting them on partitions is an privelege escalation.
In hindsight we should have never allowed any passthrough commands on
partitions, but it's probably too late to change that decision now.
Fixes: e4fbcf32c860 ("nvme: identify-namespace without CAP_SYS_ADMIN")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
---
drivers/nvme/host/ioctl.c | 47 ++++++++++++++++++++++++++-------------
1 file changed, 31 insertions(+), 16 deletions(-)
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 999ebc1b70005..06f52db34be9b 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -10,16 +10,24 @@
enum {
NVME_IOCTL_VEC = (1 << 0),
+ NVME_IOCTL_PARTITION = (1 << 1),
};
static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
- fmode_t mode)
+ unsigned int flags, fmode_t mode)
{
u32 effects;
if (capable(CAP_SYS_ADMIN))
return true;
+ /*
+ * Do not allow unprivileged passthrough on partitions, as that allows an
+ * escape from the containment of the partition.
+ */
+ if (flags & NVME_IOCTL_PARTITION)
+ return false;
+
/*
* Do not allow unprivileged processes to send vendor specific or fabrics
* commands as we can't be sure about their effects.
@@ -327,7 +335,8 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
}
static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd __user *ucmd, fmode_t mode)
+ struct nvme_passthru_cmd __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd cmd;
struct nvme_command c;
@@ -355,7 +364,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, mode))
return -EACCES;
if (cmd.timeout_ms)
@@ -402,7 +411,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, flags, mode))
return -EACCES;
if (cmd.timeout_ms)
@@ -571,7 +580,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14));
c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15));
- if (!nvme_cmd_allowed(ns, &c, ioucmd->file->f_mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode))
return -EACCES;
d.metadata = READ_ONCE(cmd->metadata);
@@ -641,7 +650,7 @@ static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd,
{
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, mode);
case NVME_IOCTL_ADMIN64_CMD:
return nvme_user_cmd64(ctrl, NULL, argp, 0, mode);
default:
@@ -668,16 +677,14 @@ struct nvme_user_io32 {
#endif /* COMPAT_FOR_U64_ALIGNMENT */
static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
- void __user *argp, fmode_t mode)
+ void __user *argp, unsigned int flags, fmode_t mode)
{
- unsigned int flags = 0;
-
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
return ns->head->ns_id;
case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->ctrl, ns, argp, mode);
+ return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode);
/*
* struct nvme_user_io can have different padding on some 32-bit ABIs.
* Just accept the compat version as all fields that are used are the
@@ -703,10 +710,14 @@ int nvme_ioctl(struct block_device *bdev, fmode_t mode,
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
void __user *argp = (void __user *)arg;
+ unsigned int flags = 0;
+
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
if (is_ctrl_ioctl(cmd))
return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode);
- return nvme_ns_ioctl(ns, cmd, argp, mode);
+ return nvme_ns_ioctl(ns, cmd, argp, flags, mode);
}
long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -717,7 +728,7 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
if (is_ctrl_ioctl(cmd))
return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode);
- return nvme_ns_ioctl(ns, cmd, argp, file->f_mode);
+ return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
}
static int nvme_uring_cmd_checks(unsigned int issue_flags)
@@ -807,6 +818,10 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret = -EWOULDBLOCK;
+ unsigned int flags = 0;
+
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
@@ -822,7 +837,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
@@ -847,7 +862,7 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
file->f_mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, file->f_mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
@@ -946,7 +961,7 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
kref_get(&ns->kref);
up_read(&ctrl->namespaces_rwsem);
- ret = nvme_user_cmd(ctrl, ns, argp, mode);
+ ret = nvme_user_cmd(ctrl, ns, argp, 0, mode);
nvme_put_ns(ns);
return ret;
@@ -963,7 +978,7 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, file->f_mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_ADMIN64_CMD:
return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_IO_CMD:
--
GitLab
From c7c0644ead24c59cc5e0f2ff0ade89b21783614a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 3 Jan 2023 17:02:05 +0000
Subject: [PATCH 0580/1167] MAINTAINERS: stop nvme matching for nvmem files
The nvme patterns detect all include files starting with nvme, which
also picks up the nvmem subsystem header files. Fix this by using
a more specific pattern.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
[hch: switched to a purely inclusive pattern instead of excluding nvmem*]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
MAINTAINERS | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 3ef137fea4f6d..b9800f5cca6d6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14830,7 +14830,8 @@ T: git://git.infradead.org/nvme.git
F: Documentation/nvme/
F: drivers/nvme/host/
F: drivers/nvme/common/
-F: include/linux/nvme*
+F: include/linux/nvme.h
+F: include/linux/nvme-*.h
F: include/uapi/linux/nvme_ioctl.h
NVM EXPRESS FABRICS AUTHENTICATION
--
GitLab
From de1ccb9e61728dd941fe0e955a7a129418657267 Mon Sep 17 00:00:00 2001
From: Adrian Chan <adchan@google.com>
Date: Mon, 9 Jan 2023 16:05:20 -0500
Subject: [PATCH 0581/1167] ALSA: hda/hdmi: Add a HP device 0x8715 to force
connect list
Add the 'HP Engage Flex Mini' device to the force connect list to
enable audio through HDMI.
Signed-off-by: Adrian Chan <adchan@google.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20230109210520.16060-1-adchan@google.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_hdmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 386dd9d9143f9..9ea633fe93393 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1981,6 +1981,7 @@ static const struct snd_pci_quirk force_connect_list[] = {
SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
+ SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
--
GitLab
From 6acd87d50998ef0afafc441613aeaf5a8f5c9eff Mon Sep 17 00:00:00 2001
From: Siddh Raman Pant <code@siddh.me>
Date: Fri, 9 Dec 2022 15:51:51 +0530
Subject: [PATCH 0582/1167] erofs/zmap.c: Fix incorrect offset calculation
Effective offset to add to length was being incorrectly calculated,
which resulted in iomap->length being set to 0, triggering a WARN_ON
in iomap_iter_done().
Fix that, and describe it in comments.
This was reported as a crash by syzbot under an issue about a warning
encountered in iomap_iter_done(), but unrelated to erofs.
C reproducer: https://syzkaller.appspot.com/text?tag=ReproC&x=1037a6b2880000
Kernel config: https://syzkaller.appspot.com/text?tag=KernelConfig&x=e2021a61197ebe02
Dashboard link: https://syzkaller.appspot.com/bug?extid=a8e049cd3abd342936b6
Reported-by: syzbot+a8e049cd3abd342936b6@syzkaller.appspotmail.com
Suggested-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Siddh Raman Pant <code@siddh.me>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20221209102151.311049-1-code@siddh.me
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
fs/erofs/zmap.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 0150570c33aae..98fb90b9af715 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -793,12 +793,16 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
/*
- * No strict rule how to describe extents for post EOF, yet
- * we need do like below. Otherwise, iomap itself will get
+ * No strict rule on how to describe extents for post EOF, yet
+ * we need to do like below. Otherwise, iomap itself will get
* into an endless loop on post EOF.
+ *
+ * Calculate the effective offset by subtracting extent start
+ * (map.m_la) from the requested offset, and add it to length.
+ * (NB: offset >= map.m_la always)
*/
if (iomap->offset >= inode->i_size)
- iomap->length = length + map.m_la - offset;
+ iomap->length = length + offset - map.m_la;
}
iomap->flags = 0;
return 0;
--
GitLab
From 12724ba38992bd045e92a9a88a868a530f89d13e Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 10 Jan 2023 15:49:27 +0800
Subject: [PATCH 0583/1167] erofs: fix kvcalloc() misuse with __GFP_NOFAIL
As reported by syzbot [1], kvcalloc() cannot work with __GFP_NOFAIL.
Let's use kcalloc() instead.
[1] https://lore.kernel.org/r/0000000000007796bd05f1852ec2@google.com
Reported-by: syzbot+c3729cda01706a04fb98@syzkaller.appspotmail.com
Fixes: fe3e5914e6dc ("erofs: try to leave (de)compressed_pages on stack if possible")
Fixes: 4f05687fd703 ("erofs: introduce struct z_erofs_decompress_backend")
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230110074927.41651-1-hsiangkao@linux.alibaba.com
---
fs/erofs/zdata.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index ccf7c55d477fe..5200bb86e2643 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1032,12 +1032,12 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
if (!be->decompressed_pages)
be->decompressed_pages =
- kvcalloc(be->nr_pages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(be->nr_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
if (!be->compressed_pages)
be->compressed_pages =
- kvcalloc(pclusterpages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(pclusterpages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
z_erofs_parse_out_bvecs(be);
err2 = z_erofs_parse_in_bvecs(be, &overlapped);
@@ -1085,7 +1085,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
}
if (be->compressed_pages < be->onstack_pages ||
be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
- kvfree(be->compressed_pages);
+ kfree(be->compressed_pages);
z_erofs_fill_other_copies(be, err);
for (i = 0; i < be->nr_pages; ++i) {
@@ -1104,7 +1104,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
}
if (be->decompressed_pages != be->onstack_pages)
- kvfree(be->decompressed_pages);
+ kfree(be->decompressed_pages);
pcl->length = 0;
pcl->partial = true;
--
GitLab
From e59370b2e96eb8e7e057a2a16e999ff385a3f2fb Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sun, 8 Jan 2023 16:45:41 +0100
Subject: [PATCH 0584/1167] selftests/net: l2_tos_ttl_inherit.sh: Set IPv6
addresses with "nodad".
The ping command can run before DAD completes. In that case, ping may
fail and break the selftest.
We don't need DAD here since we're working on isolated device pairs.
Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
tools/testing/selftests/net/l2_tos_ttl_inherit.sh | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
index dca1e6f777a89..e2574b08eabc9 100755
--- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
+++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
@@ -137,8 +137,8 @@ setup() {
if [ "$type" = "gre" ]; then
type="ip6gretap"
fi
- ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0
- $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1
+ ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 nodad
+ $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 nodad
ip link add name tep0 type $type $local_addr1 \
remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \
$vxlan $geneve
@@ -170,8 +170,8 @@ setup() {
ip addr add 198.19.0.1/24 brd + dev ${parent}0
$ns ip addr add 198.19.0.2/24 brd + dev ${parent}1
elif [ "$inner" = "6" ]; then
- ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0
- $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1
+ ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 nodad
+ $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 nodad
fi
}
--
GitLab
From c53cb00f7983a5474f2d36967f84908b85af9159 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sun, 8 Jan 2023 16:45:46 +0100
Subject: [PATCH 0585/1167] selftests/net: l2_tos_ttl_inherit.sh: Run tests in
their own netns.
This selftest currently runs half in the current namespace and half in
a netns of its own. Therefore, the test can fail if the current
namespace is already configured with incompatible parameters (for
example if it already has a veth0 interface).
Adapt the script to put both ends of the veth pair in their own netns.
Now veth0 is created in NS0 instead of the current namespace, while
veth1 is set up in NS1 (instead of the 'testing' netns).
The user visible netns names are randomised to minimise the risk of
conflicts with already existing namespaces. The cleanup() function
doesn't need to remove the virtual interface anymore: deleting NS0 and
NS1 automatically removes the virtual interfaces they contained.
We can remove $ns, which was only used to run ip commands in the
'testing' netns (let's use the builtin "-netns" option instead).
However, we still need a similar functionality as ping and tcpdump
now need to run in NS0. So we now have $RUN_NS0 for that.
Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting")
Reported-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Tested-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
.../selftests/net/l2_tos_ttl_inherit.sh | 162 ++++++++++--------
1 file changed, 93 insertions(+), 69 deletions(-)
diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
index e2574b08eabc9..cf56680d598f2 100755
--- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
+++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
@@ -25,6 +25,11 @@ expected_tos="0x00"
expected_ttl="0"
failed=false
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+
+RUN_NS0="ip netns exec ${NS0}"
+
get_random_tos() {
# Get a random hex tos value between 0x00 and 0xfc, a multiple of 4
echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\
@@ -61,7 +66,6 @@ setup() {
local vlan="$5"
local test_tos="0x00"
local test_ttl="0"
- local ns="ip netns exec testing"
# We don't want a test-tos of 0x00,
# because this is the value that we get when no tos is set.
@@ -94,14 +98,15 @@ setup() {
printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \
"$type" "$outer" "$inner" "$tos" "$ttl" "$vlan"
- # Create 'testing' netns, veth pair and connect main ns with testing ns
- ip netns add testing
- ip link add type veth
- ip link set veth1 netns testing
- ip link set veth0 up
- $ns ip link set veth1 up
- ip addr flush dev veth0
- $ns ip addr flush dev veth1
+ # Create netns NS0 and NS1 and connect them with a veth pair
+ ip netns add "${NS0}"
+ ip netns add "${NS1}"
+ ip link add name veth0 netns "${NS0}" type veth \
+ peer name veth1 netns "${NS1}"
+ ip -netns "${NS0}" link set dev veth0 up
+ ip -netns "${NS1}" link set dev veth1 up
+ ip -netns "${NS0}" address flush dev veth0
+ ip -netns "${NS1}" address flush dev veth1
local local_addr1=""
local local_addr2=""
@@ -127,51 +132,59 @@ setup() {
if [ "$type" = "gre" ]; then
type="gretap"
fi
- ip addr add 198.18.0.1/24 dev veth0
- $ns ip addr add 198.18.0.2/24 dev veth1
- ip link add name tep0 type $type $local_addr1 remote \
- 198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 remote \
- 198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0
+ ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote 198.18.0.2 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote 198.18.0.1 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
type="ip6gretap"
fi
- ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 nodad
- $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 nodad
- ip link add name tep0 type $type $local_addr1 \
- remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 \
- remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
+ ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \
+ dev veth0 nodad
+ ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \
+ dev veth1 nodad
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote fdd1:ced0:5d88:3fce::2 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote fdd1:ced0:5d88:3fce::1 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
fi
# Bring L2-tunnel link up and create VLAN on top
- ip link set tep0 up
- $ns ip link set tep1 up
- ip addr flush dev tep0
- $ns ip addr flush dev tep1
+ ip -netns "${NS0}" link set tep0 up
+ ip -netns "${NS1}" link set tep1 up
+ ip -netns "${NS0}" address flush dev tep0
+ ip -netns "${NS1}" address flush dev tep1
local parent
if $vlan; then
parent="vlan99-"
- ip link add link tep0 name ${parent}0 type vlan id 99
- $ns ip link add link tep1 name ${parent}1 type vlan id 99
- ip link set ${parent}0 up
- $ns ip link set ${parent}1 up
- ip addr flush dev ${parent}0
- $ns ip addr flush dev ${parent}1
+ ip -netns "${NS0}" link add link tep0 name ${parent}0 \
+ type vlan id 99
+ ip -netns "${NS1}" link add link tep1 name ${parent}1 \
+ type vlan id 99
+ ip -netns "${NS0}" link set dev ${parent}0 up
+ ip -netns "${NS1}" link set dev ${parent}1 up
+ ip -netns "${NS0}" address flush dev ${parent}0
+ ip -netns "${NS1}" address flush dev ${parent}1
else
parent="tep"
fi
# Assign inner IPv4/IPv6 addresses
if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then
- ip addr add 198.19.0.1/24 brd + dev ${parent}0
- $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1
+ ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0
+ ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1
elif [ "$inner" = "6" ]; then
- ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 nodad
- $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 nodad
+ ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \
+ dev ${parent}0 nodad
+ ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \
+ dev ${parent}1 nodad
fi
}
@@ -192,10 +205,10 @@ verify() {
ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6
fi
if [ "$tos_ttl" = "inherit" ]; then
- ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \
- 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos" \
+ -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!"
else
- ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
fi
local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset
if [ "$type" = "gre" ]; then
@@ -216,10 +229,12 @@ verify() {
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x01 and \
- ip[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x01 and \
+ ip[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
req_proto_offset="44"
req_offset="78"
@@ -231,10 +246,12 @@ verify() {
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x3a and \
- ip[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x3a and \
+ ip[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
req_proto_offset="36"
req_offset="45"
@@ -250,11 +267,13 @@ verify() {
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x08 and \
- ip[$((req_proto_offset + 1))] = 0x06 and \
- ip[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x08 and \
+ ip[$((req_proto_offset + 1))] = 0x06 and \
+ ip[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
@@ -273,10 +292,12 @@ verify() {
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x01 and \
- ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x01 and \
+ ip6[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
local req_proto_offset="72"
local req_offset="106"
@@ -288,10 +309,12 @@ verify() {
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x3a and \
- ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x3a and \
+ ip6[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
local req_proto_offset="64"
local req_offset="73"
@@ -307,11 +330,13 @@ verify() {
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x08 and \
- ip6[$((req_proto_offset + 1))] = 0x06 and \
- ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x08 and \
+ ip6[$((req_proto_offset + 1))] = 0x06 and \
+ ip6[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
fi
kill -9 $ping_pid
@@ -351,9 +376,8 @@ verify() {
}
cleanup() {
- ip link del veth0 2>/dev/null
- ip netns del testing 2>/dev/null
- ip link del tep0 2>/dev/null
+ ip netns del "${NS0}" 2>/dev/null
+ ip netns del "${NS1}" 2>/dev/null
}
printf "┌────────┬───────┬───────┬──────────────┬"
--
GitLab
From d68ff8ad3351b8fc8d6f14b9a4f5cc8ba3e8bd13 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Sun, 8 Jan 2023 16:45:50 +0100
Subject: [PATCH 0586/1167] selftests/net: l2_tos_ttl_inherit.sh: Ensure
environment cleanup on failure.
Use 'set -e' and an exit handler to stop the script if a command fails
and ensure the test environment is cleaned up in any case. Also, handle
the case where the script is interrupted by SIGINT.
The only command that's expected to fail is 'wait $ping_pid', since
it's killed by the script. Handle this case with '|| true' to make it
play well with 'set -e'.
Finally, return the Kselftest SKIP code (4) when the script breaks
because of an environment problem or a command line failure. The 0 and
1 return codes should now reliably indicate that all tests have been
run (0: all tests run and passed, 1: all tests run but at least one
failed, 4: test script didn't run completely).
Fixes: b690842d12fd ("selftests/net: test l2 tunnel TOS/TTL inheriting")
Reported-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Tested-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
.../selftests/net/l2_tos_ttl_inherit.sh | 40 +++++++++++++++++--
1 file changed, 36 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
index cf56680d598f2..f11756e7df2f9 100755
--- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
+++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh
@@ -12,13 +12,16 @@
# In addition this script also checks if forcing a specific field in the
# outer header is working.
+# Return 4 by default (Kselftest SKIP code)
+ERR=4
+
if [ "$(id -u)" != "0" ]; then
echo "Please run as root."
- exit 0
+ exit $ERR
fi
if ! which tcpdump > /dev/null 2>&1; then
echo "No tcpdump found. Required for this test."
- exit 0
+ exit $ERR
fi
expected_tos="0x00"
@@ -340,7 +343,7 @@ verify() {
fi
fi
kill -9 $ping_pid
- wait $ping_pid 2>/dev/null
+ wait $ping_pid 2>/dev/null || true
result="FAIL"
if [ "$outer" = "4" ]; then
captured_ttl="$(get_field "ttl" "$out")"
@@ -380,6 +383,31 @@ cleanup() {
ip netns del "${NS1}" 2>/dev/null
}
+exit_handler() {
+ # Don't exit immediately if one of the intermediate commands fails.
+ # We might be called at the end of the script, when the network
+ # namespaces have already been deleted. So cleanup() may fail, but we
+ # still need to run until 'exit $ERR' or the script won't return the
+ # correct error code.
+ set +e
+
+ cleanup
+
+ exit $ERR
+}
+
+# Restore the default SIGINT handler (just in case) and exit.
+# The exit handler will take care of cleaning everything up.
+interrupted() {
+ trap - INT
+
+ exit $ERR
+}
+
+set -e
+trap exit_handler EXIT
+trap interrupted INT
+
printf "┌────────┬───────┬───────┬──────────────┬"
printf "──────────────┬───────┬────────â”\n"
for type in gre vxlan geneve; do
@@ -409,6 +437,10 @@ done
printf "└────────┴───────┴───────┴──────────────┴"
printf "──────────────┴───────┴────────┘\n"
+# All tests done.
+# Set ERR appropriately: it will be returned by the exit handler.
if $failed; then
- exit 1
+ ERR=1
+else
+ ERR=0
fi
--
GitLab
From 80502ffab2fa92ba9777e381efea2efddc348d13 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Thu, 15 Dec 2022 15:54:02 +1300
Subject: [PATCH 0587/1167] arm64: dts: marvell: AC5/AC5X: Fix address for
UART1
The correct address offset is 0x12100.
Fixes: 31be791e26cf ("arm64: dts: marvell: Add UART1-3 for AC5/AC5X")
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
---
arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
index 7308f7b6b22c9..8bce640691387 100644
--- a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi
@@ -98,7 +98,7 @@ uart0: serial@12000 {
uart1: serial@12100 {
compatible = "snps,dw-apb-uart";
- reg = <0x11000 0x100>;
+ reg = <0x12100 0x100>;
reg-shift = <2>;
interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
reg-io-width = <1>;
--
GitLab
From 53da7aec32982f5ee775b69dce06d63992ce4af3 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Mon, 9 Jan 2023 11:43:25 +0530
Subject: [PATCH 0588/1167] octeontx2-pf: Fix resource leakage in VF driver
unbind
resources allocated like mcam entries to support the Ntuple feature
and hash tables for the tc feature are not getting freed in driver
unbind. This patch fixes the issue.
Fixes: 2da489432747 ("octeontx2-pf: devlink params support to set mcam entry count")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Link: https://lore.kernel.org/r/20230109061325.21395-1-hkelam@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 86653bb8e403a..7f8ffbf79cf74 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -758,6 +758,8 @@ static void otx2vf_remove(struct pci_dev *pdev)
if (vf->otx2_wq)
destroy_workqueue(vf->otx2_wq);
otx2_ptp_destroy(vf);
+ otx2_mcam_flow_del(vf);
+ otx2_shutdown_tc(vf);
otx2vf_disable_mbox_intr(vf);
otx2_detach_resources(&vf->mbox);
if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
--
GitLab
From 0afec5e9cea732cb47014655685a2a47fb180c31 Mon Sep 17 00:00:00 2001
From: Yonatan Nachum <ynachum@amazon.com>
Date: Mon, 9 Jan 2023 13:37:11 +0000
Subject: [PATCH 0589/1167] RDMA/core: Fix ib block iterator counter overflow
When registering a new DMA MR after selecting the best aligned page size
for it, we iterate over the given sglist to split each entry to smaller,
aligned to the selected page size, DMA blocks.
In given circumstances where the sg entry and page size fit certain
sizes and the sg entry is not aligned to the selected page size, the
total size of the aligned pages we need to cover the sg entry is >= 4GB.
Under this circumstances, while iterating page aligned blocks, the
counter responsible for counting how much we advanced from the start of
the sg entry is overflowed because its type is u32 and we pass 4GB in
size. This can lead to an infinite loop inside the iterator function
because the overflow prevents the counter to be larger
than the size of the sg entry.
Fix the presented problem by changing the advancement condition to
eliminate overflow.
Backtrace:
[ 192.374329] efa_reg_user_mr_dmabuf
[ 192.376783] efa_register_mr
[ 192.382579] pgsz_bitmap 0xfffff000 rounddown 0x80000000
[ 192.386423] pg_sz [0x80000000] umem_length[0xc0000000]
[ 192.392657] start 0x0 length 0xc0000000 params.page_shift 31 params.page_num 3
[ 192.399559] hp_cnt[3], pages_in_hp[524288]
[ 192.403690] umem->sgt_append.sgt.nents[1]
[ 192.407905] number entries: [1], pg_bit: [31]
[ 192.411397] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8]
[ 192.415601] biter->__sg_advance [665837568] sg_dma_len[3221225472]
[ 192.419823] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8]
[ 192.423976] biter->__sg_advance [2813321216] sg_dma_len[3221225472]
[ 192.428243] biter->__sg_nents [1] biter->__sg [0000000008b0c5d8]
[ 192.432397] biter->__sg_advance [665837568] sg_dma_len[3221225472]
Fixes: a808273a495c ("RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks")
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Link: https://lore.kernel.org/r/20230109133711.13678-1-ynachum@amazon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/core/verbs.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 26b021f43ba40..11b1c1603aeb4 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2957,15 +2957,18 @@ EXPORT_SYMBOL(__rdma_block_iter_start);
bool __rdma_block_iter_next(struct ib_block_iter *biter)
{
unsigned int block_offset;
+ unsigned int sg_delta;
if (!biter->__sg_nents || !biter->__sg)
return false;
biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance;
block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1);
- biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset;
+ sg_delta = BIT_ULL(biter->__pg_bit) - block_offset;
- if (biter->__sg_advance >= sg_dma_len(biter->__sg)) {
+ if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) {
+ biter->__sg_advance += sg_delta;
+ } else {
biter->__sg_advance = 0;
biter->__sg = sg_next(biter->__sg);
biter->__sg_nents--;
--
GitLab
From 0a0a6e80472c98947d73c3d13bcd7d101895f55d Mon Sep 17 00:00:00 2001
From: Dean Luick <dean.luick@cornelisnetworks.com>
Date: Mon, 9 Jan 2023 12:31:11 -0500
Subject: [PATCH 0590/1167] IB/hfi1: Reject a zero-length user expected buffer
A zero length user buffer makes no sense and the code
does not handle it correctly. Instead, reject a
zero length as invalid.
Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres")
Signed-off-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/167328547120.1472310.6362802432127399257.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/hfi1/user_exp_rcv.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 186d302912606..3c609b11e71ca 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -256,6 +256,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
if (!PAGE_ALIGNED(tinfo->vaddr))
return -EINVAL;
+ if (tinfo->length == 0)
+ return -EINVAL;
tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL);
if (!tidbuf)
--
GitLab
From ecf91551cdd2925ed6d9a9d99074fa5f67b90596 Mon Sep 17 00:00:00 2001
From: Dean Luick <dean.luick@cornelisnetworks.com>
Date: Mon, 9 Jan 2023 12:31:16 -0500
Subject: [PATCH 0591/1167] IB/hfi1: Reserve user expected TIDs
To avoid a race, reserve the number of user expected
TIDs before setup.
Fixes: 7e7a436ecb6e ("staging/hfi1: Add TID entry program function body")
Signed-off-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/167328547636.1472310.7419712824785353905.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/hfi1/user_exp_rcv.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 3c609b11e71ca..d7487555d109a 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -282,16 +282,13 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
/* Find sets of physically contiguous pages */
tidbuf->n_psets = find_phys_blocks(tidbuf, pinned);
- /*
- * We don't need to access this under a lock since tid_used is per
- * process and the same process cannot be in hfi1_user_exp_rcv_clear()
- * and hfi1_user_exp_rcv_setup() at the same time.
- */
+ /* Reserve the number of expected tids to be used. */
spin_lock(&fd->tid_lock);
if (fd->tid_used + tidbuf->n_psets > fd->tid_limit)
pageset_count = fd->tid_limit - fd->tid_used;
else
pageset_count = tidbuf->n_psets;
+ fd->tid_used += pageset_count;
spin_unlock(&fd->tid_lock);
if (!pageset_count)
@@ -400,10 +397,11 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
nomem:
hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx,
mapped_pages, ret);
+ /* adjust reserved tid_used to actual count */
+ spin_lock(&fd->tid_lock);
+ fd->tid_used -= pageset_count - tididx;
+ spin_unlock(&fd->tid_lock);
if (tididx) {
- spin_lock(&fd->tid_lock);
- fd->tid_used += tididx;
- spin_unlock(&fd->tid_lock);
tinfo->tidcnt = tididx;
tinfo->length = mapped_pages * PAGE_SIZE;
--
GitLab
From e0c4a422f5246abefbf7c178ef99a1f2dc3c5f62 Mon Sep 17 00:00:00 2001
From: Dean Luick <dean.luick@cornelisnetworks.com>
Date: Mon, 9 Jan 2023 12:31:21 -0500
Subject: [PATCH 0592/1167] IB/hfi1: Fix expected receive setup error exit
issues
Fix three error exit issues in expected receive setup.
Re-arrange error exits to increase readability.
Issues and fixes:
1. Possible missed page unpin if tidlist copyout fails and
not all pinned pages where made part of a TID.
Fix: Unpin the unused pages.
2. Return success with unset return values tidcnt and length
when no pages were pinned.
Fix: Return -ENOSPC if no pages were pinned.
3. Return success with unset return values tidcnt and length when
no rcvarray entries available.
Fix: Return -ENOSPC if no rcvarray entries are available.
Fixes: 7e7a436ecb6e ("staging/hfi1: Add TID entry program function body")
Fixes: 97736f36dbeb ("IB/hfi1: Validate page aligned for a given virtual addres")
Fixes: f404ca4c7ea8 ("IB/hfi1: Refactor hfi_user_exp_rcv_setup() IOCTL")
Signed-off-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/167328548150.1472310.1492305874804187634.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/hfi1/user_exp_rcv.c | 83 ++++++++++++++---------
1 file changed, 50 insertions(+), 33 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index d7487555d109a..88df8ca4bb577 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -268,15 +268,14 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets),
GFP_KERNEL);
if (!tidbuf->psets) {
- kfree(tidbuf);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto fail_release_mem;
}
pinned = pin_rcv_pages(fd, tidbuf);
if (pinned <= 0) {
- kfree(tidbuf->psets);
- kfree(tidbuf);
- return pinned;
+ ret = (pinned < 0) ? pinned : -ENOSPC;
+ goto fail_unpin;
}
/* Find sets of physically contiguous pages */
@@ -291,14 +290,16 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
fd->tid_used += pageset_count;
spin_unlock(&fd->tid_lock);
- if (!pageset_count)
- goto bail;
+ if (!pageset_count) {
+ ret = -ENOSPC;
+ goto fail_unreserve;
+ }
ngroups = pageset_count / dd->rcv_entries.group_size;
tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL);
if (!tidlist) {
ret = -ENOMEM;
- goto nomem;
+ goto fail_unreserve;
}
tididx = 0;
@@ -394,44 +395,60 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
}
unlock:
mutex_unlock(&uctxt->exp_mutex);
-nomem:
hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx,
mapped_pages, ret);
+
+ /* fail if nothing was programmed, set error if none provided */
+ if (tididx == 0) {
+ if (ret >= 0)
+ ret = -ENOSPC;
+ goto fail_unreserve;
+ }
+
/* adjust reserved tid_used to actual count */
spin_lock(&fd->tid_lock);
fd->tid_used -= pageset_count - tididx;
spin_unlock(&fd->tid_lock);
- if (tididx) {
- tinfo->tidcnt = tididx;
- tinfo->length = mapped_pages * PAGE_SIZE;
- if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
- tidlist, sizeof(tidlist[0]) * tididx)) {
- /*
- * On failure to copy to the user level, we need to undo
- * everything done so far so we don't leak resources.
- */
- tinfo->tidlist = (unsigned long)&tidlist;
- hfi1_user_exp_rcv_clear(fd, tinfo);
- tinfo->tidlist = 0;
- ret = -EFAULT;
- goto bail;
- }
+ /* unpin all pages not covered by a TID */
+ unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages,
+ false);
+
+ tinfo->tidcnt = tididx;
+ tinfo->length = mapped_pages * PAGE_SIZE;
+
+ if (copy_to_user(u64_to_user_ptr(tinfo->tidlist),
+ tidlist, sizeof(tidlist[0]) * tididx)) {
+ ret = -EFAULT;
+ goto fail_unprogram;
}
- /*
- * If not everything was mapped (due to insufficient RcvArray entries,
- * for example), unpin all unmapped pages so we can pin them nex time.
- */
- if (mapped_pages != pinned)
- unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages,
- (pinned - mapped_pages), false);
-bail:
+ kfree(tidbuf->pages);
kfree(tidbuf->psets);
+ kfree(tidbuf);
kfree(tidlist);
+ return 0;
+
+fail_unprogram:
+ /* unprogram, unmap, and unpin all allocated TIDs */
+ tinfo->tidlist = (unsigned long)tidlist;
+ hfi1_user_exp_rcv_clear(fd, tinfo);
+ tinfo->tidlist = 0;
+ pinned = 0; /* nothing left to unpin */
+ pageset_count = 0; /* nothing left reserved */
+fail_unreserve:
+ spin_lock(&fd->tid_lock);
+ fd->tid_used -= pageset_count;
+ spin_unlock(&fd->tid_lock);
+fail_unpin:
+ if (pinned > 0)
+ unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false);
+fail_release_mem:
kfree(tidbuf->pages);
+ kfree(tidbuf->psets);
kfree(tidbuf);
- return ret > 0 ? 0 : ret;
+ kfree(tidlist);
+ return ret;
}
int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
--
GitLab
From 1c7edde1b5720ddb0aff5ca8c7f605a0f92526eb Mon Sep 17 00:00:00 2001
From: Dean Luick <dean.luick@cornelisnetworks.com>
Date: Mon, 9 Jan 2023 12:31:26 -0500
Subject: [PATCH 0593/1167] IB/hfi1: Immediately remove invalid memory from
hardware
When a user expected receive page is unmapped, it should be
immediately removed from hardware rather than depend on a
reaction from user space.
Fixes: 2677a7680e77 ("IB/hfi1: Fix memory leak during unexpected shutdown")
Signed-off-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/167328548663.1472310.7871808081861622659.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/hfi1/user_exp_rcv.c | 43 +++++++++++++++--------
drivers/infiniband/hw/hfi1/user_exp_rcv.h | 1 +
2 files changed, 30 insertions(+), 14 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 88df8ca4bb577..f402af1e29035 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -28,8 +28,9 @@ static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
unsigned int start, u16 count,
u32 *tidlist, unsigned int *tididx,
unsigned int *pmapped);
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
- struct tid_group **grp);
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo);
+static void __clear_tid_node(struct hfi1_filedata *fd,
+ struct tid_rb_node *node);
static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
static const struct mmu_interval_notifier_ops tid_mn_ops = {
@@ -469,7 +470,7 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd,
mutex_lock(&uctxt->exp_mutex);
for (tididx = 0; tididx < tinfo->tidcnt; tididx++) {
- ret = unprogram_rcvarray(fd, tidinfo[tididx], NULL);
+ ret = unprogram_rcvarray(fd, tidinfo[tididx]);
if (ret) {
hfi1_cdbg(TID, "Failed to unprogram rcv array %d",
ret);
@@ -723,6 +724,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
}
node->fdata = fd;
+ mutex_init(&node->invalidate_mutex);
node->phys = page_to_phys(pages[0]);
node->npages = npages;
node->rcventry = rcventry;
@@ -762,8 +764,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
return -EFAULT;
}
-static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
- struct tid_group **grp)
+static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo)
{
struct hfi1_ctxtdata *uctxt = fd->uctxt;
struct hfi1_devdata *dd = uctxt->dd;
@@ -786,9 +787,6 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
if (!node || node->rcventry != (uctxt->expected_base + rcventry))
return -EBADF;
- if (grp)
- *grp = node->grp;
-
if (fd->use_mn)
mmu_interval_notifier_remove(&node->notifier);
cacheless_tid_rb_remove(fd, node);
@@ -796,23 +794,34 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo,
return 0;
}
-static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+static void __clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
{
struct hfi1_ctxtdata *uctxt = fd->uctxt;
struct hfi1_devdata *dd = uctxt->dd;
+ mutex_lock(&node->invalidate_mutex);
+ if (node->freed)
+ goto done;
+ node->freed = true;
+
trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry,
node->npages,
node->notifier.interval_tree.start, node->phys,
node->dma_addr);
- /*
- * Make sure device has seen the write before we unpin the
- * pages.
- */
+ /* Make sure device has seen the write before pages are unpinned */
hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0);
unpin_rcv_pages(fd, NULL, node, 0, node->npages, true);
+done:
+ mutex_unlock(&node->invalidate_mutex);
+}
+
+static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node)
+{
+ struct hfi1_ctxtdata *uctxt = fd->uctxt;
+
+ __clear_tid_node(fd, node);
node->grp->used--;
node->grp->map &= ~(1 << (node->rcventry - node->grp->base));
@@ -871,10 +880,16 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
if (node->freed)
return true;
+ /* take action only if unmapping */
+ if (range->event != MMU_NOTIFY_UNMAP)
+ return true;
+
trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt,
node->notifier.interval_tree.start,
node->rcventry, node->npages, node->dma_addr);
- node->freed = true;
+
+ /* clear the hardware rcvarray entry */
+ __clear_tid_node(fdata, node);
spin_lock(&fdata->invalid_lock);
if (fdata->invalid_tid_idx < uctxt->expected_count) {
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 8c53e416bf843..2ddb3dac7d916 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
@@ -27,6 +27,7 @@ struct tid_user_buf {
struct tid_rb_node {
struct mmu_interval_notifier notifier;
struct hfi1_filedata *fdata;
+ struct mutex invalidate_mutex; /* covers hw removal */
unsigned long phys;
struct tid_group *grp;
u32 rcventry;
--
GitLab
From b3deec25847bda34e34d5d7be02f633caf000bd8 Mon Sep 17 00:00:00 2001
From: Dean Luick <dean.luick@cornelisnetworks.com>
Date: Mon, 9 Jan 2023 12:31:31 -0500
Subject: [PATCH 0594/1167] IB/hfi1: Remove user expected buffer invalidate
race
During setup, there is a possible race between a page invalidate
and hardware programming. Add a covering invalidate over the user
target range during setup. If anything within that range is
invalidated during setup, fail the setup. Once set up, each
TID will have its own invalidate callback and invalidate.
Fixes: 3889551db212 ("RDMA/hfi1: Use mmu_interval_notifier_insert for user_exp_rcv")
Signed-off-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/167328549178.1472310.9867497376936699488.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
drivers/infiniband/hw/hfi1/user_exp_rcv.c | 58 +++++++++++++++++++++--
drivers/infiniband/hw/hfi1/user_exp_rcv.h | 2 +
2 files changed, 55 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index f402af1e29035..b02f2f0809c81 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -23,6 +23,9 @@ static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
const struct mmu_notifier_range *range,
unsigned long cur_seq);
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+ const struct mmu_notifier_range *range,
+ unsigned long cur_seq);
static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *,
struct tid_group *grp,
unsigned int start, u16 count,
@@ -36,6 +39,9 @@ static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node);
static const struct mmu_interval_notifier_ops tid_mn_ops = {
.invalidate = tid_rb_invalidate,
};
+static const struct mmu_interval_notifier_ops tid_cover_ops = {
+ .invalidate = tid_cover_invalidate,
+};
/*
* Initialize context and file private data needed for Expected
@@ -254,6 +260,7 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
tididx = 0, mapped, mapped_pages = 0;
u32 *tidlist = NULL;
struct tid_user_buf *tidbuf;
+ unsigned long mmu_seq = 0;
if (!PAGE_ALIGNED(tinfo->vaddr))
return -EINVAL;
@@ -264,6 +271,7 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
if (!tidbuf)
return -ENOMEM;
+ mutex_init(&tidbuf->cover_mutex);
tidbuf->vaddr = tinfo->vaddr;
tidbuf->length = tinfo->length;
tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets),
@@ -273,6 +281,16 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
goto fail_release_mem;
}
+ if (fd->use_mn) {
+ ret = mmu_interval_notifier_insert(
+ &tidbuf->notifier, current->mm,
+ tidbuf->vaddr, tidbuf->npages * PAGE_SIZE,
+ &tid_cover_ops);
+ if (ret)
+ goto fail_release_mem;
+ mmu_seq = mmu_interval_read_begin(&tidbuf->notifier);
+ }
+
pinned = pin_rcv_pages(fd, tidbuf);
if (pinned <= 0) {
ret = (pinned < 0) ? pinned : -ENOSPC;
@@ -415,6 +433,20 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages,
false);
+ if (fd->use_mn) {
+ /* check for an invalidate during setup */
+ bool fail = false;
+
+ mutex_lock(&tidbuf->cover_mutex);
+ fail = mmu_interval_read_retry(&tidbuf->notifier, mmu_seq);
+ mutex_unlock(&tidbuf->cover_mutex);
+
+ if (fail) {
+ ret = -EBUSY;
+ goto fail_unprogram;
+ }
+ }
+
tinfo->tidcnt = tididx;
tinfo->length = mapped_pages * PAGE_SIZE;
@@ -424,6 +456,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
goto fail_unprogram;
}
+ if (fd->use_mn)
+ mmu_interval_notifier_remove(&tidbuf->notifier);
kfree(tidbuf->pages);
kfree(tidbuf->psets);
kfree(tidbuf);
@@ -442,6 +476,8 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
fd->tid_used -= pageset_count;
spin_unlock(&fd->tid_lock);
fail_unpin:
+ if (fd->use_mn)
+ mmu_interval_notifier_remove(&tidbuf->notifier);
if (pinned > 0)
unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false);
fail_release_mem:
@@ -740,11 +776,6 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd,
&tid_mn_ops);
if (ret)
goto out_unmap;
- /*
- * FIXME: This is in the wrong order, the notifier should be
- * established before the pages are pinned by pin_rcv_pages.
- */
- mmu_interval_read_begin(&node->notifier);
}
fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node;
@@ -919,6 +950,23 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni,
return true;
}
+static bool tid_cover_invalidate(struct mmu_interval_notifier *mni,
+ const struct mmu_notifier_range *range,
+ unsigned long cur_seq)
+{
+ struct tid_user_buf *tidbuf =
+ container_of(mni, struct tid_user_buf, notifier);
+
+ /* take action only if unmapping */
+ if (range->event == MMU_NOTIFY_UNMAP) {
+ mutex_lock(&tidbuf->cover_mutex);
+ mmu_interval_set_seq(mni, cur_seq);
+ mutex_unlock(&tidbuf->cover_mutex);
+ }
+
+ return true;
+}
+
static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata,
struct tid_rb_node *tnode)
{
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
index 2ddb3dac7d916..f8ee997d0050e 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h
@@ -16,6 +16,8 @@ struct tid_pageset {
};
struct tid_user_buf {
+ struct mmu_interval_notifier notifier;
+ struct mutex cover_mutex;
unsigned long vaddr;
unsigned long length;
unsigned int npages;
--
GitLab
From 3bd68b32c911a3a610ad782bb04d1a7bfc440638 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Mon, 9 Jan 2023 09:06:03 +0100
Subject: [PATCH 0595/1167] drm/amdgpu: fix pipeline sync v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This fixes a potential memory leak of dma_fence objects in the CS code
as well as glitches in firefox because of missing pipeline sync.
v2: use the scheduler instead of the fence context
Signed-off-by: Christian König <christian.koenig@amd.com>
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2323
Tested-by: Michal Kubecek mkubecek@suse.cz
Tested-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230109130120.73389-1-christian.koenig@amd.com
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 46 +++++++++++++++++---------
1 file changed, 30 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 47763ac0d14a5..7b5ce00f06026 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -61,6 +61,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p,
amdgpu_ctx_put(p->ctx);
return -ECANCELED;
}
+
+ amdgpu_sync_create(&p->sync);
return 0;
}
@@ -452,18 +454,6 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p,
}
r = amdgpu_sync_fence(&p->sync, fence);
- if (r)
- goto error;
-
- /*
- * When we have an explicit dependency it might be necessary to insert a
- * pipeline sync to make sure that all caches etc are flushed and the
- * next job actually sees the results from the previous one.
- */
- if (fence->context == p->gang_leader->base.entity->fence_context)
- r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
-
-error:
dma_fence_put(fence);
return r;
}
@@ -1188,10 +1178,19 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
{
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+ struct drm_gpu_scheduler *sched;
struct amdgpu_bo_list_entry *e;
+ struct dma_fence *fence;
unsigned int i;
int r;
+ r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
+ if (r) {
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
+ return r;
+ }
+
list_for_each_entry(e, &p->validated, tv.head) {
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
struct dma_resv *resv = bo->tbo.base.resv;
@@ -1211,10 +1210,24 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
return r;
}
- r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
- if (r && r != -ERESTARTSYS)
- DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
- return r;
+ sched = p->gang_leader->base.entity->rq->sched;
+ while ((fence = amdgpu_sync_get_fence(&p->sync))) {
+ struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+
+ /*
+ * When we have an dependency it might be necessary to insert a
+ * pipeline sync to make sure that all caches etc are flushed and the
+ * next job actually sees the results from the previous one
+ * before we start executing on the same scheduler ring.
+ */
+ if (!s_fence || s_fence->sched != sched)
+ continue;
+
+ r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+ if (r)
+ return r;
+ }
+ return 0;
}
static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
@@ -1347,6 +1360,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser)
{
unsigned i;
+ amdgpu_sync_free(&parser->sync);
for (i = 0; i < parser->num_post_deps; i++) {
drm_syncobj_put(parser->post_deps[i].syncobj);
kfree(parser->post_deps[i].chain);
--
GitLab
From 526970be53d5dd60122141540142fb0eeb0b22d8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Jan 2023 11:44:51 +0100
Subject: [PATCH 0596/1167] sh/mm: Fix pmd_t for real
Because typing is hard...
Fixes: 0862ff059c9e ("sh/mm: Make pmd_t similar to pte_t")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/sh/include/asm/pgtable-3level.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h
index a889a3a938bab..d1ce73f3bd85e 100644
--- a/arch/sh/include/asm/pgtable-3level.h
+++ b/arch/sh/include/asm/pgtable-3level.h
@@ -28,7 +28,7 @@
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
-typedef struct {
+typedef union {
struct {
unsigned long pmd_low;
unsigned long pmd_high;
--
GitLab
From 7c6dd961d0c8e7e8f9fdc65071fb09ece702e18d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Jan 2023 12:15:40 +0100
Subject: [PATCH 0597/1167] x86/boot: Avoid using Intel mnemonics in AT&T
syntax asm
With 'GNU assembler (GNU Binutils for Debian) 2.39.90.20221231' the
build now reports:
arch/x86/realmode/rm/../../boot/bioscall.S: Assembler messages:
arch/x86/realmode/rm/../../boot/bioscall.S:35: Warning: found `movsd'; assuming `movsl' was meant
arch/x86/realmode/rm/../../boot/bioscall.S:70: Warning: found `movsd'; assuming `movsl' was meant
arch/x86/boot/bioscall.S: Assembler messages:
arch/x86/boot/bioscall.S:35: Warning: found `movsd'; assuming `movsl' was meant
arch/x86/boot/bioscall.S:70: Warning: found `movsd'; assuming `movsl' was meant
Which is due to:
PR gas/29525
Note that with the dropped CMPSD and MOVSD Intel Syntax string insn
templates taking operands, mixed IsString/non-IsString template groups
(with memory operands) cannot occur anymore. With that
maybe_adjust_templates() becomes unnecessary (and is hence being
removed).
More details: https://sourceware.org/bugzilla/show_bug.cgi?id=29525
Borislav Petkov further explains:
" the particular problem here is is that the 'd' suffix is
"conflicting" in the sense that you can have SSE mnemonics like movsD %xmm...
and the same thing also for string ops (which is the case here) so apparently
the agreement in binutils land is to use the always accepted suffixes 'l' or 'q'
and phase out 'd' slowly... "
Fixes: 7a734e7dd93b ("x86, setup: "glove box" BIOS calls -- infrastructure")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/Y71I3Ex2pvIxMpsP@hirez.programming.kicks-ass.net
---
arch/x86/boot/bioscall.S | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index 5521ea12f44e0..aa9b964575843 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -32,7 +32,7 @@ intcall:
movw %dx, %si
movw %sp, %di
movw $11, %cx
- rep; movsd
+ rep; movsl
/* Pop full state from the stack */
popal
@@ -67,7 +67,7 @@ intcall:
jz 4f
movw %sp, %si
movw $11, %cx
- rep; movsd
+ rep; movsl
4: addw $44, %sp
/* Restore state and return */
--
GitLab
From e66b7920aa5ac5b1a1997a454004ba9246a3c005 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 30 Dec 2022 21:07:47 +0100
Subject: [PATCH 0598/1167] wifi: mac80211: fix initialization of rx->link and
rx->link_sta
There are some codepaths that do not initialize rx->link_sta properly. This
causes a crash in places which assume that rx->link_sta is valid if rx->sta
is valid.
One known instance is triggered by __ieee80211_rx_h_amsdu being called from
fast-rx. It results in a crash like this one:
BUG: kernel NULL pointer dereference, address: 00000000000000a8
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page PGD 0 P4D 0
Oops: 0002 [#1] PREEMPT SMP PTI
CPU: 1 PID: 506 Comm: mt76-usb-rx phy Tainted: G E 6.1.0-debian64x+1.7 #3
Hardware name: ZOTAC ZBOX-ID92/ZBOX-IQ01/ZBOX-ID92/ZBOX-IQ01, BIOS B220P007 05/21/2014
RIP: 0010:ieee80211_deliver_skb+0x62/0x1f0 [mac80211]
Code: 00 48 89 04 24 e8 9e a7 c3 df 89 c0 48 03 1c c5 a0 ea 39 a1 4c 01 6b 08 48 ff 03 48
83 7d 28 00 74 11 48 8b 45 30 48 63 55 44 <48> 83 84 d0 a8 00 00 00 01 41 8b 86 c0
11 00 00 8d 50 fd 83 fa 01
RSP: 0018:ffff999040803b10 EFLAGS: 00010286
RAX: 0000000000000000 RBX: ffffb9903f496480 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff999040803ce0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffff8d21828ac900
R13: 000000000000004a R14: ffff8d2198ed89c0 R15: ffff8d2198ed8000
FS: 0000000000000000(0000) GS:ffff8d24afe80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000a8 CR3: 0000000429810002 CR4: 00000000001706e0
Call Trace:
<TASK>
__ieee80211_rx_h_amsdu+0x1b5/0x240 [mac80211]
? ieee80211_prepare_and_rx_handle+0xcdd/0x1320 [mac80211]
? __local_bh_enable_ip+0x3b/0xa0
ieee80211_prepare_and_rx_handle+0xcdd/0x1320 [mac80211]
? prepare_transfer+0x109/0x1a0 [xhci_hcd]
ieee80211_rx_list+0xa80/0xda0 [mac80211]
mt76_rx_complete+0x207/0x2e0 [mt76]
mt76_rx_poll_complete+0x357/0x5a0 [mt76]
mt76u_rx_worker+0x4f5/0x600 [mt76_usb]
? mt76_get_min_avg_rssi+0x140/0x140 [mt76]
__mt76_worker_fn+0x50/0x80 [mt76]
kthread+0xed/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x22/0x30
Since the initialization of rx->link and rx->link_sta is rather convoluted
and duplicated in many places, clean it up by using a helper function to
set it.
Fixes: ccdde7c74ffd ("wifi: mac80211: properly implement MLO key handling")
Fixes: b320d6c456ff ("wifi: mac80211: use correct rx link_sta instead of default")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20221230200747.19040-1-nbd@nbd.name
[remove unnecessary rx->sta->sta.mlo check]
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/rx.c | 222 +++++++++++++++++++++-------------------------
1 file changed, 99 insertions(+), 123 deletions(-)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7e3ab6e1b28f3..c518287b2356b 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4049,6 +4049,58 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx)
#undef CALL_RXH
}
+static bool
+ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id)
+{
+ if (!sta->mlo)
+ return false;
+
+ return !!(sta->valid_links & BIT(link_id));
+}
+
+static bool ieee80211_rx_data_set_link(struct ieee80211_rx_data *rx,
+ u8 link_id)
+{
+ rx->link_id = link_id;
+ rx->link = rcu_dereference(rx->sdata->link[link_id]);
+
+ if (!rx->sta)
+ return rx->link;
+
+ if (!ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta, link_id))
+ return false;
+
+ rx->link_sta = rcu_dereference(rx->sta->link[link_id]);
+
+ return rx->link && rx->link_sta;
+}
+
+static bool ieee80211_rx_data_set_sta(struct ieee80211_rx_data *rx,
+ struct ieee80211_sta *pubsta,
+ int link_id)
+{
+ struct sta_info *sta;
+
+ sta = container_of(pubsta, struct sta_info, sta);
+
+ rx->link_id = link_id;
+ rx->sta = sta;
+
+ if (sta) {
+ rx->local = sta->sdata->local;
+ if (!rx->sdata)
+ rx->sdata = sta->sdata;
+ rx->link_sta = &sta->deflink;
+ }
+
+ if (link_id < 0)
+ rx->link = &rx->sdata->deflink;
+ else if (!ieee80211_rx_data_set_link(rx, link_id))
+ return false;
+
+ return true;
+}
+
/*
* This function makes calls into the RX path, therefore
* it has to be invoked under RCU read lock.
@@ -4057,16 +4109,19 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
{
struct sk_buff_head frames;
struct ieee80211_rx_data rx = {
- .sta = sta,
- .sdata = sta->sdata,
- .local = sta->local,
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .link_id = -1,
};
struct tid_ampdu_rx *tid_agg_rx;
- u8 link_id;
+ int link_id = -1;
+
+ /* FIXME: statistics won't be right with this */
+ if (sta->sta.valid_links)
+ link_id = ffs(sta->sta.valid_links) - 1;
+
+ if (!ieee80211_rx_data_set_sta(&rx, &sta->sta, link_id))
+ return;
tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]);
if (!tid_agg_rx)
@@ -4086,10 +4141,6 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid)
};
drv_event_callback(rx.local, rx.sdata, &event);
}
- /* FIXME: statistics won't be right with this */
- link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0;
- rx.link = rcu_dereference(sta->sdata->link[link_id]);
- rx.link_sta = rcu_dereference(sta->link[link_id]);
ieee80211_rx_handlers(&rx, &frames);
}
@@ -4105,7 +4156,6 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
/* This is OK -- must be QoS data frame */
.security_idx = tid,
.seqno_idx = tid,
- .link_id = -1,
};
int i, diff;
@@ -4116,10 +4166,8 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid,
sta = container_of(pubsta, struct sta_info, sta);
- rx.sta = sta;
- rx.sdata = sta->sdata;
- rx.link = &rx.sdata->deflink;
- rx.local = sta->local;
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, -1))
+ return;
rcu_read_lock();
tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]);
@@ -4506,15 +4554,6 @@ void ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata)
mutex_unlock(&local->sta_mtx);
}
-static bool
-ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id)
-{
- if (!sta->mlo)
- return false;
-
- return !!(sta->valid_links & BIT(link_id));
-}
-
static void ieee80211_rx_8023(struct ieee80211_rx_data *rx,
struct ieee80211_fast_rx *fast_rx,
int orig_len)
@@ -4625,7 +4664,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
struct sk_buff *skb = rx->skb;
struct ieee80211_hdr *hdr = (void *)skb->data;
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
- struct sta_info *sta = rx->sta;
int orig_len = skb->len;
int hdrlen = ieee80211_hdrlen(hdr->frame_control);
int snap_offs = hdrlen;
@@ -4637,7 +4675,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
u8 da[ETH_ALEN];
u8 sa[ETH_ALEN];
} addrs __aligned(2);
- struct link_sta_info *link_sta;
struct ieee80211_sta_rx_stats *stats;
/* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write
@@ -4740,18 +4777,10 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
drop:
dev_kfree_skb(skb);
- if (rx->link_id >= 0) {
- link_sta = rcu_dereference(sta->link[rx->link_id]);
- if (!link_sta)
- return true;
- } else {
- link_sta = &sta->deflink;
- }
-
if (fast_rx->uses_rss)
- stats = this_cpu_ptr(link_sta->pcpu_rx_stats);
+ stats = this_cpu_ptr(rx->link_sta->pcpu_rx_stats);
else
- stats = &link_sta->rx_stats;
+ stats = &rx->link_sta->rx_stats;
stats->dropped++;
return true;
@@ -4769,8 +4798,8 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
struct ieee80211_local *local = rx->local;
struct ieee80211_sub_if_data *sdata = rx->sdata;
struct ieee80211_hdr *hdr = (void *)skb->data;
- struct link_sta_info *link_sta = NULL;
- struct ieee80211_link_data *link;
+ struct link_sta_info *link_sta = rx->link_sta;
+ struct ieee80211_link_data *link = rx->link;
rx->skb = skb;
@@ -4792,35 +4821,6 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
if (!ieee80211_accept_frame(rx))
return false;
- if (rx->link_id >= 0) {
- link = rcu_dereference(rx->sdata->link[rx->link_id]);
-
- /* we might race link removal */
- if (!link)
- return true;
- rx->link = link;
-
- if (rx->sta) {
- rx->link_sta =
- rcu_dereference(rx->sta->link[rx->link_id]);
- if (!rx->link_sta)
- return true;
- }
- } else {
- if (rx->sta)
- rx->link_sta = &rx->sta->deflink;
-
- rx->link = &sdata->deflink;
- }
-
- if (unlikely(!is_multicast_ether_addr(hdr->addr1) &&
- rx->link_id >= 0 && rx->sta && rx->sta->sta.mlo)) {
- link_sta = rcu_dereference(rx->sta->link[rx->link_id]);
-
- if (WARN_ON_ONCE(!link_sta))
- return true;
- }
-
if (!consume) {
struct skb_shared_hwtstamps *shwt;
@@ -4840,7 +4840,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
shwt->hwtstamp = skb_hwtstamps(skb)->hwtstamp;
}
- if (unlikely(link_sta)) {
+ if (unlikely(rx->sta && rx->sta->sta.mlo)) {
/* translate to MLD addresses */
if (ether_addr_equal(link->conf->addr, hdr->addr1))
ether_addr_copy(hdr->addr1, rx->sdata->vif.addr);
@@ -4870,6 +4870,7 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw,
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
struct ieee80211_fast_rx *fast_rx;
struct ieee80211_rx_data rx;
+ int link_id = -1;
memset(&rx, 0, sizeof(rx));
rx.skb = skb;
@@ -4886,12 +4887,8 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw,
if (!pubsta)
goto drop;
- rx.sta = container_of(pubsta, struct sta_info, sta);
- rx.sdata = rx.sta->sdata;
-
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(pubsta, status->link_id))
- goto drop;
+ if (status->link_valid)
+ link_id = status->link_id;
/*
* TODO: Should the frame be dropped if the right link_id is not
@@ -4900,19 +4897,8 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw,
* link_id is used only for stats purpose and updating the stats on
* the deflink is fine?
*/
- if (status->link_valid)
- rx.link_id = status->link_id;
-
- if (rx.link_id >= 0) {
- struct ieee80211_link_data *link;
-
- link = rcu_dereference(rx.sdata->link[rx.link_id]);
- if (!link)
- goto drop;
- rx.link = link;
- } else {
- rx.link = &rx.sdata->deflink;
- }
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id))
+ goto drop;
fast_rx = rcu_dereference(rx.sta->fast_rx);
if (!fast_rx)
@@ -4930,6 +4916,8 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx,
{
struct link_sta_info *link_sta;
struct ieee80211_hdr *hdr = (void *)skb->data;
+ struct sta_info *sta;
+ int link_id = -1;
/*
* Look up link station first, in case there's a
@@ -4939,24 +4927,19 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx,
*/
link_sta = link_sta_info_get_bss(rx->sdata, hdr->addr2);
if (link_sta) {
- rx->sta = link_sta->sta;
- rx->link_id = link_sta->link_id;
+ sta = link_sta->sta;
+ link_id = link_sta->link_id;
} else {
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
- rx->sta = sta_info_get_bss(rx->sdata, hdr->addr2);
- if (rx->sta) {
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta,
- status->link_id))
- return false;
-
- rx->link_id = status->link_valid ? status->link_id : -1;
- } else {
- rx->link_id = -1;
- }
+ sta = sta_info_get_bss(rx->sdata, hdr->addr2);
+ if (status->link_valid)
+ link_id = status->link_id;
}
+ if (!ieee80211_rx_data_set_sta(rx, &sta->sta, link_id))
+ return false;
+
return ieee80211_prepare_and_rx_handle(rx, skb, consume);
}
@@ -5015,19 +4998,15 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
if (ieee80211_is_data(fc)) {
struct sta_info *sta, *prev_sta;
- u8 link_id = status->link_id;
+ int link_id = -1;
- if (pubsta) {
- rx.sta = container_of(pubsta, struct sta_info, sta);
- rx.sdata = rx.sta->sdata;
+ if (status->link_valid)
+ link_id = status->link_id;
- if (status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(pubsta, link_id))
+ if (pubsta) {
+ if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id))
goto out;
- if (status->link_valid)
- rx.link_id = status->link_id;
-
/*
* In MLO connection, fetch the link_id using addr2
* when the driver does not pass link_id in status.
@@ -5045,7 +5024,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
if (!link_sta)
goto out;
- rx.link_id = link_sta->link_id;
+ ieee80211_rx_data_set_link(&rx, link_sta->link_id);
}
if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
@@ -5061,30 +5040,27 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
continue;
}
- if ((status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta,
- link_id)) ||
- (!status->link_valid && prev_sta->sta.mlo))
+ rx.sdata = prev_sta->sdata;
+ if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta,
+ link_id))
+ goto out;
+
+ if (!status->link_valid && prev_sta->sta.mlo)
continue;
- rx.link_id = status->link_valid ? link_id : -1;
- rx.sta = prev_sta;
- rx.sdata = prev_sta->sdata;
ieee80211_prepare_and_rx_handle(&rx, skb, false);
prev_sta = sta;
}
if (prev_sta) {
- if ((status->link_valid &&
- !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta,
- link_id)) ||
- (!status->link_valid && prev_sta->sta.mlo))
+ rx.sdata = prev_sta->sdata;
+ if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta,
+ link_id))
goto out;
- rx.link_id = status->link_valid ? link_id : -1;
- rx.sta = prev_sta;
- rx.sdata = prev_sta->sdata;
+ if (!status->link_valid && prev_sta->sta.mlo)
+ goto out;
if (ieee80211_prepare_and_rx_handle(&rx, skb, true))
return;
--
GitLab
From 4444bc2116aecdcde87dce80373540adc8bd478b Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <alexander@wetzel-home.de>
Date: Fri, 30 Dec 2022 13:18:49 +0100
Subject: [PATCH 0599/1167] wifi: mac80211: Proper mark iTXQs for resumption
When a running wake_tx_queue() call is aborted due to a hw queue stop
the corresponding iTXQ is not always correctly marked for resumption:
wake_tx_push_queue() can stops the queue run without setting
@IEEE80211_TXQ_STOP_NETIF_TX.
Without the @IEEE80211_TXQ_STOP_NETIF_TX flag __ieee80211_wake_txqs()
will not schedule a new queue run and remaining frames in the queue get
stuck till another frame is queued to it.
Fix the issue for all drivers - also the ones with custom wake_tx_queue
callbacks - by moving the logic into ieee80211_tx_dequeue() and drop the
redundant @txqs_stopped.
@IEEE80211_TXQ_STOP_NETIF_TX is also renamed to @IEEE80211_TXQ_DIRTY to
better describe the flag.
Fixes: c850e31f79f0 ("wifi: mac80211: add internal handler for wake_tx_queue")
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
Link: https://lore.kernel.org/r/20221230121850.218810-1-alexander@wetzel-home.de
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
include/net/mac80211.h | 4 ----
net/mac80211/debugfs_sta.c | 5 +++--
net/mac80211/driver-ops.h | 2 +-
net/mac80211/ieee80211_i.h | 2 +-
net/mac80211/tx.c | 20 +++++++++++-------
net/mac80211/util.c | 42 +++-----------------------------------
6 files changed, 21 insertions(+), 54 deletions(-)
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 689da327ce2e8..e3235b9c02c21 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1832,8 +1832,6 @@ struct ieee80211_vif_cfg {
* @drv_priv: data area for driver use, will always be aligned to
* sizeof(void \*).
* @txq: the multicast data TX queue
- * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped,
- * protected by fq->lock.
* @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see
* &enum ieee80211_offload_flags.
* @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled.
@@ -1863,8 +1861,6 @@ struct ieee80211_vif {
bool probe_req_reg;
bool rx_mcast_action_reg;
- bool txqs_stopped[IEEE80211_NUM_ACS];
-
struct ieee80211_vif *mbssid_tx_vif;
/* must be last */
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 7a3d7893e19d6..f1914bf39f0e6 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -167,7 +167,7 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf,
continue;
txqi = to_txq_info(sta->sta.txq[i]);
p += scnprintf(p, bufsz + buf - p,
- "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n",
+ "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s%s)\n",
txqi->txq.tid,
txqi->txq.ac,
txqi->tin.backlog_bytes,
@@ -182,7 +182,8 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf,
txqi->flags,
test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN",
test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "",
- test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "");
+ test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "",
+ test_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ? " DIRTY" : "");
}
rcu_read_unlock();
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 809bad53e15b6..5d13a3dfd3664 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1199,7 +1199,7 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local,
/* In reconfig don't transmit now, but mark for waking later */
if (local->in_reconfig) {
- set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags);
+ set_bit(IEEE80211_TXQ_DIRTY, &txq->flags);
return;
}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 63ff0d2524b65..d16606e84e22d 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -838,7 +838,7 @@ enum txq_info_flags {
IEEE80211_TXQ_STOP,
IEEE80211_TXQ_AMPDU,
IEEE80211_TXQ_NO_AMSDU,
- IEEE80211_TXQ_STOP_NETIF_TX,
+ IEEE80211_TXQ_DIRTY,
};
/**
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2171cd1ca807e..178043f844893 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3783,6 +3783,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
struct ieee80211_tx_data tx;
ieee80211_tx_result r;
struct ieee80211_vif *vif = txq->vif;
+ int q = vif->hw_queue[txq->ac];
+ bool q_stopped;
WARN_ON_ONCE(softirq_count() == 0);
@@ -3790,16 +3792,20 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
return NULL;
begin:
- spin_lock_bh(&fq->lock);
+ spin_lock(&local->queue_stop_reason_lock);
+ q_stopped = local->queue_stop_reasons[q];
+ spin_unlock(&local->queue_stop_reason_lock);
- if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ||
- test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
- goto out;
+ if (unlikely(q_stopped)) {
+ /* mark for waking later */
+ set_bit(IEEE80211_TXQ_DIRTY, &txqi->flags);
+ return NULL;
+ }
- if (vif->txqs_stopped[txq->ac]) {
- set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
+ spin_lock_bh(&fq->lock);
+
+ if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
goto out;
- }
/* Make sure fragments stay together. */
skb = __skb_dequeue(&txqi->frags);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 6f5407038459d..261ac667887f8 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -292,22 +292,12 @@ static void wake_tx_push_queue(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
struct ieee80211_txq *queue)
{
- int q = sdata->vif.hw_queue[queue->ac];
struct ieee80211_tx_control control = {
.sta = queue->sta,
};
struct sk_buff *skb;
- unsigned long flags;
- bool q_stopped;
while (1) {
- spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
- q_stopped = local->queue_stop_reasons[q];
- spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
-
- if (q_stopped)
- break;
-
skb = ieee80211_tx_dequeue(&local->hw, queue);
if (!skb)
break;
@@ -347,8 +337,6 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
local_bh_disable();
spin_lock(&fq->lock);
- sdata->vif.txqs_stopped[ac] = false;
-
if (!test_bit(SDATA_STATE_RUNNING, &sdata->state))
goto out;
@@ -370,7 +358,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
if (ac != txq->ac)
continue;
- if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX,
+ if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY,
&txqi->flags))
continue;
@@ -385,7 +373,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
txqi = to_txq_info(vif->txq);
- if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) ||
+ if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ||
(ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac)
goto out;
@@ -517,8 +505,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue,
bool refcounted)
{
struct ieee80211_local *local = hw_to_local(hw);
- struct ieee80211_sub_if_data *sdata;
- int n_acs = IEEE80211_NUM_ACS;
trace_stop_queue(local, queue, reason);
@@ -530,29 +516,7 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue,
else
local->q_stop_reasons[queue][reason]++;
- if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue]))
- return;
-
- if (local->hw.queues < IEEE80211_NUM_ACS)
- n_acs = 1;
-
- rcu_read_lock();
- list_for_each_entry_rcu(sdata, &local->interfaces, list) {
- int ac;
-
- if (!sdata->dev)
- continue;
-
- for (ac = 0; ac < n_acs; ac++) {
- if (sdata->vif.hw_queue[ac] == queue ||
- sdata->vif.cab_queue == queue) {
- spin_lock(&local->fq.lock);
- sdata->vif.txqs_stopped[ac] = true;
- spin_unlock(&local->fq.lock);
- }
- }
- }
- rcu_read_unlock();
+ set_bit(reason, &local->queue_stop_reasons[queue]);
}
void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue,
--
GitLab
From 69403bad97aa0162e3d7911b27e25abe774093df Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <alexander@wetzel-home.de>
Date: Fri, 30 Dec 2022 13:18:50 +0100
Subject: [PATCH 0600/1167] wifi: mac80211: sdata can be NULL during AMPDU
start
ieee80211_tx_ba_session_handle_start() may get NULL for sdata when a
deauthentication is ongoing.
Here a trace triggering the race with the hostapd test
multi_ap_fronthaul_on_ap:
(gdb) list *drv_ampdu_action+0x46
0x8b16 is in drv_ampdu_action (net/mac80211/driver-ops.c:396).
391 int ret = -EOPNOTSUPP;
392
393 might_sleep();
394
395 sdata = get_bss_sdata(sdata);
396 if (!check_sdata_in_driver(sdata))
397 return -EIO;
398
399 trace_drv_ampdu_action(local, sdata, params);
400
wlan0: moving STA 02:00:00:00:03:00 to state 3
wlan0: associated
wlan0: deauthenticating from 02:00:00:00:03:00 by local choice (Reason: 3=DEAUTH_LEAVING)
wlan3.sta1: Open BA session requested for 02:00:00:00:00:00 tid 0
wlan3.sta1: dropped frame to 02:00:00:00:00:00 (unauthorized port)
wlan0: moving STA 02:00:00:00:03:00 to state 2
wlan0: moving STA 02:00:00:00:03:00 to state 1
wlan0: Removed STA 02:00:00:00:03:00
wlan0: Destroyed STA 02:00:00:00:03:00
BUG: unable to handle page fault for address: fffffffffffffb48
PGD 11814067 P4D 11814067 PUD 11816067 PMD 0
Oops: 0000 [#1] PREEMPT SMP PTI
CPU: 2 PID: 133397 Comm: kworker/u16:1 Tainted: G W 6.1.0-rc8-wt+ #59
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.0-20220807_005459-localhost 04/01/2014
Workqueue: phy3 ieee80211_ba_session_work [mac80211]
RIP: 0010:drv_ampdu_action+0x46/0x280 [mac80211]
Code: 53 48 89 f3 be 89 01 00 00 e8 d6 43 bf ef e8 21 46 81 f0 83 bb a0 1b 00 00 04 75 0e 48 8b 9b 28 0d 00 00 48 81 eb 10 0e 00 00 <8b> 93 58 09 00 00 f6 c2 20 0f 84 3b 01 00 00 8b 05 dd 1c 0f 00 85
RSP: 0018:ffffc900025ebd20 EFLAGS: 00010287
RAX: 0000000000000000 RBX: fffffffffffff1f0 RCX: ffff888102228240
RDX: 0000000080000000 RSI: ffffffff918c5de0 RDI: ffff888102228b40
RBP: ffffc900025ebd40 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: ffff888118c18ec0
R13: 0000000000000000 R14: ffffc900025ebd60 R15: ffff888018b7efb8
FS: 0000000000000000(0000) GS:ffff88817a600000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffffffffffffb48 CR3: 0000000105228006 CR4: 0000000000170ee0
Call Trace:
<TASK>
ieee80211_tx_ba_session_handle_start+0xd0/0x190 [mac80211]
ieee80211_ba_session_work+0xff/0x2e0 [mac80211]
process_one_work+0x29f/0x620
worker_thread+0x4d/0x3d0
? process_one_work+0x620/0x620
kthread+0xfb/0x120
? kthread_complete_and_exit+0x20/0x20
ret_from_fork+0x22/0x30
</TASK>
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
Link: https://lore.kernel.org/r/20221230121850.218810-2-alexander@wetzel-home.de
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/agg-tx.c | 6 +++++-
net/mac80211/driver-ops.c | 3 +++
2 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 9c40f8d3bce8c..3dbb724d7dc47 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -491,7 +491,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
{
struct tid_ampdu_tx *tid_tx;
struct ieee80211_local *local = sta->local;
- struct ieee80211_sub_if_data *sdata = sta->sdata;
+ struct ieee80211_sub_if_data *sdata;
struct ieee80211_ampdu_params params = {
.sta = &sta->sta,
.action = IEEE80211_AMPDU_TX_START,
@@ -521,6 +521,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
*/
synchronize_net();
+ sdata = sta->sdata;
params.ssn = sta->tid_seq[tid] >> 4;
ret = drv_ampdu_action(local, sdata, ¶ms);
tid_tx->ssn = params.ssn;
@@ -534,6 +535,9 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
*/
set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state);
} else if (ret) {
+ if (!sdata)
+ return;
+
ht_dbg(sdata,
"BA request denied - HW unavailable for %pM tid %d\n",
sta->sta.addr, tid);
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index d737db4e07e24..cfb09e4aed4d3 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -392,6 +392,9 @@ int drv_ampdu_action(struct ieee80211_local *local,
might_sleep();
+ if (!sdata)
+ return -EIO;
+
sdata = get_bss_sdata(sdata);
if (!check_sdata_in_driver(sdata))
return -EIO;
--
GitLab
From 592234e941f1addaa598601c9227e3b72d608625 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <alexander@wetzel-home.de>
Date: Fri, 6 Jan 2023 23:31:41 +0100
Subject: [PATCH 0601/1167] wifi: mac80211: Fix iTXQ AMPDU fragmentation
handling
mac80211 must not enable aggregation wile transmitting a fragmented
MPDU. Enforce that for mac80211 internal TX queues (iTXQs).
Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/oe-lkp/202301021738.7cd3e6ae-oliver.sang@intel.com
Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
Link: https://lore.kernel.org/r/20230106223141.98696-1-alexander@wetzel-home.de
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/agg-tx.c | 2 --
net/mac80211/ht.c | 31 +++++++++++++++++++++++++++++++
net/mac80211/tx.c | 18 ++++++------------
3 files changed, 37 insertions(+), 14 deletions(-)
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 3dbb724d7dc47..f9514bacbd4a1 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -511,8 +511,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
*/
clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state);
- ieee80211_agg_stop_txq(sta, tid);
-
/*
* Make sure no packets are being processed. This ensures that
* we have a valid starting sequence number and that in-flight
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 83bc41346ae7f..5315ab7502802 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -391,6 +391,37 @@ void ieee80211_ba_session_work(struct work_struct *work)
tid_tx = sta->ampdu_mlme.tid_start_tx[tid];
if (!blocked && tid_tx) {
+ struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+ struct ieee80211_sub_if_data *sdata =
+ vif_to_sdata(txqi->txq.vif);
+ struct fq *fq = &sdata->local->fq;
+
+ spin_lock_bh(&fq->lock);
+
+ /* Allow only frags to be dequeued */
+ set_bit(IEEE80211_TXQ_STOP, &txqi->flags);
+
+ if (!skb_queue_empty(&txqi->frags)) {
+ /* Fragmented Tx is ongoing, wait for it to
+ * finish. Reschedule worker to retry later.
+ */
+
+ spin_unlock_bh(&fq->lock);
+ spin_unlock_bh(&sta->lock);
+
+ /* Give the task working on the txq a chance
+ * to send out the queued frags
+ */
+ synchronize_net();
+
+ mutex_unlock(&sta->ampdu_mlme.mtx);
+
+ ieee80211_queue_work(&sdata->local->hw, work);
+ return;
+ }
+
+ spin_unlock_bh(&fq->lock);
+
/*
* Assign it over to the normal tid_tx array
* where it "goes live".
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 178043f844893..defe97a31724d 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1129,7 +1129,6 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
struct sk_buff *purge_skb = NULL;
if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
- info->flags |= IEEE80211_TX_CTL_AMPDU;
reset_agg_timer = true;
} else if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) {
/*
@@ -1161,7 +1160,6 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
if (!tid_tx) {
/* do nothing, let packet pass through */
} else if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
- info->flags |= IEEE80211_TX_CTL_AMPDU;
reset_agg_timer = true;
} else {
queued = true;
@@ -3677,8 +3675,7 @@ static void __ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
info->band = fast_tx->band;
info->control.vif = &sdata->vif;
info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT |
- IEEE80211_TX_CTL_DONTFRAG |
- (ampdu ? IEEE80211_TX_CTL_AMPDU : 0);
+ IEEE80211_TX_CTL_DONTFRAG;
info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT |
u32_encode_bits(IEEE80211_LINK_UNSPECIFIED,
IEEE80211_TX_CTRL_MLO_LINK);
@@ -3804,9 +3801,6 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
spin_lock_bh(&fq->lock);
- if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
- goto out;
-
/* Make sure fragments stay together. */
skb = __skb_dequeue(&txqi->frags);
if (unlikely(skb)) {
@@ -3816,6 +3810,9 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
IEEE80211_SKB_CB(skb)->control.flags &=
~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
} else {
+ if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags)))
+ goto out;
+
skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
}
@@ -3866,9 +3863,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
}
if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags))
- info->flags |= IEEE80211_TX_CTL_AMPDU;
- else
- info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+ info->flags |= (IEEE80211_TX_CTL_AMPDU |
+ IEEE80211_TX_CTL_DONTFRAG);
if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) {
@@ -4602,8 +4598,6 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
info = IEEE80211_SKB_CB(skb);
memset(info, 0, sizeof(*info));
- if (tid_tx)
- info->flags |= IEEE80211_TX_CTL_AMPDU;
info->hw_queue = sdata->vif.hw_queue[queue];
--
GitLab
From 0eb38842ada035d71bb06fb9116f26f24ee0f998 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <quic_alokad@quicinc.com>
Date: Wed, 21 Dec 2022 10:56:16 -0800
Subject: [PATCH 0602/1167] wifi: mac80211: reset multiple BSSID options in
stop_ap()
Reset multiple BSSID options when all AP related configurations are
reset in ieee80211_stop_ap().
Stale values result in HWSIM test failures (e.g. p2p_group_cli_invalid),
if run after 'he_ap_ema'.
Reported-by: Jouni Malinen <j@w1.fi>
Signed-off-by: Aloka Dixit <quic_alokad@quicinc.com>
Link: https://lore.kernel.org/r/20221221185616.11514-1-quic_alokad@quicinc.com
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/cfg.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 8f9a2ab502b38..672eff6f5d328 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -147,6 +147,7 @@ static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata,
link_conf->bssid_index = 0;
link_conf->nontransmitted = false;
link_conf->ema_ap = false;
+ link_conf->bssid_indicator = 0;
if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev)
return -EINVAL;
@@ -1511,6 +1512,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
kfree(link_conf->ftmr_params);
link_conf->ftmr_params = NULL;
+ sdata->vif.mbssid_tx_vif = NULL;
+ link_conf->bssid_index = 0;
+ link_conf->nontransmitted = false;
+ link_conf->ema_ap = false;
+ link_conf->bssid_indicator = 0;
+
__sta_info_flush(sdata, true);
ieee80211_free_keys(sdata, true);
--
GitLab
From fa22b51ace8aa106267636f36170e940e676809c Mon Sep 17 00:00:00 2001
From: Sriram R <quic_srirrama@quicinc.com>
Date: Thu, 8 Dec 2022 09:30:50 +0530
Subject: [PATCH 0603/1167] mac80211: Fix MLO address translation for multiple
bss case
When multiple interfaces are present in the local interface
list, new skb copy is taken before rx processing except for
the first interface. The address translation happens each
time only on the original skb since the hdr pointer is not
updated properly to the newly created skb.
As a result frames start to drop in userspace when address
based checks or search fails.
Signed-off-by: Sriram R <quic_srirrama@quicinc.com>
Link: https://lore.kernel.org/r/20221208040050.25922-1-quic_srirrama@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/rx.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c518287b2356b..c6562a6d25035 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4838,6 +4838,9 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
*/
shwt = skb_hwtstamps(rx->skb);
shwt->hwtstamp = skb_hwtstamps(skb)->hwtstamp;
+
+ /* Update the hdr pointer to the new skb for translation below */
+ hdr = (struct ieee80211_hdr *)rx->skb->data;
}
if (unlikely(rx->sta && rx->sta->sta.mlo)) {
--
GitLab
From f216033d770f7ca0eda491fe01a9f02e7af59576 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 14 Dec 2022 14:03:26 +0100
Subject: [PATCH 0604/1167] wifi: mac80211: fix MLO + AP_VLAN check
Instead of preventing adding AP_VLAN to MLO enabled APs, this check was
preventing adding more than one 4-addr AP_VLAN regardless of the MLO status.
Fix this by adding missing extra checks.
Fixes: ae960ee90bb1 ("wifi: mac80211: prevent VLANs on MLDs")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://lore.kernel.org/r/20221214130326.37756-1-nbd@nbd.name
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
net/mac80211/iface.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d49a5906a9435..e20c3fe9a0b19 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -364,7 +364,9 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
/* No support for VLAN with MLO yet */
if (iftype == NL80211_IFTYPE_AP_VLAN &&
- nsdata->wdev.use_4addr)
+ sdata->wdev.use_4addr &&
+ nsdata->vif.type == NL80211_IFTYPE_AP &&
+ nsdata->vif.valid_links)
return -EOPNOTSUPP;
/*
--
GitLab
From 8c6a42b5b0ed6f96624f56954e93eeae107440a6 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 6 Jan 2023 23:15:06 +0000
Subject: [PATCH 0605/1167] ASoC: fsl_ssi: Rename AC'97 streams to avoid
collisions with AC'97 CODEC
The SSI driver calls the AC'97 playback and transmit streams "AC97 Playback"
and "AC97 Capture" respectively. This is the same name used by the generic
AC'97 CODEC driver in ASoC, creating confusion for the Freescale ASoC card
when it attempts to use these widgets in routing. Add a "CPU" in the name
like the regular DAIs registered by the driver to disambiguate.
Acked-by: Shengjiu Wang <shengjiu.wang@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20230106-asoc-udoo-probe-v1-1-a5d7469d4f67@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/fsl/fsl-asoc-card.c | 8 ++++----
sound/soc/fsl/fsl_ssi.c | 4 ++--
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index c836848ef0a65..1dfd0341e4873 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -121,11 +121,11 @@ static const struct snd_soc_dapm_route audio_map[] = {
static const struct snd_soc_dapm_route audio_map_ac97[] = {
/* 1st half -- Normal DAPM routes */
- {"Playback", NULL, "AC97 Playback"},
- {"AC97 Capture", NULL, "Capture"},
+ {"Playback", NULL, "CPU AC97 Playback"},
+ {"CPU AC97 Capture", NULL, "Capture"},
/* 2nd half -- ASRC DAPM routes */
- {"AC97 Playback", NULL, "ASRC-Playback"},
- {"ASRC-Capture", NULL, "AC97 Capture"},
+ {"CPU AC97 Playback", NULL, "ASRC-Playback"},
+ {"ASRC-Capture", NULL, "CPU AC97 Capture"},
};
static const struct snd_soc_dapm_route audio_map_tx[] = {
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index c9e0e31d5b34d..46a53551b955c 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1189,14 +1189,14 @@ static struct snd_soc_dai_driver fsl_ssi_ac97_dai = {
.symmetric_channels = 1,
.probe = fsl_ssi_dai_probe,
.playback = {
- .stream_name = "AC97 Playback",
+ .stream_name = "CPU AC97 Playback",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_8000_48000,
.formats = SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S20,
},
.capture = {
- .stream_name = "AC97 Capture",
+ .stream_name = "CPU AC97 Capture",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_48000,
--
GitLab
From 242fc66ae6e1e2b8519daacc7590a73cd0e8a6e4 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 6 Jan 2023 23:15:07 +0000
Subject: [PATCH 0606/1167] ASoC: fsl-asoc-card: Fix naming of AC'97 CODEC
widgets
The fsl-asoc-card AC'97 support currently tries to route to Playback and
Capture widgets provided by the AC'97 CODEC. This doesn't work since the
generic AC'97 driver registers with an "AC97" at the front of the stream
and hence widget names, update to reflect reality. It's not clear to me
if or how this ever worked.
Acked-by: Shengjiu Wang <shengjiu.wang@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20230106-asoc-udoo-probe-v1-2-a5d7469d4f67@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
sound/soc/fsl/fsl-asoc-card.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 1dfd0341e4873..8d14b5593658d 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -121,8 +121,8 @@ static const struct snd_soc_dapm_route audio_map[] = {
static const struct snd_soc_dapm_route audio_map_ac97[] = {
/* 1st half -- Normal DAPM routes */
- {"Playback", NULL, "CPU AC97 Playback"},
- {"CPU AC97 Capture", NULL, "Capture"},
+ {"AC97 Playback", NULL, "CPU AC97 Playback"},
+ {"CPU AC97 Capture", NULL, "AC97 Capture"},
/* 2nd half -- ASRC DAPM routes */
{"CPU AC97 Playback", NULL, "ASRC-Playback"},
{"ASRC-Capture", NULL, "CPU AC97 Capture"},
--
GitLab
From c2337a40e04dde1692b5b0a46ecc59f89aaba8a1 Mon Sep 17 00:00:00 2001
From: Alexander Egorenkov <egorenar@linux.ibm.com>
Date: Mon, 14 Nov 2022 11:40:08 +0100
Subject: [PATCH 0607/1167] s390/kexec: fix ipl report address for kdump
This commit addresses the following erroneous situation with file-based
kdump executed on a system with a valid IPL report.
On s390, a kdump kernel, its initrd and IPL report if present are loaded
into a special and reserved on boot memory region - crashkernel. When
a system crashes and kdump was activated before, the purgatory code
is entered first which swaps the crashkernel and [0 - crashkernel size]
memory regions. Only after that the kdump kernel is entered. For this
reason, the pointer to an IPL report in lowcore must point to the IPL report
after the swap and not to the address of the IPL report that was located in
crashkernel memory region before the swap. Failing to do so, makes the
kdump's decompressor try to read memory from the crashkernel memory region
which already contains the production's kernel memory.
The situation described above caused spontaneous kdump failures/hangs
on systems where the Secure IPL is activated because on such systems
an IPL report is always present. In that case kdump's decompressor tried
to parse an IPL report which frequently lead to illegal memory accesses
because an IPL report contains addresses to various data.
Cc: <stable@vger.kernel.org>
Fixes: 99feaa717e55 ("s390/kexec_file: Create ipl report and pass to next kernel")
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Alexander Egorenkov <egorenar@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/kernel/machine_kexec_file.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index fc6d5f58debeb..2df94d32140c4 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image,
data->memsz = ALIGN(data->memsz, PAGE_SIZE);
buf.mem = data->memsz;
- if (image->type == KEXEC_TYPE_CRASH)
- buf.mem += crashk_res.start;
ptr = (void *)ipl_cert_list_addr;
end = ptr + ipl_cert_list_size;
@@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image,
data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
*lc_ipl_parmblock_ptr = (__u32)buf.mem;
+ if (image->type == KEXEC_TYPE_CRASH)
+ buf.mem += crashk_res.start;
+
ret = kexec_add_buffer(&buf);
out:
return ret;
--
GitLab
From d891f2b724b39a2a41e3ad7b57110193993242ff Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Jan 2023 07:13:19 -0800
Subject: [PATCH 0608/1167] perf build: Properly guard libbpf includes
Including libbpf header files should be guarded by HAVE_LIBBPF_SUPPORT.
In bpf_counter.h, move the skeleton utilities under HAVE_BPF_SKEL.
Fixes: d6a735ef3277c45f ("perf bpf_counter: Move common functions to bpf_counter.h")
Reported-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Mike Leach <mike.leach@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230105172243.7238-1-mike.leach@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-trace.c | 2 ++
tools/perf/util/bpf_counter.h | 6 ++++++
2 files changed, 8 insertions(+)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 86e06f136f402..d21fe0f32a6de 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,7 +16,9 @@
#include "util/record.h"
#include <api/fs/tracing_path.h>
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
+#endif
#include "util/bpf_map.h"
#include "util/rlimit.h"
#include "builtin.h"
diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h
index 4dbf26408b692..c6d21c07b14cd 100644
--- a/tools/perf/util/bpf_counter.h
+++ b/tools/perf/util/bpf_counter.h
@@ -4,9 +4,12 @@
#include <linux/list.h>
#include <sys/resource.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
#include <bpf/btf.h>
#include <bpf/libbpf.h>
+#endif
struct evsel;
struct target;
@@ -87,6 +90,8 @@ static inline void set_max_rlimit(void)
setrlimit(RLIMIT_MEMLOCK, &rinf);
}
+#ifdef HAVE_BPF_SKEL
+
static inline __u32 bpf_link_get_id(int fd)
{
struct bpf_link_info link_info = { .id = 0, };
@@ -127,5 +132,6 @@ static inline int bperf_trigger_reading(int prog_fd, int cpu)
return bpf_prog_test_run_opts(prog_fd, &opts);
}
+#endif /* HAVE_BPF_SKEL */
#endif /* __PERF_BPF_COUNTER_H */
--
GitLab
From b3719108ae60169eda5c941ca5e1be1faa371c57 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Sun, 8 Jan 2023 14:23:59 +0800
Subject: [PATCH 0609/1167] perf kmem: Support legacy tracepoints
Commit 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of
tracepoints") removed tracepoints 'kmalloc_node' and
'kmem_cache_alloc_node', we need to consider the tool should be backward
compatible.
If it detect the tracepoint "kmem:kmalloc_node", this patch enables the
legacy tracepoints, otherwise, it will ignore them.
Fixes: 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints")
Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20230108062400.250690-1-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-kmem.c | 29 ++++++++++++++++++++++++++---
1 file changed, 26 insertions(+), 3 deletions(-)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index e20656c431a4b..50a3df5dc18a8 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1824,6 +1824,19 @@ static int parse_line_opt(const struct option *opt __maybe_unused,
return 0;
}
+static bool slab_legacy_tp_is_exposed(void)
+{
+ /*
+ * The tracepoints "kmem:kmalloc_node" and
+ * "kmem:kmem_cache_alloc_node" have been removed on the latest
+ * kernel, if the tracepoint "kmem:kmalloc_node" is existed it
+ * means the tool is running on an old kernel, we need to
+ * rollback to support these legacy tracepoints.
+ */
+ return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ?
+ false : true;
+}
+
static int __cmd_record(int argc, const char **argv)
{
const char * const record_args[] = {
@@ -1831,22 +1844,28 @@ static int __cmd_record(int argc, const char **argv)
};
const char * const slab_events[] = {
"-e", "kmem:kmalloc",
- "-e", "kmem:kmalloc_node",
"-e", "kmem:kfree",
"-e", "kmem:kmem_cache_alloc",
- "-e", "kmem:kmem_cache_alloc_node",
"-e", "kmem:kmem_cache_free",
};
+ const char * const slab_legacy_events[] = {
+ "-e", "kmem:kmalloc_node",
+ "-e", "kmem:kmem_cache_alloc_node",
+ };
const char * const page_events[] = {
"-e", "kmem:mm_page_alloc",
"-e", "kmem:mm_page_free",
};
unsigned int rec_argc, i, j;
const char **rec_argv;
+ unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed();
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
- if (kmem_slab)
+ if (kmem_slab) {
rec_argc += ARRAY_SIZE(slab_events);
+ if (slab_legacy_tp_exposed)
+ rec_argc += ARRAY_SIZE(slab_legacy_events);
+ }
if (kmem_page)
rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
@@ -1861,6 +1880,10 @@ static int __cmd_record(int argc, const char **argv)
if (kmem_slab) {
for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
rec_argv[i] = strdup(slab_events[j]);
+ if (slab_legacy_tp_exposed) {
+ for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++)
+ rec_argv[i] = strdup(slab_legacy_events[j]);
+ }
}
if (kmem_page) {
rec_argv[i++] = strdup("-g");
--
GitLab
From dce088ab0d51ae3b14fb2bd608e9c649aadfe5dc Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Sun, 8 Jan 2023 14:24:00 +0800
Subject: [PATCH 0610/1167] perf kmem: Support field "node" in
evsel__process_alloc_event() coping with recent tracepoint restructuring
Commit 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of
tracepoints") adds the field "node" into the tracepoints 'kmalloc' and
'kmem_cache_alloc', so this patch modifies the event process function to
support the field "node".
If field "node" is detected by checking function evsel__field(), it
stats the cross allocation.
When the "node" value is NUMA_NO_NODE (-1), it means the memory can be
allocated from any memory node, in this case, we don't account it as a
cross allocation.
Fixes: 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints")
Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Leo Yan <leo.yan@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/r/20230108062400.250690-2-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-kmem.c | 36 ++++++++++++++++++++++++------------
1 file changed, 24 insertions(+), 12 deletions(-)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 50a3df5dc18a8..8ae0a15352936 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -26,6 +26,7 @@
#include "util/string2.h"
#include <linux/kernel.h>
+#include <linux/numa.h>
#include <linux/rbtree.h>
#include <linux/string.h>
#include <linux/zalloc.h>
@@ -185,22 +186,33 @@ static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *s
total_allocated += bytes_alloc;
nr_allocs++;
- return 0;
-}
-static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample)
-{
- int ret = evsel__process_alloc_event(evsel, sample);
+ /*
+ * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA
+ * version of tracepoints") adds the field "node" into the
+ * tracepoints 'kmalloc' and 'kmem_cache_alloc'.
+ *
+ * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node'
+ * also contain the field "node".
+ *
+ * If the tracepoint contains the field "node" the tool stats the
+ * cross allocation.
+ */
+ if (evsel__field(evsel, "node")) {
+ int node1, node2;
- if (!ret) {
- int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
- node2 = evsel__intval(evsel, sample, "node");
+ node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu});
+ node2 = evsel__intval(evsel, sample, "node");
- if (node1 != node2)
+ /*
+ * If the field "node" is NUMA_NO_NODE (-1), we don't take it
+ * as a cross allocation.
+ */
+ if ((node2 != NUMA_NO_NODE) && (node1 != node2))
nr_cross_allocs++;
}
- return ret;
+ return 0;
}
static int ptr_cmp(void *, void *);
@@ -1369,8 +1381,8 @@ static int __cmd_kmem(struct perf_session *session)
/* slab allocator */
{ "kmem:kmalloc", evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", evsel__process_alloc_event, },
- { "kmem:kmalloc_node", evsel__process_alloc_node_event, },
- { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, },
+ { "kmem:kmalloc_node", evsel__process_alloc_event, },
+ { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, },
{ "kmem:kfree", evsel__process_free_event, },
{ "kmem:kmem_cache_free", evsel__process_free_event, },
/* page allocator */
--
GitLab
From 213b760fbc69f2d6aed8f64f006a17869f0d8da4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 9 Jan 2023 11:59:30 -0300
Subject: [PATCH 0611/1167] perf tools: Don't install libtraceevent plugins as
its not anymore in the kernel sources
While doing 'make -C tools/perf build-test' one can notice error
messages while trying to install libtraceevent plugins, stop doing that
as libtraceevent isn't anymore a homie.
These are the warnings dealt with:
make_install_prefix_slash_O: make install prefix=/tmp/krava/
failed to find: /tmp/krava/etc/bash_completion.d/perf
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_cfg80211.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_scsi.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_xen.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_function.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_sched_switch.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_mac80211.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_kvm.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_kmem.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_hrtimer.so
failed to find: /tmp/krava/lib64/traceevent/plugins/plugin_jbd2.so
Fixes: 4171925aa9f3f7bf ("tools lib traceevent: Remove libtraceevent")
Acked-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lore.kernel.org/lkml/Y7xXz+TSpiCbQGjw@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.config | 8 --------
tools/perf/tests/make | 12 ------------
2 files changed, 20 deletions(-)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index c2504c39bdcb8..156440ea01914 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -1314,14 +1314,6 @@ tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
export perfexec_instdir_SQ
-# If we install to $(HOME) we keep the traceevent default:
-# $(HOME)/.traceevent/plugins
-# Otherwise we install plugins into the global $(libdir).
-ifdef DESTDIR
-plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(plugindir))
-endif
-
print_var = $(eval $(print_var_code)) $(info $(MSG))
define print_var_code
MSG = $(shell printf '...%40s: %s' $(1) $($(1)))
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 05e818a8bbad1..009d6efb673ce 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -222,19 +222,7 @@ installed_files_bin := bin/perf
installed_files_bin += etc/bash_completion.d/perf
installed_files_bin += libexec/perf-core/perf-archive
-installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
-
installed_files_all := $(installed_files_bin)
-installed_files_all += $(installed_files_plugins)
test_make_install := $(call test_dest_files,$(installed_files_all))
test_make_install_O := $(call test_dest_files,$(installed_files_all))
--
GitLab
From f00eccb447762c99675f3f5b0311a1216135af95 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 6 Jan 2023 07:13:20 -0800
Subject: [PATCH 0612/1167] perf build: Fix build error when NO_LIBBPF=1
The $(LIBBPF) target should only be a dependency of prepare if the
static version of libbpf is needed. Add a new LIBBPF_STATIC variable
that is set by Makefile.config. Use LIBBPF_STATIC to determine whether
the CFLAGS, etc. need updating and for adding $(LIBBPF) as a prepare
dependency.
As Makefile.config isn't loaded for "clean" as a target, always set
LIBBPF_OUTPUT regardless of whether it is needed for $(LIBBPF). This
is done to minimize conditional logic for $(LIBBPF)-clean.
This issue and an original fix was reported by Mike Leach in:
https://lore.kernel.org/lkml/20230105172243.7238-1-mike.leach@linaro.org/
Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path")
Reported-by: Mike Leach <mike.leach@linaro.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: bpf@vger.kernel.org
Cc: Ian Rogers <irogers@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20230106151320.619514-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.config | 2 ++
tools/perf/Makefile.perf | 21 ++++++++++++---------
2 files changed, 14 insertions(+), 9 deletions(-)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 156440ea01914..9962ae23ab8c5 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -602,6 +602,8 @@ ifndef NO_LIBELF
dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
endif
else
+ # Libbpf will be built as a static library from tools/lib/bpf.
+ LIBBPF_STATIC := 1
CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 1e32c93b80429..b7d9c42062300 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -303,10 +303,12 @@ ifneq ($(OUTPUT),)
else
LIBBPF_OUTPUT = $(CURDIR)/libbpf
endif
-LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
-LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
-LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
-CFLAGS += -I$(LIBBPF_OUTPUT)/include
+ifdef LIBBPF_STATIC
+ LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
+ LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
+ LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
+ CFLAGS += -I$(LIBBPF_OUTPUT)/include
+endif
ifneq ($(OUTPUT),)
LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd
@@ -393,10 +395,8 @@ endif
export PERL_PATH
PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL)
-ifndef NO_LIBBPF
- ifndef LIBBPF_DYNAMIC
- PERFLIBS += $(LIBBPF)
- endif
+ifdef LIBBPF_STATIC
+ PERFLIBS += $(LIBBPF)
endif
# We choose to avoid "if .. else if .. else .. endif endif"
@@ -756,12 +756,15 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
$(arch_errno_name_array) \
$(sync_file_range_arrays) \
$(LIBAPI) \
- $(LIBBPF) \
$(LIBPERF) \
$(LIBSUBCMD) \
$(LIBSYMBOL) \
bpf-skel
+ifdef LIBBPF_STATIC
+prepare: $(LIBBPF)
+endif
+
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
--
GitLab
From eef034ac6690118c88f357b00e2b3239c9d8575d Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Tue, 10 Jan 2023 13:49:30 +0100
Subject: [PATCH 0613/1167] affs: initialize fsdata in affs_truncate()
When aops->write_begin() does not initialize fsdata, KMSAN may report
an error passing the latter to aops->write_end().
Fix this by unconditionally initializing fsdata.
Fixes: f2b6a16eb8f5 ("fs: affs convert to new aops")
Suggested-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Alexander Potapenko <glider@google.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/affs/file.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/affs/file.c b/fs/affs/file.c
index cefa222f7881c..8daeed31e1af9 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -880,7 +880,7 @@ affs_truncate(struct inode *inode)
if (inode->i_size > AFFS_I(inode)->mmu_private) {
struct address_space *mapping = inode->i_mapping;
struct page *page;
- void *fsdata;
+ void *fsdata = NULL;
loff_t isize = inode->i_size;
int res;
--
GitLab
From 14292a4ae1a37a7c97fda59b85cd625c77165ddf Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Jan 2023 11:46:37 -0300
Subject: [PATCH 0614/1167] perf bpf: Avoid build breakage with libbpf < 0.8.0
+ LIBBPF_DYNAMIC=1
In 746bd29e348f99b4 ("perf build: Use tools/lib headers from install
path") we stopped having the tools/lib/ directory from the kernel
sources in the header include path unconditionally, which breaks the
build on systems with older versions of libbpf-devel, in this case 0.7.0
as some of the structures and function declarations present in the newer
version of libbpf included in the kernel sources (tools/lib/bpf) are not
anymore used, just the ones in the system libbpf.
So instead of trying to provide alternative functions when the
libbpf-bpf_program__set_insns feature test fails, fail a
LIBBPF_DYNAMIC=1 build (requesting the use of the system's libbpf) and
emit this build error message:
$ make LIBBPF_DYNAMIC=1 -C tools/perf
Makefile.config:593: *** Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources. Stop.
$
For v6.3 these tests will be revamped and we'll require libbpf 1.0 as a
minimal version for using LIBBPF_DYNAMIC=1, most distros should have it
by now or at v6.3 time.
Fixes: 746bd29e348f99b4 ("perf build: Use tools/lib headers from install path")
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/CAP-5=fVa51_URGsdDFVTzpyGmdDRj_Dj2EKPuDHNQ0BYgMSzUA@mail.gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.config | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 9962ae23ab8c5..5b87846759036 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -589,6 +589,8 @@ ifndef NO_LIBELF
$(call feature_check,libbpf-bpf_program__set_insns)
ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+ else
+ dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources);
endif
$(call feature_check,libbpf-btf__raw_data)
ifeq ($(feature-libbpf-btf__raw_data), 1)
--
GitLab
From 380cd3a34b7f9825a60ccb045611af9cb4533b70 Mon Sep 17 00:00:00 2001
From: Dominik Kobinski <dominikkobinski314@gmail.com>
Date: Fri, 30 Dec 2022 20:48:45 +0100
Subject: [PATCH 0615/1167] arm64: dts: msm8994-angler: fix the memory map
Add reserved regions for memory hole and tz app mem to prevent
rebooting. Also enable cont_splash_mem, it is the same as the
generic 8994 one.
Reported-by: Petr Vorel <petr.vorel@gmail.com>
Signed-off-by: Dominik Kobinski <dominikkobinski314@gmail.com>
Reviewed-by: Petr Vorel <petr.vorel@gmail.com>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221230194845.57780-1-dominikkobinski314@gmail.com
---
.../qcom/msm8994-huawei-angler-rev-101.dts | 19 ++++++++++++++++---
1 file changed, 16 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts
index 85abff0e9b3f7..7b0f62144c3ee 100644
--- a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts
+++ b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts
@@ -9,9 +9,6 @@
#include "msm8994.dtsi"
-/* Angler's firmware does not report where the memory is allocated */
-/delete-node/ &cont_splash_mem;
-
/ {
model = "Huawei Nexus 6P";
compatible = "huawei,angler", "qcom,msm8994";
@@ -28,6 +25,22 @@ aliases {
chosen {
stdout-path = "serial0:115200n8";
};
+
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ tzapp_mem: tzapp@4800000 {
+ reg = <0 0x04800000 0 0x1900000>;
+ no-map;
+ };
+
+ removed_region: reserved@6300000 {
+ reg = <0 0x06300000 0 0xD00000>;
+ no-map;
+ };
+ };
};
&blsp1_uart2 {
--
GitLab
From 6049aae52392539e505bfb8ccbcff3c26f1d2f0b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 17 Dec 2022 17:05:41 +0100
Subject: [PATCH 0616/1167] PM: AVS: qcom-cpr: Fix an error handling path in
cpr_probe()
If an error occurs after a successful pm_genpd_init() call, it should be
undone by a corresponding pm_genpd_remove().
Add the missing call in the error handling path, as already done in the
remove function.
Fixes: bf6910abf548 ("power: avs: Add support for CPR (Core Power Reduction)")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/0f520597dbad89ab99c217c8986912fa53eaf5f9.1671293108.git.christophe.jaillet@wanadoo.fr
---
drivers/soc/qcom/cpr.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/soc/qcom/cpr.c b/drivers/soc/qcom/cpr.c
index e9b854ed1bdfd..144ea68e0920a 100644
--- a/drivers/soc/qcom/cpr.c
+++ b/drivers/soc/qcom/cpr.c
@@ -1708,12 +1708,16 @@ static int cpr_probe(struct platform_device *pdev)
ret = of_genpd_add_provider_simple(dev->of_node, &drv->pd);
if (ret)
- return ret;
+ goto err_remove_genpd;
platform_set_drvdata(pdev, drv);
cpr_debugfs_init(drv);
return 0;
+
+err_remove_genpd:
+ pm_genpd_remove(&drv->pd);
+ return ret;
}
static int cpr_remove(struct platform_device *pdev)
--
GitLab
From 2bd5ab93335bf2c4d22c8db427822ae637ed8dc3 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 19 Dec 2022 14:19:17 +0100
Subject: [PATCH 0617/1167] arm64: dts: qcom: msm8992: Don't use sfpb mutex
MSM8992 uses the same mutex hardware as MSM8994. This was wrong
from the start, but never presented as an issue until the sfpb
compatible was given different driver data.
Fixes: 6a6d1978f9c0 ("arm64: dts: msm8992 SoC and LG Bullhead (Nexus 5X) support")
Reported-by: Eugene Lepshy <fekz115@gmail.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221219131918.446587-1-konrad.dybcio@linaro.org
---
arch/arm64/boot/dts/qcom/msm8992.dtsi | 4 ----
1 file changed, 4 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/msm8992.dtsi b/arch/arm64/boot/dts/qcom/msm8992.dtsi
index 10adb4986ef1b..02fc3795dbfd7 100644
--- a/arch/arm64/boot/dts/qcom/msm8992.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8992.dtsi
@@ -37,10 +37,6 @@ &rpmcc {
compatible = "qcom,rpmcc-msm8992", "qcom,rpmcc";
};
-&tcsr_mutex {
- compatible = "qcom,sfpb-mutex";
-};
-
&timer {
interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
--
GitLab
From 69876bc6fd4de3ad2dc7826fe269e91fa2c1807f Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@linaro.org>
Date: Mon, 19 Dec 2022 14:19:18 +0100
Subject: [PATCH 0618/1167] arm64: dts: qcom: msm8992-libra: Fix the memory map
The memory map was wrong. Fix it to prevent the device from randomly
rebooting.
Fixes: 0f5cdb31e850 ("arm64: dts: qcom: Add Xiaomi Libra (Mi 4C) device tree")
Signed-off-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
Link: https://lore.kernel.org/r/20221219131918.446587-2-konrad.dybcio@linaro.org
---
.../boot/dts/qcom/msm8992-xiaomi-libra.dts | 77 +++++++++++++++----
1 file changed, 60 insertions(+), 17 deletions(-)
diff --git a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
index b242c272d2af1..fcca1ba94da69 100644
--- a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
+++ b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts
@@ -11,6 +11,12 @@
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/input/gpio-keys.h>
+/delete-node/ &adsp_mem;
+/delete-node/ &audio_mem;
+/delete-node/ &mpss_mem;
+/delete-node/ &peripheral_region;
+/delete-node/ &rmtfs_mem;
+
/ {
model = "Xiaomi Mi 4C";
compatible = "xiaomi,libra", "qcom,msm8992";
@@ -70,25 +76,67 @@ reserved-memory {
#size-cells = <2>;
ranges;
- /* This is for getting crash logs using Android downstream kernels */
- ramoops@dfc00000 {
- compatible = "ramoops";
- reg = <0x0 0xdfc00000 0x0 0x40000>;
- console-size = <0x10000>;
- record-size = <0x10000>;
- ftrace-size = <0x10000>;
- pmsg-size = <0x20000>;
+ memory_hole: hole@6400000 {
+ reg = <0 0x06400000 0 0x600000>;
+ no-map;
+ };
+
+ memory_hole2: hole2@6c00000 {
+ reg = <0 0x06c00000 0 0x2400000>;
+ no-map;
+ };
+
+ mpss_mem: mpss@9000000 {
+ reg = <0 0x09000000 0 0x5a00000>;
+ no-map;
+ };
+
+ tzapp: tzapp@ea00000 {
+ reg = <0 0x0ea00000 0 0x1900000>;
+ no-map;
+ };
+
+ mdm_rfsa_mem: mdm-rfsa@ca0b0000 {
+ reg = <0 0xca0b0000 0 0x10000>;
+ no-map;
+ };
+
+ rmtfs_mem: rmtfs@ca100000 {
+ compatible = "qcom,rmtfs-mem";
+ reg = <0 0xca100000 0 0x180000>;
+ no-map;
+
+ qcom,client-id = <1>;
};
- modem_region: modem_region@9000000 {
- reg = <0x0 0x9000000 0x0 0x5a00000>;
+ audio_mem: audio@cb400000 {
+ reg = <0 0xcb000000 0 0x400000>;
+ no-mem;
+ };
+
+ qseecom_mem: qseecom@cb400000 {
+ reg = <0 0xcb400000 0 0x1c00000>;
+ no-mem;
+ };
+
+ adsp_rfsa_mem: adsp-rfsa@cd000000 {
+ reg = <0 0xcd000000 0 0x10000>;
no-map;
};
- tzapp: modem_region@ea00000 {
- reg = <0x0 0xea00000 0x0 0x1900000>;
+ sensor_rfsa_mem: sensor-rfsa@cd010000 {
+ reg = <0 0xcd010000 0 0x10000>;
no-map;
};
+
+ ramoops@dfc00000 {
+ compatible = "ramoops";
+ reg = <0 0xdfc00000 0 0x40000>;
+ console-size = <0x10000>;
+ record-size = <0x10000>;
+ ftrace-size = <0x10000>;
+ pmsg-size = <0x20000>;
+ };
};
};
@@ -130,11 +178,6 @@ &blsp2_uart2 {
status = "okay";
};
-&peripheral_region {
- reg = <0x0 0x7400000 0x0 0x1c00000>;
- no-map;
-};
-
&pm8994_spmi_regulators {
VDD_APC0: s8 {
regulator-min-microvolt = <680000>;
--
GitLab
From d3de5616d36462a646f5b360ba82d3b09ff668eb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 12 Dec 2022 17:13:38 +0100
Subject: [PATCH 0619/1167] drm/i915/gt: Reset twice
After applying an engine reset, on some platforms like Jasperlake, we
occasionally detect that the engine state is not cleared until shortly
after the resume. As we try to resume the engine with volatile internal
state, the first request fails with a spurious CS event (it looks like
it reports a lite-restore to the hung context, instead of the expected
idle->active context switch).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221212161338.1007659-1-andi.shyti@linux.intel.com
(cherry picked from commit 3db9d590557da3aa2c952f2fecd3e9b703dad790)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gt/intel_reset.c | 34 ++++++++++++++++++++++-----
1 file changed, 28 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 24736ebee17c2..78dc5e493c622 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -278,6 +278,7 @@ static int ilk_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask,
static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
{
struct intel_uncore *uncore = gt->uncore;
+ int loops = 2;
int err;
/*
@@ -285,18 +286,39 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
* for fifo space for the write or forcewake the chip for
* the read
*/
- intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
+ do {
+ intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
- /* Wait for the device to ack the reset requests */
- err = __intel_wait_for_register_fw(uncore,
- GEN6_GDRST, hw_domain_mask, 0,
- 500, 0,
- NULL);
+ /*
+ * Wait for the device to ack the reset requests.
+ *
+ * On some platforms, e.g. Jasperlake, we see that the
+ * engine register state is not cleared until shortly after
+ * GDRST reports completion, causing a failure as we try
+ * to immediately resume while the internal state is still
+ * in flux. If we immediately repeat the reset, the second
+ * reset appears to serialise with the first, and since
+ * it is a no-op, the registers should retain their reset
+ * value. However, there is still a concern that upon
+ * leaving the second reset, the internal engine state
+ * is still in flux and not ready for resuming.
+ */
+ err = __intel_wait_for_register_fw(uncore, GEN6_GDRST,
+ hw_domain_mask, 0,
+ 2000, 0,
+ NULL);
+ } while (err == 0 && --loops);
if (err)
GT_TRACE(gt,
"Wait for 0x%08x engines reset failed\n",
hw_domain_mask);
+ /*
+ * As we have observed that the engine state is still volatile
+ * after GDRST is acked, impose a small delay to let everything settle.
+ */
+ udelay(50);
+
return err;
}
--
GitLab
From 90b926e68f500844dff16b5bcea178dc55cf580a Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 10 Jan 2023 07:54:27 +0100
Subject: [PATCH 0620/1167] x86/pat: Fix pat_x_mtrr_type() for MTRR disabled
case
Since
72cbc8f04fe2 ("x86/PAT: Have pat_enabled() properly reflect state when running on Xen")
PAT can be enabled without MTRR.
This has resulted in problems e.g. for a SEV-SNP guest running under Hyper-V,
when trying to establish a new mapping via memremap() with WB caching mode, as
pat_x_mtrr_type() will call mtrr_type_lookup(), which in turn is returning
MTRR_TYPE_INVALID due to MTRR being disabled in this configuration.
The result is a mapping with UC- caching, leading to severe performance
degradation.
Fix that by handling MTRR_TYPE_INVALID the same way as MTRR_TYPE_WRBACK
in pat_x_mtrr_type() because MTRR_TYPE_INVALID means MTRRs are disabled.
[ bp: Massage commit message. ]
Fixes: 72cbc8f04fe2 ("x86/PAT: Have pat_enabled() properly reflect state when running on Xen")
Reported-by: Michael Kelley (LINUX) <mikelley@microsoft.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Tested-by: Michael Kelley <mikelley@microsoft.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20230110065427.20767-1-jgross@suse.com
---
arch/x86/mm/pat/memtype.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 46de9cf5c91d2..fb4b1b5e0deab 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end,
u8 mtrr_type, uniform;
mtrr_type = mtrr_type_lookup(start, end, &uniform);
- if (mtrr_type != MTRR_TYPE_WRBACK)
+ if (mtrr_type != MTRR_TYPE_WRBACK &&
+ mtrr_type != MTRR_TYPE_INVALID)
return _PAGE_CACHE_MODE_UC_MINUS;
return _PAGE_CACHE_MODE_WB;
--
GitLab
From ea97cbebaf861d99c3e892275147e6fca6d2c1ca Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 10 Jan 2023 10:24:52 -0700
Subject: [PATCH 0621/1167] io_uring/fdinfo: include locked hash table in
fdinfo output
A previous commit split the hash table for polled requests into two
parts, but didn't get the fdinfo output updated. This means that it's
less useful for debugging, as we may think a given request is not pending
poll.
Fix this up by dumping the locked hash table contents too.
Fixes: 9ca9fb24d5fe ("io_uring: mutex locked poll hashing")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/fdinfo.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index 2e04850a657b0..882bd56b01ed0 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -170,12 +170,11 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
xa_for_each(&ctx->personalities, index, cred)
io_uring_show_cred(m, index, cred);
}
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
seq_puts(m, "PollList:\n");
for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+ struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i];
struct io_kiocb *req;
spin_lock(&hb->lock);
@@ -183,8 +182,17 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
task_work_pending(req->task));
spin_unlock(&hb->lock);
+
+ if (!has_lock)
+ continue;
+ hlist_for_each_entry(req, &hbl->list, hash_node)
+ seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
+ task_work_pending(req->task));
}
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
+
seq_puts(m, "CqOverflowList:\n");
spin_lock(&ctx->completion_lock);
list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
--
GitLab
From 895c0747f726bb50c9b7a805613a61d1b6f9fa06 Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Tue, 10 Jan 2023 17:44:27 +0100
Subject: [PATCH 0622/1167] vfio/type1: Respect IOMMU reserved regions in
vfio_test_domain_fgsp()
Since commit cbf7827bc5dc ("iommu/s390: Fix potential s390_domain
aperture shrinking") the s390 IOMMU driver uses reserved regions for the
system provided DMA ranges of PCI devices. Previously it reduced the
size of the IOMMU aperture and checked it on each mapping operation.
On current machines the system denies use of DMA addresses below 2^32 for
all PCI devices.
Usually mapping IOVAs in a reserved regions is harmless until a DMA
actually tries to utilize the mapping. However on s390 there is
a virtual PCI device called ISM which is implemented in firmware and
used for cross LPAR communication. Unlike real PCI devices this device
does not use the hardware IOMMU but inspects IOMMU translation tables
directly on IOTLB flush (s390 RPCIT instruction). If it detects IOVA
mappings outside the allowed ranges it goes into an error state. This
error state then causes the device to be unavailable to the KVM guest.
Analysing this we found that vfio_test_domain_fgsp() maps 2 pages at DMA
address 0 irrespective of the IOMMUs reserved regions. Even if usually
harmless this seems wrong in the general case so instead go through the
freshly updated IOVA list and try to find a range that isn't reserved,
and fits 2 pages, is PAGE_SIZE * 2 aligned. If found use that for
testing for fine grained super pages.
Fixes: af029169b8fd ("vfio/type1: Check reserved region conflict and update iova list")
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20230110164427.4051938-2-schnelle@linux.ibm.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
drivers/vfio/vfio_iommu_type1.c | 31 ++++++++++++++++++++-----------
1 file changed, 20 insertions(+), 11 deletions(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 23c24fe98c00d..2209372f236db 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1856,24 +1856,33 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
* significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when
* hugetlbfs is in use.
*/
-static void vfio_test_domain_fgsp(struct vfio_domain *domain)
+static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *regions)
{
- struct page *pages;
int ret, order = get_order(PAGE_SIZE * 2);
+ struct vfio_iova *region;
+ struct page *pages;
+ dma_addr_t start;
pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!pages)
return;
- ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
- IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
- if (!ret) {
- size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
+ list_for_each_entry(region, regions, list) {
+ start = ALIGN(region->start, PAGE_SIZE * 2);
+ if (start >= region->end || (region->end - start < PAGE_SIZE * 2))
+ continue;
- if (unmapped == PAGE_SIZE)
- iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE);
- else
- domain->fgsp = true;
+ ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2,
+ IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
+ if (!ret) {
+ size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE);
+
+ if (unmapped == PAGE_SIZE)
+ iommu_unmap(domain->domain, start + PAGE_SIZE, PAGE_SIZE);
+ else
+ domain->fgsp = true;
+ }
+ break;
}
__free_pages(pages, order);
@@ -2326,7 +2335,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
}
}
- vfio_test_domain_fgsp(domain);
+ vfio_test_domain_fgsp(domain, &iova_copy);
/* replay mappings on new domains */
ret = vfio_iommu_replay(iommu, domain);
--
GitLab
From fe1f0714385fbcf76b0cbceb02b7277d842014fc Mon Sep 17 00:00:00 2001
From: Peter Newman <peternewman@google.com>
Date: Tue, 20 Dec 2022 17:11:23 +0100
Subject: [PATCH 0623/1167] x86/resctrl: Fix task CLOSID/RMID update race
When the user moves a running task to a new rdtgroup using the task's
file interface or by deleting its rdtgroup, the resulting change in
CLOSID/RMID must be immediately propagated to the PQR_ASSOC MSR on the
task(s) CPUs.
x86 allows reordering loads with prior stores, so if the task starts
running between a task_curr() check that the CPU hoisted before the
stores in the CLOSID/RMID update then it can start running with the old
CLOSID/RMID until it is switched again because __rdtgroup_move_task()
failed to determine that it needs to be interrupted to obtain the new
CLOSID/RMID.
Refer to the diagram below:
CPU 0 CPU 1
----- -----
__rdtgroup_move_task():
curr <- t1->cpu->rq->curr
__schedule():
rq->curr <- t1
resctrl_sched_in():
t1->{closid,rmid} -> {1,1}
t1->{closid,rmid} <- {2,2}
if (curr == t1) // false
IPI(t1->cpu)
A similar race impacts rdt_move_group_tasks(), which updates tasks in a
deleted rdtgroup.
In both cases, use smp_mb() to order the task_struct::{closid,rmid}
stores before the loads in task_curr(). In particular, in the
rdt_move_group_tasks() case, simply execute an smp_mb() on every
iteration with a matching task.
It is possible to use a single smp_mb() in rdt_move_group_tasks(), but
this would require two passes and a means of remembering which
task_structs were updated in the first loop. However, benchmarking
results below showed too little performance impact in the simple
approach to justify implementing the two-pass approach.
Times below were collected using `perf stat` to measure the time to
remove a group containing a 1600-task, parallel workload.
CPU: Intel(R) Xeon(R) Platinum P-8136 CPU @ 2.00GHz (112 threads)
# mkdir /sys/fs/resctrl/test
# echo $$ > /sys/fs/resctrl/test/tasks
# perf bench sched messaging -g 40 -l 100000
task-clock time ranges collected using:
# perf stat rmdir /sys/fs/resctrl/test
Baseline: 1.54 - 1.60 ms
smp_mb() every matching task: 1.57 - 1.67 ms
[ bp: Massage commit message. ]
Fixes: ae28d1aae48a ("x86/resctrl: Use an IPI instead of task_work_add() to update PQR_ASSOC MSR")
Fixes: 0efc89be9471 ("x86/intel_rdt: Update task closid immediately on CPU in rmdir and unmount")
Signed-off-by: Peter Newman <peternewman@google.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Reviewed-by: Babu Moger <babu.moger@amd.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20221220161123.432120-1-peternewman@google.com
---
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index e5a48f05e7876..5993da21d8225 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
/*
* Ensure the task's closid and rmid are written before determining if
* the task is current that will decide if it will be interrupted.
+ * This pairs with the full barrier between the rq->curr update and
+ * resctrl_sched_in() during context switch.
*/
- barrier();
+ smp_mb();
/*
* By now, the task's closid and rmid are set. If the task is current
@@ -2401,6 +2403,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
WRITE_ONCE(t->closid, to->closid);
WRITE_ONCE(t->rmid, to->mon.rmid);
+ /*
+ * Order the closid/rmid stores above before the loads
+ * in task_curr(). This pairs with the full barrier
+ * between the rq->curr update and resctrl_sched_in()
+ * during context switch.
+ */
+ smp_mb();
+
/*
* If the task is on a CPU, set the CPU in the mask.
* The detection is inaccurate as tasks might move or
--
GitLab
From 2a81160d29d65b5876ab3f824fda99ae0219f05e Mon Sep 17 00:00:00 2001
From: Peter Newman <peternewman@google.com>
Date: Tue, 20 Dec 2022 17:41:31 +0100
Subject: [PATCH 0624/1167] x86/resctrl: Fix event counts regression in reused
RMIDs
When creating a new monitoring group, the RMID allocated for it may have
been used by a group which was previously removed. In this case, the
hardware counters will have non-zero values which should be deducted
from what is reported in the new group's counts.
resctrl_arch_reset_rmid() initializes the prev_msr value for counters to
0, causing the initial count to be charged to the new group. Resurrect
__rmid_read() and use it to initialize prev_msr correctly.
Unlike before, __rmid_read() checks for error bits in the MSR read so
that callers don't need to.
Fixes: 1d81d15db39c ("x86/resctrl: Move mbm_overflow_count() into resctrl_arch_rmid_read()")
Signed-off-by: Peter Newman <peternewman@google.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20221220164132.443083-1-peternewman@google.com
---
arch/x86/kernel/cpu/resctrl/monitor.c | 49 ++++++++++++++++++---------
1 file changed, 33 insertions(+), 16 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index efe0c30d3a12d..77538abeb72af 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
return entry;
}
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+ u64 msr_val;
+
+ /*
+ * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+ * with a valid event code for supported resource type and the bits
+ * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+ * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+ * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+ * are error bits.
+ */
+ wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+ rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+ if (msr_val & RMID_VAL_ERROR)
+ return -EIO;
+ if (msr_val & RMID_VAL_UNAVAIL)
+ return -EINVAL;
+
+ *val = msr_val;
+ return 0;
+}
+
static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
u32 rmid,
enum resctrl_event_id eventid)
@@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
struct arch_mbm_state *am;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
- if (am)
+ if (am) {
memset(am, 0, sizeof(*am));
+
+ /* Record any initial, non-zero count value. */
+ __rmid_read(rmid, eventid, &am->prev_msr);
+ }
}
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
@@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct arch_mbm_state *am;
u64 msr_val, chunks;
+ int ret;
if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
return -EINVAL;
- /*
- * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
- * with a valid event code for supported resource type and the bits
- * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
- * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
- * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
- * are error bits.
- */
- wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
- rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
- if (msr_val & RMID_VAL_ERROR)
- return -EIO;
- if (msr_val & RMID_VAL_UNAVAIL)
- return -EINVAL;
+ ret = __rmid_read(rmid, eventid, &msr_val);
+ if (ret)
+ return ret;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
if (am) {
--
GitLab
From 77c7248882385397cd7dffe9e1437f59f32ce2de Mon Sep 17 00:00:00 2001
From: Tamim Khan <tamim@fusetak.com>
Date: Fri, 30 Dec 2022 00:58:39 -0500
Subject: [PATCH 0625/1167] ACPI: resource: Skip IRQ override on Asus
Expertbook B2402CBA
Like the Asus Expertbook B2502CBA and various Asus Vivobook laptops,
the Asus Expertbook B2402CBA has an ACPI DSDT table that describes IRQ 1
as ActiveLow while the kernel overrides it to Edge_High. This prevents the
keyboard from working. To fix this issue, add this laptop to the
skip_override_table so that the kernel does not override IRQ 1.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216864
Tested-by: zelenat <zelenat@gmail.com>
Signed-off-by: Tamim Khan <tamim@fusetak.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/resource.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 16dcd31d124fe..192d1784e409b 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -432,6 +432,13 @@ static const struct dmi_system_id asus_laptop[] = {
DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
},
},
+ {
+ .ident = "Asus ExpertBook B2402CBA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"),
+ },
+ },
{
.ident = "Asus ExpertBook B2502",
.matches = {
--
GitLab
From 420a1116aef0e8e12c305508f45ce73e5ae30a09 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 9 Jan 2023 20:18:11 +0100
Subject: [PATCH 0626/1167] ACPI: video: Allow selecting NVidia-WMI-EC or Apple
GMUX backlight from the cmdline
The patches adding NVidia-WMI-EC and Apple GMUX backlight detection
support to acpi_video_get_backlight_type(), forgot to update
acpi_video_parse_cmdline() to allow manually selecting these from
the commandline.
Add support for these to acpi_video_parse_cmdline().
Fixes: fe7aebb40d42 ("ACPI: video: Add Nvidia WMI EC brightness control detection (v3)")
Fixes: 21245df307cb ("ACPI: video: Add Apple GMUX brightness control detection")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/video_detect.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 1b78c74344928..8a541efc56756 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -50,6 +50,10 @@ static void acpi_video_parse_cmdline(void)
acpi_backlight_cmdline = acpi_backlight_video;
if (!strcmp("native", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_native;
+ if (!strcmp("nvidia_wmi_ec", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
+ if (!strcmp("apple_gmux", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_apple_gmux;
if (!strcmp("none", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_none;
}
--
GitLab
From 8debed3efe3a731451ad9a91a7a74eeb18a7f7eb Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 9 Jan 2023 04:23:17 +0900
Subject: [PATCH 0627/1167] kbuild: export top-level LDFLAGS_vmlinux only to
scripts/Makefile.vmlinux
Nathan Chancellor reports that $(NM) emits an error message when
GNU Make 4.4 is used to build the ARM zImage.
$ make-4.4 ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- O=build defconfig zImage
[snip]
LD vmlinux
NM System.map
SORTTAB vmlinux
OBJCOPY arch/arm/boot/Image
Kernel: arch/arm/boot/Image is ready
arm-linux-gnueabi-nm: 'arch/arm/boot/compressed/../../../../vmlinux': No such file
/bin/sh: 1: arithmetic expression: expecting primary: " "
LDS arch/arm/boot/compressed/vmlinux.lds
AS arch/arm/boot/compressed/head.o
GZIP arch/arm/boot/compressed/piggy_data
AS arch/arm/boot/compressed/piggy.o
CC arch/arm/boot/compressed/misc.o
This occurs since GNU Make commit 98da874c4303 ("[SV 10593] Export
variables to $(shell ...) commands"), and the O= option is needed to
reproduce it. The generated zImage is correct despite the error message.
As the commit description of 98da874c4303 [1] says, exported variables
are passed down to $(shell ) functions, which means exported recursive
variables might be expanded earlier than before, in the parse stage.
The following test code demonstrates the change for GNU Make 4.4.
[Test Makefile]
$(shell echo hello > foo)
export foo = $(shell cat bar/../foo)
$(shell mkdir bar)
all:
@echo $(foo)
[GNU Make 4.3]
$ rm -rf bar; make-4.3
hello
[GNU Make 4.4]
$ rm -rf bar; make-4.4
cat: bar/../foo: No such file or directory
hello
The 'foo' is a resursively expanded (i.e. lazily expanded) variable.
GNU Make 4.3 expands 'foo' just before running the recipe '@echo $(foo)',
at this point, the directory 'bar' exists.
GNU Make 4.4 expands 'foo' to evaluate $(shell mkdir bar) because it is
exported. At this point, the directory 'bar' does not exit yet. The cat
command cannot resolve the bar/../foo path, hence the error message.
Let's get back to the kernel Makefile.
In arch/arm/boot/compressed/Makefile, KBSS_SZ is referenced by
LDFLAGS_vmlinux, which is recursive and also exported by the top
Makefile.
GNU Make 4.3 expands KBSS_SZ just before running the recipes, so no
error message.
GNU Make 4.4 expands KBSS_SZ in the parse stage, where the directory
arm/arm/boot/compressed does not exit yet. When compiled with O=,
the output directory is created by $(shell mkdir -p $(obj-dirs))
in scripts/Makefile.build.
There are two ways to fix this particular issue:
- change "$(obj)/../../../../vmlinux" in KBSS_SZ to "vmlinux"
- unexport LDFLAGS_vmlinux
This commit takes the latter course because it is what I originally
intended.
Commit 3ec8a5b33dea ("kbuild: do not export LDFLAGS_vmlinux")
unexported LDFLAGS_vmlinux.
Commit 5d4aeffbf709 ("kbuild: rebuild .vmlinux.export.o when its
prerequisite is updated") accidentally exported it again.
We can clean up arch/arm/boot/compressed/Makefile later.
[1]: https://git.savannah.gnu.org/cgit/make.git/commit/?id=98da874c43035a490cdca81331724f233a3d0c9a
Link: https://lore.kernel.org/all/Y7i8+EjwdnhHtlrr@dev-arch.thelio-3990X/
Fixes: 5d4aeffbf709 ("kbuild: rebuild .vmlinux.export.o when its prerequisite is updated")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
Tested-by: Nathan Chancellor <nathan@kernel.org>
---
Makefile | 14 +++++++++++++-
1 file changed, 13 insertions(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index 460716314fb3c..7607e20385a8d 100644
--- a/Makefile
+++ b/Makefile
@@ -549,7 +549,7 @@ LDFLAGS_MODULE =
CFLAGS_KERNEL =
RUSTFLAGS_KERNEL =
AFLAGS_KERNEL =
-export LDFLAGS_vmlinux =
+LDFLAGS_vmlinux =
# Use USERINCLUDE when you must reference the UAPI directories only.
USERINCLUDE := \
@@ -1248,6 +1248,18 @@ vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
@:
PHONY += vmlinux
+# LDFLAGS_vmlinux in the top Makefile defines linker flags for the top vmlinux,
+# not for decompressors. LDFLAGS_vmlinux in arch/*/boot/compressed/Makefile is
+# unrelated; the decompressors just happen to have the same base name,
+# arch/*/boot/compressed/vmlinux.
+# Export LDFLAGS_vmlinux only to scripts/Makefile.vmlinux.
+#
+# _LDFLAGS_vmlinux is a workaround for the 'private export' bug:
+# https://savannah.gnu.org/bugs/?61463
+# For Make > 4.4, the following simple code will work:
+# vmlinux: private export LDFLAGS_vmlinux := $(LDFLAGS_vmlinux)
+vmlinux: private _LDFLAGS_vmlinux := $(LDFLAGS_vmlinux)
+vmlinux: export LDFLAGS_vmlinux = $(_LDFLAGS_vmlinux)
vmlinux: vmlinux.o $(KBUILD_LDS) modpost
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux
--
GitLab
From 74d3320f6f7cf72de88a7e8df573821f6db90239 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 10 Jan 2023 14:48:00 +0900
Subject: [PATCH 0628/1167] kbuild: fix 'make modules' error when
CONFIG_DEBUG_INFO_BTF_MODULES=y
When CONFIG_DEBUG_INFO_BTF_MODULES=y, running 'make modules'
in the clean kernel tree will get the following error.
$ grep CONFIG_DEBUG_INFO_BTF_MODULES .config
CONFIG_DEBUG_INFO_BTF_MODULES=y
$ make -s clean
$ make modules
[snip]
AR vmlinux.a
ar: ./built-in.a: No such file or directory
make: *** [Makefile:1241: vmlinux.a] Error 1
'modules' depends on 'vmlinux', but builtin objects are not built.
Define KBUILD_BUILTIN.
Fixes: f73edc8951b2 ("kbuild: unify two modpost invocations")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/Makefile b/Makefile
index 7607e20385a8d..eb02f3823ce6d 100644
--- a/Makefile
+++ b/Makefile
@@ -1545,6 +1545,7 @@ endif
# *.ko are usually independent of vmlinux, but CONFIG_DEBUG_INFOBTF_MODULES
# is an exception.
ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+KBUILD_BUILTIN := 1
modules: vmlinux
endif
--
GitLab
From f64e4275ef7407d5c3eca20436519bbd1f796e40 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 10 Jan 2023 16:30:28 +0100
Subject: [PATCH 0629/1167] ACPI: Fix selecting wrong ACPI fwnode for the iGPU
on some Dell laptops
The Dell Latitude E6430 both with and without the optional NVidia dGPU
has a bug in its ACPI tables which is causing Linux to assign the wrong
ACPI fwnode / companion to the pci_device for the i915 iGPU.
Specifically under the PCI root bridge there are these 2 ACPI Device()s :
Scope (_SB.PCI0)
{
Device (GFX0)
{
Name (_ADR, 0x00020000) // _ADR: Address
}
...
Device (VID)
{
Name (_ADR, 0x00020000) // _ADR: Address
...
Method (_DOS, 1, NotSerialized) // _DOS: Disable Output Switching
{
VDP8 = Arg0
VDP1 (One, VDP8)
}
Method (_DOD, 0, NotSerialized) // _DOD: Display Output Devices
{
...
}
...
}
}
The non-functional GFX0 ACPI device is a problem, because this gets
returned as ACPI companion-device by acpi_find_child_device() for the iGPU.
This is a long standing problem and the i915 driver does use the ACPI
companion for some things, but works fine without it.
However since commit 63f534b8bad9 ("ACPI: PCI: Rework acpi_get_pci_dev()")
acpi_get_pci_dev() relies on the physical-node pointer in the acpi_device
and that is set on the wrong acpi_device because of the wrong
acpi_find_child_device() return. This breaks the ACPI video code,
leading to non working backlight control in some cases.
Add a type.backlight flag, mark ACPI video bus devices with this and make
find_child_checks() return a higher score for children with this flag set,
so that it picks the right companion-device.
Fixes: 63f534b8bad9 ("ACPI: PCI: Rework acpi_get_pci_dev()")
Co-developed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: 6.1+ <stable@vger.kernel.org> # 6.1+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/glue.c | 14 ++++++++++++--
drivers/acpi/scan.c | 7 +++++--
include/acpi/acpi_bus.h | 3 ++-
3 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c
index 204fe94c7e458..a194f30876c59 100644
--- a/drivers/acpi/glue.c
+++ b/drivers/acpi/glue.c
@@ -75,7 +75,8 @@ static struct acpi_bus_type *acpi_get_bus_type(struct device *dev)
}
#define FIND_CHILD_MIN_SCORE 1
-#define FIND_CHILD_MAX_SCORE 2
+#define FIND_CHILD_MID_SCORE 2
+#define FIND_CHILD_MAX_SCORE 3
static int match_any(struct acpi_device *adev, void *not_used)
{
@@ -96,8 +97,17 @@ static int find_child_checks(struct acpi_device *adev, bool check_children)
return -ENODEV;
status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
- if (status == AE_NOT_FOUND)
+ if (status == AE_NOT_FOUND) {
+ /*
+ * Special case: backlight device objects without _STA are
+ * preferred to other objects with the same _ADR value, because
+ * it is more likely that they are actually useful.
+ */
+ if (adev->pnp.type.backlight)
+ return FIND_CHILD_MID_SCORE;
+
return FIND_CHILD_MIN_SCORE;
+ }
if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
return -ENODEV;
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 274344434282e..0c6f06abe3f47 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1370,9 +1370,12 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp,
* Some devices don't reliably have _HIDs & _CIDs, so add
* synthetic HIDs to make sure drivers can find them.
*/
- if (acpi_is_video_device(handle))
+ if (acpi_is_video_device(handle)) {
acpi_add_id(pnp, ACPI_VIDEO_HID);
- else if (acpi_bay_match(handle))
+ pnp->type.backlight = 1;
+ break;
+ }
+ if (acpi_bay_match(handle))
acpi_add_id(pnp, ACPI_BAY_HID);
else if (acpi_dock_match(handle))
acpi_add_id(pnp, ACPI_DOCK_HID);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index cd3b75e08ec3f..e44be31115a67 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -230,7 +230,8 @@ struct acpi_pnp_type {
u32 hardware_id:1;
u32 bus_address:1;
u32 platform_id:1;
- u32 reserved:29;
+ u32 backlight:1;
+ u32 reserved:28;
};
struct acpi_device_pnp {
--
GitLab
From 4f3085f87b51a551a0647f218d4f324796ecb703 Mon Sep 17 00:00:00 2001
From: Perry Yuan <perry.yuan@amd.com>
Date: Tue, 10 Jan 2023 23:10:29 +0800
Subject: [PATCH 0630/1167] cpufreq: amd-pstate: fix kernel hang issue while
amd-pstate unregistering
In the amd_pstate_adjust_perf(), there is one cpufreq_cpu_get() call to
increase increments the kobject reference count of policy and make it as
busy. Therefore, a corresponding call to cpufreq_cpu_put() is needed to
decrement the kobject reference count back, it will resolve the kernel
hang issue when unregistering the amd-pstate driver and register the
`amd_pstate_epp` driver instance.
Fixes: 1d215f0319 ("cpufreq: amd-pstate: Add fast switch function for AMD P-State")
Acked-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Wyes Karny <wyes.karny@amd.com>
Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Cc: 5.17+ <stable@vger.kernel.org> # 5.17+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/cpufreq/amd-pstate.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 204e39006dda8..c17bd845f5fcb 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -307,6 +307,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
max_perf = min_perf;
amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
+ cpufreq_cpu_put(policy);
}
static int amd_get_min_freq(struct amd_cpudata *cpudata)
--
GitLab
From b93fb4405fcb5112c5739c5349afb52ec7f15c07 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Tue, 29 Nov 2022 09:57:48 +0800
Subject: [PATCH 0631/1167] ixgbe: fix pci device refcount leak
As the comment of pci_get_domain_bus_and_slot() says, it
returns a PCI device with refcount incremented, when finish
using it, the caller must decrement the reference count by
calling pci_dev_put().
In ixgbe_get_first_secondary_devfn() and ixgbe_x550em_a_has_mii(),
pci_dev_put() is called to avoid leak.
Fixes: 8fa10ef01260 ("ixgbe: register a mdiobus")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 24aa97f993ca1..123dca9ce4683 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -855,9 +855,11 @@ static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn)
rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
if (rp_pdev && rp_pdev->subordinate) {
bus = rp_pdev->subordinate->number;
+ pci_dev_put(rp_pdev);
return pci_get_domain_bus_and_slot(0, bus, 0);
}
+ pci_dev_put(rp_pdev);
return NULL;
}
@@ -874,6 +876,7 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw)
struct ixgbe_adapter *adapter = hw->back;
struct pci_dev *pdev = adapter->pdev;
struct pci_dev *func0_pdev;
+ bool has_mii = false;
/* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
* are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
@@ -884,15 +887,16 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw)
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
if (func0_pdev) {
if (func0_pdev == pdev)
- return true;
- else
- return false;
+ has_mii = true;
+ goto out;
}
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
if (func0_pdev == pdev)
- return true;
+ has_mii = true;
- return false;
+out:
+ pci_dev_put(func0_pdev);
+ return has_mii;
}
/**
--
GitLab
From 5e91c72e560cc85f7163bbe3d14197268de31383 Mon Sep 17 00:00:00 2001
From: Christopher S Hall <christopher.s.hall@intel.com>
Date: Wed, 14 Dec 2022 16:10:38 +0800
Subject: [PATCH 0632/1167] igc: Fix PPS delta between two synchronized
end-points
This patch fix the pulse per second output delta between
two synchronized end-points.
Based on Intel Discrete I225 Software User Manual Section
4.2.15 TimeSync Auxiliary Control Register, ST0[Bit 4] and
ST1[Bit 7] must be set to ensure that clock output will be
toggles based on frequency value defined. This is to ensure
that output of the PPS is aligned with the clock.
How to test:
1) Running time synchronization on both end points.
Ex: ptp4l --step_threshold=1 -m -f gPTP.cfg -i <interface name>
2) Configure PPS output using below command for both end-points
Ex: SDP0 on I225 REV4 SKU variant
./testptp -d /dev/ptp0 -L 0,2
./testptp -d /dev/ptp0 -p 1000000000
3) Measure the output using analyzer for both end-points
Fixes: 87938851b6ef ("igc: enable auxiliary PHC functions for the i225")
Signed-off-by: Christopher S Hall <christopher.s.hall@intel.com>
Signed-off-by: Muhammad Husaini Zulkifli <muhammad.husaini.zulkifli@intel.com>
Acked-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/igc/igc_defines.h | 2 ++
drivers/net/ethernet/intel/igc/igc_ptp.c | 10 ++++++----
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index a7b22639cfcd9..e9747ec5ac0b8 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -475,7 +475,9 @@
#define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */
#define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */
#define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */
+#define IGC_TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */
#define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */
+#define IGC_TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */
#define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */
#define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */
#define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */
diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c
index 8dbb9f903ca70..c34734d432e0d 100644
--- a/drivers/net/ethernet/intel/igc/igc_ptp.c
+++ b/drivers/net/ethernet/intel/igc/igc_ptp.c
@@ -322,7 +322,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
ts = ns_to_timespec64(ns);
if (rq->perout.index == 1) {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK1;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK1 | IGC_TSAUXC_ST1;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT1;
@@ -333,7 +333,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
freqout = IGC_FREQOUT1;
} else {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK0;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK0 | IGC_TSAUXC_ST0;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT0;
@@ -347,10 +347,12 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp,
tsauxc = rd32(IGC_TSAUXC);
tsim = rd32(IGC_TSIM);
if (rq->perout.index == 1) {
- tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1 |
+ IGC_TSAUXC_ST1);
tsim &= ~IGC_TSICR_TT1;
} else {
- tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0 |
+ IGC_TSAUXC_ST0);
tsim &= ~IGC_TSICR_TT0;
}
if (on) {
--
GitLab
From 6650c8e906ce58404bfdfceceeba7bd10d397d40 Mon Sep 17 00:00:00 2001
From: Daniil Tatianin <d-tatianin@yandex-team.ru>
Date: Tue, 20 Dec 2022 09:32:46 +0300
Subject: [PATCH 0633/1167] iavf/iavf_main: actually log ->src mask when
talking about it
This fixes a copy-paste issue where dev_err would log the dst mask even
though it is clearly talking about src.
Found by Linux Verification Center (linuxtesting.org) with the SVACE
static analysis tool.
Fixes: 0075fa0fadd0 ("i40evf: Add support to apply cloud filters")
Signed-off-by: Daniil Tatianin <d-tatianin@yandex-team.ru>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/iavf/iavf_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index c4e451ef79422..adc02adef83a2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3850,7 +3850,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
field_flags |= IAVF_CLOUD_FIELD_IIP;
} else {
dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
- be32_to_cpu(match.mask->dst));
+ be32_to_cpu(match.mask->src));
return -EINVAL;
}
}
--
GitLab
From 2f57e4464cddfceda850ae4224779d11b6eb171f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 5 Jan 2023 13:41:11 +0000
Subject: [PATCH 0634/1167] cifs: remove redundant assignment to the variable
match
The variable match is being assigned a value that is never read, it
is being re-assigned a new value later on. The assignment is redundant
and can be removed.
Cleans up clang scan-build warning:
fs/cifs/dfs_cache.c:1302:2: warning: Value stored to 'match' is never read
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 43ad1176dcb9d..e20f8880363fa 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1299,7 +1299,6 @@ static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, c
* Resolve share's hostname and check if server address matches. Otherwise just ignore it
* as we could not have upcall to resolve hostname or failed to convert ip address.
*/
- match = true;
extract_unc_hostname(s1, &host, &hostlen);
scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host);
--
GitLab
From 39e8db3c860e2678ce5a7d74193925876507c9eb Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 10 Jan 2023 17:55:20 -0300
Subject: [PATCH 0635/1167] cifs: fix double free on failed kerberos auth
If session setup failed with kerberos auth, we ended up freeing
cifs_ses::auth_key.response twice in SMB2_auth_kerberos() and
sesInfoFree().
Fix this by zeroing out cifs_ses::auth_key.response after freeing it
in SMB2_auth_kerberos().
Fixes: a4e430c8c8ba ("cifs: replace kfree() with kfree_sensitive() for sensitive data")
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Acked-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb2pdu.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2c484d47c5922..727f16b426be5 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1482,8 +1482,11 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
out_put_spnego_key:
key_invalidate(spnego_key);
key_put(spnego_key);
- if (rc)
+ if (rc) {
kfree_sensitive(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
out:
sess_data->result = rc;
sess_data->func = NULL;
--
GitLab
From a1904fa4dfc929e5ea36bd409cf0d800df56fb8b Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Mon, 2 Jan 2023 12:52:55 +0100
Subject: [PATCH 0636/1167] firmware: raspberrypi: Fix type assignment
We silently cast an unsigned int into a __le32 which makes sparse
complain. Moreover, we never actually convert endianness between the
CPU's and the expected little-endian value. Fix both at once by calling
cpu_to_le32().
Fixes: 40c31955e4e9 ("firmware: raspberrypi: Provide a helper to query a clock max rate")
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/r/20221116091712.1309651-3-maxime@cerno.tech
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://lore.kernel.org/r/20230102115255.17802-1-maxime@cerno.tech
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
include/soc/bcm2835/raspberrypi-firmware.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h
index ab955591cb72c..73cac8d0287e8 100644
--- a/include/soc/bcm2835/raspberrypi-firmware.h
+++ b/include/soc/bcm2835/raspberrypi-firmware.h
@@ -170,7 +170,7 @@ struct rpi_firmware_clk_rate_request {
#define RPI_FIRMWARE_CLK_RATE_REQUEST(_id) \
{ \
- .id = _id, \
+ .id = cpu_to_le32(_id), \
}
#if IS_ENABLED(CONFIG_RASPBERRYPI_FIRMWARE)
--
GitLab
From 980a637d11fe8dfc734f508a422185c2de55e669 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 4 Jan 2023 09:35:09 +0100
Subject: [PATCH 0637/1167] ARM: omap1: fix !ARCH_OMAP1_ANY link failures
While compile-testing randconfig builds for the upcoming boardfile
removal, I noticed that an earlier patch of mine was completely
broken, and the introduction of CONFIG_ARCH_OMAP1_ANY only replaced
one set of build failures with another one, now resulting in
link failures like
ld: drivers/video/fbdev/omap/omapfb_main.o: in function `omapfb_do_probe':
drivers/video/fbdev/omap/omapfb_main.c:1703: undefined reference to `omap_set_dma_priority'
ld: drivers/dma/ti/omap-dma.o: in function `omap_dma_free_chan_resources':
drivers/dma/ti/omap-dma.c:777: undefined reference to `omap_free_dma'
drivers/dma/ti/omap-dma.c:1685: undefined reference to `omap_get_plat_info'
ld: drivers/usb/gadget/udc/omap_udc.o: in function `next_in_dma':
drivers/usb/gadget/udc/omap_udc.c:820: undefined reference to `omap_get_dma_active_status'
I tried reworking it, but the resulting patch ended up much bigger than
simply avoiding the original problem of unused-function warnings like
arch/arm/mach-omap1/mcbsp.c:76:30: error: unused variable 'omap1_mcbsp_ops' [-Werror,-Wunused-variable]
As a result, revert the previous fix, and rearrange the code that
produces warnings to hide them. For mcbsp, the #ifdef check can
simply be removed as the cpu_is_omapxxx() checks already achieve
the same result, while in the io.c the easiest solution appears to
be to merge the common map bits into each soc specific portion.
This gets cleaned in a nicer way after omap7xx support gets dropped,
as the remaining SoCs all have the exact same I/O map.
Fixes: 615dce5bf736 ("ARM: omap1: fix build with no SoC selected")
Cc: stable@vger.kernel.org
Acked-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/mach-omap1/Kconfig | 5 +----
arch/arm/mach-omap1/Makefile | 4 ----
arch/arm/mach-omap1/io.c | 32 +++++++++++++++-----------------
arch/arm/mach-omap1/mcbsp.c | 21 ---------------------
arch/arm/mach-omap1/pm.h | 7 -------
include/linux/soc/ti/omap1-io.h | 4 ++--
6 files changed, 18 insertions(+), 55 deletions(-)
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index 538a960257cc7..7ec7ada287e05 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -4,6 +4,7 @@ menuconfig ARCH_OMAP1
depends on ARCH_MULTI_V4T || ARCH_MULTI_V5
depends on CPU_LITTLE_ENDIAN
depends on ATAGS
+ select ARCH_OMAP
select ARCH_HAS_HOLES_MEMORYMODEL
select ARCH_OMAP
select CLKSRC_MMIO
@@ -45,10 +46,6 @@ config ARCH_OMAP16XX
select CPU_ARM926T
select OMAP_DM_TIMER
-config ARCH_OMAP1_ANY
- select ARCH_OMAP
- def_bool ARCH_OMAP730 || ARCH_OMAP850 || ARCH_OMAP15XX || ARCH_OMAP16XX
-
config ARCH_OMAP
bool
diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile
index 506074b86333f..0615cb0ba580b 100644
--- a/arch/arm/mach-omap1/Makefile
+++ b/arch/arm/mach-omap1/Makefile
@@ -3,8 +3,6 @@
# Makefile for the linux kernel.
#
-ifdef CONFIG_ARCH_OMAP1_ANY
-
# Common support
obj-y := io.o id.o sram-init.o sram.o time.o irq.o mux.o flash.o \
serial.o devices.o dma.o omap-dma.o fb.o
@@ -59,5 +57,3 @@ obj-$(CONFIG_ARCH_OMAP730) += gpio7xx.o
obj-$(CONFIG_ARCH_OMAP850) += gpio7xx.o
obj-$(CONFIG_ARCH_OMAP15XX) += gpio15xx.o
obj-$(CONFIG_ARCH_OMAP16XX) += gpio16xx.o
-
-endif
diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c
index d2db9b8aed3fb..0074b011a05a4 100644
--- a/arch/arm/mach-omap1/io.c
+++ b/arch/arm/mach-omap1/io.c
@@ -22,17 +22,14 @@
* The machine specific code may provide the extra mapping besides the
* default mapping provided here.
*/
-static struct map_desc omap_io_desc[] __initdata = {
+#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
+static struct map_desc omap7xx_io_desc[] __initdata = {
{
.virtual = OMAP1_IO_VIRT,
.pfn = __phys_to_pfn(OMAP1_IO_PHYS),
.length = OMAP1_IO_SIZE,
.type = MT_DEVICE
- }
-};
-
-#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
-static struct map_desc omap7xx_io_desc[] __initdata = {
+ },
{
.virtual = OMAP7XX_DSP_BASE,
.pfn = __phys_to_pfn(OMAP7XX_DSP_START),
@@ -49,6 +46,12 @@ static struct map_desc omap7xx_io_desc[] __initdata = {
#ifdef CONFIG_ARCH_OMAP15XX
static struct map_desc omap1510_io_desc[] __initdata = {
+ {
+ .virtual = OMAP1_IO_VIRT,
+ .pfn = __phys_to_pfn(OMAP1_IO_PHYS),
+ .length = OMAP1_IO_SIZE,
+ .type = MT_DEVICE
+ },
{
.virtual = OMAP1510_DSP_BASE,
.pfn = __phys_to_pfn(OMAP1510_DSP_START),
@@ -65,6 +68,12 @@ static struct map_desc omap1510_io_desc[] __initdata = {
#if defined(CONFIG_ARCH_OMAP16XX)
static struct map_desc omap16xx_io_desc[] __initdata = {
+ {
+ .virtual = OMAP1_IO_VIRT,
+ .pfn = __phys_to_pfn(OMAP1_IO_PHYS),
+ .length = OMAP1_IO_SIZE,
+ .type = MT_DEVICE
+ },
{
.virtual = OMAP16XX_DSP_BASE,
.pfn = __phys_to_pfn(OMAP16XX_DSP_START),
@@ -79,18 +88,9 @@ static struct map_desc omap16xx_io_desc[] __initdata = {
};
#endif
-/*
- * Maps common IO regions for omap1
- */
-static void __init omap1_map_common_io(void)
-{
- iotable_init(omap_io_desc, ARRAY_SIZE(omap_io_desc));
-}
-
#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850)
void __init omap7xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap7xx_io_desc, ARRAY_SIZE(omap7xx_io_desc));
}
#endif
@@ -98,7 +98,6 @@ void __init omap7xx_map_io(void)
#ifdef CONFIG_ARCH_OMAP15XX
void __init omap15xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap1510_io_desc, ARRAY_SIZE(omap1510_io_desc));
}
#endif
@@ -106,7 +105,6 @@ void __init omap15xx_map_io(void)
#if defined(CONFIG_ARCH_OMAP16XX)
void __init omap16xx_map_io(void)
{
- omap1_map_common_io();
iotable_init(omap16xx_io_desc, ARRAY_SIZE(omap16xx_io_desc));
}
#endif
diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c
index 05c25c432449f..b1632cbe37e6f 100644
--- a/arch/arm/mach-omap1/mcbsp.c
+++ b/arch/arm/mach-omap1/mcbsp.c
@@ -89,7 +89,6 @@ static struct omap_mcbsp_ops omap1_mcbsp_ops = {
#define OMAP1610_MCBSP2_BASE 0xfffb1000
#define OMAP1610_MCBSP3_BASE 0xe1017000
-#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850)
struct resource omap7xx_mcbsp_res[][6] = {
{
{
@@ -159,14 +158,7 @@ static struct omap_mcbsp_platform_data omap7xx_mcbsp_pdata[] = {
};
#define OMAP7XX_MCBSP_RES_SZ ARRAY_SIZE(omap7xx_mcbsp_res[1])
#define OMAP7XX_MCBSP_COUNT ARRAY_SIZE(omap7xx_mcbsp_res)
-#else
-#define omap7xx_mcbsp_res_0 NULL
-#define omap7xx_mcbsp_pdata NULL
-#define OMAP7XX_MCBSP_RES_SZ 0
-#define OMAP7XX_MCBSP_COUNT 0
-#endif
-#ifdef CONFIG_ARCH_OMAP15XX
struct resource omap15xx_mcbsp_res[][6] = {
{
{
@@ -266,14 +258,7 @@ static struct omap_mcbsp_platform_data omap15xx_mcbsp_pdata[] = {
};
#define OMAP15XX_MCBSP_RES_SZ ARRAY_SIZE(omap15xx_mcbsp_res[1])
#define OMAP15XX_MCBSP_COUNT ARRAY_SIZE(omap15xx_mcbsp_res)
-#else
-#define omap15xx_mcbsp_res_0 NULL
-#define omap15xx_mcbsp_pdata NULL
-#define OMAP15XX_MCBSP_RES_SZ 0
-#define OMAP15XX_MCBSP_COUNT 0
-#endif
-#ifdef CONFIG_ARCH_OMAP16XX
struct resource omap16xx_mcbsp_res[][6] = {
{
{
@@ -373,12 +358,6 @@ static struct omap_mcbsp_platform_data omap16xx_mcbsp_pdata[] = {
};
#define OMAP16XX_MCBSP_RES_SZ ARRAY_SIZE(omap16xx_mcbsp_res[1])
#define OMAP16XX_MCBSP_COUNT ARRAY_SIZE(omap16xx_mcbsp_res)
-#else
-#define omap16xx_mcbsp_res_0 NULL
-#define omap16xx_mcbsp_pdata NULL
-#define OMAP16XX_MCBSP_RES_SZ 0
-#define OMAP16XX_MCBSP_COUNT 0
-#endif
static void omap_mcbsp_register_board_cfg(struct resource *res, int res_count,
struct omap_mcbsp_platform_data *config, int size)
diff --git a/arch/arm/mach-omap1/pm.h b/arch/arm/mach-omap1/pm.h
index d9165709c5323..0d1f092821ff8 100644
--- a/arch/arm/mach-omap1/pm.h
+++ b/arch/arm/mach-omap1/pm.h
@@ -106,13 +106,6 @@
#define OMAP7XX_IDLECT3 0xfffece24
#define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00
-#if !defined(CONFIG_ARCH_OMAP730) && \
- !defined(CONFIG_ARCH_OMAP850) && \
- !defined(CONFIG_ARCH_OMAP15XX) && \
- !defined(CONFIG_ARCH_OMAP16XX)
-#warning "Power management for this processor not implemented yet"
-#endif
-
#ifndef __ASSEMBLER__
#include <linux/clk.h>
diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h
index f7f12728d4a63..9a60f45899d3c 100644
--- a/include/linux/soc/ti/omap1-io.h
+++ b/include/linux/soc/ti/omap1-io.h
@@ -5,7 +5,7 @@
#ifndef __ASSEMBLER__
#include <linux/types.h>
-#ifdef CONFIG_ARCH_OMAP1_ANY
+#ifdef CONFIG_ARCH_OMAP1
/*
* NOTE: Please use ioremap + __raw_read/write where possible instead of these
*/
@@ -15,7 +15,7 @@ extern u32 omap_readl(u32 pa);
extern void omap_writeb(u8 v, u32 pa);
extern void omap_writew(u16 v, u32 pa);
extern void omap_writel(u32 v, u32 pa);
-#else
+#elif defined(CONFIG_COMPILE_TEST)
static inline u8 omap_readb(u32 pa) { return 0; }
static inline u16 omap_readw(u32 pa) { return 0; }
static inline u32 omap_readl(u32 pa) { return 0; }
--
GitLab
From 9d46ce57f4d1c626bb48170226ea5e35deb5877c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 13 Dec 2022 22:06:49 +0100
Subject: [PATCH 0638/1167] ARM: omap1: fix building gpio15xx
In some randconfig builds, the asm/irq.h header is not included
in gpio15xx.c, so add an explicit include to avoid a build fialure:
In file included from arch/arm/mach-omap1/gpio15xx.c:15:
arch/arm/mach-omap1/irqs.h:99:34: error: 'NR_IRQS_LEGACY' undeclared here (not in a function)
99 | #define IH2_BASE (NR_IRQS_LEGACY + 32)
| ^~~~~~~~~~~~~~
arch/arm/mach-omap1/irqs.h:105:38: note: in expansion of macro 'IH2_BASE'
105 | #define INT_MPUIO (5 + IH2_BASE)
| ^~~~~~~~
arch/arm/mach-omap1/gpio15xx.c:28:27: note: in expansion of macro 'INT_MPUIO'
28 | .start = INT_MPUIO,
| ^~~~~~~~~
Acked-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/mach-omap1/gpio15xx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c
index c675f11de99db..61fa26efd8653 100644
--- a/arch/arm/mach-omap1/gpio15xx.c
+++ b/arch/arm/mach-omap1/gpio15xx.c
@@ -11,6 +11,7 @@
#include <linux/gpio.h>
#include <linux/platform_data/gpio-omap.h>
#include <linux/soc/ti/omap1-soc.h>
+#include <asm/irq.h>
#include "irqs.h"
--
GitLab
From ba029e9991d9be90a28b6a0ceb25e9a6fb348829 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Mon, 9 Jan 2023 14:16:42 -0500
Subject: [PATCH 0639/1167] drm/amdkfd: Add sync after creating vram bo
There will be data corruption on vram allocated by svm
if the initialization is not complete and application is
writting on the memory. Adding sync to wait for the
initialization completion is to resolve this issue.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 814f99888ab10..b94d2c1422ad8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -570,6 +570,15 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
goto reserve_bo_failed;
}
+ if (clear) {
+ r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false);
+ if (r) {
+ pr_debug("failed %d to sync bo\n", r);
+ amdgpu_bo_unreserve(bo);
+ goto reserve_bo_failed;
+ }
+ }
+
r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (r) {
pr_debug("failed %d to reserve bo\n", r);
--
GitLab
From 972fb53d3605eb6cdf0d6ae9a52e910626a91ff7 Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Tue, 10 Jan 2023 11:33:44 +0800
Subject: [PATCH 0640/1167] drm/amd/pm/smu13: BACO is supported when it's in
BACO state
This leverages the logic in smu11. No need to talk to SMU to
check BACO enablement as it's in BACO state already.
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.0, 6.1
---
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index d1f50d42288d2..b4373b6568ae6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -2298,6 +2298,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu)
!smu_baco->platform_support)
return false;
+ /* return true if ASIC is in BACO state already */
+ if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER)
+ return true;
+
if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
return false;
--
GitLab
From a6941f89d7c6a6ba49316bbd7da2fb2f719119a7 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Thu, 5 Jan 2023 14:01:18 -0500
Subject: [PATCH 0641/1167] drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on
mGPU
The point bo->kfd_bo is NULL for queue's write pointer BO
when creating queue on mGPU. To avoid using the pointer
fixes the error.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index b15091d8310d9..3b5c53712d319 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2099,7 +2099,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b
}
amdgpu_amdkfd_remove_eviction_fence(
- bo, bo->kfd_bo->process_info->eviction_fence);
+ bo, bo->vm_bo->vm->process_info->eviction_fence);
amdgpu_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index ecb4c3abc6297..c06ada0844ba1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
if (q->wptr_bo) {
- wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+ wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1);
queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
}
--
GitLab
From 96398560f26aa07e8f2969d73c8197e6a6d10407 Mon Sep 17 00:00:00 2001
From: Frederick Lawler <fred@cloudflare.com>
Date: Mon, 9 Jan 2023 10:39:06 -0600
Subject: [PATCH 0642/1167] net: sched: disallow noqueue for qdisc classes
While experimenting with applying noqueue to a classful queue discipline,
we discovered a NULL pointer dereference in the __dev_queue_xmit()
path that generates a kernel OOPS:
# dev=enp0s5
# tc qdisc replace dev $dev root handle 1: htb default 1
# tc class add dev $dev parent 1: classid 1:1 htb rate 10mbit
# tc qdisc add dev $dev parent 1:1 handle 10: noqueue
# ping -I $dev -w 1 -c 1 1.1.1.1
[ 2.172856] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 2.173217] #PF: supervisor instruction fetch in kernel mode
...
[ 2.178451] Call Trace:
[ 2.178577] <TASK>
[ 2.178686] htb_enqueue+0x1c8/0x370
[ 2.178880] dev_qdisc_enqueue+0x15/0x90
[ 2.179093] __dev_queue_xmit+0x798/0xd00
[ 2.179305] ? _raw_write_lock_bh+0xe/0x30
[ 2.179522] ? __local_bh_enable_ip+0x32/0x70
[ 2.179759] ? ___neigh_create+0x610/0x840
[ 2.179968] ? eth_header+0x21/0xc0
[ 2.180144] ip_finish_output2+0x15e/0x4f0
[ 2.180348] ? dst_output+0x30/0x30
[ 2.180525] ip_push_pending_frames+0x9d/0xb0
[ 2.180739] raw_sendmsg+0x601/0xcb0
[ 2.180916] ? _raw_spin_trylock+0xe/0x50
[ 2.181112] ? _raw_spin_unlock_irqrestore+0x16/0x30
[ 2.181354] ? get_page_from_freelist+0xcd6/0xdf0
[ 2.181594] ? sock_sendmsg+0x56/0x60
[ 2.181781] sock_sendmsg+0x56/0x60
[ 2.181958] __sys_sendto+0xf7/0x160
[ 2.182139] ? handle_mm_fault+0x6e/0x1d0
[ 2.182366] ? do_user_addr_fault+0x1e1/0x660
[ 2.182627] __x64_sys_sendto+0x1b/0x30
[ 2.182881] do_syscall_64+0x38/0x90
[ 2.183085] entry_SYSCALL_64_after_hwframe+0x63/0xcd
...
[ 2.187402] </TASK>
Previously in commit d66d6c3152e8 ("net: sched: register noqueue
qdisc"), NULL was set for the noqueue discipline on noqueue init
so that __dev_queue_xmit() falls through for the noqueue case. This
also sets a bypass of the enqueue NULL check in the
register_qdisc() function for the struct noqueue_disc_ops.
Classful queue disciplines make it past the NULL check in
__dev_queue_xmit() because the discipline is set to htb (in this case),
and then in the call to __dev_xmit_skb(), it calls into htb_enqueue()
which grabs a leaf node for a class and then calls qdisc_enqueue() by
passing in a queue discipline which assumes ->enqueue() is not set to NULL.
Fix this by not allowing classes to be assigned to the noqueue
discipline. Linux TC Notes states that classes cannot be set to
the noqueue discipline. [1] Let's enforce that here.
Links:
1. https://linux-tc-notes.sourceforge.net/tc/doc/sch_noqueue.txt
Fixes: d66d6c3152e8 ("net: sched: register noqueue qdisc")
Cc: stable@vger.kernel.org
Signed-off-by: Frederick Lawler <fred@cloudflare.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20230109163906.706000-1-fred@cloudflare.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/sch_api.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2317db02c764d..72d2c204d5f34 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1133,6 +1133,11 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent,
return -ENOENT;
}
+ if (new && new->ops == &noqueue_qdisc_ops) {
+ NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class");
+ return -EINVAL;
+ }
+
err = cops->graft(parent, cl, new, &old, extack);
if (err)
return err;
--
GitLab
From 9c445d2637c938a800fcc8b5f0b10e60c94460c7 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Tue, 10 Jan 2023 14:45:24 +0100
Subject: [PATCH 0643/1167] Input: i8042 - add Clevo PCX0DX to i8042 quirk
table
The Clevo PCX0DX/TUXEDO XP1511, need quirks for the keyboard to not be
occasionally unresponsive after resume.
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Cc: stable@vger.kernel.org
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Mattijs Korpershoek <mkorpershoek@baylibre.com>
Link: https://lore.kernel.org/r/20230110134524.553620-1-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
drivers/input/serio/i8042-acpipnpio.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 46f8a694291ed..efc61736099b9 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1238,6 +1238,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"),
+ },
+ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+ },
{
.matches = {
DMI_MATCH(DMI_BOARD_NAME, "X170SM"),
--
GitLab
From 22aeb01db7080e18c6aeb4361cc2556c9887099a Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 10 Jan 2023 19:23:21 -0300
Subject: [PATCH 0644/1167] cifs: do not query ifaces on smb1 mounts
Users have reported the following error on every 600 seconds
(SMB_INTERFACE_POLL_INTERVAL) when mounting SMB1 shares:
CIFS: VFS: \\srv\share error -5 on ioctl to get interface list
It's supported only by SMB2+, so do not query network interfaces on
SMB1 mounts.
Fixes: 6e1c1c08cdf3 ("cifs: periodically query network interfaces from server")
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Tom Talpey <tom@talpey.com>
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/connect.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d371259d6808a..b2a04b4e89a5e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2606,11 +2606,14 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
INIT_LIST_HEAD(&tcon->pending_opens);
tcon->status = TID_GOOD;
- /* schedule query interfaces poll */
INIT_DELAYED_WORK(&tcon->query_interfaces,
smb2_query_server_interfaces);
- queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
- (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ if (ses->server->dialect >= SMB30_PROT_ID &&
+ (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+ /* schedule query interfaces poll */
+ queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+ (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ }
spin_lock(&cifs_tcp_ses_lock);
list_add(&tcon->tcon_list, &ses->tcon_list);
--
GitLab
From 2fe58d977ee05da5bb89ef5dc4f5bf2dc15db46f Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 10 Jan 2023 20:35:46 -0300
Subject: [PATCH 0645/1167] cifs: fix potential memory leaks in session setup
Make sure to free cifs_ses::auth_key.response before allocating it as
we might end up leaking memory in reconnect or mounting.
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/cifsencrypt.c | 1 +
fs/cifs/sess.c | 2 ++
fs/cifs/smb2pdu.c | 1 +
3 files changed, 4 insertions(+)
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 5db73c0f792a5..cbc18b4a9cb20 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -278,6 +278,7 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp)
* ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) +
* unicode length of a netbios domain name
*/
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.len = size + 2 * dlen;
ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL);
if (!ses->auth_key.response) {
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 0b842a07e1579..c47b254f0d1e2 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -815,6 +815,7 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len,
return -EINVAL;
}
if (tilen) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(bcc_ptr + tioffset, tilen,
GFP_KERNEL);
if (!ses->auth_key.response) {
@@ -1428,6 +1429,7 @@ sess_auth_kerberos(struct sess_data *sess_data)
goto out_put_spnego_key;
}
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 727f16b426be5..4b71f4a92f76c 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1453,6 +1453,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
/* keep session key if binding */
if (!is_binding) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
--
GitLab
From 3287ebd7fd01e853ca4da8be675322429400e2bd Mon Sep 17 00:00:00 2001
From: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Date: Thu, 5 Jan 2023 01:54:37 +0530
Subject: [PATCH 0646/1167] powerpc/boot: Fix incorrect version calculation
issue in ld_version
The ld_version() function computes the wrong version value for certain
ld versions such as the following:
$ ld --version
GNU ld (GNU Binutils; SUSE Linux Enterprise 15)
2.37.20211103-150100.7.37
For input 2.37.20211103, the value computed is 202348030000 which is
higher than the value for a later version like 2.39.0, which is
23900000.
This issue was highlighted because with the above ld version, the
powerpc kernel build started failing with ld error: "unrecognized option
--no-warn-rwx-segments". This was caused due to the recent commit
579aee9fc594 ("powerpc: suppress some linker warnings in recent linker
versions") which added the --no-warn-rwx-segments linker flag if the ld
version is greater than 2.39.
Due to the bug in ld_version(), ld version 2.37.20111103 is wrongly
calculated to be greater than 2.39 and the unsupported flag is added.
To fix it, if version is of the form x.y.z and length(z) == 8, then most
probably it is a date [yyyymmdd] commonly used for release snapshots and
not an actual new version. Hence, ignore the date part replacing it with
0.
Fixes: 579aee9fc594 ("powerpc: suppress some linker warnings in recent linker versions")
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
[mpe: Tweak change log wording/formatting, add Fixes tag]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20230104202437.90039-1-ojaswin@linux.ibm.com
---
arch/powerpc/boot/wrapper | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index af04cea82b941..352d7de24018f 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -210,6 +210,10 @@ ld_version()
gsub(".*version ", "");
gsub("-.*", "");
split($1,a, ".");
+ if( length(a[3]) == "8" )
+ # a[3] is probably a date of format yyyymmdd used for release snapshots. We
+ # can assume it to be zero as it does not signify a new version as such.
+ a[3] = 0;
print a[1]*100000000 + a[2]*1000000 + a[3]*10000;
exit
}'
--
GitLab
From 76d588dddc459fefa1da96e0a081a397c5c8e216 Mon Sep 17 00:00:00 2001
From: Kajol Jain <kjain@linux.ibm.com>
Date: Fri, 6 Jan 2023 12:21:57 +0530
Subject: [PATCH 0647/1167] powerpc/imc-pmu: Fix use of mutex in IRQs disabled
section
Current imc-pmu code triggers a WARNING with CONFIG_DEBUG_ATOMIC_SLEEP
and CONFIG_PROVE_LOCKING enabled, while running a thread_imc event.
Command to trigger the warning:
# perf stat -e thread_imc/CPM_CS_FROM_L4_MEM_X_DPTEG/ sleep 5
Performance counter stats for 'sleep 5':
0 thread_imc/CPM_CS_FROM_L4_MEM_X_DPTEG/
5.002117947 seconds time elapsed
0.000131000 seconds user
0.001063000 seconds sys
Below is snippet of the warning in dmesg:
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:580
in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 2869, name: perf-exec
preempt_count: 2, expected: 0
4 locks held by perf-exec/2869:
#0: c00000004325c540 (&sig->cred_guard_mutex){+.+.}-{3:3}, at: bprm_execve+0x64/0xa90
#1: c00000004325c5d8 (&sig->exec_update_lock){++++}-{3:3}, at: begin_new_exec+0x460/0xef0
#2: c0000003fa99d4e0 (&cpuctx_lock){-...}-{2:2}, at: perf_event_exec+0x290/0x510
#3: c000000017ab8418 (&ctx->lock){....}-{2:2}, at: perf_event_exec+0x29c/0x510
irq event stamp: 4806
hardirqs last enabled at (4805): [<c000000000f65b94>] _raw_spin_unlock_irqrestore+0x94/0xd0
hardirqs last disabled at (4806): [<c0000000003fae44>] perf_event_exec+0x394/0x510
softirqs last enabled at (0): [<c00000000013c404>] copy_process+0xc34/0x1ff0
softirqs last disabled at (0): [<0000000000000000>] 0x0
CPU: 36 PID: 2869 Comm: perf-exec Not tainted 6.2.0-rc2-00011-g1247637727f2 #61
Hardware name: 8375-42A POWER9 0x4e1202 opal:v7.0-16-g9b85f7d961 PowerNV
Call Trace:
dump_stack_lvl+0x98/0xe0 (unreliable)
__might_resched+0x2f8/0x310
__mutex_lock+0x6c/0x13f0
thread_imc_event_add+0xf4/0x1b0
event_sched_in+0xe0/0x210
merge_sched_in+0x1f0/0x600
visit_groups_merge.isra.92.constprop.166+0x2bc/0x6c0
ctx_flexible_sched_in+0xcc/0x140
ctx_sched_in+0x20c/0x2a0
ctx_resched+0x104/0x1c0
perf_event_exec+0x340/0x510
begin_new_exec+0x730/0xef0
load_elf_binary+0x3f8/0x1e10
...
do not call blocking ops when !TASK_RUNNING; state=2001 set at [<00000000fd63e7cf>] do_nanosleep+0x60/0x1a0
WARNING: CPU: 36 PID: 2869 at kernel/sched/core.c:9912 __might_sleep+0x9c/0xb0
CPU: 36 PID: 2869 Comm: sleep Tainted: G W 6.2.0-rc2-00011-g1247637727f2 #61
Hardware name: 8375-42A POWER9 0x4e1202 opal:v7.0-16-g9b85f7d961 PowerNV
NIP: c000000000194a1c LR: c000000000194a18 CTR: c000000000a78670
REGS: c00000004d2134e0 TRAP: 0700 Tainted: G W (6.2.0-rc2-00011-g1247637727f2)
MSR: 9000000000021033 <SF,HV,ME,IR,DR,RI,LE> CR: 48002824 XER: 00000000
CFAR: c00000000013fb64 IRQMASK: 1
The above warning triggered because the current imc-pmu code uses mutex
lock in interrupt disabled sections. The function mutex_lock()
internally calls __might_resched(), which will check if IRQs are
disabled and in case IRQs are disabled, it will trigger the warning.
Fix the issue by changing the mutex lock to spinlock.
Fixes: 8f95faaac56c ("powerpc/powernv: Detect and create IMC device")
Reported-by: Michael Petlan <mpetlan@redhat.com>
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
[mpe: Fix comments, trim oops in change log, add reported-by tags]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20230106065157.182648-1-kjain@linux.ibm.com
---
arch/powerpc/include/asm/imc-pmu.h | 2 +-
arch/powerpc/perf/imc-pmu.c | 136 ++++++++++++++---------------
2 files changed, 67 insertions(+), 71 deletions(-)
diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h
index 4f897993b7107..699a88584ae16 100644
--- a/arch/powerpc/include/asm/imc-pmu.h
+++ b/arch/powerpc/include/asm/imc-pmu.h
@@ -137,7 +137,7 @@ struct imc_pmu {
* are inited.
*/
struct imc_pmu_ref {
- struct mutex lock;
+ spinlock_t lock;
unsigned int id;
int refc;
};
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index d517aba94d1bc..100e97daf76ba 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -14,6 +14,7 @@
#include <asm/cputhreads.h>
#include <asm/smp.h>
#include <linux/string.h>
+#include <linux/spinlock.h>
/* Nest IMC data structures and variables */
@@ -21,7 +22,7 @@
* Used to avoid races in counting the nest-pmu units during hotplug
* register and unregister
*/
-static DEFINE_MUTEX(nest_init_lock);
+static DEFINE_SPINLOCK(nest_init_lock);
static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
static struct imc_pmu **per_nest_pmu_arr;
static cpumask_t nest_imc_cpumask;
@@ -50,7 +51,7 @@ static int trace_imc_mem_size;
* core and trace-imc
*/
static struct imc_pmu_ref imc_global_refc = {
- .lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+ .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock),
.id = 0,
.refc = 0,
};
@@ -400,7 +401,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
get_hard_smp_processor_id(cpu));
/*
* If this is the last cpu in this chip then, skip the reference
- * count mutex lock and make the reference count on this chip zero.
+ * count lock and make the reference count on this chip zero.
*/
ref = get_nest_pmu_ref(cpu);
if (!ref)
@@ -462,15 +463,15 @@ static void nest_imc_counters_release(struct perf_event *event)
/*
* See if we need to disable the nest PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the nest counters.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return;
- /* Take the mutex lock for this node and then decrement the reference count */
- mutex_lock(&ref->lock);
+ /* Take the lock for this node and then decrement the reference count */
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
@@ -482,7 +483,7 @@ static void nest_imc_counters_release(struct perf_event *event)
* an OPAL call to disable the engine in that node.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
@@ -490,7 +491,7 @@ static void nest_imc_counters_release(struct perf_event *event)
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id);
return;
}
@@ -498,7 +499,7 @@ static void nest_imc_counters_release(struct perf_event *event)
WARN(1, "nest-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
}
static int nest_imc_event_init(struct perf_event *event)
@@ -557,26 +558,25 @@ static int nest_imc_event_init(struct perf_event *event)
/*
* Get the imc_pmu_ref struct for this node.
- * Take the mutex lock and then increment the count of nest pmu events
- * inited.
+ * Take the lock and then increment the count of nest pmu events inited.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to start the counters for node %d\n",
node_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
event->destroy = nest_imc_counters_release;
return 0;
@@ -612,9 +612,8 @@ static int core_imc_mem_init(int cpu, int size)
return -ENOMEM;
mem_info->vbase = page_address(page);
- /* Init the mutex */
core_imc_refc[core_id].id = core_id;
- mutex_init(&core_imc_refc[core_id].lock);
+ spin_lock_init(&core_imc_refc[core_id].lock);
rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE,
__pa((void *)mem_info->vbase),
@@ -703,9 +702,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu);
} else {
/*
- * If this is the last cpu in this core then, skip taking refernce
- * count mutex lock for this core and directly zero "refc" for
- * this core.
+ * If this is the last cpu in this core then skip taking reference
+ * count lock for this core and directly zero "refc" for this core.
*/
opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(cpu));
@@ -720,11 +718,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
* last cpu in this core and core-imc event running
* in this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_CORE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
return 0;
}
@@ -739,7 +737,7 @@ static int core_imc_pmu_cpumask_init(void)
static void reset_global_refc(struct perf_event *event)
{
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
imc_global_refc.refc--;
/*
@@ -751,7 +749,7 @@ static void reset_global_refc(struct perf_event *event)
imc_global_refc.refc = 0;
imc_global_refc.id = 0;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
static void core_imc_counters_release(struct perf_event *event)
@@ -764,17 +762,17 @@ static void core_imc_counters_release(struct perf_event *event)
/*
* See if we need to disable the IMC PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the core counters.
*/
core_id = event->cpu / threads_per_core;
- /* Take the mutex lock and decrement the refernce count for this core */
+ /* Take the lock and decrement the refernce count for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
@@ -786,7 +784,7 @@ static void core_imc_counters_release(struct perf_event *event)
* an OPAL call to disable the engine in that core.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
@@ -794,7 +792,7 @@ static void core_imc_counters_release(struct perf_event *event)
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("IMC: Unable to stop the counters for core %d\n", core_id);
return;
}
@@ -802,7 +800,7 @@ static void core_imc_counters_release(struct perf_event *event)
WARN(1, "core-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
reset_global_refc(event);
}
@@ -840,7 +838,6 @@ static int core_imc_event_init(struct perf_event *event)
if ((!pcmi->vbase))
return -ENODEV;
- /* Get the core_imc mutex for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
@@ -848,22 +845,22 @@ static int core_imc_event_init(struct perf_event *event)
/*
* Core pmu units are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the core counters.
+ * If yes, take the lock and enable the core counters.
* If not, just increment the count in core_imc_refc struct.
*/
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("core-imc: Unable to start the counters for core %d\n",
core_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/*
* Since the system can run either in accumulation or trace-mode
@@ -874,7 +871,7 @@ static int core_imc_event_init(struct perf_event *event)
* to know whether any other trace/thread imc
* events are running.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
/*
* No other trace/thread imc events are running in
@@ -883,10 +880,10 @@ static int core_imc_event_init(struct perf_event *event)
imc_global_refc.id = IMC_DOMAIN_CORE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
event->destroy = core_imc_counters_release;
@@ -958,10 +955,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu)
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
/* Reduce the refc if thread-imc event running on this cpu */
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_THREAD)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
@@ -1001,7 +998,7 @@ static int thread_imc_event_init(struct perf_event *event)
if (!target)
return -EINVAL;
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
/*
* Check if any other trace/core imc events are running in the
* system, if not set the global id to thread-imc.
@@ -1010,10 +1007,10 @@ static int thread_imc_event_init(struct perf_event *event)
imc_global_refc.id = IMC_DOMAIN_THREAD;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->pmu->task_ctx_nr = perf_sw_context;
event->destroy = reset_global_refc;
@@ -1135,25 +1132,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags)
/*
* imc pmus are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the counters.
+ * If yes, take the lock and enable the counters.
* If not, just increment the count in ref count struct.
*/
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to start the counter\
for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
@@ -1170,12 +1167,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to stop the counters\
for core %d\n", core_id);
return;
@@ -1183,7 +1180,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
@@ -1224,9 +1221,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size)
}
}
- /* Init the mutex, if not already */
trace_imc_refc[core_id].id = core_id;
- mutex_init(&trace_imc_refc[core_id].lock);
+ spin_lock_init(&trace_imc_refc[core_id].lock);
mtspr(SPRN_LDBAR, 0);
return 0;
@@ -1246,10 +1242,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu)
* Reduce the refc if any trace-imc event running
* on this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_TRACE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
@@ -1371,17 +1367,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
}
mtspr(SPRN_LDBAR, ldbar_value);
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
@@ -1414,19 +1410,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
return;
}
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
trace_imc_event_stop(event, flags);
}
@@ -1448,7 +1444,7 @@ static int trace_imc_event_init(struct perf_event *event)
* no other thread is running any core/thread imc
* events
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
/*
* No core/thread imc events are running in the
@@ -1457,10 +1453,10 @@ static int trace_imc_event_init(struct perf_event *event)
imc_global_refc.id = IMC_DOMAIN_TRACE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.idx = -1;
@@ -1533,10 +1529,10 @@ static int init_nest_pmu_ref(void)
i = 0;
for_each_node(nid) {
/*
- * Mutex lock to avoid races while tracking the number of
+ * Take the lock to avoid races while tracking the number of
* sessions using the chip's nest pmu units.
*/
- mutex_init(&nest_imc_refc[i].lock);
+ spin_lock_init(&nest_imc_refc[i].lock);
/*
* Loop to init the "id" with the node_id. Variable "i" initialized to
@@ -1633,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr)
static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
{
if (pmu_ptr->domain == IMC_DOMAIN_NEST) {
- mutex_lock(&nest_init_lock);
+ spin_lock(&nest_init_lock);
if (nest_pmus == 1) {
cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
kfree(nest_imc_refc);
@@ -1643,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
if (nest_pmus > 0)
nest_pmus--;
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
}
/* Free core_imc memory */
@@ -1800,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
* rest. To handle the cpuhotplug callback unregister, we track
* the number of nest pmus in "nest_pmus".
*/
- mutex_lock(&nest_init_lock);
+ spin_lock(&nest_init_lock);
if (nest_pmus == 0) {
ret = init_nest_pmu_ref();
if (ret) {
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
kfree(per_nest_pmu_arr);
per_nest_pmu_arr = NULL;
goto err_free_mem;
@@ -1812,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
/* Register for cpu hotplug notification. */
ret = nest_pmu_cpumask_init();
if (ret) {
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
kfree(nest_imc_refc);
kfree(per_nest_pmu_arr);
per_nest_pmu_arr = NULL;
@@ -1820,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
}
}
nest_pmus++;
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
break;
case IMC_DOMAIN_CORE:
ret = core_imc_pmu_cpumask_init();
--
GitLab
From 7124c93887cc4e6c5b48920f83115e4a5892e870 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 9 Jan 2023 22:25:29 -0800
Subject: [PATCH 0648/1167] phy: ti: fix Kconfig warning and operator
precedence
Fix Kconfig depends operator precedence to prevent a Kconfig warning:
WARNING: unmet direct dependencies detected for MUX_MMIO
Depends on [n]: MULTIPLEXER [=m] && OF [=n]
Selected by [m]:
- PHY_AM654_SERDES [=m] && (OF [=n] && ARCH_K3 || COMPILE_TEST [=y]) && COMMON_CLK [=y]
Fixes: 71e2f5c5c224 ("phy: ti: Add a new SERDES driver for TI's AM654x SoC")
Fixes: 091876cc355d ("phy: ti: j721e-wiz: Add support for WIZ module present in TI J721E SoC")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Vinod Koul <vkoul@kernel.org>
Cc: Kishon Vijay Abraham I <kishon@kernel.org>
Cc: linux-phy@lists.infradead.org
Cc: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230110062529.22668-1-rdunlap@infradead.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/ti/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/phy/ti/Kconfig b/drivers/phy/ti/Kconfig
index 15a3bcf323086..b905902d57508 100644
--- a/drivers/phy/ti/Kconfig
+++ b/drivers/phy/ti/Kconfig
@@ -23,7 +23,7 @@ config PHY_DM816X_USB
config PHY_AM654_SERDES
tristate "TI AM654 SERDES support"
- depends on OF && ARCH_K3 || COMPILE_TEST
+ depends on OF && (ARCH_K3 || COMPILE_TEST)
depends on COMMON_CLK
select GENERIC_PHY
select MULTIPLEXER
@@ -35,7 +35,7 @@ config PHY_AM654_SERDES
config PHY_J721E_WIZ
tristate "TI J721E WIZ (SERDES Wrapper) support"
- depends on OF && ARCH_K3 || COMPILE_TEST
+ depends on OF && (ARCH_K3 || COMPILE_TEST)
depends on HAS_IOMEM && OF_ADDRESS
depends on COMMON_CLK
select GENERIC_PHY
--
GitLab
From b0e380b5d4275299adf43e249f18309331b6f54f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <clement.leger@bootlin.com>
Date: Mon, 9 Jan 2023 16:32:23 +0100
Subject: [PATCH 0649/1167] net: lan966x: check for ptp to be enabled in
lan966x_ptp_deinit()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If ptp was not enabled due to missing IRQ for instance,
lan966x_ptp_deinit() will dereference NULL pointers.
Fixes: d096459494a8 ("net: lan966x: Add support for ptp clocks")
Signed-off-by: Clément Léger <clement.leger@bootlin.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
index f9ebfaafbebc2..a8348437dd87f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c
@@ -1073,6 +1073,9 @@ void lan966x_ptp_deinit(struct lan966x *lan966x)
struct lan966x_port *port;
int i;
+ if (!lan966x->ptp)
+ return;
+
for (i = 0; i < lan966x->num_phys_ports; i++) {
port = lan966x->ports[i];
if (!port)
--
GitLab
From 4e2ec2500bfc5cf429ddcfe78b49cb76b36bc46d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 10 Jan 2023 13:35:26 +0100
Subject: [PATCH 0650/1167] drm/nouveau: Remove file nouveau_fbcon.c
Commit 4a16dd9d18a0 ("drm/nouveau/kms: switch to drm fbdev helpers")
converted nouveau to generic fbdev emulation. The driver's internal
implementation later got accidentally restored during a merge commit.
Remove the file from the driver. No functional changes.
v2:
* point Fixes tag to merge commit (Alex)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: 4e291f2f5853 ("Merge tag 'drm-misc-next-2022-11-10-1' of git://anongit.freedesktop.org/drm/drm-misc into drm-next")
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Karol Herbst <kherbst@redhat.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: dri-devel@lists.freedesktop.org
Cc: nouveau@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20230110123526.28770-1-tzimmermann@suse.de
---
drivers/gpu/drm/nouveau/nouveau_fbcon.c | 613 ------------------------
1 file changed, 613 deletions(-)
delete mode 100644 drivers/gpu/drm/nouveau/nouveau_fbcon.c
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
deleted file mode 100644
index e87de7906f780..0000000000000
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ /dev/null
@@ -1,613 +0,0 @@
-/*
- * Copyright © 2007 David Airlie
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Authors:
- * David Airlie
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/tty.h>
-#include <linux/sysrq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/screen_info.h>
-#include <linux/vga_switcheroo.h>
-#include <linux/console.h>
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_probe_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_atomic.h>
-
-#include "nouveau_drv.h"
-#include "nouveau_gem.h"
-#include "nouveau_bo.h"
-#include "nouveau_fbcon.h"
-#include "nouveau_chan.h"
-#include "nouveau_vmm.h"
-
-#include "nouveau_crtc.h"
-
-MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration");
-int nouveau_nofbaccel = 0;
-module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
-
-MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)");
-static int nouveau_fbcon_bpp;
-module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400);
-
-static void
-nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_fillrect(info, rect);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_fillrect(info, rect);
- else
- ret = nvc0_fbcon_fillrect(info, rect);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_fillrect(info, rect);
-}
-
-static void
-nouveau_fbcon_copyarea(struct fb_info *info, const struct fb_copyarea *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_copyarea(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_copyarea(info, image);
- else
- ret = nvc0_fbcon_copyarea(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_copyarea(info, image);
-}
-
-static void
-nouveau_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_imageblit(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_imageblit(info, image);
- else
- ret = nvc0_fbcon_imageblit(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_imageblit(info, image);
-}
-
-static int
-nouveau_fbcon_sync(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nouveau_channel *chan = drm->channel;
- int ret;
-
- if (!chan || !chan->accel_done || in_interrupt() ||
- info->state != FBINFO_STATE_RUNNING ||
- info->flags & FBINFO_HWACCEL_DISABLED)
- return 0;
-
- if (!mutex_trylock(&drm->client.mutex))
- return 0;
-
- ret = nouveau_channel_idle(chan);
- mutex_unlock(&drm->client.mutex);
- if (ret) {
- nouveau_fbcon_gpu_lockup(info);
- return 0;
- }
-
- chan->accel_done = false;
- return 0;
-}
-
-static int
-nouveau_fbcon_open(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- int ret = pm_runtime_get_sync(drm->dev->dev);
- if (ret < 0 && ret != -EACCES) {
- pm_runtime_put(drm->dev->dev);
- return ret;
- }
- return 0;
-}
-
-static int
-nouveau_fbcon_release(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- pm_runtime_put(drm->dev->dev);
- return 0;
-}
-
-static const struct fb_ops nouveau_fbcon_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = nouveau_fbcon_fillrect,
- .fb_copyarea = nouveau_fbcon_copyarea,
- .fb_imageblit = nouveau_fbcon_imageblit,
- .fb_sync = nouveau_fbcon_sync,
-};
-
-static const struct fb_ops nouveau_fbcon_sw_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = drm_fb_helper_cfb_fillrect,
- .fb_copyarea = drm_fb_helper_cfb_copyarea,
- .fb_imageblit = drm_fb_helper_cfb_imageblit,
-};
-
-void
-nouveau_fbcon_accel_save_disable(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info) {
- drm->fbcon->saved_flags = drm->fbcon->helper.info->flags;
- drm->fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- }
-}
-
-void
-nouveau_fbcon_accel_restore(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info)
- drm->fbcon->helper.info->flags = drm->fbcon->saved_flags;
-}
-
-static void
-nouveau_fbcon_accel_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- if (fbcon && drm->channel) {
- console_lock();
- if (fbcon->helper.info)
- fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- console_unlock();
- nouveau_channel_idle(drm->channel);
- nvif_object_dtor(&fbcon->twod);
- nvif_object_dtor(&fbcon->blit);
- nvif_object_dtor(&fbcon->gdi);
- nvif_object_dtor(&fbcon->patt);
- nvif_object_dtor(&fbcon->rop);
- nvif_object_dtor(&fbcon->clip);
- nvif_object_dtor(&fbcon->surf2d);
- }
-}
-
-static void
-nouveau_fbcon_accel_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- struct fb_info *info = fbcon->helper.info;
- int ret;
-
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_accel_init(info);
- else
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_accel_init(info);
- else
- ret = nvc0_fbcon_accel_init(info);
-
- if (ret == 0)
- info->fbops = &nouveau_fbcon_ops;
-}
-
-static void
-nouveau_fbcon_zfill(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct fb_info *info = fbcon->helper.info;
- struct fb_fillrect rect;
-
- /* Clear the entire fbcon. The drm will program every connector
- * with it's preferred mode. If the sizes differ, one display will
- * quite likely have garbage around the console.
- */
- rect.dx = rect.dy = 0;
- rect.width = info->var.xres_virtual;
- rect.height = info->var.yres_virtual;
- rect.color = 0;
- rect.rop = ROP_COPY;
- info->fbops->fb_fillrect(info, &rect);
-}
-
-static int
-nouveau_fbcon_create(struct drm_fb_helper *helper,
- struct drm_fb_helper_surface_size *sizes)
-{
- struct nouveau_fbdev *fbcon =
- container_of(helper, struct nouveau_fbdev, helper);
- struct drm_device *dev = fbcon->helper.dev;
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nvif_device *device = &drm->client.device;
- struct fb_info *info;
- struct drm_framebuffer *fb;
- struct nouveau_channel *chan;
- struct nouveau_bo *nvbo;
- struct drm_mode_fb_cmd2 mode_cmd = {};
- int ret;
-
- mode_cmd.width = sizes->surface_width;
- mode_cmd.height = sizes->surface_height;
-
- mode_cmd.pitches[0] = mode_cmd.width * (sizes->surface_bpp >> 3);
- mode_cmd.pitches[0] = roundup(mode_cmd.pitches[0], 256);
-
- mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
- sizes->surface_depth);
-
- ret = nouveau_gem_new(&drm->client, mode_cmd.pitches[0] *
- mode_cmd.height, 0, NOUVEAU_GEM_DOMAIN_VRAM,
- 0, 0x0000, &nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to allocate framebuffer\n");
- goto out;
- }
-
- ret = nouveau_framebuffer_new(dev, &mode_cmd, &nvbo->bo.base, &fb);
- if (ret)
- goto out_unref;
-
- ret = nouveau_bo_pin(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, false);
- if (ret) {
- NV_ERROR(drm, "failed to pin fb: %d\n", ret);
- goto out_unref;
- }
-
- ret = nouveau_bo_map(nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to map fb: %d\n", ret);
- goto out_unpin;
- }
-
- chan = nouveau_nofbaccel ? NULL : drm->channel;
- if (chan && device->info.family >= NV_DEVICE_INFO_V0_TESLA) {
- ret = nouveau_vma_new(nvbo, chan->vmm, &fbcon->vma);
- if (ret) {
- NV_ERROR(drm, "failed to map fb into chan: %d\n", ret);
- chan = NULL;
- }
- }
-
- info = drm_fb_helper_alloc_info(helper);
- if (IS_ERR(info)) {
- ret = PTR_ERR(info);
- goto out_unlock;
- }
-
- /* setup helper */
- fbcon->helper.fb = fb;
-
- if (!chan)
- info->flags = FBINFO_HWACCEL_DISABLED;
- else
- info->flags = FBINFO_HWACCEL_COPYAREA |
- FBINFO_HWACCEL_FILLRECT |
- FBINFO_HWACCEL_IMAGEBLIT;
- info->fbops = &nouveau_fbcon_sw_ops;
- info->fix.smem_start = nvbo->bo.resource->bus.offset;
- info->fix.smem_len = nvbo->bo.base.size;
-
- info->screen_base = nvbo_kmap_obj_iovirtual(nvbo);
- info->screen_size = nvbo->bo.base.size;
-
- drm_fb_helper_fill_info(info, &fbcon->helper, sizes);
-
- /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
-
- if (chan)
- nouveau_fbcon_accel_init(dev);
- nouveau_fbcon_zfill(dev, fbcon);
-
- /* To allow resizeing without swapping buffers */
- NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
- fb->width, fb->height, nvbo->offset, nvbo);
-
- if (dev_is_pci(dev->dev))
- vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), info);
-
- return 0;
-
-out_unlock:
- if (chan)
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
-out_unpin:
- nouveau_bo_unpin(nvbo);
-out_unref:
- nouveau_bo_ref(NULL, &nvbo);
-out:
- return ret;
-}
-
-static int
-nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct drm_framebuffer *fb = fbcon->helper.fb;
- struct nouveau_bo *nvbo;
-
- drm_fb_helper_unregister_info(&fbcon->helper);
- drm_fb_helper_fini(&fbcon->helper);
-
- if (fb && fb->obj[0]) {
- nvbo = nouveau_gem_object(fb->obj[0]);
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
- nouveau_bo_unpin(nvbo);
- drm_framebuffer_put(fb);
- }
-
- return 0;
-}
-
-void nouveau_fbcon_gpu_lockup(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
-
- NV_ERROR(drm, "GPU lockup - switching to software fbcon\n");
- info->flags |= FBINFO_HWACCEL_DISABLED;
-}
-
-static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = {
- .fb_probe = nouveau_fbcon_create,
-};
-
-static void
-nouveau_fbcon_set_suspend_work(struct work_struct *work)
-{
- struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
- int state = READ_ONCE(drm->fbcon_new_state);
-
- if (state == FBINFO_STATE_RUNNING)
- pm_runtime_get_sync(drm->dev->dev);
-
- console_lock();
- if (state == FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_restore(drm->dev);
- drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
- if (state != FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_save_disable(drm->dev);
- console_unlock();
-
- if (state == FBINFO_STATE_RUNNING) {
- nouveau_fbcon_hotplug_resume(drm->fbcon);
- pm_runtime_mark_last_busy(drm->dev->dev);
- pm_runtime_put_autosuspend(drm->dev->dev);
- }
-}
-
-void
-nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm->fbcon_new_state = state;
- /* Since runtime resume can happen as a result of a sysfs operation,
- * it's possible we already have the console locked. So handle fbcon
- * init/deinit from a seperate work thread
- */
- schedule_work(&drm->fbcon_work);
-}
-
-void
-nouveau_fbcon_output_poll_changed(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- int ret;
-
- if (!fbcon)
- return;
-
- mutex_lock(&fbcon->hotplug_lock);
-
- ret = pm_runtime_get(dev->dev);
- if (ret == 1 || ret == -EACCES) {
- drm_fb_helper_hotplug_event(&fbcon->helper);
-
- pm_runtime_mark_last_busy(dev->dev);
- pm_runtime_put_autosuspend(dev->dev);
- } else if (ret == 0) {
- /* If the GPU was already in the process of suspending before
- * this event happened, then we can't block here as we'll
- * deadlock the runtime pmops since they wait for us to
- * finish. So, just defer this event for when we runtime
- * resume again. It will be handled by fbcon_work.
- */
- NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n");
- fbcon->hotplug_waiting = true;
- pm_runtime_put_noidle(drm->dev->dev);
- } else {
- DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n",
- ret);
- }
-
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-void
-nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon)
-{
- struct nouveau_drm *drm;
-
- if (!fbcon)
- return;
- drm = nouveau_drm(fbcon->helper.dev);
-
- mutex_lock(&fbcon->hotplug_lock);
- if (fbcon->hotplug_waiting) {
- fbcon->hotplug_waiting = false;
-
- NV_DEBUG(drm, "Handling deferred fbcon HPD events\n");
- drm_fb_helper_hotplug_event(&fbcon->helper);
- }
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-int
-nouveau_fbcon_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon;
- int preferred_bpp = nouveau_fbcon_bpp;
- int ret;
-
- if (!dev->mode_config.num_crtc ||
- (to_pci_dev(dev->dev)->class >> 8) != PCI_CLASS_DISPLAY_VGA)
- return 0;
-
- fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL);
- if (!fbcon)
- return -ENOMEM;
-
- drm->fbcon = fbcon;
- INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);
- mutex_init(&fbcon->hotplug_lock);
-
- drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);
-
- ret = drm_fb_helper_init(dev, &fbcon->helper);
- if (ret)
- goto free;
-
- if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) {
- if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
- preferred_bpp = 8;
- else
- if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
- preferred_bpp = 16;
- else
- preferred_bpp = 32;
- }
-
- /* disable all the possible outputs/crtcs before entering KMS mode */
- if (!drm_drv_uses_atomic_modeset(dev))
- drm_helper_disable_unused_functions(dev);
-
- ret = drm_fb_helper_initial_config(&fbcon->helper, preferred_bpp);
- if (ret)
- goto fini;
-
- if (fbcon->helper.info)
- fbcon->helper.info->pixmap.buf_align = 4;
- return 0;
-
-fini:
- drm_fb_helper_fini(&fbcon->helper);
-free:
- kfree(fbcon);
- drm->fbcon = NULL;
- return ret;
-}
-
-void
-nouveau_fbcon_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm_kms_helper_poll_fini(dev);
- nouveau_fbcon_accel_fini(dev);
- nouveau_fbcon_destroy(dev, drm->fbcon);
- kfree(drm->fbcon);
- drm->fbcon = NULL;
-}
--
GitLab
From 0f9c608d4a1eb852d6769d2fc5906c71c02565ae Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Wed, 11 Jan 2023 10:38:22 +0100
Subject: [PATCH 0651/1167] init/Kconfig: fix LOCALVERSION_AUTO help text
It was never guaranteed to be exactly eight, but since commit
548b8b5168c9 ("scripts/setlocalversion: make git describe output more
reliable"), it has been exactly 12.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
init/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/init/Kconfig b/init/Kconfig
index 7e5c3ddc341de..ccd3cdcf3df19 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -204,7 +204,7 @@ config LOCALVERSION_AUTO
appended after any matching localversion* files, and after the value
set in CONFIG_LOCALVERSION.
- (The actual string used here is the first eight characters produced
+ (The actual string used here is the first 12 characters produced
by running the command:
$ git rev-parse --verify HEAD
--
GitLab
From 169dd78043f7f4eabdef8d7ba0d4ddffe5cb3930 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Wed, 11 Jan 2023 11:11:56 +0100
Subject: [PATCH 0652/1167] scripts: rpm: make clear that mkspec script
contains 4.13 feature
A fix was made in the mkspec script that uses a feature, ie. the
OR expression, which requires RPM 4.13. However, the script indicates
another minimum version. Lower versions may have success by using
the --no-deps option as suggested, but feels like bumping the version
to 4.13 is reasonable as it put me on the wrong track at first with
RPM 4.11 on my Centos7 machine.
Fixes: 02a893bc9975 ("kbuild: rpm-pkg: add libelf-devel as alternative for BuildRequires")
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/package/mkspec | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index adab28fa7f892..094e52c979a8c 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -1,7 +1,7 @@
#!/bin/sh
#
# Output a simple RPM spec file.
-# This version assumes a minimum of RPM 4.0.3.
+# This version assumes a minimum of RPM 4.13
#
# The only gothic bit here is redefining install_post to avoid
# stripping the symbols from files in the kernel which we want
--
GitLab
From cb3e9864cdbe35ff6378966660edbcbac955fe17 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Tue, 10 Jan 2023 08:59:06 +0800
Subject: [PATCH 0653/1167] ipv6: raw: Deduct extension header length in
rawv6_push_pending_frames
The total cork length created by ip6_append_data includes extension
headers, so we must exclude them when comparing them against the
IPV6_CHECKSUM offset which does not include extension headers.
Reported-by: Kyle Zeng <zengyhkyle@gmail.com>
Fixes: 357b40a18b04 ("[IPV6]: IPV6_CHECKSUM socket option can corrupt kernel memory")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/raw.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a06a9f847db5c..ada087b50541a 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -505,6 +505,7 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
+ struct ipv6_txoptions *opt;
struct sk_buff *skb;
int err = 0;
int offset;
@@ -522,6 +523,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
offset = rp->offset;
total_len = inet_sk(sk)->cork.base.length;
+ opt = inet6_sk(sk)->cork.opt;
+ total_len -= opt ? opt->opt_flen : 0;
+
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
--
GitLab
From a720416d94634068951773cb9e9d6f1b73769e5b Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Fri, 6 Jan 2023 11:07:18 +0100
Subject: [PATCH 0654/1167] spi: spidev: fix a race condition when accessing
spidev->spi
There's a spinlock in place that is taken in file_operations callbacks
whenever we check if spidev->spi is still alive (not null). It's also
taken when spidev->spi is set to NULL in remove().
This however doesn't protect the code against driver unbind event while
one of the syscalls is still in progress. To that end we need a lock taken
continuously as long as we may still access spidev->spi. As both the file
ops and the remove callback are never called from interrupt context, we
can replace the spinlock with a mutex.
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/r/20230106100719.196243-1-brgl@bgdev.pl
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spidev.c | 34 ++++++++++++++++++----------------
1 file changed, 18 insertions(+), 16 deletions(-)
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 6313e7d0cdf87..42aaaca672654 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -68,7 +68,7 @@ static_assert(N_SPI_MINORS > 0 && N_SPI_MINORS <= 256);
struct spidev_data {
dev_t devt;
- spinlock_t spi_lock;
+ struct mutex spi_lock;
struct spi_device *spi;
struct list_head device_entry;
@@ -95,9 +95,8 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message)
int status;
struct spi_device *spi;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spidev->spi;
- spin_unlock_irq(&spidev->spi_lock);
if (spi == NULL)
status = -ESHUTDOWN;
@@ -107,6 +106,7 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message)
if (status == 0)
status = message->actual_length;
+ mutex_unlock(&spidev->spi_lock);
return status;
}
@@ -359,12 +359,12 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* use the buffer lock here for triple duty:
* - prevent I/O (from us) so calling spi_setup() is safe;
@@ -508,6 +508,7 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
@@ -529,12 +530,12 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd,
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* SPI_IOC_MESSAGE needs the buffer locked "normally" */
mutex_lock(&spidev->buf_lock);
@@ -561,6 +562,7 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd,
done:
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
@@ -640,10 +642,10 @@ static int spidev_release(struct inode *inode, struct file *filp)
spidev = filp->private_data;
filp->private_data = NULL;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
/* ... after we unbound from the underlying device? */
dofree = (spidev->spi == NULL);
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
/* last close? */
spidev->users--;
@@ -776,7 +778,7 @@ static int spidev_probe(struct spi_device *spi)
/* Initialize the driver data */
spidev->spi = spi;
- spin_lock_init(&spidev->spi_lock);
+ mutex_init(&spidev->spi_lock);
mutex_init(&spidev->buf_lock);
INIT_LIST_HEAD(&spidev->device_entry);
@@ -821,9 +823,9 @@ static void spidev_remove(struct spi_device *spi)
/* prevent new opens */
mutex_lock(&device_list_lock);
/* make sure ops on existing fds can abort cleanly */
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spidev->spi = NULL;
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
list_del(&spidev->device_entry);
device_destroy(spidev_class, spidev->devt);
--
GitLab
From 6b35b173dbc1711f8d272e3f322d2ad697015919 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Fri, 6 Jan 2023 11:07:19 +0100
Subject: [PATCH 0655/1167] spi: spidev: remove debug messages that access
spidev->spi without locking
The two debug messages in spidev_open() dereference spidev->spi without
taking the lock and without checking if it's not null. This can lead to
a crash. Drop the messages as they're not needed - the user-space will
get informed about ENOMEM with the syscall return value.
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/r/20230106100719.196243-2-brgl@bgdev.pl
Signed-off-by: Mark Brown <broonie@kernel.org>
---
drivers/spi/spidev.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 42aaaca672654..1935ca6134470 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -603,7 +603,6 @@ static int spidev_open(struct inode *inode, struct file *filp)
if (!spidev->tx_buffer) {
spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->tx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_find_dev;
}
@@ -612,7 +611,6 @@ static int spidev_open(struct inode *inode, struct file *filp)
if (!spidev->rx_buffer) {
spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->rx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_alloc_rx_buf;
}
--
GitLab
From 82d3edb50a11bf3c5ef63294d5358ba230181413 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Thu, 5 Jan 2023 15:44:20 +0100
Subject: [PATCH 0656/1167] s390/cpum_sf: add READ_ONCE() semantics to compare
and swap loops
The current cmpxchg_double() loops within the perf hw sampling code do not
have READ_ONCE() semantics to read the old value from memory. This allows
the compiler to generate code which reads the "old" value several times
from memory, which again allows for inconsistencies.
For example:
/* Reset trailer (using compare-double-and-swap) */
do {
te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
te_flags |= SDB_TE_ALERT_REQ_MASK;
} while (!cmpxchg_double(&te->flags, &te->overflow,
te->flags, te->overflow,
te_flags, 0ULL));
The compiler could generate code where te->flags used within the
cmpxchg_double() call may be refetched from memory and which is not
necessarily identical to the previous read version which was used to
generate te_flags. Which in turn means that an incorrect update could
happen.
Fix this by adding READ_ONCE() semantics to all cmpxchg_double()
loops. Given that READ_ONCE() cannot generate code on s390 which atomically
reads 16 bytes, use a private compare-and-swap-double implementation to
achieve that.
Also replace cmpxchg_double() with the private implementation to be able to
re-use the old value within the loops.
As a side effect this converts the whole code to only use bit fields
to read and modify bits within the hws trailer header.
Reported-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/linux-s390/Y71QJBhNTIatvxUT@osiris/T/#ma14e2a5f7aa8ed4b94b6f9576799b3ad9c60f333
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/include/asm/cpu_mf.h | 31 +++++-----
arch/s390/kernel/perf_cpum_sf.c | 101 ++++++++++++++++++++------------
2 files changed, 77 insertions(+), 55 deletions(-)
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index feaba12dbecb8..efa103b52a1a1 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -131,19 +131,21 @@ struct hws_combined_entry {
struct hws_diag_entry diag; /* Diagnostic-sampling data entry */
} __packed;
-struct hws_trailer_entry {
- union {
- struct {
- unsigned int f:1; /* 0 - Block Full Indicator */
- unsigned int a:1; /* 1 - Alert request control */
- unsigned int t:1; /* 2 - Timestamp format */
- unsigned int :29; /* 3 - 31: Reserved */
- unsigned int bsdes:16; /* 32-47: size of basic SDE */
- unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */
- };
- unsigned long long flags; /* 0 - 63: All indicators */
+union hws_trailer_header {
+ struct {
+ unsigned int f:1; /* 0 - Block Full Indicator */
+ unsigned int a:1; /* 1 - Alert request control */
+ unsigned int t:1; /* 2 - Timestamp format */
+ unsigned int :29; /* 3 - 31: Reserved */
+ unsigned int bsdes:16; /* 32-47: size of basic SDE */
+ unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */
+ unsigned long long overflow; /* 64 - Overflow Count */
};
- unsigned long long overflow; /* 64 - sample Overflow count */
+ __uint128_t val;
+};
+
+struct hws_trailer_entry {
+ union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */
unsigned char timestamp[16]; /* 16 - 31 timestamp */
unsigned long long reserved1; /* 32 -Reserved */
unsigned long long reserved2; /* */
@@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
return USEC_PER_SEC * qsi->cpu_speed / rate;
}
-#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL
-#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
-
/* Return TOD timestamp contained in an trailer entry */
static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
{
/* TOD in STCKE format */
- if (te->t)
+ if (te->header.t)
return *((unsigned long long *) &te->timestamp[1]);
/* TOD in STCK format */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 332a499651308..ce886a03545ae 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
{
- unsigned long sdb, *trailer;
+ struct hws_trailer_entry *te;
+ unsigned long sdb;
/* Allocate and initialize sample-data-block */
sdb = get_zeroed_page(gfp_flags);
if (!sdb)
return -ENOMEM;
- trailer = trailer_entry_ptr(sdb);
- *trailer = SDB_TE_ALERT_REQ_MASK;
+ te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+ te->header.a = 1;
/* Link SDB into the sample-data-block-table */
*sdbt = sdb;
@@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
"%s: Found unknown"
" sampling data entry: te->f %i"
" basic.def %#4x (%p)\n", __func__,
- te->f, sample->def, sample);
+ te->header.f, sample->def, sample);
/* Sample slot is not yet written or other record.
*
* This condition can occur if the buffer was reused
@@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
* that are not full. Stop processing if the first
* invalid format was detected.
*/
- if (!te->f)
+ if (!te->header.f)
break;
}
@@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
}
}
+static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new)
+{
+ asm volatile(
+ " cdsg %[old],%[new],%[ptr]\n"
+ : [old] "+d" (old), [ptr] "+QS" (*ptr)
+ : [new] "d" (new)
+ : "memory", "cc");
+ return old;
+}
+
/* hw_perf_event_update() - Process sampling buffer
* @event: The perf event
* @flush_all: Flag to also flush partially filled sample-data-blocks
@@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
*/
static void hw_perf_event_update(struct perf_event *event, int flush_all)
{
+ unsigned long long event_overflow, sampl_overflow, num_sdb;
+ union hws_trailer_header old, prev, new;
struct hw_perf_event *hwc = &event->hw;
struct hws_trailer_entry *te;
unsigned long *sdbt;
- unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
int done;
/*
@@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
/* Leave loop if no more work to do (block full indicator) */
- if (!te->f) {
+ if (!te->header.f) {
done = 1;
if (!flush_all)
break;
}
/* Check the sample overflow count */
- if (te->overflow)
+ if (te->header.overflow)
/* Account sample overflows and, if a particular limit
* is reached, extend the sampling buffer.
* For details, see sfb_account_overflows().
*/
- sampl_overflow += te->overflow;
+ sampl_overflow += te->header.overflow;
/* Timestamps are valid for full sample-data-blocks only */
debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx "
"overflow %llu timestamp %#llx\n",
- __func__, (unsigned long)sdbt, te->overflow,
- (te->f) ? trailer_timestamp(te) : 0ULL);
+ __func__, (unsigned long)sdbt, te->header.overflow,
+ (te->header.f) ? trailer_timestamp(te) : 0ULL);
/* Collect all samples from a single sample-data-block and
* flag if an (perf) event overflow happened. If so, the PMU
@@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
num_sdb++;
/* Reset trailer (using compare-double-and-swap) */
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
- te_flags |= SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- te->flags, te->overflow,
- te_flags, 0ULL));
+ old.val = prev.val;
+ new.val = prev.val;
+ new.f = 0;
+ new.a = 1;
+ new.overflow = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
/* Advance to next sample-data-block */
sdbt++;
@@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle)
range_scan = AUX_SDB_NUM_ALERT(aux);
for (i = 0, idx = aux->head; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- if (!(te->flags & SDB_TE_BUFFER_FULL_MASK))
+ if (!te->header.f)
break;
}
/* i is num of SDBs which are full */
@@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle)
/* Remove alert indicators in the buffer */
te = aux_sdb_trailer(aux, aux->alert_mark);
- te->flags &= ~SDB_TE_ALERT_REQ_MASK;
+ te->header.a = 0;
debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n",
__func__, i, range_scan, aux->head);
@@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle,
idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- te->flags &= ~(SDB_TE_BUFFER_FULL_MASK |
- SDB_TE_ALERT_REQ_MASK);
- te->overflow = 0;
+ te->header.f = 0;
+ te->header.a = 0;
+ te->header.overflow = 0;
}
/* Save the position of empty SDBs */
aux->empty_mark = aux->head + range - 1;
@@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle,
/* Set alert indicator */
aux->alert_mark = aux->head + range/2 - 1;
te = aux_sdb_trailer(aux, aux->alert_mark);
- te->flags = te->flags | SDB_TE_ALERT_REQ_MASK;
+ te->header.a = 1;
/* Reset hardware buffer head */
head = AUX_SDB_INDEX(aux, aux->head);
@@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle,
static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
unsigned long long *overflow)
{
- unsigned long long orig_overflow, orig_flags, new_flags;
+ union hws_trailer_header old, prev, new;
struct hws_trailer_entry *te;
te = aux_sdb_trailer(aux, alert_index);
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- orig_flags = te->flags;
- *overflow = orig_overflow = te->overflow;
- if (orig_flags & SDB_TE_BUFFER_FULL_MASK) {
+ old.val = prev.val;
+ new.val = prev.val;
+ *overflow = old.overflow;
+ if (old.f) {
/*
* SDB is already set by hardware.
* Abort and try to set somewhere
@@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
*/
return false;
}
- new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- orig_flags, orig_overflow,
- new_flags, 0ULL));
+ new.a = 1;
+ new.overflow = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
return true;
}
@@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
unsigned long long *overflow)
{
- unsigned long long orig_overflow, orig_flags, new_flags;
unsigned long i, range_scan, idx, idx_old;
+ union hws_trailer_header old, prev, new;
+ unsigned long long orig_overflow;
struct hws_trailer_entry *te;
debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld "
@@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
idx_old = idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
+ /* READ_ONCE() 16 byte header */
+ prev.val = __cdsg(&te->header.val, 0, 0);
do {
- orig_flags = te->flags;
- orig_overflow = te->overflow;
- new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK;
+ old.val = prev.val;
+ new.val = prev.val;
+ orig_overflow = old.overflow;
+ new.f = 0;
+ new.overflow = 0;
if (idx == aux->alert_mark)
- new_flags |= SDB_TE_ALERT_REQ_MASK;
+ new.a = 1;
else
- new_flags &= ~SDB_TE_ALERT_REQ_MASK;
- } while (!cmpxchg_double(&te->flags, &te->overflow,
- orig_flags, orig_overflow,
- new_flags, 0ULL));
+ new.a = 0;
+ prev.val = __cdsg(&te->header.val, old.val, new.val);
+ } while (prev.val != old.val);
*overflow += orig_overflow;
}
--
GitLab
From e3f360db08d55a14112bd27454e616a24296a8b0 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 9 Jan 2023 11:51:20 +0100
Subject: [PATCH 0657/1167] s390/percpu: add READ_ONCE() to
arch_this_cpu_to_op_simple()
Make sure that *ptr__ within arch_this_cpu_to_op_simple() is only
dereferenced once by using READ_ONCE(). Otherwise the compiler could
generate incorrect code.
Cc: <stable@vger.kernel.org>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/include/asm/percpu.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index cb5fc06904354..081837b391e35 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -31,7 +31,7 @@
pcp_op_T__ *ptr__; \
preempt_disable_notrace(); \
ptr__ = raw_cpu_ptr(&(pcp)); \
- prev__ = *ptr__; \
+ prev__ = READ_ONCE(*ptr__); \
do { \
old__ = prev__; \
new__ = old__ op (val); \
--
GitLab
From 42400d99e9f0728c17240edb9645637ead40f6b9 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 9 Jan 2023 15:54:56 +0100
Subject: [PATCH 0658/1167] KVM: s390: interrupt: use READ_ONCE() before
cmpxchg()
Use READ_ONCE() before cmpxchg() to prevent that the compiler generates
code that fetches the to be compared old value several times from memory.
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Link: https://lore.kernel.org/r/20230109145456.2895385-1-hca@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/kvm/interrupt.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1dae78deddf28..ab26aa53ee371 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+ union esca_sigp_ctrl new_val = {0}, old_val;
+ old_val = READ_ONCE(*sigp_ctrl);
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
@@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+ union bsca_sigp_ctrl new_val = {0}, old_val;
+ old_val = READ_ONCE(*sigp_ctrl);
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
@@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union esca_sigp_ctrl old = *sigp_ctrl;
+ union esca_sigp_ctrl old;
+ old = READ_ONCE(*sigp_ctrl);
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
- union bsca_sigp_ctrl old = *sigp_ctrl;
+ union bsca_sigp_ctrl old;
+ old = READ_ONCE(*sigp_ctrl);
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
}
--
GitLab
From 58fc14e14d288d728bf48377b81bb77fd17bfe3f Mon Sep 17 00:00:00 2001
From: Gustavo Sousa <gustavo.sousa@intel.com>
Date: Thu, 5 Jan 2023 10:37:01 -0300
Subject: [PATCH 0659/1167] drm/i915/gt: Cover rest of SVG unit MCR registers
CHICKEN_RASTER_{1,2} got overlooked with the move done in commit
a9e69428b1b4 ("drm/i915: Define MCR registers explicitly"). Registers
from the SVG unit became multicast as of Xe_HP graphics.
BSpec: 66534
Fixes: a9e69428b1b4 ("drm/i915: Define MCR registers explicitly")
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230105133701.19556-1-gustavo.sousa@intel.com
(cherry picked from commit 10903b0a0f4d4964b352fa3df12d3d2ef5fb7a3b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 4 ++--
drivers/gpu/drm/i915/gt/intel_workarounds.c | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index c3cd926917957..4a14f87e441e5 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -406,10 +406,10 @@
#define GEN9_WM_CHICKEN3 _MMIO(0x5588)
#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9)
-#define CHICKEN_RASTER_1 _MMIO(0x6204)
+#define CHICKEN_RASTER_1 MCR_REG(0x6204)
#define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8)
-#define CHICKEN_RASTER_2 _MMIO(0x6208)
+#define CHICKEN_RASTER_2 MCR_REG(0x6208)
#define TBIMR_FAST_CLIP REG_BIT(5)
#define VFLSKPD MCR_REG(0x62a8)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 2afb4f80a954d..5be2f91801fbf 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -645,7 +645,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
struct i915_wa_list *wal)
{
- wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
wa_mcr_add(wal,
@@ -775,7 +775,7 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
/* Wa_15010599737:dg2 */
- wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
}
static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
--
GitLab
From a4e03921c1bb118e6718e0a3b0322a2c13ed172b Mon Sep 17 00:00:00 2001
From: Giulio Benetti <giulio.benetti@benettiengineering.com>
Date: Tue, 13 Dec 2022 20:24:03 +0100
Subject: [PATCH 0660/1167] ARM: 9280/1: mm: fix warning on phys_addr_t to void
pointer assignment
zero_page is a void* pointer but memblock_alloc() returns phys_addr_t type
so this generates a warning while using clang and with -Wint-error enabled
that becomes and error. So let's cast the return of memblock_alloc() to
(void *).
Cc: <stable@vger.kernel.org> # 4.14.x +
Fixes: 340a982825f7 ("ARM: 9266/1: mm: fix no-MMU ZERO_PAGE() implementation")
Signed-off-by: Giulio Benetti <giulio.benetti@benettiengineering.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
arch/arm/mm/nommu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index c1494a4dee25b..53f2d8774fdb9 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -161,7 +161,7 @@ void __init paging_init(const struct machine_desc *mdesc)
mpu_setup();
/* allocate the zero page. */
- zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!zero_page)
panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
__func__, PAGE_SIZE, PAGE_SIZE);
--
GitLab
From 3cb0f23039e0e3395a96e0f52bd69910ced2f720 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 6 Jan 2023 17:18:21 +0100
Subject: [PATCH 0661/1167] ARM: 9284/1: include <asm/pgtable.h> from
proc-macros.S to fix -Wundef warnings
Since commit 80b6093b55e3 ("kbuild: add -Wundef to KBUILD_CPPFLAGS
for W=1 builds"), building with W=1 detects -Wundef warnings for
assembly code.
$ make W=1 ARCH=arm CROSS_COMPILE=arm-linux-gnueabihf- arch/arm/mm/
[snip]
AS arch/arm/mm/cache-v7.o
In file included from arch/arm/mm/cache-v7.S:17:
arch/arm/mm/proc-macros.S:109:5: warning: "L_PTE_SHARED" is not defined, evaluates to 0 [-Wundef]
109 | #if L_PTE_SHARED != PTE_EXT_SHARED
| ^~~~~~~~~~~~
arch/arm/mm/proc-macros.S:109:21: warning: "PTE_EXT_SHARED" is not defined, evaluates to 0 [-Wundef]
109 | #if L_PTE_SHARED != PTE_EXT_SHARED
| ^~~~~~~~~~~~~~
arch/arm/mm/proc-macros.S:113:10: warning: "L_PTE_XN" is not defined, evaluates to 0 [-Wundef]
113 | (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
| ^~~~~~~~
arch/arm/mm/proc-macros.S:113:19: warning: "L_PTE_USER" is not defined, evaluates to 0 [-Wundef]
113 | (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
| ^~~~~~~~~~
arch/arm/mm/proc-macros.S:113:30: warning: "L_PTE_RDONLY" is not defined, evaluates to 0 [-Wundef]
113 | (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
| ^~~~~~~~~~~~
arch/arm/mm/proc-macros.S:113:43: warning: "L_PTE_DIRTY" is not defined, evaluates to 0 [-Wundef]
113 | (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
| ^~~~~~~~~~~
arch/arm/mm/proc-macros.S:113:55: warning: "L_PTE_YOUNG" is not defined, evaluates to 0 [-Wundef]
113 | (L_PTE_XN+L_PTE_USER+L_PTE_RDONLY+L_PTE_DIRTY+L_PTE_YOUNG+\
| ^~~~~~~~~~~
arch/arm/mm/proc-macros.S:114:10: warning: "L_PTE_PRESENT" is not defined, evaluates to 0 [-Wundef]
114 | L_PTE_PRESENT) > L_PTE_SHARED
| ^~~~~~~~~~~~~
arch/arm/mm/proc-macros.S:114:27: warning: "L_PTE_SHARED" is not defined, evaluates to 0 [-Wundef]
114 | L_PTE_PRESENT) > L_PTE_SHARED
| ^~~~~~~~~~~~
Include <asm/pgtable.h> from proc-macros.S to fix the warnings.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
arch/arm/mm/proc-macros.S | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index fa6999e24b074..e43f6d716b4b8 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -6,6 +6,7 @@
* VM_EXEC
*/
#include <asm/asm-offsets.h>
+#include <asm/pgtable.h>
#include <asm/thread_info.h>
#ifdef CONFIG_CPU_V7M
--
GitLab
From e752e5454e6417da3f40ec1306a041ea96c56423 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Mon, 9 Jan 2023 22:25:47 +0000
Subject: [PATCH 0662/1167] adreno: Shutdown the GPU properly
During kexec on ARM device, we notice that device_shutdown() only calls
pm_runtime_force_suspend() while shutting down the GPU. This means the GPU
kthread is still running and further, there maybe active submits.
This causes all kinds of issues during a kexec reboot:
Warning from shutdown path:
[ 292.509662] WARNING: CPU: 0 PID: 6304 at [...] adreno_runtime_suspend+0x3c/0x44
[ 292.509863] Hardware name: Google Lazor (rev3 - 8) with LTE (DT)
[ 292.509872] pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 292.509881] pc : adreno_runtime_suspend+0x3c/0x44
[ 292.509891] lr : pm_generic_runtime_suspend+0x30/0x44
[ 292.509905] sp : ffffffc014473bf0
[...]
[ 292.510043] Call trace:
[ 292.510051] adreno_runtime_suspend+0x3c/0x44
[ 292.510061] pm_generic_runtime_suspend+0x30/0x44
[ 292.510071] pm_runtime_force_suspend+0x54/0xc8
[ 292.510081] adreno_shutdown+0x1c/0x28
[ 292.510090] platform_shutdown+0x2c/0x38
[ 292.510104] device_shutdown+0x158/0x210
[ 292.510119] kernel_restart_prepare+0x40/0x4c
And here from GPU kthread, an SError OOPs:
[ 192.648789] el1h_64_error+0x7c/0x80
[ 192.648812] el1_interrupt+0x20/0x58
[ 192.648833] el1h_64_irq_handler+0x18/0x24
[ 192.648854] el1h_64_irq+0x7c/0x80
[ 192.648873] local_daif_inherit+0x10/0x18
[ 192.648900] el1h_64_sync_handler+0x48/0xb4
[ 192.648921] el1h_64_sync+0x7c/0x80
[ 192.648941] a6xx_gmu_set_oob+0xbc/0x1fc
[ 192.648968] a6xx_hw_init+0x44/0xe38
[ 192.648991] msm_gpu_hw_init+0x48/0x80
[ 192.649013] msm_gpu_submit+0x5c/0x1a8
[ 192.649034] msm_job_run+0xb0/0x11c
[ 192.649058] drm_sched_main+0x170/0x434
[ 192.649086] kthread+0x134/0x300
[ 192.649114] ret_from_fork+0x10/0x20
Fix by calling adreno_system_suspend() in the device_shutdown() path.
[ Applied Rob Clark feedback on fixing adreno_unbind() similarly, also
tested as above. ]
Cc: Rob Clark <robdclark@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ricardo Ribalda <ribalda@chromium.org>
Cc: Ross Zwisler <zwisler@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Ricardo Ribalda <ribalda@chromium.org>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/517633/
Link: https://lore.kernel.org/r/20230109222547.1368644-1-joel@joelfernandes.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
drivers/gpu/drm/msm/adreno/adreno_device.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 628806423f7d2..36f062c7582f9 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -551,13 +551,14 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
return 0;
}
+static int adreno_system_suspend(struct device *dev);
static void adreno_unbind(struct device *dev, struct device *master,
void *data)
{
struct msm_drm_private *priv = dev_get_drvdata(master);
struct msm_gpu *gpu = dev_to_gpu(dev);
- pm_runtime_force_suspend(dev);
+ WARN_ON_ONCE(adreno_system_suspend(dev));
gpu->funcs->destroy(gpu);
priv->gpu_pdev = NULL;
@@ -609,7 +610,7 @@ static int adreno_remove(struct platform_device *pdev)
static void adreno_shutdown(struct platform_device *pdev)
{
- pm_runtime_force_suspend(&pdev->dev);
+ WARN_ON_ONCE(adreno_system_suspend(&pdev->dev));
}
static const struct of_device_id dt_match[] = {
--
GitLab
From a66f1efcf748febea7758c4c3c8b5bc5294949ef Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Tue, 10 Jan 2023 13:28:59 -0800
Subject: [PATCH 0663/1167] drm/msm/gpu: Fix potential double-free
If userspace was calling the MSM_SET_PARAM ioctl on multiple threads to
set the COMM or CMDLINE param, it could trigger a race causing the
previous value to be kfree'd multiple times. Fix this by serializing on
the gpu lock.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Fixes: d4726d770068 ("drm/msm: Add a way to override processes comm/cmdline")
Patchwork: https://patchwork.freedesktop.org/patch/517778/
Link: https://lore.kernel.org/r/20230110212903.1925878-1-robdclark@gmail.com
---
drivers/gpu/drm/msm/adreno/adreno_gpu.c | 4 ++++
drivers/gpu/drm/msm/msm_gpu.c | 2 ++
drivers/gpu/drm/msm/msm_gpu.h | 12 ++++++++++--
3 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 57586c794b84b..3605f095b2de2 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -352,6 +352,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
/* Ensure string is null terminated: */
str[len] = '\0';
+ mutex_lock(&gpu->lock);
+
if (param == MSM_PARAM_COMM) {
paramp = &ctx->comm;
} else {
@@ -361,6 +363,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx,
kfree(*paramp);
*paramp = str;
+ mutex_unlock(&gpu->lock);
+
return 0;
}
case MSM_PARAM_SYSPROF:
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 021f4e29b613b..4f495eecc34ba 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -335,6 +335,8 @@ static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char **
struct msm_file_private *ctx = submit->queue->ctx;
struct task_struct *task;
+ WARN_ON(!mutex_is_locked(&submit->gpu->lock));
+
/* Note that kstrdup will return NULL if argument is NULL: */
*comm = kstrdup(ctx->comm, GFP_KERNEL);
*cmd = kstrdup(ctx->cmdline, GFP_KERNEL);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 58a72e6b14008..a89bfdc3d7f90 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -366,10 +366,18 @@ struct msm_file_private {
*/
int sysprof;
- /** comm: Overridden task comm, see MSM_PARAM_COMM */
+ /**
+ * comm: Overridden task comm, see MSM_PARAM_COMM
+ *
+ * Accessed under msm_gpu::lock
+ */
char *comm;
- /** cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE */
+ /**
+ * cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE
+ *
+ * Accessed under msm_gpu::lock
+ */
char *cmdline;
/**
--
GitLab
From cf129830ee820f7fc90b98df193cd49d49344d09 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 10 Jan 2023 20:56:59 +0200
Subject: [PATCH 0664/1167] perf auxtrace: Fix address filter duplicate symbol
selection
When a match has been made to the nth duplicate symbol, return
success not error.
Example:
Before:
$ cat file.c
cat: file.c: No such file or directory
$ cat file1.c
#include <stdio.h>
static void func(void)
{
printf("First func\n");
}
void other(void);
int main()
{
func();
other();
return 0;
}
$ cat file2.c
#include <stdio.h>
static void func(void)
{
printf("Second func\n");
}
void other(void)
{
func();
}
$ gcc -Wall -Wextra -o test file1.c file2.c
$ perf record -e intel_pt//u --filter 'filter func @ ./test' -- ./test
Multiple symbols with name 'func'
#1 0x1149 l func
which is near main
#2 0x1179 l func
which is near other
Disambiguate symbol name by inserting #n after the name e.g. func #2
Or select a global symbol by inserting #0 or #g or #G
Failed to parse address filter: 'filter func @ ./test'
Filter format is: filter|start|stop|tracestop <start symbol or address> [/ <end symbol or size>] [@<file name>]
Where multiple filters are separated by space or comma.
$ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test
Failed to parse address filter: 'filter func #2 @ ./test'
Filter format is: filter|start|stop|tracestop <start symbol or address> [/ <end symbol or size>] [@<file name>]
Where multiple filters are separated by space or comma.
After:
$ perf record -e intel_pt//u --filter 'filter func #2 @ ./test' -- ./test
First func
Second func
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.016 MB perf.data ]
$ perf script --itrace=b -Ftime,flags,ip,sym,addr --ns
1231062.526977619: tr strt 0 [unknown] => 558495708179 func
1231062.526977619: tr end call 558495708188 func => 558495708050 _init
1231062.526979286: tr strt 0 [unknown] => 55849570818d func
1231062.526979286: tr end return 55849570818f func => 55849570819d other
Fixes: 1b36c03e356936d6 ("perf record: Add support for using symbols in address filters")
Reported-by: Dmitrii Dolgov <9erthalion6@gmail.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Dmitry Dolgov <9erthalion6@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230110185659.15979-1-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/auxtrace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 265d20cc126b1..c2e323cd7d496 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -2611,7 +2611,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
*size = sym->start - *start;
if (idx > 0) {
if (*size)
- return 1;
+ return 0;
} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
print_duplicate_syms(dso, sym_name);
return -EINVAL;
--
GitLab
From c273289fac370b6488757236cd62cc2cf04830b7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 4 Jan 2023 12:54:42 +0100
Subject: [PATCH 0665/1167] selftests: netfilter: fix transaction test script
timeout handling
The kselftest framework uses a default timeout of 45 seconds for
all test scripts.
Increase the timeout to two minutes for the netfilter tests, this
should hopefully be enough,
Make sure that, should the script be canceled, the net namespace and
the spawned ping instances are removed.
Fixes: 25d8bcedbf43 ("selftests: add script to stress-test nft packet path vs. control plane")
Reported-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Signed-off-by: Florian Westphal <fw@strlen.de>
Tested-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../selftests/netfilter/nft_trans_stress.sh | 16 +++++++++-------
tools/testing/selftests/netfilter/settings | 1 +
2 files changed, 10 insertions(+), 7 deletions(-)
create mode 100644 tools/testing/selftests/netfilter/settings
diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh
index a7f62ad4f6611..2ffba45a78bf4 100755
--- a/tools/testing/selftests/netfilter/nft_trans_stress.sh
+++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh
@@ -10,12 +10,20 @@
ksft_skip=4
testns=testns-$(mktemp -u "XXXXXXXX")
+tmp=""
tables="foo bar baz quux"
global_ret=0
eret=0
lret=0
+cleanup() {
+ ip netns pids "$testns" | xargs kill 2>/dev/null
+ ip netns del "$testns"
+
+ rm -f "$tmp"
+}
+
check_result()
{
local r=$1
@@ -43,6 +51,7 @@ if [ $? -ne 0 ];then
exit $ksft_skip
fi
+trap cleanup EXIT
tmp=$(mktemp)
for table in $tables; do
@@ -139,11 +148,4 @@ done
check_result $lret "add/delete with nftrace enabled"
-pkill -9 ping
-
-wait
-
-rm -f "$tmp"
-ip netns del "$testns"
-
exit $global_ret
diff --git a/tools/testing/selftests/netfilter/settings b/tools/testing/selftests/netfilter/settings
new file mode 100644
index 0000000000000..6091b45d226ba
--- /dev/null
+++ b/tools/testing/selftests/netfilter/settings
@@ -0,0 +1 @@
+timeout=120
--
GitLab
From 9ea4b476cea1b7d461d16dda25ca3c7e616e2d15 Mon Sep 17 00:00:00 2001
From: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Date: Wed, 11 Jan 2023 11:57:39 +0000
Subject: [PATCH 0666/1167] netfilter: ipset: Fix overflow before widen in the
bitmap_ip_create() function.
When first_ip is 0, last_ip is 0xFFFFFFFF, and netmask is 31, the value of
an arithmetic expression 2 << (netmask - mask_bits - 1) is subject
to overflow due to a failure casting operands to a larger data type
before performing the arithmetic.
Note that it's harmless since the value will be checked at the next step.
Found by InfoTeCS on behalf of Linux Verification Center
(linuxtesting.org) with SVACE.
Fixes: b9fed748185a ("netfilter: ipset: Check and reject crazy /0 input parameters")
Signed-off-by: Ilia.Gavrilov <Ilia.Gavrilov@infotecs.ru>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/ipset/ip_set_bitmap_ip.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index a8ce04a4bb72a..e4fa00abde6a2 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -308,8 +308,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
return -IPSET_ERR_BITMAP_RANGE;
pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask);
- hosts = 2 << (32 - netmask - 1);
- elements = 2 << (netmask - mask_bits - 1);
+ hosts = 2U << (32 - netmask - 1);
+ elements = 2UL << (netmask - mask_bits - 1);
}
if (elements > IPSET_BITMAP_MAX_RANGE + 1)
return -IPSET_ERR_BITMAP_RANGE_SIZE;
--
GitLab
From 696e1a48b1a1b01edad542a1ef293665864a4dd0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 11 Jan 2023 17:07:33 +0100
Subject: [PATCH 0667/1167] netfilter: nft_payload: incorrect arithmetics when
fetching VLAN header bits
If the offset + length goes over the ethernet + vlan header, then the
length is adjusted to copy the bytes that are within the boundaries of
the vlan_ethhdr scratchpad area. The remaining bytes beyond ethernet +
vlan header are copied directly from the skbuff data area.
Fix incorrect arithmetic operator: subtract, not add, the size of the
vlan header in case of double-tagged packets to adjust the length
accordingly to address CVE-2023-0179.
Reported-by: Davide Ornaghi <d.ornaghi97@gmail.com>
Fixes: f6ae9f120dad ("netfilter: nft_payload: add C-VLAN support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_payload.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 17b418a5a593a..3a3c7746e88fe 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -63,7 +63,7 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len)
return false;
if (offset + len > VLAN_ETH_HLEN + vlan_hlen)
- ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen;
+ ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen;
memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen);
--
GitLab
From 3a9ae31ac26a58d33008c42f6cd022afc2af2dc0 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 9 Jan 2023 06:02:16 -0500
Subject: [PATCH 0668/1167] Documentation: kvm: fix SRCU locking order docs
kvm->srcu is taken in KVM_RUN and several other vCPU ioctls, therefore
vcpu->mutex is susceptible to the same deadlock that is documented
for kvm->slots_lock. The same holds for kvm->lock, since kvm->lock
is held outside vcpu->mutex. Fix the documentation and rearrange it
to highlight the difference between these locks and kvm->slots_arch_lock,
and how kvm->slots_arch_lock can be useful while processing a vmexit.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
Documentation/virt/kvm/locking.rst | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index a3ca76f9be751..5ee017740d554 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -24,17 +24,18 @@ The acquisition orders for mutexes are as follows:
For SRCU:
-- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
- the kvm->slots_lock critical section, therefore kvm->slots_lock
- cannot be taken inside a kvm->srcu read-side critical section.
- Instead, kvm->slots_arch_lock is released before the call
- to ``synchronize_srcu()`` and _can_ be taken inside a
- kvm->srcu read-side critical section.
-
-- kvm->lock is taken inside kvm->srcu, therefore
- ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
- a kvm->lock critical section. If you cannot delay the
- call until after kvm->lock is released, use ``call_srcu``.
+- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+ for kvm->lock, vcpu->mutex and kvm->slots_lock. These locks _cannot_
+ be taken inside a kvm->srcu read-side critical section; that is, the
+ following is broken::
+
+ srcu_read_lock(&kvm->srcu);
+ mutex_lock(&kvm->slots_lock);
+
+- kvm->slots_arch_lock instead is released before the call to
+ ``synchronize_srcu()``. It _can_ therefore be taken inside a
+ kvm->srcu read-side critical section, for example while processing
+ a vmexit.
On x86:
--
GitLab
From 23e60258aeafb04e5dd813f03cb0c8ab7b01462a Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 11 Jan 2023 18:06:48 +0000
Subject: [PATCH 0669/1167] KVM: x86/xen: Fix lockdep warning on "recursive"
gpc locking
In commit 5ec3289b31 ("KVM: x86/xen: Compatibility fixes for shared runstate
area") we declared it safe to obtain two gfn_to_pfn_cache locks at the same
time:
/*
* The guest's runstate_info is split across two pages and we
* need to hold and validate both GPCs simultaneously. We can
* declare a lock ordering GPC1 > GPC2 because nothing else
* takes them more than one at a time.
*/
However, we forgot to tell lockdep. Do so, by setting a subclass on the
first lock before taking the second.
Fixes: 5ec3289b31 ("KVM: x86/xen: Compatibility fixes for shared runstate area")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20230111180651.14394-1-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/xen.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 2e29bdc2949ca..bfa9809721b5b 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -304,8 +304,10 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
* The guest's runstate_info is split across two pages and we
* need to hold and validate both GPCs simultaneously. We can
* declare a lock ordering GPC1 > GPC2 because nothing else
- * takes them more than one at a time.
+ * takes them more than one at a time. Set a subclass on the
+ * gpc1 lock to make lockdep shut up about it.
*/
+ lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
read_lock(&gpc2->lock);
if (!kvm_gpc_check(gpc2, user_len2)) {
--
GitLab
From bbe17c625d6843e9cdf14d81fbece1b0f0c3fb2f Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 11 Jan 2023 18:06:49 +0000
Subject: [PATCH 0670/1167] KVM: x86/xen: Fix potential deadlock in
kvm_xen_update_runstate_guest()
The kvm_xen_update_runstate_guest() function can be called when the vCPU
is being scheduled out, from a preempt notifier. It *opportunistically*
updates the runstate area in the guest memory, if the gfn_to_pfn_cache
which caches the appropriate address is still valid.
If there is *contention* when it attempts to obtain gpc->lock, then
locking inside the priority inheritance checks may cause a deadlock.
Lockdep reports:
[13890.148997] Chain exists of:
&gpc->lock --> &p->pi_lock --> &rq->__lock
[13890.149002] Possible unsafe locking scenario:
[13890.149003] CPU0 CPU1
[13890.149004] ---- ----
[13890.149005] lock(&rq->__lock);
[13890.149007] lock(&p->pi_lock);
[13890.149009] lock(&rq->__lock);
[13890.149011] lock(&gpc->lock);
[13890.149013]
*** DEADLOCK ***
In the general case, if there's contention for a read lock on gpc->lock,
that's going to be because something else is either invalidating or
revalidating the cache. Either way, we've raced with seeing it in an
invalid state, in which case we would have aborted the opportunistic
update anyway.
So in the 'atomic' case when called from the preempt notifier, just
switch to using read_trylock() and avoid the PI handling altogether.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20230111180651.14394-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/xen.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index bfa9809721b5b..651f9c5b873dd 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -271,7 +271,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
* Attempt to obtain the GPC lock on *both* (if there are two)
* gfn_to_pfn caches that cover the region.
*/
- read_lock_irqsave(&gpc1->lock, flags);
+ if (atomic) {
+ local_irq_save(flags);
+ if (!read_trylock(&gpc1->lock)) {
+ local_irq_restore(flags);
+ return;
+ }
+ } else {
+ read_lock_irqsave(&gpc1->lock, flags);
+ }
while (!kvm_gpc_check(gpc1, user_len1)) {
read_unlock_irqrestore(&gpc1->lock, flags);
@@ -308,7 +316,14 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic)
* gpc1 lock to make lockdep shut up about it.
*/
lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
- read_lock(&gpc2->lock);
+ if (atomic) {
+ if (!read_trylock(&gpc2->lock)) {
+ read_unlock_irqrestore(&gpc1->lock, flags);
+ return;
+ }
+ } else {
+ read_lock(&gpc2->lock);
+ }
if (!kvm_gpc_check(gpc2, user_len2)) {
read_unlock(&gpc2->lock);
--
GitLab
From 42a90008f890afc41837dfeec1f0b1e7bcecf94a Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 11 Jan 2023 18:06:50 +0000
Subject: [PATCH 0671/1167] KVM: Ensure lockdep knows about kvm->lock vs.
vcpu->mutex ordering rule
Documentation/virt/kvm/locking.rst tells us that kvm->lock is taken outside
vcpu->mutex. But that doesn't actually happen very often; it's only in
some esoteric cases like migration with AMD SEV. This means that lockdep
usually doesn't notice, and doesn't do its job of keeping us honest.
Ensure that lockdep *always* knows about the ordering of these two locks,
by briefly taking vcpu->mutex in kvm_vm_ioctl_create_vcpu() while kvm->lock
is held.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20230111180651.14394-3-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
virt/kvm/kvm_main.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 13e88297f9996..9c60384b5ae0b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3954,6 +3954,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
}
mutex_lock(&kvm->lock);
+
+#ifdef CONFIG_LOCKDEP
+ /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */
+ mutex_lock(&vcpu->mutex);
+ mutex_unlock(&vcpu->mutex);
+#endif
+
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;
--
GitLab
From ed02363fbbed52a3f5ea0d188edd09045a806eb5 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 12 Dec 2022 10:19:37 +0800
Subject: [PATCH 0672/1167] btrfs: add extra error messages to cover non-ENOMEM
errors from device_add_list()
[BUG]
When test case btrfs/219 (aka, mount a registered device but with a lower
generation) failed, there is not any useful information for the end user
to find out what's going wrong.
The mount failure just looks like this:
# mount -o loop /tmp/219.img2 /mnt/btrfs/
mount: /mnt/btrfs: mount(2) system call failed: File exists.
dmesg(1) may have more information after failed mount system call.
While the dmesg contains nothing but the loop device change:
loop1: detected capacity change from 0 to 524288
[CAUSE]
In device_list_add() we have a lot of extra checks to reject invalid
cases.
That function also contains the regular device scan result like the
following prompt:
BTRFS: device fsid 6222333e-f9f1-47e6-b306-55ddd4dcaef4 devid 1 transid 8 /dev/loop0 scanned by systemd-udevd (3027)
But unfortunately not all errors have their own error messages, thus if
we hit something wrong in device_add_list(), there may be no error
messages at all.
[FIX]
Add errors message for all non-ENOMEM errors.
For ENOMEM, I'd say we're in a much worse situation, and there should be
some OOM messages way before our call sites.
CC: stable@vger.kernel.org # 6.0+
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/volumes.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index aa25fa335d3ed..bf0decaac7f30 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -768,8 +768,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
error = lookup_bdev(path, &path_devt);
- if (error)
+ if (error) {
+ btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+ path, error);
return ERR_PTR(error);
+ }
if (fsid_change_in_progress) {
if (!has_metadata_uuid)
@@ -836,6 +839,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
unsigned int nofs_flag;
if (fs_devices->opened) {
+ btrfs_err(NULL,
+ "device %s belongs to fsid %pU, and the fs is already mounted",
+ path, fs_devices->fsid);
mutex_unlock(&fs_devices->device_list_mutex);
return ERR_PTR(-EBUSY);
}
@@ -905,6 +911,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
* generation are equal.
*/
mutex_unlock(&fs_devices->device_list_mutex);
+ btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+ path, found_transid, device->generation);
return ERR_PTR(-EEXIST);
}
--
GitLab
From 75181406b4eafacc531ff2ee5fb032bd93317e2b Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 10 Jan 2023 15:14:17 +0800
Subject: [PATCH 0673/1167] btrfs: qgroup: do not warn on record without
old_roots populated
[BUG]
There are some reports from the mailing list that since v6.1 kernel, the
WARN_ON() inside btrfs_qgroup_account_extent() gets triggered during
rescan:
WARNING: CPU: 3 PID: 6424 at fs/btrfs/qgroup.c:2756 btrfs_qgroup_account_extents+0x1ae/0x260 [btrfs]
CPU: 3 PID: 6424 Comm: snapperd Tainted: P OE 6.1.2-1-default #1 openSUSE Tumbleweed 05c7a1b1b61d5627475528f71f50444637b5aad7
RIP: 0010:btrfs_qgroup_account_extents+0x1ae/0x260 [btrfs]
Call Trace:
<TASK>
btrfs_commit_transaction+0x30c/0xb40 [btrfs c39c9c546c241c593f03bd6d5f39ea1b676250f6]
? start_transaction+0xc3/0x5b0 [btrfs c39c9c546c241c593f03bd6d5f39ea1b676250f6]
btrfs_qgroup_rescan+0x42/0xc0 [btrfs c39c9c546c241c593f03bd6d5f39ea1b676250f6]
btrfs_ioctl+0x1ab9/0x25c0 [btrfs c39c9c546c241c593f03bd6d5f39ea1b676250f6]
? __rseq_handle_notify_resume+0xa9/0x4a0
? mntput_no_expire+0x4a/0x240
? __seccomp_filter+0x319/0x4d0
__x64_sys_ioctl+0x90/0xd0
do_syscall_64+0x5b/0x80
? syscall_exit_to_user_mode+0x17/0x40
? do_syscall_64+0x67/0x80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fd9b790d9bf
</TASK>
[CAUSE]
Since commit e15e9f43c7ca ("btrfs: introduce
BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING to skip qgroup accounting"), if
our qgroup is already in inconsistent state, we will no longer do the
time-consuming backref walk.
This can leave some qgroup records without a valid old_roots ulist.
Normally this is fine, as btrfs_qgroup_account_extents() would also skip
those records if we have NO_ACCOUNTING flag set.
But there is a small window, if we have NO_ACCOUNTING flag set, and
inserted some qgroup_record without a old_roots ulist, but then the user
triggered a qgroup rescan.
During btrfs_qgroup_rescan(), we firstly clear NO_ACCOUNTING flag, then
commit current transaction.
And since we have a qgroup_record with old_roots = NULL, we trigger the
WARN_ON() during btrfs_qgroup_account_extents().
[FIX]
Unfortunately due to the introduction of NO_ACCOUNTING flag, the
assumption that every qgroup_record would have its old_roots populated
is no longer correct.
Fix the false alerts and drop the WARN_ON().
Reported-by: Lukas Straub <lukasstraub2@web.de>
Reported-by: HanatoK <summersnow9403@gmail.com>
Fixes: e15e9f43c7ca ("btrfs: introduce BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING to skip qgroup accounting")
CC: stable@vger.kernel.org # 6.1
Link: https://lore.kernel.org/linux-btrfs/2403c697-ddaf-58ad-3829-0335fc89df09@gmail.com/
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/qgroup.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d275bf24b250b..00851c86aa8aa 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2765,9 +2765,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
/*
* Old roots should be searched when inserting qgroup
- * extent record
+ * extent record.
+ *
+ * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case,
+ * we may have some record inserted during
+ * NO_ACCOUNTING (thus no old_roots populated), but
+ * later we start rescan, which clears NO_ACCOUNTING,
+ * leaving some inserted records without old_roots
+ * populated.
+ *
+ * Those cases are rare and should not cause too much
+ * time spent during commit_transaction().
*/
- if (WARN_ON(!record->old_roots)) {
+ if (!record->old_roots) {
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
--
GitLab
From 85e79ec7b78f863178ca488fd8cb5b3de6347756 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Tue, 10 Jan 2023 15:04:32 +0900
Subject: [PATCH 0674/1167] btrfs: zoned: enable metadata over-commit for
non-ZNS setup
The commit 79417d040f4f ("btrfs: zoned: disable metadata overcommit for
zoned") disabled the metadata over-commit to track active zones properly.
However, it also introduced a heavy overhead by allocating new metadata
block groups and/or flushing dirty buffers to release the space
reservations. Specifically, a workload (write only without any sync
operations) worsen its performance from 343.77 MB/sec (v5.19) to 182.89
MB/sec (v6.0).
The performance is still bad on current misc-next which is 187.95 MB/sec.
And, with this patch applied, it improves back to 326.70 MB/sec (+73.82%).
This patch introduces a new fs_info->flag BTRFS_FS_NO_OVERCOMMIT to
indicate it needs to disable the metadata over-commit. The flag is enabled
when a device with max active zones limit is loaded into a file-system.
Fixes: 79417d040f4f ("btrfs: zoned: disable metadata overcommit for zoned")
CC: stable@vger.kernel.org # 6.0+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/fs.h | 6 ++++++
fs/btrfs/space-info.c | 3 ++-
fs/btrfs/zoned.c | 2 ++
3 files changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index a749367e5ae2a..37b86acfcbcf8 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -119,6 +119,12 @@ enum {
/* Indicate that we want to commit the transaction. */
BTRFS_FS_NEED_TRANS_COMMIT,
+ /*
+ * Indicate metadata over-commit is disabled. This is set when active
+ * zone tracking is needed.
+ */
+ BTRFS_FS_NO_OVERCOMMIT,
+
#if BITS_PER_LONG == 32
/* Indicate if we have error/warn message printed on 32bit systems */
BTRFS_FS_32BIT_ERROR,
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d28ee4e36f3d9..69c09508afb50 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -407,7 +407,8 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
return 0;
used = btrfs_space_info_used(space_info, true);
- if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
+ if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) &&
+ (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
avail = 0;
else
avail = calc_available_free_space(fs_info, space_info, flush);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index a759668477bb2..1f503e8e42d48 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -539,6 +539,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
}
atomic_set(&zone_info->active_zones_left,
max_active_zones - nactive);
+ /* Overcommit does not work well with active zone tacking. */
+ set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags);
}
/* Validate superblock log */
--
GitLab
From 1ecf7bd9c267ab85aff3c4a17fe56bc9754a13be Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 11 Jan 2023 15:04:47 +0100
Subject: [PATCH 0675/1167] s390: update defconfigs
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/configs/debug_defconfig | 7 ++++---
arch/s390/configs/defconfig | 6 ++++--
arch/s390/configs/zfcpdump_defconfig | 2 +-
3 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index a7b4e1d827580..74b35ec2ad28a 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -190,7 +190,6 @@ CONFIG_NFT_CT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
@@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_HANGCHECK_TIMER=m
@@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
CONFIG_SQUASHFS_XATTR=y
CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
@@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
@@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m
CONFIG_PKEY=m
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
CONFIG_CORDIC=m
CONFIG_CRYPTO_LIB_CURVE25519=m
CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
@@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
CONFIG_FTRACE_STARTUP_TEST=y
# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
@@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y
CONFIG_FAIL_IO_TIMEOUT=y
CONFIG_FAIL_FUTEX=y
CONFIG_FAULT_INJECTION_DEBUG_FS=y
-CONFIG_FAIL_FUNCTION=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LKDTM=m
CONFIG_TEST_MIN_HEAP=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 2bc2d0fe57743..cec71268e3bc2 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -181,7 +181,6 @@ CONFIG_NFT_CT=m
CONFIG_NFT_LOG=m
CONFIG_NFT_LIMIT=m
CONFIG_NFT_NAT=m
-CONFIG_NFT_OBJREF=m
CONFIG_NFT_REJECT=m
CONFIG_NFT_COMPAT=m
CONFIG_NFT_HASH=m
@@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+# CONFIG_LEGACY_TIOCSTI is not set
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_HANGCHECK_TIMER=m
@@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
+CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y
CONFIG_SQUASHFS_XATTR=y
CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
@@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_INTEGRITY_PLATFORM_KEYRING=y
CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
@@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m
CONFIG_PKEY=m
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_DEV_VIRTIO=m
+CONFIG_SYSTEM_BLACKLIST_KEYRING=y
CONFIG_CORDIC=m
CONFIG_PRIME_NUMBERS=m
CONFIG_CRYPTO_LIB_CURVE25519=m
@@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
CONFIG_SAMPLES=y
CONFIG_SAMPLE_TRACE_PRINTK=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index ae14ab0b864d5..a9c0c81d1de99 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y
# CONFIG_COMPAT is not set
CONFIG_NR_CPUS=2
CONFIG_HZ_100=y
-# CONFIG_RELOCATABLE is not set
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
@@ -50,6 +49,7 @@ CONFIG_ZFCP=y
# CONFIG_INPUT_KEYBOARD is not set
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
+# CONFIG_LEGACY_TIOCSTI is not set
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
# CONFIG_HMC_DRV is not set
--
GitLab
From a33ae832bf3f2ac33e2e44b99f76130d3be848c5 Mon Sep 17 00:00:00 2001
From: Akira Yokosawa <akiyks@gmail.com>
Date: Tue, 10 Jan 2023 18:47:25 +0900
Subject: [PATCH 0676/1167] docs/conf.py: Use about.html only in sidebar of
alabaster theme
"about.html" is available only for the alabaster theme [1].
Unconditionally putting it to html_sidebars prevents us from
using other themes which respect html_sidebars.
Remove about.html from the initialization and insert it at the
front for the alabaster theme.
Link: [1] https://alabaster.readthedocs.io/en/latest/installation.html#sidebars
Fixes: d5389d3145ef ("docs: Switch the default HTML theme to alabaster")
Signed-off-by: Akira Yokosawa <akiyks@gmail.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Link: https://lore.kernel.org/r/4b162dbe-2a7f-1710-93e0-754cf8680aae@gmail.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
Documentation/conf.py | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 44899be7b2cca..d927737e3c10f 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -345,7 +345,11 @@ html_use_smartypants = False
# Custom sidebar templates, maps document names to template names.
# Note that the RTD theme ignores this
-html_sidebars = { '**': ["about.html", 'searchbox.html', 'localtoc.html', 'sourcelink.html']}
+html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']}
+
+# about.html is available for alabaster theme. Add it at the front.
+if html_theme == 'alabaster':
+ html_sidebars['**'].insert(0, 'about.html')
# Output file base name for HTML help builder.
htmlhelp_basename = 'TheLinuxKerneldoc'
--
GitLab
From a48fe6376919c182597b737984bb905a909727c2 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 10 Jan 2023 12:02:42 -0600
Subject: [PATCH 0677/1167] x86/pci: Simplify is_mmconf_reserved() messages
is_mmconf_reserved() takes a "with_e820" parameter that only determines the
message logged if it finds the MMCONFIG region is reserved. Pass the
message directly, which will simplify a future patch that adds a new way of
looking for that reservation. No functional change intended.
Link: https://lore.kernel.org/r/20230110180243.1590045-2-helgaas@kernel.org
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
arch/x86/pci/mmconfig-shared.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 758cbfe55daa3..51c951699b2ed 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -446,13 +446,12 @@ typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
struct pci_mmcfg_region *cfg,
- struct device *dev, int with_e820)
+ struct device *dev, const char *method)
{
u64 addr = cfg->res.start;
u64 size = resource_size(&cfg->res);
u64 old_size = size;
int num_buses;
- char *method = with_e820 ? "E820" : "ACPI motherboard resources";
while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
size >>= 1;
@@ -464,10 +463,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
return false;
if (dev)
- dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+ dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
else
- pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+ pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
if (old_size != size) {
@@ -500,7 +499,8 @@ static bool __ref
pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
{
if (!early && !acpi_disabled) {
- if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+ if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+ "ACPI motherboard resource"))
return true;
if (dev)
@@ -527,7 +527,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
/* Don't try to do this check unless configuration
type 1 is available. how about type 2 ?*/
if (raw_pci_ops)
- return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
+ return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+ "E820 entry");
return false;
}
--
GitLab
From 310bc39546a435c83cc27a0eba878afac0d74714 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 11 Jan 2023 18:06:51 +0000
Subject: [PATCH 0678/1167] KVM: x86/xen: Avoid deadlock by adding
kvm->arch.xen.xen_lock leaf node lock
In commit 14243b387137a ("KVM: x86/xen: Add KVM_IRQ_ROUTING_XEN_EVTCHN
and event channel delivery") the clever version of me left some helpful
notes for those who would come after him:
/*
* For the irqfd workqueue, using the main kvm->lock mutex is
* fine since this function is invoked from kvm_set_irq() with
* no other lock held, no srcu. In future if it will be called
* directly from a vCPU thread (e.g. on hypercall for an IPI)
* then it may need to switch to using a leaf-node mutex for
* serializing the shared_info mapping.
*/
mutex_lock(&kvm->lock);
In commit 2fd6df2f2b47 ("KVM: x86/xen: intercept EVTCHNOP_send from guests")
the other version of me ran straight past that comment without reading it,
and introduced a potential deadlock by taking vcpu->mutex and kvm->lock
in the wrong order.
Solve this as originally suggested, by adding a leaf-node lock in the Xen
state rather than using kvm->lock for it.
Fixes: 2fd6df2f2b47 ("KVM: x86/xen: intercept EVTCHNOP_send from guests")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20230111180651.14394-4-dwmw2@infradead.org>
[Rebase, add docs. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
Documentation/virt/kvm/locking.rst | 2 +-
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/kvm/xen.c | 67 +++++++++++++-----------------
3 files changed, 32 insertions(+), 38 deletions(-)
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 5ee017740d554..a0146793d1972 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -39,7 +39,7 @@ For SRCU:
On x86:
-- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
+- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and
kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f35f1ff4427bb..6aaae18f18544 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1111,6 +1111,7 @@ struct msr_bitmap_range {
/* Xen emulation context */
struct kvm_xen {
+ struct mutex xen_lock;
u32 xen_version;
bool long_mode;
bool runstate_update_flag;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 651f9c5b873dd..8fd41f5deae39 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -607,26 +607,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
r = -EINVAL;
} else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.long_mode = !!data->u.long_mode;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
case KVM_XEN_ATTR_TYPE_SHARED_INFO:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
break;
case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
if (data->u.vector && data->u.vector < 0x10)
r = -EINVAL;
else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.upcall_vector = data->u.vector;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
@@ -636,9 +636,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
break;
case KVM_XEN_ATTR_TYPE_XEN_VERSION:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.xen_version = data->u.xen_version;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
@@ -647,9 +647,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
r = -EOPNOTSUPP;
break;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
@@ -664,7 +664,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
{
int r = -ENOENT;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_ATTR_TYPE_LONG_MODE:
@@ -703,7 +703,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
break;
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return r;
}
@@ -711,7 +711,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
int idx, r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
idx = srcu_read_lock(&vcpu->kvm->srcu);
switch (data->type) {
@@ -939,7 +939,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
}
srcu_read_unlock(&vcpu->kvm->srcu, idx);
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
@@ -947,7 +947,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
{
int r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
@@ -1030,7 +1030,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
break;
}
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
@@ -1123,7 +1123,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
xhc->blob_size_32 || xhc->blob_size_64))
return -EINVAL;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
static_branch_inc(&kvm_xen_enabled.key);
@@ -1132,7 +1132,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return 0;
}
@@ -1675,15 +1675,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
mm_borrowed = true;
}
- /*
- * For the irqfd workqueue, using the main kvm->lock mutex is
- * fine since this function is invoked from kvm_set_irq() with
- * no other lock held, no srcu. In future if it will be called
- * directly from a vCPU thread (e.g. on hypercall for an IPI)
- * then it may need to switch to using a leaf-node mutex for
- * serializing the shared_info mapping.
- */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
/*
* It is theoretically possible for the page to be unmapped
@@ -1712,7 +1704,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm)
srcu_read_unlock(&kvm->srcu, idx);
} while(!rc);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (mm_borrowed)
kthread_unuse_mm(kvm->mm);
@@ -1828,7 +1820,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
int ret;
/* Protect writes to evtchnfd as well as the idr lookup. */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
ret = -ENOENT;
@@ -1859,7 +1851,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm,
}
ret = 0;
out_unlock:
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return ret;
}
@@ -1922,10 +1914,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
GFP_KERNEL);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (ret >= 0)
return 0;
@@ -1943,9 +1935,9 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port)
{
struct evtchnfd *evtchnfd;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (!evtchnfd)
return -ENOENT;
@@ -1963,7 +1955,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
int i;
int n = 0;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
/*
* Because synchronize_srcu() cannot be called inside the
@@ -1975,7 +1967,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
if (!all_evtchnfds) {
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return -ENOMEM;
}
@@ -1984,7 +1976,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm)
all_evtchnfds[n++] = evtchnfd;
idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
synchronize_srcu(&kvm->srcu);
@@ -2086,6 +2078,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
void kvm_xen_init_vm(struct kvm *kvm)
{
+ mutex_init(&kvm->arch.xen.xen_lock);
idr_init(&kvm->arch.xen.evtchn_ports);
kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
}
--
GitLab
From f12cd06109f47c2fb4b23a45ab55404c47ef7fae Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Wed, 28 Dec 2022 17:36:03 +0800
Subject: [PATCH 0679/1167] powerpc/64s/hash: Make stress_hpt_timer_fn() static
stress_hpt_timer_fn() is only used in hash_utils.c, make it static.
Fixes: 6b34a099faa1 ("powerpc/64s/hash: add stress_hpt kernel boot option to increase hash faults")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221228093603.3166599-1-yangyingliang@huawei.com
---
arch/powerpc/mm/book3s64/hash_utils.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 80a148c57de81..44a35ed4f6860 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1012,7 +1012,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
void hpt_clear_stress(void);
static struct timer_list stress_hpt_timer;
-void stress_hpt_timer_fn(struct timer_list *timer)
+static void stress_hpt_timer_fn(struct timer_list *timer)
{
int next_cpu;
--
GitLab
From 0e678153f5be7e6c8d28835f5a678618da4b7a9c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 22 Dec 2022 21:55:10 +0100
Subject: [PATCH 0680/1167] mm/hugetlb: fix PTE marker handling in
hugetlb_change_protection()
Patch series "mm/hugetlb: uffd-wp fixes for hugetlb_change_protection()".
Playing with virtio-mem and background snapshots (using uffd-wp) on
hugetlb in QEMU, I managed to trigger a VM_BUG_ON(). Looking into the
details, hugetlb_change_protection() seems to not handle uffd-wp correctly
in all cases.
Patch #1 fixes my test case. I don't have reproducers for patch #2, as it
requires running into migration entries.
I did not yet check in detail yet if !hugetlb code requires similar care.
This patch (of 2):
There are two problematic cases when stumbling over a PTE marker in
hugetlb_change_protection():
(1) We protect an uffd-wp PTE marker a second time using uffd-wp: we will
end up in the "!huge_pte_none(pte)" case and mess up the PTE marker.
(2) We unprotect a uffd-wp PTE marker: we will similarly end up in the
"!huge_pte_none(pte)" case even though we cleared the PTE, because
the "pte" variable is stale. We'll mess up the PTE marker.
For example, if we later stumble over such a "wrongly modified" PTE marker,
we'll treat it like a present PTE that maps some garbage page.
This can, for example, be triggered by mapping a memfd backed by huge
pages, registering uffd-wp, uffd-wp'ing an unmapped page and (a)
uffd-wp'ing it a second time; or (b) uffd-unprotecting it; or (c)
unregistering uffd-wp. Then, ff we trigger fallocate(FALLOC_FL_PUNCH_HOLE)
on that file range, we will run into a VM_BUG_ON:
[ 195.039560] page:00000000ba1f2987 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x0
[ 195.039565] flags: 0x7ffffc0001000(reserved|node=0|zone=0|lastcpupid=0x1fffff)
[ 195.039568] raw: 0007ffffc0001000 ffffe742c0000008 ffffe742c0000008 0000000000000000
[ 195.039569] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
[ 195.039569] page dumped because: VM_BUG_ON_PAGE(compound && !PageHead(page))
[ 195.039573] ------------[ cut here ]------------
[ 195.039574] kernel BUG at mm/rmap.c:1346!
[ 195.039579] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[ 195.039581] CPU: 7 PID: 4777 Comm: qemu-system-x86 Not tainted 6.0.12-200.fc36.x86_64 #1
[ 195.039583] Hardware name: LENOVO 20WNS1F81N/20WNS1F81N, BIOS N35ET50W (1.50 ) 09/15/2022
[ 195.039584] RIP: 0010:page_remove_rmap+0x45b/0x550
[ 195.039588] Code: [...]
[ 195.039589] RSP: 0018:ffffbc03c3633ba8 EFLAGS: 00010292
[ 195.039591] RAX: 0000000000000040 RBX: ffffe742c0000000 RCX: 0000000000000000
[ 195.039592] RDX: 0000000000000002 RSI: ffffffff8e7aac1a RDI: 00000000ffffffff
[ 195.039592] RBP: 0000000000000001 R08: 0000000000000000 R09: ffffbc03c3633a08
[ 195.039593] R10: 0000000000000003 R11: ffffffff8f146328 R12: ffff9b04c42754b0
[ 195.039594] R13: ffffffff8fcc6328 R14: ffffbc03c3633c80 R15: ffff9b0484ab9100
[ 195.039595] FS: 00007fc7aaf68640(0000) GS:ffff9b0bbf7c0000(0000) knlGS:0000000000000000
[ 195.039596] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 195.039597] CR2: 000055d402c49110 CR3: 0000000159392003 CR4: 0000000000772ee0
[ 195.039598] PKRU: 55555554
[ 195.039599] Call Trace:
[ 195.039600] <TASK>
[ 195.039602] __unmap_hugepage_range+0x33b/0x7d0
[ 195.039605] unmap_hugepage_range+0x55/0x70
[ 195.039608] hugetlb_vmdelete_list+0x77/0xa0
[ 195.039611] hugetlbfs_fallocate+0x410/0x550
[ 195.039612] ? _raw_spin_unlock_irqrestore+0x23/0x40
[ 195.039616] vfs_fallocate+0x12e/0x360
[ 195.039618] __x64_sys_fallocate+0x40/0x70
[ 195.039620] do_syscall_64+0x58/0x80
[ 195.039623] ? syscall_exit_to_user_mode+0x17/0x40
[ 195.039624] ? do_syscall_64+0x67/0x80
[ 195.039626] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 195.039628] RIP: 0033:0x7fc7b590651f
[ 195.039653] Code: [...]
[ 195.039654] RSP: 002b:00007fc7aaf66e70 EFLAGS: 00000293 ORIG_RAX: 000000000000011d
[ 195.039655] RAX: ffffffffffffffda RBX: 0000558ef4b7f370 RCX: 00007fc7b590651f
[ 195.039656] RDX: 0000000018000000 RSI: 0000000000000003 RDI: 000000000000000c
[ 195.039657] RBP: 0000000008000000 R08: 0000000000000000 R09: 0000000000000073
[ 195.039658] R10: 0000000008000000 R11: 0000000000000293 R12: 0000000018000000
[ 195.039658] R13: 00007fb8bbe00000 R14: 000000000000000c R15: 0000000000001000
[ 195.039661] </TASK>
Fix it by not going into the "!huge_pte_none(pte)" case if we stumble over
an exclusive marker. spin_unlock() + continue would get the job done.
However, instead, make it clearer that there are no fall-through
statements: we process each case (hwpoison, migration, marker, !none,
none) and then unlock the page table to continue with the next PTE. Let's
avoid "continue" statements and use a single spin_unlock() at the end.
Link: https://lkml.kernel.org/r/20221222205511.675832-1-david@redhat.com
Link: https://lkml.kernel.org/r/20221222205511.675832-2-david@redhat.com
Fixes: 60dfaad65aa9 ("mm/hugetlb: allow uffd wr-protect none ptes")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 21 +++++++--------------
1 file changed, 7 insertions(+), 14 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index db895230ee7e4..3f0686b54701f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6658,10 +6658,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
}
pte = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(is_hugetlb_entry_migration(pte))) {
+ /* Nothing to do. */
+ } else if (unlikely(is_hugetlb_entry_migration(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
struct page *page = pfn_swap_entry_to_page(entry);
@@ -6682,18 +6680,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
set_huge_pte_at(mm, address, ptep, newpte);
pages++;
}
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(pte_marker_uffd_wp(pte))) {
- /*
- * This is changing a non-present pte into a none pte,
- * no need for huge_ptep_modify_prot_start/commit().
- */
+ } else if (unlikely(is_pte_marker(pte))) {
+ /* No other markers apply for now. */
+ WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
if (uffd_wp_resolve)
+ /* Safe to modify directly (non-present->none). */
huge_pte_clear(mm, address, ptep, psize);
- }
- if (!huge_pte_none(pte)) {
+ } else if (!huge_pte_none(pte)) {
pte_t old_pte;
unsigned int shift = huge_page_shift(hstate_vma(vma));
--
GitLab
From 44f86392bdd165da7e43d3c772aeb1e128ffd6c8 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 22 Dec 2022 21:55:11 +0100
Subject: [PATCH 0681/1167] mm/hugetlb: fix uffd-wp handling for migration
entries in hugetlb_change_protection()
We have to update the uffd-wp SWP PTE bit independent of the type of
migration entry. Currently, if we're unlucky and we want to install/clear
the uffd-wp bit just while we're migrating a read-only mapped hugetlb
page, we would miss to set/clear the uffd-wp bit.
Further, if we're processing a readable-exclusive migration entry and
neither want to set or clear the uffd-wp bit, we could currently end up
losing the uffd-wp bit. Note that the same would hold for writable
migrating entries, however, having a writable migration entry with the
uffd-wp bit set would already mean that something went wrong.
Note that the change from !is_readable_migration_entry ->
writable_migration_entry is harmless and actually cleaner, as raised by
Miaohe Lin and discussed in [1].
[1] https://lkml.kernel.org/r/90dd6a93-4500-e0de-2bf0-bf522c311b0c@huawei.com
Link: https://lkml.kernel.org/r/20221222205511.675832-3-david@redhat.com
Fixes: 60dfaad65aa9 ("mm/hugetlb: allow uffd wr-protect none ptes")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3f0686b54701f..bd7d39227344e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6662,10 +6662,9 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
} else if (unlikely(is_hugetlb_entry_migration(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
struct page *page = pfn_swap_entry_to_page(entry);
+ pte_t newpte = pte;
- if (!is_readable_migration_entry(entry)) {
- pte_t newpte;
-
+ if (is_writable_migration_entry(entry)) {
if (PageAnon(page))
entry = make_readable_exclusive_migration_entry(
swp_offset(entry));
@@ -6673,13 +6672,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
entry = make_readable_migration_entry(
swp_offset(entry));
newpte = swp_entry_to_pte(entry);
- if (uffd_wp)
- newpte = pte_swp_mkuffd_wp(newpte);
- else if (uffd_wp_resolve)
- newpte = pte_swp_clear_uffd_wp(newpte);
- set_huge_pte_at(mm, address, ptep, newpte);
pages++;
}
+
+ if (uffd_wp)
+ newpte = pte_swp_mkuffd_wp(newpte);
+ else if (uffd_wp_resolve)
+ newpte = pte_swp_clear_uffd_wp(newpte);
+ if (!pte_same(pte, newpte))
+ set_huge_pte_at(mm, address, ptep, newpte);
} else if (unlikely(is_pte_marker(pte))) {
/* No other markers apply for now. */
WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
--
GitLab
From ab0c3f1251b4670978fde0bd54161795a139b060 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Thu, 22 Dec 2022 12:41:50 -0800
Subject: [PATCH 0682/1167] mm/khugepaged: fix collapse_pte_mapped_thp() to
allow anon_vma
uprobe_write_opcode() uses collapse_pte_mapped_thp() to restore huge pmd,
when removing a breakpoint from hugepage text: vma->anon_vma is always set
in that case, so undo the prohibition. And MADV_COLLAPSE ought to be able
to collapse some page tables in a vma which happens to have anon_vma set
from CoWing elsewhere.
Is anon_vma lock required? Almost not: if any page other than expected
subpage of the non-anon huge page is found in the page table, collapse is
aborted without making any change. However, it is possible that an anon
page was CoWed from this extent in another mm or vma, in which case a
concurrent lookup might look here: so keep it away while clearing pmd (but
perhaps we shall go back to using pmd_lock() there in future).
Note that collapse_pte_mapped_thp() is exceptional in freeing a page table
without having cleared its ptes: I'm uneasy about that, and had thought
pte_clear()ing appropriate; but exclusive i_mmap lock does fix the
problem, and we would have to move the mmu_notification if clearing those
ptes.
What this fixes is not a dangerous instability. But I suggest Cc stable
because uprobes "healing" has regressed in that way, so this should follow
8d3c106e19e8 into those stable releases where it was backported (and may
want adjustment there - I'll supply backports as needed).
Link: https://lkml.kernel.org/r/b740c9fb-edba-92ba-59fb-7a5592e5dfc@google.com
Fixes: 8d3c106e19e8 ("mm/khugepaged: take the right locks for page table retraction")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: <stable@vger.kernel.org> [5.4+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/khugepaged.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 5cb401aa2b9d8..9a0135b39b197 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1460,14 +1460,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
return SCAN_VMA_CHECK;
- /*
- * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
- * that got written to. Without this, we'd have to also lock the
- * anon_vma if one exists.
- */
- if (vma->anon_vma)
- return SCAN_VMA_CHECK;
-
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
@@ -1567,8 +1559,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
}
/* step 4: remove pte entries */
+ /* we make no change to anon, but protect concurrent anon page lookup */
+ if (vma->anon_vma)
+ anon_vma_lock_write(vma->anon_vma);
+
collapse_and_free_pmd(mm, vma, haddr, pmd);
+ if (vma->anon_vma)
+ anon_vma_unlock_write(vma->anon_vma);
i_mmap_unlock_write(vma->vm_file->f_mapping);
maybe_install_pmd:
--
GitLab
From 51d3d5eb74ff53b92dcff48b30ae2ed8edd85a32 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 9 Dec 2022 09:09:12 +0100
Subject: [PATCH 0683/1167] mm/userfaultfd: enable writenotify while
userfaultfd-wp is enabled for a VMA
Currently, we don't enable writenotify when enabling userfaultfd-wp on a
shared writable mapping (for now only shmem and hugetlb). The consequence
is that vma->vm_page_prot will still include write permissions, to be set
as default for all PTEs that get remapped (e.g., mprotect(), NUMA hinting,
page migration, ...).
So far, vma->vm_page_prot is assumed to be a safe default, meaning that we
only add permissions (e.g., mkwrite) but not remove permissions (e.g.,
wrprotect). For example, when enabling softdirty tracking, we enable
writenotify. With uffd-wp on shared mappings, that changed. More details
on vma->vm_page_prot semantics were summarized in [1].
This is problematic for uffd-wp: we'd have to manually check for a uffd-wp
PTEs/PMDs and manually write-protect PTEs/PMDs, which is error prone.
Prone to such issues is any code that uses vma->vm_page_prot to set PTE
permissions: primarily pte_modify() and mk_pte().
Instead, let's enable writenotify such that PTEs/PMDs/... will be mapped
write-protected as default and we will only allow selected PTEs that are
definitely safe to be mapped without write-protection (see
can_change_pte_writable()) to be writable. In the future, we might want
to enable write-bit recovery -- e.g., can_change_pte_writable() -- at more
locations, for example, also when removing uffd-wp protection.
This fixes two known cases:
(a) remove_migration_pte() mapping uffd-wp'ed PTEs writable, resulting
in uffd-wp not triggering on write access.
(b) do_numa_page() / do_huge_pmd_numa_page() mapping uffd-wp'ed PTEs/PMDs
writable, resulting in uffd-wp not triggering on write access.
Note that do_numa_page() / do_huge_pmd_numa_page() can be reached even
without NUMA hinting (which currently doesn't seem to be applicable to
shmem), for example, by using uffd-wp with a PROT_WRITE shmem VMA. On
such a VMA, userfaultfd-wp is currently non-functional.
Note that when enabling userfaultfd-wp, there is no need to walk page
tables to enforce the new default protection for the PTEs: we know that
they cannot be uffd-wp'ed yet, because that can only happen after enabling
uffd-wp for the VMA in general.
Also note that this makes mprotect() on ranges with uffd-wp'ed PTEs not
accidentally set the write bit -- which would result in uffd-wp not
triggering on later write access. This commit makes uffd-wp on shmem
behave just like uffd-wp on anonymous memory in that regard, even though,
mixing mprotect with uffd-wp is controversial.
[1] https://lkml.kernel.org/r/92173bad-caa3-6b43-9d1e-9a471fdbc184@redhat.com
Link: https://lkml.kernel.org/r/20221209080912.7968-1-david@redhat.com
Fixes: b1f9e876862d ("mm/uffd: enable write protection for shmem & hugetlbfs")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Ives van Hoorne <ives@codesandbox.io>
Debugged-by: Peter Xu <peterx@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/userfaultfd.c | 28 ++++++++++++++++++++++------
mm/mmap.c | 4 ++++
2 files changed, 26 insertions(+), 6 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 98ac37e34e3d4..cc694846617a5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+ vma->vm_flags = flags;
+ /*
+ * For shared mappings, we want to enable writenotify while
+ * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+ * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+ */
+ if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+ vma_set_page_prot(vma);
+}
+
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
@@ -618,7 +633,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
for_each_vma(vmi, vma) {
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma,
+ vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
mmap_write_unlock(mm);
@@ -652,7 +668,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
return 0;
}
@@ -733,7 +749,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
@@ -895,7 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
prev = vma;
}
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
mmap_write_unlock(mm);
@@ -1463,7 +1479,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
@@ -1651,7 +1667,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
skip:
diff --git a/mm/mmap.c b/mm/mmap.c
index 87d929316d572..420476fcfbfca 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1524,6 +1524,10 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
return 1;
+ /* Do we need write faults for uffd-wp tracking? */
+ if (userfaultfd_wp(vma))
+ return 1;
+
/* Specialty mapping? */
if (vm_flags & VM_PFNMAP)
return 0;
--
GitLab
From 52dc031088f00e323140ece4004e70c33153c6dd Mon Sep 17 00:00:00 2001
From: Zach O'Keefe <zokeefe@google.com>
Date: Sat, 24 Dec 2022 00:20:34 -0800
Subject: [PATCH 0684/1167] mm/MADV_COLLAPSE: don't expand collapse when vm_end
is past requested end
MADV_COLLAPSE acts on one hugepage-aligned/sized region at a time, until
it has collapsed all eligible memory contained within the bounds supplied
by the user.
At the top of each hugepage iteration we (re)lock mmap_lock and
(re)validate the VMA for eligibility and update variables that might have
changed while mmap_lock was dropped. One thing that might occur is that
the VMA could be resized, and as such, we refetch vma->vm_end to make sure
we don't collapse past the end of the VMA's new end.
However, it's possible that when refetching vma->vm_end that we expand the
region acted on by MADV_COLLAPSE if vma->vm_end is greater than size+len
supplied by the user.
The consequence here is that we may attempt to collapse more memory than
requested, possibly yielding either "too much success" or "false failure"
user-visible results. An example of the former is if we MADV_COLLAPSE the
first 4MiB of a 2TiB mmap()'d file, the incorrect refetch would cause the
operation to block for much longer than anticipated as we attempt to
collapse the entire TiB region. An example of the latter is that applying
MADV_COLLPSE to a 4MiB file mapped to the start of a 6MiB VMA will
successfully collapse the first 4MiB, then incorrectly attempt to collapse
the last hugepage-aligned/sized region -- fail (since readahead/page cache
lookup will fail) -- and report a failure to the user.
I don't believe there is a kernel stability concern here as we always
(re)validate the VMA / region accordingly. Also as Hugh mentions, the
user-visible effects are: we try to collapse more memory than requested
by the user, and/or failing an operation that should have otherwise
succeeded. An example is trying to collapse a 4MiB file contained
within a 12MiB VMA.
Don't expand the acted-on region when refetching vma->vm_end.
Link: https://lkml.kernel.org/r/20221224082035.3197140-1-zokeefe@google.com
Fixes: 4d24de9425f7 ("mm: MADV_COLLAPSE: refetch vm_end after reacquiring mmap_lock")
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Reported-by: Hugh Dickins <hughd@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/khugepaged.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 9a0135b39b197..79be131333223 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2647,7 +2647,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
goto out_nolock;
}
- hend = vma->vm_end & HPAGE_PMD_MASK;
+ hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
}
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
--
GitLab
From 3de0c269adc6c2fac0bb1fb11965f0de699dc32b Mon Sep 17 00:00:00 2001
From: Zach O'Keefe <zokeefe@google.com>
Date: Sat, 24 Dec 2022 00:20:35 -0800
Subject: [PATCH 0685/1167] mm/shmem: restore SHMEM_HUGE_DENY precedence over
MADV_COLLAPSE
SHMEM_HUGE_DENY is for emergency use by the admin, to disable allocation
of shmem huge pages if, for example, a dangerous bug is found in their
usage: see "deny" in Documentation/mm/transhuge.rst. An app using
madvise(,,MADV_COLLAPSE) should not be allowed to override it: restore its
precedence over shmem_huge_force.
Restore SHMEM_HUGE_DENY precedence over MADV_COLLAPSE.
Link: https://lkml.kernel.org/r/20221224082035.3197140-2-zokeefe@google.com
Fixes: 7c6c6cc4d3a2 ("mm/shmem: add flag to enforce shmem THP in hugepage_vma_check()")
Signed-off-by: Zach O'Keefe <zokeefe@google.com>
Suggested-by: Hugh Dickins <hughd@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/shmem.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index c301487be5fb4..0005ab2c29af7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -478,12 +478,10 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode,
if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
return false;
- if (shmem_huge_force)
- return true;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- return true;
if (shmem_huge == SHMEM_HUGE_DENY)
return false;
+ if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
+ return true;
switch (SHMEM_SB(inode->i_sb)->huge) {
case SHMEM_HUGE_ALWAYS:
--
GitLab
From a1193de562f54c7c9f60ca9f2db96e50a7608de1 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 4 Jan 2023 16:02:40 -0800
Subject: [PATCH 0686/1167] mm: fix vma->anon_name memory leak for anonymous
shmem VMAs
free_anon_vma_name() is missing a check for anonymous shmem VMA which
leads to a memory leak due to refcount not being dropped. Fix this by
calling anon_vma_name_put() unconditionally. It will free vma->anon_name
whenever it's non-NULL.
Link: https://lkml.kernel.org/r/20230105000241.1450843-1-surenb@google.com
Fixes: d09e8ca6cb93 ("mm: anonymous shared memory naming")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reported-by: syzbot+91edf9178386a07d06a7@syzkaller.appspotmail.com
Cc: Hugh Dickins <hughd@google.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm_inline.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index e8ed225d8f7ca..ff3f3f23f6498 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -413,8 +413,7 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma)
* Not using anon_vma_name because it generates a warning if mmap_lock
* is not held, which might be the case here.
*/
- if (!vma->vm_file)
- anon_vma_name_put(vma->anon_name);
+ anon_vma_name_put(vma->anon_name);
}
static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
--
GitLab
From b30c14cd61025eeea2f2e8569606cd167ba9ad2d Mon Sep 17 00:00:00 2001
From: James Houghton <jthoughton@google.com>
Date: Wed, 4 Jan 2023 23:19:10 +0000
Subject: [PATCH 0687/1167] hugetlb: unshare some PMDs when splitting VMAs
PMD sharing can only be done in PUD_SIZE-aligned pieces of VMAs; however,
it is possible that HugeTLB VMAs are split without unsharing the PMDs
first.
Without this fix, it is possible to hit the uffd-wp-related WARN_ON_ONCE
in hugetlb_change_protection [1]. The key there is that
hugetlb_unshare_all_pmds will not attempt to unshare PMDs in
non-PUD_SIZE-aligned sections of the VMA.
It might seem ideal to unshare in hugetlb_vm_op_open, but we need to
unshare in both the new and old VMAs, so unsharing in hugetlb_vm_op_split
seems natural.
[1]: https://lore.kernel.org/linux-mm/CADrL8HVeOkj0QH5VZZbRzybNE8CG-tEGFshnA+bG9nMgcWtBSg@mail.gmail.com/
Link: https://lkml.kernel.org/r/20230104231910.1464197-1-jthoughton@google.com
Fixes: 6dfeaff93be1 ("hugetlb/userfaultfd: unshare all pmds for hugetlbfs when register wp")
Signed-off-by: James Houghton <jthoughton@google.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 44 +++++++++++++++++++++++++++++++++++---------
1 file changed, 35 insertions(+), 9 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bd7d39227344e..2ce912c915ebc 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta);
static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
@@ -4834,6 +4836,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
{
if (addr & ~(huge_page_mask(hstate_vma(vma))))
return -EINVAL;
+
+ /*
+ * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+ * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+ * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+ */
+ if (addr & ~PUD_MASK) {
+ /*
+ * hugetlb_vm_op_split is called right before we attempt to
+ * split the VMA. We will need to unshare PMDs in the old and
+ * new VMAs, so let's unshare before we split.
+ */
+ unsigned long floor = addr & PUD_MASK;
+ unsigned long ceil = floor + PUD_SIZE;
+
+ if (floor >= vma->vm_start && ceil <= vma->vm_end)
+ hugetlb_unshare_pmds(vma, floor, ceil);
+ }
+
return 0;
}
@@ -7322,26 +7343,21 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
}
}
-/*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
- */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end)
{
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
- unsigned long address, start, end;
+ unsigned long address;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & VM_MAYSHARE))
return;
- start = ALIGN(vma->vm_start, PUD_SIZE);
- end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
if (start >= end)
return;
@@ -7373,6 +7389,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
mmu_notifier_invalidate_range_end(&range);
}
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+ hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
+ ALIGN_DOWN(vma->vm_end, PUD_SIZE));
+}
+
#ifdef CONFIG_CMA
static bool cma_reserve_called __initdata;
--
GitLab
From fed15f1345dc8a7fc8baa81e8b55c3ba010d7f4b Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Wed, 4 Jan 2023 17:52:05 -0500
Subject: [PATCH 0688/1167] mm/hugetlb: pre-allocate pgtable pages for uffd
wr-protects
Userfaultfd-wp uses pte markers to mark wr-protected pages for both shmem
and hugetlb. Shmem has pre-allocation ready for markers, but hugetlb path
was overlooked.
Doing so by calling huge_pte_alloc() if the initial pgtable walk fails to
find the huge ptep. It's possible that huge_pte_alloc() can fail with
high memory pressure, in that case stop the loop immediately and fail
silently. This is not the most ideal solution but it matches with what we
do with shmem meanwhile it avoids the splat in dmesg.
Link: https://lkml.kernel.org/r/20230104225207.1066932-2-peterx@redhat.com
Fixes: 60dfaad65aa9 ("mm/hugetlb: allow uffd wr-protect none ptes")
Signed-off-by: Peter Xu <peterx@redhat.com>
Reported-by: James Houghton <jthoughton@google.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: James Houghton <jthoughton@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: <stable@vger.kernel.org> [5.19+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2ce912c915ebc..f96794be71d50 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6660,8 +6660,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
spinlock_t *ptl;
ptep = huge_pte_offset(mm, address, psize);
if (!ptep) {
- address |= last_addr_mask;
- continue;
+ if (!uffd_wp) {
+ address |= last_addr_mask;
+ continue;
+ }
+ /*
+ * Userfaultfd wr-protect requires pgtable
+ * pre-allocations to install pte markers.
+ */
+ ptep = huge_pte_alloc(mm, vma, address, psize);
+ if (!ptep)
+ break;
}
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, address, ptep)) {
--
GitLab
From 1beb8ae302a01fb487787f5a4fb97cf5338a86c1 Mon Sep 17 00:00:00 2001
From: Nhat Pham <nphamcs@gmail.com>
Date: Fri, 6 Jan 2023 14:00:16 -0800
Subject: [PATCH 0689/1167] Docs/admin-guide/mm/zswap: remove zsmalloc's lack
of writeback warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Writeback has been implemented for zsmalloc, so this warning no longer
holds.
Link: https://lkml.kernel.org/r/20230106220016.172303-1-nphamcs@gmail.com
Fixes: 9997bc017549a ("zsmalloc: implement writeback mechanism for zsmalloc")
Suggested-by: Thomas Weißschuh <linux@weissschuh.net>
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
Documentation/admin-guide/mm/zswap.rst | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index f67de481c7f60..6dd74a18268ba 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -70,9 +70,7 @@ e.g. ``zswap.zpool=zbud``. It can also be changed at runtime using the sysfs
The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
means the compression ratio will always be 2:1 or worse (because of half-full
zbud pages). The zsmalloc type zpool has a more complex compressed page
-storage method, and it can achieve greater storage densities. However,
-zsmalloc does not implement compressed page eviction, so once zswap fills it
-cannot evict the oldest page, it can only reject new pages.
+storage method, and it can achieve greater storage densities.
When a swap page is passed from frontswap to zswap, zswap maintains a mapping
of the swap entry, a combination of the swap type and swap offset, to the zpool
--
GitLab
From 7633355e5c7f29c049a9048e461427d1d8ed3051 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Date: Thu, 5 Jan 2023 14:53:56 +0900
Subject: [PATCH 0690/1167] nilfs2: fix general protection fault in
nilfs_btree_insert()
If nilfs2 reads a corrupted disk image and tries to reads a b-tree node
block by calling __nilfs_btree_get_block() against an invalid virtual
block address, it returns -ENOENT because conversion of the virtual block
address to a disk block address fails. However, this return value is the
same as the internal code that b-tree lookup routines return to indicate
that the block being searched does not exist, so functions that operate on
that b-tree may misbehave.
When nilfs_btree_insert() receives this spurious 'not found' code from
nilfs_btree_do_lookup(), it misunderstands that the 'not found' check was
successful and continues the insert operation using incomplete lookup path
data, causing the following crash:
general protection fault, probably for non-canonical address
0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f]
...
RIP: 0010:nilfs_btree_get_nonroot_node fs/nilfs2/btree.c:418 [inline]
RIP: 0010:nilfs_btree_prepare_insert fs/nilfs2/btree.c:1077 [inline]
RIP: 0010:nilfs_btree_insert+0x6d3/0x1c10 fs/nilfs2/btree.c:1238
Code: bc 24 80 00 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 28 00 74 08 4c 89
ff e8 4b 02 92 fe 4d 8b 3f 49 83 c7 28 4c 89 f8 48 c1 e8 03 <42> 80 3c
28 00 74 08 4c 89 ff e8 2e 02 92 fe 4d 8b 3f 49 83 c7 02
...
Call Trace:
<TASK>
nilfs_bmap_do_insert fs/nilfs2/bmap.c:121 [inline]
nilfs_bmap_insert+0x20d/0x360 fs/nilfs2/bmap.c:147
nilfs_get_block+0x414/0x8d0 fs/nilfs2/inode.c:101
__block_write_begin_int+0x54c/0x1a80 fs/buffer.c:1991
__block_write_begin fs/buffer.c:2041 [inline]
block_write_begin+0x93/0x1e0 fs/buffer.c:2102
nilfs_write_begin+0x9c/0x110 fs/nilfs2/inode.c:261
generic_perform_write+0x2e4/0x5e0 mm/filemap.c:3772
__generic_file_write_iter+0x176/0x400 mm/filemap.c:3900
generic_file_write_iter+0xab/0x310 mm/filemap.c:3932
call_write_iter include/linux/fs.h:2186 [inline]
new_sync_write fs/read_write.c:491 [inline]
vfs_write+0x7dc/0xc50 fs/read_write.c:584
ksys_write+0x177/0x2a0 fs/read_write.c:637
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
...
</TASK>
This patch fixes the root cause of this problem by replacing the error
code that __nilfs_btree_get_block() returns on block address conversion
failure from -ENOENT to another internal code -EINVAL which means that the
b-tree metadata is corrupted.
By returning -EINVAL, it propagates without glitches, and for all relevant
b-tree operations, functions in the upper bmap layer output an error
message indicating corrupted b-tree metadata via
nilfs_bmap_convert_error(), and code -EIO will be eventually returned as
it should be.
Link: https://lkml.kernel.org/r/000000000000bd89e205f0e38355@google.com
Link: https://lkml.kernel.org/r/20230105055356.8811-1-konishi.ryusuke@gmail.com
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Reported-by: syzbot+ede796cecd5296353515@syzkaller.appspotmail.com
Tested-by: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
fs/nilfs2/btree.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b9d15c3df3cc1..40ce92a332fe7 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
&submit_ptr);
if (ret) {
- if (ret != -EEXIST)
- return ret;
- goto out_check;
+ if (likely(ret == -EEXIST))
+ goto out_check;
+ if (ret == -ENOENT) {
+ /*
+ * Block address translation failed due to invalid
+ * value of 'ptr'. In this case, return internal code
+ * -EINVAL (broken bmap) to notify bmap layer of fatal
+ * metadata corruption.
+ */
+ ret = -EINVAL;
+ }
+ return ret;
}
if (ra) {
--
GitLab
From 0de4a7f5ba5744d1de5ce0b076bb73a86530c60c Mon Sep 17 00:00:00 2001
From: Andrey Konovalov <andreyknvl@google.com>
Date: Wed, 4 Jan 2023 02:09:33 +0100
Subject: [PATCH 0691/1167] kasan: mark kasan_kunit_executing as static
Mark kasan_kunit_executing as static, as it is only used within
mm/kasan/report.c.
Link: https://lkml.kernel.org/r/f64778a4683b16a73bba72576f73bf4a2b45a82f.1672794398.git.andreyknvl@google.com
Fixes: c8c7016f50c8 ("kasan: fail non-kasan KUnit tests on KASAN reports")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Marco Elver <elver@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/kasan/report.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 1d02757e90a32..22598b20c7b75 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot);
* Whether the KASAN KUnit test suite is currently being executed.
* Updated in kasan_test.c.
*/
-bool kasan_kunit_executing;
+static bool kasan_kunit_executing;
void kasan_kunit_test_suite_start(void)
{
--
GitLab
From d09dce1fff8a9da10144e878ef4bbf90c65559e5 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 2 Jan 2023 13:16:14 -0800
Subject: [PATCH 0692/1167] lib/win_minmax: use /* notation for regular
comments
Don't use kernel-doc "/**" notation for non-kernel-doc comments.
Prevents a kernel-doc warning:
lib/win_minmax.c:31: warning: expecting prototype for lib/minmax.c(). Prototype was for minmax_subwin_update() instead
Link: https://lkml.kernel.org/r/20230102211614.26343-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
lib/win_minmax.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/win_minmax.c b/lib/win_minmax.c
index 6bdc1cd15f761..ec10506834b62 100644
--- a/lib/win_minmax.c
+++ b/lib/win_minmax.c
@@ -1,5 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* lib/minmax.c: windowed min/max tracker
*
* Kathleen Nichols' algorithm for tracking the minimum (or maximum)
--
GitLab
From 0411d6ee50e3b74a793848e4f41f45860163f5cc Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 6 Jan 2023 20:33:31 +0000
Subject: [PATCH 0693/1167] include/linux/mm: fix release_pages_arg kernel doc
comment
Commit 449c796768c9 ("mm: teach release_pages() to take an array of
encoded page pointers too") added the kernel doc comment for
release_pages() on top of 'union release_pages_arg', so making 'make
htmldocs' complains as below:
./include/linux/mm.h:1268: warning: cannot understand function prototype: 'typedef union '
The kernel doc comment for the function is already on top of the
function's definition in mm/swap.c, and the new comment is actually not
for the function but indeed release_pages_arg. Fixing the comment to
reflect the intent would be one option. But, kernel doc cannot parse
the union as below due to the attribute.
./include/linux/mm.h:1272: error: Cannot parse struct or union!
Modify the comment to reflect the intent but do not mark it as a kernel
doc comment.
Link: https://lkml.kernel.org/r/20230106203331.127532-1-sj@kernel.org
Fixes: 449c796768c9 ("mm: teach release_pages() to take an array of encoded page pointers too")
Signed-off-by: SeongJae Park <sj@kernel.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f3f196e4d66d6..8f857163ac89c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1270,10 +1270,10 @@ static inline void folio_put_refs(struct folio *folio, int refs)
__folio_put(folio);
}
-/**
- * release_pages - release an array of pages or folios
+/*
+ * union release_pages_arg - an array of pages or folios
*
- * This just releases a simple array of multiple pages, and
+ * release_pages() releases a simple array of multiple pages, and
* accepts various different forms of said page array: either
* a regular old boring array of pages, an array of folios, or
* an array of encoded page pointers.
--
GitLab
From 8651a137e62ebfde3df95cbb1ca055d013ec5b9e Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lstoakes@gmail.com>
Date: Sat, 7 Jan 2023 00:00:05 +0000
Subject: [PATCH 0694/1167] mm: update mmap_sem comments to refer to mmap_lock
The rename from mm->mmap_sem to mm->mmap_lock was performed in commit
da1c55f1b272 ("mmap locking API: rename mmap_sem to mmap_lock") and commit
c1e8d7c6a7a6 ("map locking API: convert mmap_sem comments"), however some
incorrect comments remain.
This patch simply corrects those comments which are obviously incorrect
within mm itself.
Link: https://lkml.kernel.org/r/33fba04389ab63fc4980e7ba5442f521df6dc657.1673048927.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/mm_types.h | 2 +-
include/linux/page_ref.h | 2 +-
mm/hugetlb.c | 4 ++--
mm/madvise.c | 2 +-
mm/mmap.c | 4 ++--
5 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3b8475007734d..9757067c30537 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -581,7 +581,7 @@ struct vm_area_struct {
/*
* For private and shared anonymous mappings, a pointer to a null
* terminated string containing the name given to the vma, or NULL if
- * unnamed. Serialized by mmap_sem. Use anon_vma_name to access.
+ * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
*/
struct anon_vma_name *anon_name;
#endif
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 2e677e6ad09fc..d7c2d33baa7f8 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -301,7 +301,7 @@ static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
*
* You can also use this function if you're holding a lock that prevents
* pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_sem or page table lock for page tables. In this case,
+ * or the mmap_lock or page table lock for page tables. In this case,
* it will always succeed, and you could have used a plain folio_get(),
* but it's sometimes more convenient to have a common function called
* from both locked and RCU-protected contexts.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f96794be71d50..7fcdb98c9e689 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1183,7 +1183,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma)
/*
* Reset and decrement one ref on hugepage private reservation.
- * Called with mm->mmap_sem writer semaphore held.
+ * Called with mm->mmap_lock writer semaphore held.
* This function should be only used by move_vma() and operate on
* same sized vma. It should never come here with last ref on the
* reservation.
@@ -5152,7 +5152,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
/*
* We don't have to worry about the ordering of src and dst ptlocks
- * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock.
+ * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
*/
if (src_ptl != dst_ptl)
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
diff --git a/mm/madvise.c b/mm/madvise.c
index a56a6d17e201e..b6ea204d4e23b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
#endif /* CONFIG_ANON_VMA_NAME */
/*
* Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary. Must be called with mmap_sem held for writing;
+ * necessary. Must be called with mmap_lock held for writing;
* Caller should ensure anon_name stability by raising its refcount even when
* anon_name belongs to a valid vma because this function might free that vma.
*/
diff --git a/mm/mmap.c b/mm/mmap.c
index 420476fcfbfca..425a9349e6108 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2294,7 +2294,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma,
* @start: The aligned start address to munmap.
* @end: The aligned end address to munmap.
* @uf: The userfaultfd list_head
- * @downgrade: Set to true to attempt a write downgrade of the mmap_sem
+ * @downgrade: Set to true to attempt a write downgrade of the mmap_lock
*
* If @downgrade is true, check return code for potential release of the lock.
*/
@@ -2469,7 +2469,7 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
* @len: The length of the range to munmap
* @uf: The userfaultfd list_head
* @downgrade: set to true if the user wants to attempt to write_downgrade the
- * mmap_sem
+ * mmap_lock
*
* This function takes a @mas that is either pointing to the previous VMA or set
* to MA_START and sets it up to remove the mapping(s). The @len will be
--
GitLab
From 5316a017d093f644675a56523bcf5787ba8f4fef Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Fri, 6 Jan 2023 22:30:14 +0300
Subject: [PATCH 0695/1167] proc: fix PIE proc-empty-vm, proc-pid-vm tests
vsyscall detection code uses direct call to the beginning of
the vsyscall page:
asm ("call %P0" :: "i" (0xffffffffff600000))
It generates "call rel32" instruction but it is not relocated if binary
is PIE, so binary segfaults into random userspace address and vsyscall
page status is detected incorrectly.
Do more direct:
asm ("call *%rax")
which doesn't do need any relocaltions.
Mark g_vsyscall as volatile for a good measure, I didn't find instruction
setting it to 0. Now the code is obviously correct:
xor eax, eax
mov rdi, rbp
mov rsi, rbp
mov DWORD PTR [rip+0x2d15], eax # g_vsyscall = 0
mov rax, 0xffffffffff600000
call rax
mov DWORD PTR [rip+0x2d02], 1 # g_vsyscall = 1
mov eax, DWORD PTR ds:0xffffffffff600000
mov DWORD PTR [rip+0x2cf1], 2 # g_vsyscall = 2
mov edi, [rip+0x2ceb] # exit(g_vsyscall)
call exit
Note: fixed proc-empty-vm test oopses 5.19.0-28-generic kernel
but this is separate story.
Link: https://lkml.kernel.org/r/Y7h2xvzKLg36DSq8@p183
Fixes: 5bc73bb3451b9 ("proc: test how it holds up with mapping'less process")
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Reported-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Tested-by: Mirsad Goran Todorovac <mirsad.todorovac@alu.unizg.hr>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
tools/testing/selftests/proc/proc-empty-vm.c | 12 +++++++-----
tools/testing/selftests/proc/proc-pid-vm.c | 9 +++++----
2 files changed, 12 insertions(+), 9 deletions(-)
diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c
index d95b1cb43d9d0..7588428b8fcd7 100644
--- a/tools/testing/selftests/proc/proc-empty-vm.c
+++ b/tools/testing/selftests/proc/proc-empty-vm.c
@@ -25,6 +25,7 @@
#undef NDEBUG
#include <assert.h>
#include <errno.h>
+#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
@@ -41,7 +42,7 @@
* 1: vsyscall VMA is --xp vsyscall=xonly
* 2: vsyscall VMA is r-xp vsyscall=emulate
*/
-static int g_vsyscall;
+static volatile int g_vsyscall;
static const char *g_proc_pid_maps_vsyscall;
static const char *g_proc_pid_smaps_vsyscall;
@@ -147,11 +148,12 @@ static void vsyscall(void)
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 69551bfa215c4..cacbd2a4aec91 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -257,11 +257,12 @@ static void vsyscall(void)
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
--
GitLab
From bf61acbed8a8b38949a247333ee253899acdc35d Mon Sep 17 00:00:00 2001
From: Robert Foss <robert.foss@linaro.org>
Date: Fri, 6 Jan 2023 16:21:51 +0100
Subject: [PATCH 0696/1167] MAINTAINERS: update Robert Foss' email address
Update the email address for Robert's maintainer entries and fill in
.mailmap accordingly.
Link: https://lkml.kernel.org/r/20230106152151.115648-1-robert.foss@linaro.org
Signed-off-by: Robert Foss <rfoss@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Colin Ian King <colin.i.king@gmail.com>
Cc: Kalle Valo <kvalo@kernel.org>
Cc: Kirill Tkhai <tkhai@ya.ru>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Vasily Averin <vasily.averin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
.mailmap | 1 +
MAINTAINERS | 6 +++---
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/.mailmap b/.mailmap
index ccba4cf0d8938..7a882bc7f376f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -371,6 +371,7 @@ Rémi Denis-Courmont <rdenis@simphalempin.com>
Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
+Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
diff --git a/MAINTAINERS b/MAINTAINERS
index a36df9ed283d3..320dc090d57ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6948,7 +6948,7 @@ F: drivers/gpu/drm/atmel-hlcdc/
DRM DRIVERS FOR BRIDGE CHIPS
M: Andrzej Hajda <andrzej.hajda@intel.com>
M: Neil Armstrong <neil.armstrong@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
R: Jonas Karlman <jonas@kwiboo.se>
R: Jernej Skrabec <jernej.skrabec@gmail.com>
@@ -17237,7 +17237,7 @@ F: Documentation/devicetree/bindings/net/qcom,bam-dmux.yaml
F: drivers/net/wwan/qcom_bam_dmux.c
QUALCOMM CAMERA SUBSYSTEM DRIVER
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
M: Todor Tomov <todor.too@gmail.com>
L: linux-media@vger.kernel.org
S: Maintained
@@ -17317,7 +17317,7 @@ F: drivers/dma/qcom/hidma*
QUALCOMM I2C CCI DRIVER
M: Loic Poulain <loic.poulain@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
L: linux-i2c@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Maintained
--
GitLab
From 7f31cced5724e6d414fe750aa1cd7e7b578ec22f Mon Sep 17 00:00:00 2001
From: Liam Howlett <liam.howlett@oracle.com>
Date: Mon, 9 Jan 2023 20:55:21 +0000
Subject: [PATCH 0697/1167] nommu: fix memory leak in do_mmap() error path
The preallocation of the maple tree nodes may leak if the error path to
"error_just_free" is taken. Fix this by moving the freeing of the maple
tree nodes to a shared location for all error paths.
Link: https://lkml.kernel.org/r/20230109205507.955577-1-Liam.Howlett@oracle.com
Fixes: 8220543df148 ("nommu: remove uses of VMA linked list")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/nommu.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/nommu.c b/mm/nommu.c
index 214c70e1d0594..c8252f01d5dbb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1240,6 +1240,7 @@ unsigned long do_mmap(struct file *file,
error_just_free:
up_write(&nommu_region_sem);
error:
+ mas_destroy(&mas);
if (region->vm_file)
fput(region->vm_file);
kmem_cache_free(vm_region_jar, region);
@@ -1250,7 +1251,6 @@ unsigned long do_mmap(struct file *file,
sharing_violation:
up_write(&nommu_region_sem);
- mas_destroy(&mas);
pr_warn("Attempt to share mismatched mappings\n");
ret = -EINVAL;
goto error;
--
GitLab
From 80be727ec87225797771a39f3e6801baf291faaf Mon Sep 17 00:00:00 2001
From: Liam Howlett <liam.howlett@oracle.com>
Date: Mon, 9 Jan 2023 20:57:21 +0000
Subject: [PATCH 0698/1167] nommu: fix do_munmap() error path
When removing a VMA from the tree fails due to no memory, do not free the
VMA since a reference still exists.
Link: https://lkml.kernel.org/r/20230109205708.956103-1-Liam.Howlett@oracle.com
Fixes: 8220543df148 ("nommu: remove uses of VMA linked list")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/nommu.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/nommu.c b/mm/nommu.c
index c8252f01d5dbb..844af5be76400 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1509,7 +1509,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list
erase_whole_vma:
if (delete_vma_from_mm(vma))
ret = -ENOMEM;
- delete_vma(mm, vma);
+ else
+ delete_vma(mm, vma);
return ret;
}
--
GitLab
From fd9edbdbdcde6b489ce59f326755ef16a2ffadd7 Mon Sep 17 00:00:00 2001
From: Liam Howlett <liam.howlett@oracle.com>
Date: Mon, 9 Jan 2023 20:58:20 +0000
Subject: [PATCH 0699/1167] nommu: fix split_vma() map_count error
During the maple tree conversion of nommu, an error in counting the VMAs
was introduced by counting the existing VMA again. The counting used to
be decremented by one and incremented by two, but now it only increments
by two. Fix the counting error by moving the increment outside the
setup_vma_to_mm() function to the callers.
Link: https://lkml.kernel.org/r/20230109205809.956325-1-Liam.Howlett@oracle.com
Fixes: 8220543df148 ("nommu: remove uses of VMA linked list")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/nommu.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/mm/nommu.c b/mm/nommu.c
index 844af5be76400..5b83938ecb67c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -559,7 +559,6 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm)
{
- mm->map_count++;
vma->vm_mm = mm;
/* add the VMA to the mapping */
@@ -587,6 +586,7 @@ static void mas_add_vma_to_mm(struct ma_state *mas, struct mm_struct *mm,
BUG_ON(!vma->vm_region);
setup_vma_to_mm(vma, mm);
+ mm->map_count++;
/* add the VMA to the tree */
vma_mas_store(vma, mas);
@@ -1347,6 +1347,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
if (vma->vm_file)
return -ENOMEM;
+ mm = vma->vm_mm;
if (mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
@@ -1398,6 +1399,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
mas_set_range(&mas, vma->vm_start, vma->vm_end - 1);
mas_store(&mas, vma);
vma_mas_store(new, &mas);
+ mm->map_count++;
return 0;
err_mas_preallocate:
--
GitLab
From 19fa92fb72f8bc542f1673862058f3b078114004 Mon Sep 17 00:00:00 2001
From: Lizzy Fleckenstein <eliasfleckenstein@web.de>
Date: Mon, 9 Jan 2023 21:18:37 +0100
Subject: [PATCH 0700/1167] init/Kconfig: fix typo (usafe -> unsafe)
Fix the help text for the PRINTK_SAFE_LOG_BUF_SHIFT setting.
Link: https://lkml.kernel.org/r/20230109201837.23873-1-eliasfleckenstein@web.de
Signed-off-by: Lizzy Fleckenstein <eliasfleckenstein@web.de>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
init/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/init/Kconfig b/init/Kconfig
index 7e5c3ddc341de..57c8d224ea4cf 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -776,7 +776,7 @@ config PRINTK_SAFE_LOG_BUF_SHIFT
depends on PRINTK
help
Select the size of an alternate printk per-CPU buffer where messages
- printed from usafe contexts are temporary stored. One example would
+ printed from unsafe contexts are temporary stored. One example would
be NMI messages, another one - printk recursion. The messages are
copied to the main log buffer in a safe context to avoid a deadlock.
The value defines the size as a power of 2.
--
GitLab
From e6cf91b7b47ff82b624bdfe2fdcde32bb52e71dd Mon Sep 17 00:00:00 2001
From: Xingyuan Mo <hdthky0@gmail.com>
Date: Thu, 12 Jan 2023 00:24:53 +0800
Subject: [PATCH 0701/1167] NFSD: fix use-after-free in nfsd4_ssc_setup_dul()
If signal_pending() returns true, schedule_timeout() will not be executed,
causing the waiting task to remain in the wait queue.
Fixed by adding a call to finish_wait(), which ensures that the waiting
task will always be removed from the wait queue.
Fixes: f4e44b393389 ("NFSD: delay unmount source's export after inter-server copy completed.")
Signed-off-by: Xingyuan Mo <hdthky0@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs4proc.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9b81d012666e2..f189ba7995f5a 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1318,6 +1318,7 @@ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
/* allow 20secs for mount/unmount for now - revisit */
if (signal_pending(current) ||
(schedule_timeout(20*HZ) == 0)) {
+ finish_wait(&nn->nfsd_ssc_waitq, &wait);
kfree(work);
return nfserr_eagain;
}
--
GitLab
From f385f7d244134246f984975ed34cd75f77de479f Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Wed, 11 Jan 2023 12:17:09 -0800
Subject: [PATCH 0702/1167] NFSD: register/unregister of nfsd-client shrinker
at nfsd startup/shutdown time
Currently the nfsd-client shrinker is registered and unregistered at
the time the nfsd module is loaded and unloaded. The problem with this
is the shrinker is being registered before all of the relevant fields
in nfsd_net are initialized when nfsd is started. This can lead to an
oops when memory is low and the shrinker is called while nfsd is not
running.
This patch moves the register/unregister of nfsd-client shrinker from
module load/unload time to nfsd startup/shutdown time.
Fixes: 44df6f439a17 ("NFSD: add delegation reaper to react to low memory condition")
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/nfs4state.c | 22 +++++++++++-----------
fs/nfsd/nfsctl.c | 7 +------
fs/nfsd/nfsd.h | 6 ++----
3 files changed, 14 insertions(+), 21 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 313f666d53578..db41358bd0d30 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4421,7 +4421,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc)
return SHRINK_STOP;
}
-int
+void
nfsd4_init_leases_net(struct nfsd_net *nn)
{
struct sysinfo si;
@@ -4443,16 +4443,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn)
nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
atomic_set(&nn->nfsd_courtesy_clients, 0);
- nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
- nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
- nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
- return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
-}
-
-void
-nfsd4_leases_net_shutdown(struct nfsd_net *nn)
-{
- unregister_shrinker(&nn->nfsd_client_shrinker);
}
static void init_nfs4_replay(struct nfs4_replay *rp)
@@ -8069,8 +8059,17 @@ static int nfs4_state_create_net(struct net *net)
INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+
+ if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"))
+ goto err_shrinker;
return 0;
+err_shrinker:
+ put_net(net);
+ kfree(nn->sessionid_hashtbl);
err_sessionid:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
@@ -8163,6 +8162,7 @@ nfs4_state_shutdown_net(struct net *net)
struct list_head *pos, *next, reaplist;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ unregister_shrinker(&nn->nfsd_client_shrinker);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index d1e581a60480c..c2577ee7ffb22 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1457,9 +1457,7 @@ static __net_init int nfsd_init_net(struct net *net)
goto out_idmap_error;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
- retval = nfsd4_init_leases_net(nn);
- if (retval)
- goto out_drc_error;
+ nfsd4_init_leases_net(nn);
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_cache_error;
@@ -1469,8 +1467,6 @@ static __net_init int nfsd_init_net(struct net *net)
return 0;
out_cache_error:
- nfsd4_leases_net_shutdown(nn);
-out_drc_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
nfsd_export_shutdown(net);
@@ -1486,7 +1482,6 @@ static __net_exit void nfsd_exit_net(struct net *net)
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
- nfsd4_leases_net_shutdown(nn);
}
static struct pernet_operations nfsd_net_ops = {
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 93b42ef9ed91b..fa0144a742678 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void);
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
-extern int nfsd4_init_leases_net(struct nfsd_net *nn);
-extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
@@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry)
return 0;
}
-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
-static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
--
GitLab
From ae9f29fdfd827ad06c1ae8155c042245a9d00757 Mon Sep 17 00:00:00 2001
From: Jie Wang <wangjie125@huawei.com>
Date: Tue, 10 Jan 2023 19:53:59 +0800
Subject: [PATCH 0703/1167] net: hns3: fix wrong use of rss size during VF rss
config
Currently, it used old rss size to get current tc mode. As a result, the
rss size is updated, but the tc mode is still configured based on the old
rss size.
So this patch fixes it by using the new rss size in both process.
Fixes: 93969dc14fcd ("net: hns3: refactor VF rss init APIs with new common rss init APIs")
Signed-off-by: Jie Wang <wangjie125@huawei.com>
Signed-off-by: Hao Lan <lanhao@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230110115359.10163-1-lanhao@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 081bd2c3f2891..e84e5be8e59ed 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -3130,7 +3130,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num,
hclgevf_update_rss_size(handle, new_tqps_num);
- hclge_comm_get_rss_tc_info(cur_rss_size, hdev->hw_tc_map,
+ hclge_comm_get_rss_tc_info(kinfo->rss_size, hdev->hw_tc_map,
tc_offset, tc_valid, tc_size);
ret = hclge_comm_set_rss_tc_mode(&hdev->hw.hw, tc_offset,
tc_valid, tc_size);
--
GitLab
From 97f5e03a4a27d27ee4fed0cdb1658c81cf2784db Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Jan 2023 20:25:47 -0800
Subject: [PATCH 0704/1167] bnxt: make sure we return pages to the pool
Before the commit under Fixes the page would have been released
from the pool before the napi_alloc_skb() call, so normal page
freeing was fine (released page == no longer in the pool).
After the change we just mark the page for recycling so it's still
in the pool if the skb alloc fails, we need to recycle.
Same commit added the same bug in the new bnxt_rx_multi_page_skb().
Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff")
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
Link: https://lore.kernel.org/r/20230111042547.987749-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 16ce7a90610c5..240a7e8a76528 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -993,7 +993,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp,
DMA_ATTR_WEAK_ORDERING);
skb = build_skb(page_address(page), PAGE_SIZE);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
skb_mark_for_recycle(skb);
@@ -1031,7 +1031,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
--
GitLab
From 037b48057e8b485a8d72f808122796aeadbbee32 Mon Sep 17 00:00:00 2001
From: Xingui Yang <yangxingui@huawei.com>
Date: Wed, 4 Jan 2023 12:03:19 +0800
Subject: [PATCH 0705/1167] scsi: hisi_sas: Use abort task set to reset SAS
disks when discovered
Currently clear task set is used to abort all commands remaining in the
disk when the SAS disk is discovered, and if the disk is discovered by two
initiators, other I_T nexuses are also affected. So use abort task set
instead and take effect only on the specified I_T nexus.
Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Link: https://lore.kernel.org/r/1672805000-141102-2-git-send-email-chenxiang66@hisilicon.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index e9c2d306ed873..5e06b7add125b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -704,7 +704,7 @@ static int hisi_sas_init_device(struct domain_device *device)
int_to_scsilun(0, &lun);
while (retry-- > 0) {
- rc = sas_clear_task_set(device, lun.scsi_lun);
+ rc = sas_abort_task_set(device, lun.scsi_lun);
if (rc == TMF_RESP_FUNC_COMPLETE) {
hisi_sas_release_task(hisi_hba, device);
break;
--
GitLab
From f58c89700630da6554b24fd3df293a24874c10c1 Mon Sep 17 00:00:00 2001
From: Yihang Li <liyihang9@huawei.com>
Date: Wed, 4 Jan 2023 12:03:20 +0800
Subject: [PATCH 0706/1167] scsi: hisi_sas: Set a port invalid only if there
are no devices attached when refreshing port id
Currently the driver sets the port invalid if one phy in the port is not
enabled, which may cause issues in expander situation. In directly attached
situation, if phy up doesn't occur in time when refreshing port id, the
port is incorrectly set to invalid which will also cause disk lost.
Therefore set a port invalid only if there are no devices attached to the
port.
Signed-off-by: Yihang Li <liyihang9@huawei.com>
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Link: https://lore.kernel.org/r/1672805000-141102-3-git-send-email-chenxiang66@hisilicon.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/hisi_sas/hisi_sas_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 5e06b7add125b..8c038ccf1c095 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1316,7 +1316,7 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba)
device->linkrate = phy->sas_phy.linkrate;
hisi_hba->hw->setup_itct(hisi_hba, sas_dev);
- } else
+ } else if (!port->port_attached)
port->id = 0xff;
}
}
--
GitLab
From ae9dcb91c6069e20b3b9505d79cbc89fd6e086f5 Mon Sep 17 00:00:00 2001
From: Noor Azura Ahmad Tarmizi <noor.azura.ahmad.tarmizi@intel.com>
Date: Wed, 11 Jan 2023 13:02:00 +0800
Subject: [PATCH 0707/1167] net: stmmac: add aux timestamps fifo clearance wait
Add timeout polling wait for auxiliary timestamps snapshot FIFO clear bit
(ATSFC) to clear. This is to ensure no residue fifo value is being read
erroneously.
Fixes: f4da56529da6 ("net: stmmac: Add support for external trigger timestamping")
Cc: <stable@vger.kernel.org> # 5.10.x
Signed-off-by: Noor Azura Ahmad Tarmizi <noor.azura.ahmad.tarmizi@intel.com>
Link: https://lore.kernel.org/r/20230111050200.2130-1-noor.azura.ahmad.tarmizi@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index fc06ddeac0d53..b4388ca8d2116 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -210,7 +210,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp,
}
writel(acr_value, ptpaddr + PTP_ACR);
mutex_unlock(&priv->aux_ts_lock);
- ret = 0;
+ /* wait for auxts fifo clear to finish */
+ ret = readl_poll_timeout(ptpaddr + PTP_ACR, acr_value,
+ !(acr_value & PTP_ACR_ATSFC),
+ 10, 10000);
break;
default:
--
GitLab
From 26ce6ec364f18d2915923bc05784084e54a5c4cc Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Mon, 9 Jan 2023 16:09:22 +0100
Subject: [PATCH 0708/1167] x86/mm: fix poking_init() for Xen PV guests
Commit 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()") broke
the kernel for running as Xen PV guest.
It seems as if the new address space is never activated before being
used, resulting in Xen rejecting to accept the new CR3 value (the PGD
isn't pinned).
Fix that by adding the now missing call of paravirt_arch_dup_mmap() to
poking_init(). That call was previously done by dup_mm()->dup_mmap() and
it is a NOP for all cases but for Xen PV, where it is just doing the
pinning of the PGD.
Fixes: 3f4c8211d982 ("x86/mm: Use mm_alloc() in poking_init()")
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230109150922.10578-1-jgross@suse.com
---
arch/x86/mm/init.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d3987359d4414..cb258f58fdc87 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -26,6 +26,7 @@
#include <asm/pti.h>
#include <asm/text-patching.h>
#include <asm/memtype.h>
+#include <asm/paravirt.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -804,6 +805,9 @@ void __init poking_init(void)
poking_mm = mm_alloc();
BUG_ON(!poking_mm);
+ /* Xen PV guests need the PGD to be pinned. */
+ paravirt_arch_dup_mmap(NULL, poking_mm);
+
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
--
GitLab
From ca88eeb308a221c2dcd4a64031d2e5fcd3db9eaa Mon Sep 17 00:00:00 2001
From: Luka Guzenko <l.guzenko@web.de>
Date: Tue, 10 Jan 2023 21:25:14 +0100
Subject: [PATCH 0709/1167] ALSA: hda/realtek: Enable mute/micmute LEDs on HP
Spectre x360 13-aw0xxx
The HP Spectre x360 13-aw0xxx devices use the ALC285 codec with GPIO 0x04
controlling the micmute LED and COEF 0x0b index 8 controlling the mute LED.
A quirk was added to make these work as well as a fixup.
Signed-off-by: Luka Guzenko <l.guzenko@web.de>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20230110202514.2792-1-l.guzenko@web.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/pci/hda/patch_realtek.c | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 8362eb4642d86..6fab7c8fc19ae 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4646,6 +4646,16 @@ static void alc285_fixup_hp_coef_micmute_led(struct hda_codec *codec,
}
}
+static void alc285_fixup_hp_gpio_micmute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ spec->micmute_led_polarity = 1;
+ alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
+}
+
static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -4667,6 +4677,13 @@ static void alc285_fixup_hp_mute_led(struct hda_codec *codec,
alc285_fixup_hp_coef_micmute_led(codec, fix, action);
}
+static void alc285_fixup_hp_spectre_x360_mute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+ alc285_fixup_hp_gpio_micmute_led(codec, fix, action);
+}
+
static void alc236_fixup_hp_mute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -7108,6 +7125,7 @@ enum {
ALC285_FIXUP_ASUS_G533Z_PINS,
ALC285_FIXUP_HP_GPIO_LED,
ALC285_FIXUP_HP_MUTE_LED,
+ ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED,
ALC236_FIXUP_HP_GPIO_LED,
ALC236_FIXUP_HP_MUTE_LED,
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
@@ -8488,6 +8506,10 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_mute_led,
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_mute_led,
+ },
[ALC236_FIXUP_HP_GPIO_LED] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc236_fixup_hp_gpio_led,
@@ -9330,6 +9352,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
--
GitLab
From 9bfa2544dbd1133f0b0af4e967de3bb9c1e3a497 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Thu, 8 Dec 2022 13:52:41 +0200
Subject: [PATCH 0710/1167] ARM: dts: at91: sam9x60: fix the ddr clock for
sam9x60
The 2nd DDR clock for sam9x60 DDR controller is peripheral clock with
id 49.
Fixes: 1e5f532c2737 ("ARM: dts: at91: sam9x60: add device tree for soc and board")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Link: https://lore.kernel.org/r/20221208115241.36312-1-claudiu.beznea@microchip.com
---
arch/arm/boot/dts/sam9x60.dtsi | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi
index 8f5477e307dd4..37a5d96aaf642 100644
--- a/arch/arm/boot/dts/sam9x60.dtsi
+++ b/arch/arm/boot/dts/sam9x60.dtsi
@@ -564,7 +564,7 @@ pmecc: ecc-engine@ffffe000 {
mpddrc: mpddrc@ffffe800 {
compatible = "microchip,sam9x60-ddramc", "atmel,sama5d3-ddramc";
reg = <0xffffe800 0x200>;
- clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_CORE PMC_MCK>;
+ clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_PERIPHERAL 49>;
clock-names = "ddrck", "mpddr";
};
--
GitLab
From 040b35c19bf2bdbb8ba5f8742b4e199ace3cbdc3 Mon Sep 17 00:00:00 2001
From: Zack Rusin <zackr@vmware.com>
Date: Wed, 11 Jan 2023 12:50:15 -0500
Subject: [PATCH 0711/1167] drm/ttm: Fix a regression causing kernel oops'es
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The branch is explicitly taken if ttm == NULL which means that to avoid
a null pointer reference the ttm object can not be used inside. Switch
back to dst_mem to avoid kernel oops'es.
This fixes kernel oops'es with any buffer objects which don't have ttm_tt,
e.g. with vram based screen objects on vmwgfx.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Fixes: e3c92eb4a84f ("drm/ttm: rework on ttm_resource to use size_t type")
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230111175015.1134923-1-zack@kde.org
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/ttm/ttm_bo_util.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index ba3aa0a0fc43c..da5493f789dfe 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -173,7 +173,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo,
clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm));
if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)))
- ttm_move_memcpy(clear, ttm->num_pages, dst_iter, src_iter);
+ ttm_move_memcpy(clear, PFN_UP(dst_mem->size), dst_iter, src_iter);
if (!src_iter->ops->maps_tt)
ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem);
--
GitLab
From 5640e81607152d7f2d2558227c0f6cb78b8f39cf Mon Sep 17 00:00:00 2001
From: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Date: Thu, 12 Jan 2023 04:00:27 -0800
Subject: [PATCH 0712/1167] drm: Optimize drm buddy top-down allocation method
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
We are observing performance drop in many usecases which include
games, 3D benchmark applications,etc.. To solve this problem, We
are strictly not allowing top down flag enabled allocations to
steal the memory space from cpu visible region.
The idea is, we are sorting each order list entries in
ascending order and compare the last entry of each order
list in the freelist and return the max block.
This patch improves the 3D benchmark scores and solves
fragmentation issues.
All drm buddy selftests are verfied.
drm_buddy: pass:6 fail:0 skip:0 total:6
Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230112120027.3072-1-Arunpravin.PaneerSelvam@amd.com
Signed-off-by: Christian König <christian.koenig@amd.com>
CC: Cc: stable@vger.kernel.org # 5.18+
---
drivers/gpu/drm/drm_buddy.c | 81 ++++++++++++++++++++++++-------------
1 file changed, 54 insertions(+), 27 deletions(-)
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 11bb593994718..3d1f50f481cfd 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -38,6 +38,25 @@ static void drm_block_free(struct drm_buddy *mm,
kmem_cache_free(slab_blocks, block);
}
+static void list_insert_sorted(struct drm_buddy *mm,
+ struct drm_buddy_block *block)
+{
+ struct drm_buddy_block *node;
+ struct list_head *head;
+
+ head = &mm->free_list[drm_buddy_block_order(block)];
+ if (list_empty(head)) {
+ list_add(&block->link, head);
+ return;
+ }
+
+ list_for_each_entry(node, head, link)
+ if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node))
+ break;
+
+ __list_add(&block->link, node->link.prev, &node->link);
+}
+
static void mark_allocated(struct drm_buddy_block *block)
{
block->header &= ~DRM_BUDDY_HEADER_STATE;
@@ -52,8 +71,7 @@ static void mark_free(struct drm_buddy *mm,
block->header &= ~DRM_BUDDY_HEADER_STATE;
block->header |= DRM_BUDDY_FREE;
- list_add(&block->link,
- &mm->free_list[drm_buddy_block_order(block)]);
+ list_insert_sorted(mm, block);
}
static void mark_split(struct drm_buddy_block *block)
@@ -387,20 +405,26 @@ alloc_range_bias(struct drm_buddy *mm,
}
static struct drm_buddy_block *
-get_maxblock(struct list_head *head)
+get_maxblock(struct drm_buddy *mm, unsigned int order)
{
struct drm_buddy_block *max_block = NULL, *node;
+ unsigned int i;
- max_block = list_first_entry_or_null(head,
- struct drm_buddy_block,
- link);
- if (!max_block)
- return NULL;
+ for (i = order; i <= mm->max_order; ++i) {
+ if (!list_empty(&mm->free_list[i])) {
+ node = list_last_entry(&mm->free_list[i],
+ struct drm_buddy_block,
+ link);
+ if (!max_block) {
+ max_block = node;
+ continue;
+ }
- list_for_each_entry(node, head, link) {
- if (drm_buddy_block_offset(node) >
- drm_buddy_block_offset(max_block))
- max_block = node;
+ if (drm_buddy_block_offset(node) >
+ drm_buddy_block_offset(max_block)) {
+ max_block = node;
+ }
+ }
}
return max_block;
@@ -412,20 +436,23 @@ alloc_from_freelist(struct drm_buddy *mm,
unsigned long flags)
{
struct drm_buddy_block *block = NULL;
- unsigned int i;
+ unsigned int tmp;
int err;
- for (i = order; i <= mm->max_order; ++i) {
- if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
- block = get_maxblock(&mm->free_list[i]);
- if (block)
- break;
- } else {
- block = list_first_entry_or_null(&mm->free_list[i],
- struct drm_buddy_block,
- link);
- if (block)
- break;
+ if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+ block = get_maxblock(mm, order);
+ if (block)
+ /* Store the obtained block order */
+ tmp = drm_buddy_block_order(block);
+ } else {
+ for (tmp = order; tmp <= mm->max_order; ++tmp) {
+ if (!list_empty(&mm->free_list[tmp])) {
+ block = list_last_entry(&mm->free_list[tmp],
+ struct drm_buddy_block,
+ link);
+ if (block)
+ break;
+ }
}
}
@@ -434,18 +461,18 @@ alloc_from_freelist(struct drm_buddy *mm,
BUG_ON(!drm_buddy_block_is_free(block));
- while (i != order) {
+ while (tmp != order) {
err = split_block(mm, block);
if (unlikely(err))
goto err_undo;
block = block->right;
- i--;
+ tmp--;
}
return block;
err_undo:
- if (i != order)
+ if (tmp != order)
__drm_buddy_free(mm, block);
return ERR_PTR(err);
}
--
GitLab
From 07a2975c65f2be2e22591d795a9c39b00f95fd11 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Thu, 12 Jan 2023 10:12:43 +0100
Subject: [PATCH 0713/1167] drm/vc4: bo: Fix drmm_mutex_init memory hog
Commit 374146cad469 ("drm/vc4: Switch to drmm_mutex_init") converted,
among other functions, vc4_create_object() to use drmm_mutex_init().
However, that function is used to allocate a BO, and therefore the
mutex needs to be freed much sooner than when the DRM device is removed
from the system.
For each buffer allocation we thus end up allocating a small structure
as part of the DRM-managed mechanism that is never freed, eventually
leading us to no longer having any free memory anymore.
Let's switch back to mutex_init/mutex_destroy to deal with it properly.
Fixes: 374146cad469 ("drm/vc4: Switch to drmm_mutex_init")
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20230112091243.490799-1-maxime@cerno.tech
---
drivers/gpu/drm/vc4/vc4_bo.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 43d9b3a6a352c..29ce2fa72cc4c 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -179,6 +179,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo)
bo->validated_shader = NULL;
}
+ mutex_destroy(&bo->madv_lock);
drm_gem_dma_free(&bo->base);
}
@@ -406,9 +407,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
bo->madv = VC4_MADV_WILLNEED;
refcount_set(&bo->usecnt, 0);
- ret = drmm_mutex_init(dev, &bo->madv_lock);
- if (ret)
- return ERR_PTR(ret);
+ mutex_init(&bo->madv_lock);
mutex_lock(&vc4->bo_lock);
bo->label = VC4_BO_TYPE_KERNEL;
--
GitLab
From be53771c87f4e322a9835d3faa9cd73a4ecdec5b Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@arm.com>
Date: Wed, 11 Jan 2023 13:32:28 +0000
Subject: [PATCH 0714/1167] r8152: add vendor/device ID pair for Microsoft
Devkit
The Microsoft Devkit 2023 is a an ARM64 based machine featuring a
Realtek 8153 USB3.0-to-GBit Ethernet adapter. As in their other
machines, Microsoft uses a custom USB device ID.
Add the respective ID values to the driver. This makes Ethernet work on
the MS Devkit device. The chip has been visually confirmed to be a
RTL8153.
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Link: https://lore.kernel.org/r/20230111133228.190801-1-andre.przywara@arm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/usb/r8152.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index a481a1d831e2f..23da1d9dafd1f 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -9836,6 +9836,7 @@ static const struct usb_device_id rtl8152_table[] = {
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927),
+ REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e),
REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054),
--
GitLab
From 7c24fa225081f31bc6da6a355c1ba801889ab29a Mon Sep 17 00:00:00 2001
From: Dai Ngo <dai.ngo@oracle.com>
Date: Wed, 11 Jan 2023 16:06:51 -0800
Subject: [PATCH 0715/1167] NFSD: replace delayed_work with work_struct for
nfsd_client_shrinker
Since nfsd4_state_shrinker_count always calls mod_delayed_work with
0 delay, we can replace delayed_work with work_struct to save some
space and overhead.
Also add the call to cancel_work after unregister the shrinker
in nfs4_state_shutdown_net.
Signed-off-by: Dai Ngo <dai.ngo@oracle.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/netns.h | 2 +-
fs/nfsd/nfs4state.c | 8 ++++----
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 8c854ba3285bb..51a4b7885cae2 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -195,7 +195,7 @@ struct nfsd_net {
atomic_t nfsd_courtesy_clients;
struct shrinker nfsd_client_shrinker;
- struct delayed_work nfsd_shrinker_work;
+ struct work_struct nfsd_shrinker_work;
};
/* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index db41358bd0d30..f194d029c3d64 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4411,7 +4411,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
if (!count)
count = atomic_long_read(&num_delegations);
if (count)
- mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ queue_work(laundry_wq, &nn->nfsd_shrinker_work);
return (unsigned long)count;
}
@@ -6225,8 +6225,7 @@ deleg_reaper(struct nfsd_net *nn)
static void
nfsd4_state_shrinker_worker(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
- struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ struct nfsd_net *nn = container_of(work, struct nfsd_net,
nfsd_shrinker_work);
courtesy_client_reaper(nn);
@@ -8056,7 +8055,7 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
- INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
+ INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
@@ -8163,6 +8162,7 @@ nfs4_state_shutdown_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
unregister_shrinker(&nn->nfsd_client_shrinker);
+ cancel_work(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
--
GitLab
From 6d3d970b2735b967650d319be27268fedc5598d1 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Jan 2023 14:56:34 +0000
Subject: [PATCH 0716/1167] btrfs: fix missing error handling when logging
directory items
When logging a directory, at log_dir_items(), if we get an error when
attempting to search the subvolume tree for a dir index item, we end up
returning 0 (success) from log_dir_items() because 'err' is left with a
value of 0.
This can lead to a few problems, specially in the case the variable
'last_offset' has a value of (u64)-1 (and it's initialized to that when
it was declared):
1) By returning from log_dir_items() with success (0) and a value of
(u64)-1 for '*last_offset_ret', we end up not logging any other dir
index keys that follow the missing, just deleted, index key. The
(u64)-1 value makes log_directory_changes() not call log_dir_items()
again;
2) Before returning with success (0), log_dir_items(), will log a dir
index range item covering a range from the last old dentry index
(stored in the variable 'last_old_dentry_offset') to the value of
'last_offset'. If 'last_offset' has a value of (u64)-1, then it means
if the log is persisted and replayed after a power failure, it will
cause deletion of all the directory entries that have an index number
between last_old_dentry_offset + 1 and (u64)-1;
3) We can end up returning from log_dir_items() with
ctx->last_dir_item_offset having a lower value than
inode->last_dir_index_offset, because the former is set to the current
key we are processing at process_dir_items_leaf(), and at the end of
log_directory_changes() we set inode->last_dir_index_offset to the
current value of ctx->last_dir_item_offset. So if for example a
deletion of a lower dir index key happened, we set
ctx->last_dir_item_offset to that index value, then if we return from
log_dir_items() because btrfs_search_slot() returned an error, we end up
returning without any error from log_dir_items() and then
log_directory_changes() sets inode->last_dir_index_offset to a lower
value than it had before.
This can result in unpredictable and unexpected behaviour when we
need to log again the directory in the same transaction, and can result
in ending up with a log tree leaf that has duplicated keys, as we do
batch insertions of dir index keys into a log tree.
Fix this by setting 'err' to the value of 'ret' in case
btrfs_search_slot() or btrfs_previous_item() returned an error. That will
result in falling back to a full transaction commit.
Reported-by: David Arendt <admin@prnet.org>
Link: https://lore.kernel.org/linux-btrfs/ae169fc6-f504-28f0-a098-6fa6a4dfb612@leemhuis.info/
Fixes: e02119d5a7b4 ("Btrfs: Add a write ahead tree log to optimize synchronous operations")
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fb52aa0600930..3ef0266e95274 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3826,7 +3826,10 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
path->slots[0]);
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
}
+
goto done;
}
@@ -3846,7 +3849,11 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
*/
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
+ goto done;
}
+
btrfs_release_path(path);
/*
@@ -3859,6 +3866,8 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
*/
search:
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+ if (ret < 0)
+ err = ret;
if (ret != 0)
goto done;
--
GitLab
From 8bb6898da6271d82d8e76d8088d66b971a7dcfa6 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Jan 2023 14:56:35 +0000
Subject: [PATCH 0717/1167] btrfs: fix directory logging due to race with
concurrent index key deletion
Sometimes we log a directory without holding its VFS lock, so while we
logging it, dir index entries may be added or removed. This typically
happens when logging a dentry from a parent directory that points to a
new directory, through log_new_dir_dentries(), or when while logging
some other inode we also need to log its parent directories (through
btrfs_log_all_parents()).
This means that while we are at log_dir_items(), we may not find a dir
index key we found before, because it was deleted in the meanwhile, so
a call to btrfs_search_slot() may return 1 (key not found). In that case
we return from log_dir_items() with a success value (the variable 'err'
has a value of 0). This can lead to a few problems, specially in the case
where the variable 'last_offset' has a value of (u64)-1 (and it's
initialized to that when it was declared):
1) By returning from log_dir_items() with success (0) and a value of
(u64)-1 for '*last_offset_ret', we end up not logging any other dir
index keys that follow the missing, just deleted, index key. The
(u64)-1 value makes log_directory_changes() not call log_dir_items()
again;
2) Before returning with success (0), log_dir_items(), will log a dir
index range item covering a range from the last old dentry index
(stored in the variable 'last_old_dentry_offset') to the value of
'last_offset'. If 'last_offset' has a value of (u64)-1, then it means
if the log is persisted and replayed after a power failure, it will
cause deletion of all the directory entries that have an index number
between last_old_dentry_offset + 1 and (u64)-1;
3) We can end up returning from log_dir_items() with
ctx->last_dir_item_offset having a lower value than
inode->last_dir_index_offset, because the former is set to the current
key we are processing at process_dir_items_leaf(), and at the end of
log_directory_changes() we set inode->last_dir_index_offset to the
current value of ctx->last_dir_item_offset. So if for example a
deletion of a lower dir index key happened, we set
ctx->last_dir_item_offset to that index value, then if we return from
log_dir_items() because btrfs_search_slot() returned 1, we end up
returning from log_dir_items() with success (0) and then
log_directory_changes() sets inode->last_dir_index_offset to a lower
value than it had before.
This can result in unpredictable and unexpected behaviour when we
need to log again the directory in the same transaction, and can result
in ending up with a log tree leaf that has duplicated keys, as we do
batch insertions of dir index keys into a log tree.
So fix this by making log_dir_items() move on to the next dir index key
if it does not find the one it was looking for.
Reported-by: David Arendt <admin@prnet.org>
Link: https://lore.kernel.org/linux-btrfs/ae169fc6-f504-28f0-a098-6fa6a4dfb612@leemhuis.info/
CC: stable@vger.kernel.org # 4.14+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 21 +++++++++++++++------
1 file changed, 15 insertions(+), 6 deletions(-)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3ef0266e95274..c09daab3f19e8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3857,17 +3857,26 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
/*
- * Find the first key from this transaction again. See the note for
- * log_new_dir_dentries, if we're logging a directory recursively we
- * won't be holding its i_mutex, which means we can modify the directory
- * while we're logging it. If we remove an entry between our first
- * search and this search we'll not find the key again and can just
- * bail.
+ * Find the first key from this transaction again or the one we were at
+ * in the loop below in case we had to reschedule. We may be logging the
+ * directory without holding its VFS lock, which happen when logging new
+ * dentries (through log_new_dir_dentries()) or in some cases when we
+ * need to log the parent directory of an inode. This means a dir index
+ * key might be deleted from the inode's root, and therefore we may not
+ * find it anymore. If we can't find it, just move to the next key. We
+ * can not bail out and ignore, because if we do that we will simply
+ * not log dir index keys that come after the one that was just deleted
+ * and we can end up logging a dir index range that ends at (u64)-1
+ * (@last_offset is initialized to that), resulting in removing dir
+ * entries we should not remove at log replay time.
*/
search:
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+ if (ret > 0)
+ ret = btrfs_next_item(root, path);
if (ret < 0)
err = ret;
+ /* If ret is 1, there are no more keys in the inode's root. */
if (ret != 0)
goto done;
--
GitLab
From 94cd63ae679973edeb5ea95ec25a54467c3e54c8 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Jan 2023 14:56:36 +0000
Subject: [PATCH 0718/1167] btrfs: add missing setup of log for full commit at
add_conflicting_inode()
When logging conflicting inodes, if we reach the maximum limit of inodes,
we return BTRFS_LOG_FORCE_COMMIT to force a transaction commit. However
we don't mark the log for full commit (with btrfs_set_log_full_commit()),
which means that once we leave the log transaction and before we commit
the transaction, some other task may sync the log, which is incomplete
as we have not logged all conflicting inodes, leading to some inconsistent
in case that log ends up being replayed.
So also call btrfs_set_log_full_commit() at add_conflicting_inode().
Fixes: e09d94c9e448 ("btrfs: log conflicting inodes without holding log mutex of the initial inode")
CC: stable@vger.kernel.org # 6.1
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c09daab3f19e8..afad44a0becfe 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5598,8 +5598,10 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
* LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
* commits.
*/
- if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
+ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
+ btrfs_set_log_full_commit(trans);
return BTRFS_LOG_FORCE_COMMIT;
+ }
inode = btrfs_iget(root->fs_info->sb, ino, root);
/*
--
GitLab
From 16199ad9eb6db60a6b10794a09fc1ac6d09312ff Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Jan 2023 14:56:37 +0000
Subject: [PATCH 0719/1167] btrfs: do not abort transaction on failure to write
log tree when syncing log
When syncing the log, if we fail to write log tree extent buffers, we mark
the log for a full commit and abort the transaction. However we don't need
to abort the transaction, all we really need to do is to make sure no one
can commit a superblock pointing to new log tree roots. Just because we
got a failure writing extent buffers for a log tree, it does not mean we
will also fail to do a transaction commit.
One particular case is if due to a bug somewhere, when writing log tree
extent buffers, the tree checker detects some corruption and the writeout
fails because of that. Aborting the transaction can be very disruptive for
a user, specially if the issue happened on a root filesystem. One example
is the scenario in the Link tag below, where an isolated corruption on log
tree leaves was causing transaction aborts when syncing the log.
Link: https://lore.kernel.org/linux-btrfs/ae169fc6-f504-28f0-a098-6fa6a4dfb612@leemhuis.info/
CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/disk-io.c | 9 ++++++++-
fs/btrfs/tree-log.c | 2 --
2 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8aeaada1fcaec..3aa04224315eb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -367,7 +367,14 @@ static int csum_one_extent_buffer(struct extent_buffer *eb)
btrfs_print_tree(eb, 0);
btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
eb->start);
- WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ /*
+ * Be noisy if this is an extent buffer from a log tree. We don't abort
+ * a transaction in case there's a bad log tree extent buffer, we just
+ * fallback to a transaction commit. Still we want to know when there is
+ * a bad log tree extent buffer, as that may signal a bug somewhere.
+ */
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+ btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID);
return ret;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index afad44a0becfe..1f70d4ebffae4 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2980,7 +2980,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
ret = 0;
if (ret) {
blk_finish_plug(&plug);
- btrfs_abort_transaction(trans, ret);
btrfs_set_log_full_commit(trans);
mutex_unlock(&root->log_mutex);
goto out;
@@ -3112,7 +3111,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
goto out_wake_log_root;
} else if (ret) {
btrfs_set_log_full_commit(trans);
- btrfs_abort_transaction(trans, ret);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
--
GitLab
From 09e44868f1e03c7825ca4283256abedc95e249a3 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 10 Jan 2023 14:56:38 +0000
Subject: [PATCH 0720/1167] btrfs: do not abort transaction on failure to
update log root
When syncing a log, if we fail to update a log root in the log root tree,
we are aborting the transaction if the failure was not -ENOSPC. This is
excessive because there is a chance that a transaction commit can succeed,
and therefore avoid to turn the filesystem into RO mode. All we need to be
careful about is to mark the log for a full commit, which we already do,
to make sure no one commits a super block pointing to an outdated log root
tree.
So don't abort the transaction if we fail to update a log root in the log
root tree, and log an error if the failure is not -ENOSPC, so that it does
not go completely unnoticed.
CC: stable@vger.kernel.org # 6.0+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/tree-log.c | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1f70d4ebffae4..d43261545264e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3044,15 +3044,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
blk_finish_plug(&plug);
btrfs_set_log_full_commit(trans);
-
- if (ret != -ENOSPC) {
- btrfs_abort_transaction(trans, ret);
- mutex_unlock(&log_root_tree->log_mutex);
- goto out;
- }
+ if (ret != -ENOSPC)
+ btrfs_err(fs_info,
+ "failed to update log for root %llu ret %d",
+ root->root_key.objectid, ret);
btrfs_wait_tree_log_extents(log, mark);
mutex_unlock(&log_root_tree->log_mutex);
- ret = BTRFS_LOG_FORCE_COMMIT;
goto out;
}
--
GitLab
From a152d05ae4a71d802d50cf9177dba34e8bb09f68 Mon Sep 17 00:00:00 2001
From: Volker Lendecke <vl@samba.org>
Date: Wed, 11 Jan 2023 12:37:58 +0100
Subject: [PATCH 0721/1167] cifs: Fix uninitialized memory read for smb311
posix symlink create
If smb311 posix is enabled, we send the intended mode for file
creation in the posix create context. Instead of using what's there on
the stack, create the mfsymlink file with 0644.
Fixes: ce558b0e17f8a ("smb3: Add posix create context for smb3.11 posix mounts")
Cc: stable@vger.kernel.org
Signed-off-by: Volker Lendecke <vl@samba.org>
Reviewed-by: Tom Talpey <tom@talpey.com>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/link.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index bd374feeccaa1..a5a097a699837 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -428,6 +428,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
oparms.disposition = FILE_CREATE;
oparms.fid = &fid;
oparms.reconnect = false;
+ oparms.mode = 0644;
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL,
NULL, NULL);
--
GitLab
From bb78654b0b46316dac687fd4b7dc7cce636f46cd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?=
<duke_xinanwen@163.com>
Date: Tue, 27 Dec 2022 01:28:25 -0800
Subject: [PATCH 0722/1167] USB: serial: option: add Quectel EM05-G (CS) modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The EM05-G (CS) modem has 2 USB configurations that are configurable via
the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate
with the following interfaces, respectively:
"RMNET" : AT + DIAG + NMEA + Modem + QMI
"MBIM" : MBIM + AT + DIAG + NMEA + Modem
The detailed description of the USB configuration for each mode as follows:
RMNET Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=030C Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
MBIM Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=030C Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms
I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Duke Xin(辛安文) <duke_xinanwen@163.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index dee79c7d82d5c..7eeca6c7b270d 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -255,6 +255,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EP06 0x0306
#define QUECTEL_PRODUCT_EM05G 0x030a
#define QUECTEL_PRODUCT_EM060K 0x030b
+#define QUECTEL_PRODUCT_EM05G_CS 0x030c
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
@@ -1161,6 +1162,8 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
.driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
--
GitLab
From 6c331f32e32ac71eb3e8b93fceda2802d7ecb889 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?=
<duke_xinanwen@163.com>
Date: Tue, 27 Dec 2022 01:44:30 -0800
Subject: [PATCH 0723/1167] USB: serial: option: add Quectel EM05-G (GR) modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The EM05-G (GR) modem has 2 USB configurations that are configurable via
the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate
with the following interfaces, respectively:
"RMNET" : AT + DIAG + NMEA + Modem + QMI
"MBIM" : MBIM + AT + DIAG + NMEA + Modem
The detailed description of the USB configuration for each mode as follows:
RMNET Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0313 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
MBIM Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0313 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms
I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Duke Xin(辛安文) <duke_xinanwen@163.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7eeca6c7b270d..07ffff889ed1e 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -257,6 +257,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EM060K 0x030b
#define QUECTEL_PRODUCT_EM05G_CS 0x030c
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
+#define QUECTEL_PRODUCT_EM05G_GR 0x0313
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
#define QUECTEL_PRODUCT_RM520N 0x0801
@@ -1164,6 +1165,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff),
.driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
--
GitLab
From 36c2b9d6710427f802494ba070621cb415198293 Mon Sep 17 00:00:00 2001
From: Michael Klein <m.klein@mvz-labor-lb.de>
Date: Tue, 20 Dec 2022 13:11:03 +0100
Subject: [PATCH 0724/1167] platform/x86: touchscreen_dmi: Add info for the CSL
Panther Tab HD
Add touchscreen info for the CSL Panther Tab HD.
Signed-off-by: Michael Klein <m.klein@mvz-labor-lb.de>
Link: https://lore.kernel.org/r/20221220121103.uiwn5l7fii2iggct@LLGMVZLB-0037
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/touchscreen_dmi.c | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c
index baae3120efd05..f00995390fdfe 100644
--- a/drivers/platform/x86/touchscreen_dmi.c
+++ b/drivers/platform/x86/touchscreen_dmi.c
@@ -264,6 +264,23 @@ static const struct ts_dmi_data connect_tablet9_data = {
.properties = connect_tablet9_props,
};
+static const struct property_entry csl_panther_tab_hd_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 20),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1980),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1526),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ { }
+};
+
+static const struct ts_dmi_data csl_panther_tab_hd_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = csl_panther_tab_hd_props,
+};
+
static const struct property_entry cube_iwork8_air_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
PROPERTY_ENTRY_U32("touchscreen-min-y", 3),
@@ -1124,6 +1141,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Tablet 9"),
},
},
+ {
+ /* CSL Panther Tab HD */
+ .driver_data = (void *)&csl_panther_tab_hd_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"),
+ },
+ },
{
/* CUBE iwork8 Air */
.driver_data = (void *)&cube_iwork8_air_data,
--
GitLab
From 6e5aedb9324aab1c14a23fae3d8eeb64a679c20e Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 10 Jan 2023 10:44:37 -0700
Subject: [PATCH 0725/1167] io_uring/poll: attempt request issue after racy
poll wakeup
If we have multiple requests waiting on the same target poll waitqueue,
then it's quite possible to get a request triggered and get disappointed
in not being able to make any progress with it. If we race in doing so,
we'll potentially leave the poll request on the internal tables, but
removed from the waitqueue. That means that any subsequent trigger of
the poll waitqueue will not kick that request into action, causing an
application to potentially wait for completion of a request that will
never happen.
Fix this by adding a new poll return state, IOU_POLL_REISSUE. Rather
than have complicated logic for how to re-arm a given type of request,
just punt it for a reissue.
While in there, move the 'ret' variable to the only section where it
gets used. This avoids confusion the scope of it.
Cc: stable@vger.kernel.org
Fixes: eb0089d629ba ("io_uring: single shot poll removal optimisation")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/poll.c | 31 ++++++++++++++++++++-----------
1 file changed, 20 insertions(+), 11 deletions(-)
diff --git a/io_uring/poll.c b/io_uring/poll.c
index cf6a70bd54e09..32e5fc8365e6a 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -223,21 +223,22 @@ enum {
IOU_POLL_DONE = 0,
IOU_POLL_NO_ACTION = 1,
IOU_POLL_REMOVE_POLL_USE_RES = 2,
+ IOU_POLL_REISSUE = 3,
};
/*
* All poll tw should go through this. Checks for poll events, manages
* references, does rewait, etc.
*
- * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require,
- * which is either spurious wakeup or multishot CQE is served.
- * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res.
- * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result
- * is stored in req->cqe.
+ * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
+ * require, which is either spurious wakeup or multishot CQE is served.
+ * IOU_POLL_DONE when it's done with the request, then the mask is stored in
+ * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
+ * poll and that the result is stored in req->cqe.
*/
static int io_poll_check_events(struct io_kiocb *req, bool *locked)
{
- int v, ret;
+ int v;
/* req->task == current here, checking PF_EXITING is safe */
if (unlikely(req->task->flags & PF_EXITING))
@@ -276,10 +277,15 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked)
if (!req->cqe.res) {
struct poll_table_struct pt = { ._key = req->apoll_events };
req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
+ /*
+ * We got woken with a mask, but someone else got to
+ * it first. The above vfs_poll() doesn't add us back
+ * to the waitqueue, so if we get nothing back, we
+ * should be safe and attempt a reissue.
+ */
+ if (unlikely(!req->cqe.res))
+ return IOU_POLL_REISSUE;
}
-
- if ((unlikely(!req->cqe.res)))
- continue;
if (req->apoll_events & EPOLLONESHOT)
return IOU_POLL_DONE;
@@ -294,7 +300,7 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked)
return IOU_POLL_REMOVE_POLL_USE_RES;
}
} else {
- ret = io_poll_issue(req, locked);
+ int ret = io_poll_issue(req, locked);
if (ret == IOU_STOP_MULTISHOT)
return IOU_POLL_REMOVE_POLL_USE_RES;
if (ret < 0)
@@ -330,6 +336,9 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
poll = io_kiocb_to_cmd(req, struct io_poll);
req->cqe.res = mangle_poll(req->cqe.res & poll->events);
+ } else if (ret == IOU_POLL_REISSUE) {
+ io_req_task_submit(req, locked);
+ return;
} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
req->cqe.res = ret;
req_set_fail(req);
@@ -342,7 +351,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked)
if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
io_req_task_complete(req, locked);
- else if (ret == IOU_POLL_DONE)
+ else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
io_req_task_submit(req, locked);
else
io_req_defer_failed(req, ret);
--
GitLab
From ae0fa0a3126a86c801c3220fcd8eefe03aa39f3e Mon Sep 17 00:00:00 2001
From: Maximilian Luz <luzmaximilian@gmail.com>
Date: Fri, 2 Dec 2022 23:33:19 +0100
Subject: [PATCH 0726/1167] platform/surface: aggregator: Ignore command
messages not intended for us
It is possible that we (the host/kernel driver) receive command messages
that are not intended for us. Ignore those for now.
The whole story is a bit more complicated: It is possible to enable
debug output on SAM, which is sent via SSH command messages. By default
this output is sent to a debug connector, with its own target ID
(TID=0x03). It is possible to override the target of the debug output
and set it to the host/kernel driver. This, however, does not change the
original target ID of the message. Meaning, we receive messages with
TID=0x03 (debug) but expect to only receive messages with TID=0x00
(host).
The problem is that the different target ID also comes with a different
scope of request IDs. In particular, these do not follow the standard
event rules (i.e. do not fall into a set of small reserved values).
Therefore, current message handling interprets them as responses to
pending requests and tries to match them up via the request ID. However,
these debug output messages are not in fact responses, and therefore
this will at best fail to find the request and at worst pass on the
wrong data as response for a request.
Therefore ignore any command messages not intended for us (host) for
now. We can implement support for the debug messages once we have a
better understanding of them.
Note that this may also provide a bit more stability and avoid some
driver confusion in case any other targets want to talk to us in the
future, since we don't yet know what to do with those as well. A warning
for the dropped messages should suffice for now and also give us a
chance of discovering new targets if they come along without any
potential for bugs/instabilities.
Fixes: c167b9c7e3d6 ("platform/surface: Add Surface Aggregator subsystem")
Signed-off-by: Maximilian Luz <luzmaximilian@gmail.com>
Link: https://lore.kernel.org/r/20221202223327.690880-2-luzmaximilian@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
.../surface/aggregator/ssh_request_layer.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.c b/drivers/platform/surface/aggregator/ssh_request_layer.c
index f5565570f16c7..69132976d297e 100644
--- a/drivers/platform/surface/aggregator/ssh_request_layer.c
+++ b/drivers/platform/surface/aggregator/ssh_request_layer.c
@@ -916,6 +916,20 @@ static void ssh_rtl_rx_command(struct ssh_ptl *p, const struct ssam_span *data)
if (sshp_parse_command(dev, data, &command, &command_data))
return;
+ /*
+ * Check if the message was intended for us. If not, drop it.
+ *
+ * Note: We will need to change this to handle debug messages. On newer
+ * generation devices, these seem to be sent to tid_out=0x03. We as
+ * host can still receive them as they can be forwarded via an override
+ * option on SAM, but doing so does not change tid_out=0x00.
+ */
+ if (command->tid_out != 0x00) {
+ rtl_warn(rtl, "rtl: dropping message not intended for us (tid = %#04x)\n",
+ command->tid_out);
+ return;
+ }
+
if (ssh_rqid_is_event(get_unaligned_le16(&command->rqid)))
ssh_rtl_rx_event(rtl, command, &command_data);
else
--
GitLab
From c965daac370f08a9b71d573a71d13cda76f2a884 Mon Sep 17 00:00:00 2001
From: Maximilian Luz <luzmaximilian@gmail.com>
Date: Tue, 20 Dec 2022 18:56:07 +0100
Subject: [PATCH 0727/1167] platform/surface: aggregator: Add missing call to
ssam_request_sync_free()
Although rare, ssam_request_sync_init() can fail. In that case, the
request should be freed via ssam_request_sync_free(). Currently it is
leaked instead. Fix this.
Fixes: c167b9c7e3d6 ("platform/surface: Add Surface Aggregator subsystem")
Signed-off-by: Maximilian Luz <luzmaximilian@gmail.com>
Link: https://lore.kernel.org/r/20221220175608.1436273-1-luzmaximilian@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/surface/aggregator/controller.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c
index 43e7651991371..c6537a1b3a2ec 100644
--- a/drivers/platform/surface/aggregator/controller.c
+++ b/drivers/platform/surface/aggregator/controller.c
@@ -1700,8 +1700,10 @@ int ssam_request_sync(struct ssam_controller *ctrl,
return status;
status = ssam_request_sync_init(rqst, spec->flags);
- if (status)
+ if (status) {
+ ssam_request_sync_free(rqst);
return status;
+ }
ssam_request_sync_set_resp(rqst, rsp);
--
GitLab
From 17eee264ef386ef30a69dd70e36f29893b85c170 Mon Sep 17 00:00:00 2001
From: Shang XiaoJing <shangxiaojing@huawei.com>
Date: Fri, 25 Nov 2022 10:12:22 +0800
Subject: [PATCH 0728/1167] phy: usb: sunplus: Fix potential null-ptr-deref in
sp_usb_phy_probe()
sp_usb_phy_probe() will call platform_get_resource_byname() that may fail
and return NULL. devm_ioremap() will use usbphy->moon4_res_mem->start as
input, which may causes null-ptr-deref. Check the ret value of
platform_get_resource_byname() to avoid the null-ptr-deref.
Fixes: 99d9ccd97385 ("phy: usb: Add USB2.0 phy driver for Sunplus SP7021")
Signed-off-by: Shang XiaoJing <shangxiaojing@huawei.com>
Link: https://lore.kernel.org/r/20221125021222.25687-1-shangxiaojing@huawei.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/sunplus/phy-sunplus-usb2.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c
index e827b79f6d493..56de41091d639 100644
--- a/drivers/phy/sunplus/phy-sunplus-usb2.c
+++ b/drivers/phy/sunplus/phy-sunplus-usb2.c
@@ -254,6 +254,9 @@ static int sp_usb_phy_probe(struct platform_device *pdev)
return PTR_ERR(usbphy->phy_regs);
usbphy->moon4_res_mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "moon4");
+ if (!usbphy->moon4_res_mem)
+ return -EINVAL;
+
usbphy->moon4_regs = devm_ioremap(&pdev->dev, usbphy->moon4_res_mem->start,
resource_size(usbphy->moon4_res_mem));
if (!usbphy->moon4_regs)
--
GitLab
From c78a4e191839edc1e8c3e51565cf2e71d40e8883 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 21 Dec 2022 03:49:59 +0000
Subject: [PATCH 0729/1167] platform/x86: asus-nb-wmi: Add alternate mapping
for KEY_CAMERA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This keycode is emitted on a Asus VivoBook E410MAB with firmware
E410MAB.304.
The physical key has a strikken-through camera printed on it.
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221216-asus-key-v1-1-45da124119a3@weissschuh.net
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/asus-nb-wmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index c685a705b73dd..8ee5d108e9e05 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -544,6 +544,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
{ KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */
{ KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */
{ KE_KEY, 0x82, { KEY_CAMERA } },
+ { KE_KEY, 0x85, { KEY_CAMERA } },
{ KE_KEY, 0x86, { KEY_PROG1 } }, /* MyASUS Key */
{ KE_KEY, 0x88, { KEY_RFKILL } }, /* Radio Toggle Key */
{ KE_KEY, 0x8A, { KEY_PROG1 } }, /* Color enhancement mode */
--
GitLab
From db9494895b405bf318dc7e563dee6daa51b3b6ed Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 12 Jan 2023 19:18:41 +0100
Subject: [PATCH 0730/1167] platform/x86: asus-nb-wmi: Add alternate mapping
for KEY_SCREENLOCK
The 0x33 keycode is emitted by Fn + F6 on a ASUS FX705GE laptop.
Reported-by: Nemcev Aleksey <Nemcev_Aleksey@inbox.ru>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230112181841.84652-1-hdegoede@redhat.com
---
drivers/platform/x86/asus-nb-wmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 8ee5d108e9e05..b34bddda0a9b3 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -511,6 +511,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
{ KE_KEY, 0x30, { KEY_VOLUMEUP } },
{ KE_KEY, 0x31, { KEY_VOLUMEDOWN } },
{ KE_KEY, 0x32, { KEY_MUTE } },
+ { KE_KEY, 0x33, { KEY_SCREENLOCK } },
{ KE_KEY, 0x35, { KEY_SCREENLOCK } },
{ KE_KEY, 0x38, { KEY_PROG3 } }, /* Armoury Crate */
{ KE_KEY, 0x40, { KEY_PREVIOUSSONG } },
--
GitLab
From ec4a1d9301100c011312357ea25627b98eb293d5 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Mon, 26 Dec 2022 15:42:16 +0900
Subject: [PATCH 0731/1167] phy: renesas: r8a779f0-eth-serdes: Fix register
setting
Fix register setting which is typo in r8a779f0_eth_serdes_chan_setting().
Fixes: 742859441d44 ("phy: renesas: Add Renesas Ethernet SERDES driver for R-Car S4-8")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20221226064216.3895421-1-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/renesas/r8a779f0-ether-serdes.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/phy/renesas/r8a779f0-ether-serdes.c b/drivers/phy/renesas/r8a779f0-ether-serdes.c
index ec6594e6dc275..e7588a940d699 100644
--- a/drivers/phy/renesas/r8a779f0-ether-serdes.c
+++ b/drivers/phy/renesas/r8a779f0-ether-serdes.c
@@ -126,7 +126,7 @@ r8a779f0_eth_serdes_chan_setting(struct r8a779f0_eth_serdes_channel *channel)
r8a779f0_eth_serdes_write32(channel->addr, 0x0160, 0x180, 0x0007);
r8a779f0_eth_serdes_write32(channel->addr, 0x01ac, 0x180, 0x0000);
r8a779f0_eth_serdes_write32(channel->addr, 0x00c4, 0x180, 0x0310);
- r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x380, 0x0101);
+ r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x180, 0x0101);
ret = r8a779f0_eth_serdes_reg_wait(channel, 0x00c8, 0x0180, BIT(0), 0);
if (ret)
return ret;
--
GitLab
From c874b6de4cdfa2822a07b479887cd5f87fb5d078 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 21 Dec 2022 17:59:49 +0000
Subject: [PATCH 0732/1167] platform/x86: asus-wmi: Add quirk wmi_ignore_fan
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Some laptops have a fan device listed in their ACPI tables but do not
actually contain a fan.
Introduce a quirk that can be used to override the fan detection logic.
This was observed with a ASUS VivoBook E410MA running firmware
E410MAB.304.
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221221-asus-fan-v1-1-e07f3949725b@weissschuh.net
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/asus-wmi.c | 4 +++-
drivers/platform/x86/asus-wmi.h | 1 +
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 6f81b2844dcbe..4a289ca7e76c9 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -2243,7 +2243,9 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
asus->fan_type = FAN_TYPE_NONE;
asus->agfn_pwm = -1;
- if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
+ if (asus->driver->quirks->wmi_ignore_fan)
+ asus->fan_type = FAN_TYPE_NONE;
+ else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
asus->fan_type = FAN_TYPE_SPEC83;
else if (asus_wmi_has_agfn_fan(asus))
asus->fan_type = FAN_TYPE_AGFN;
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 65316998b898a..a478ebfd34dfa 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -38,6 +38,7 @@ struct quirk_entry {
bool store_backlight_power;
bool wmi_backlight_set_devstate;
bool wmi_force_als_set;
+ bool wmi_ignore_fan;
enum asus_wmi_tablet_switch_mode tablet_switch_mode;
int wapf;
/*
--
GitLab
From 82cc5c6c624c63f7b57214e325e2ea685d924e89 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 21 Dec 2022 17:59:50 +0000
Subject: [PATCH 0733/1167] platform/x86: asus-wmi: Ignore fan on E410MA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The ASUS VivoBook has a fan device described in its ACPI tables but does
not actually contain any physical fan.
Use the quirk to inhibit fan handling.
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221221-asus-fan-v1-2-e07f3949725b@weissschuh.net
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/asus-nb-wmi.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index b34bddda0a9b3..cb15acdf14a30 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -121,6 +121,10 @@ static struct quirk_entry quirk_asus_tablet_mode = {
.tablet_switch_mode = asus_wmi_lid_flip_rog_devid,
};
+static struct quirk_entry quirk_asus_ignore_fan = {
+ .wmi_ignore_fan = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
@@ -473,6 +477,15 @@ static const struct dmi_system_id asus_quirks[] = {
},
.driver_data = &quirk_asus_tablet_mode,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS VivoBook E410MA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E410MA"),
+ },
+ .driver_data = &quirk_asus_ignore_fan,
+ },
{},
};
--
GitLab
From 01fd7e7851ba2275662f771ee17d1f80e7bbfa52 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Wed, 21 Dec 2022 17:59:51 +0000
Subject: [PATCH 0734/1167] platform/x86: asus-wmi: Don't load fan curves
without fan
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If we do not have a fan it does not make sense to load curves for it.
This removes the following warnings from the kernel log:
asus_wmi: fan_curve_get_factory_default (0x00110024) failed: -19
asus_wmi: fan_curve_get_factory_default (0x00110025) failed: -19
Fixes: a2bdf10ce96e ("platform/x86: asus-wmi: Increase FAN_CURVE_BUF_LEN to 32")
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20221221-asus-fan-v1-3-e07f3949725b@weissschuh.net
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/asus-wmi.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 4a289ca7e76c9..104188d70988c 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -2438,6 +2438,9 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available,
*available = false;
+ if (asus->fan_type == FAN_TYPE_NONE)
+ return 0;
+
err = fan_curve_get_factory_default(asus, fan_dev);
if (err) {
return 0;
--
GitLab
From 1af7fef0d9d3fa075bf4e850f705df1fe97d33ce Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 21 Dec 2022 23:07:23 +0100
Subject: [PATCH 0735/1167] platform/x86: dell-privacy: Fix
SW_CAMERA_LENS_COVER reporting
Use KE_VSW instead of KE_SW for the SW_CAMERA_LENS_COVER key_entry
and get the value of the switch from the status field when handling
SW_CAMERA_LENS_COVER events, instead of always reporting 0.
Also correctly set the initial SW_CAMERA_LENS_COVER value.
Fixes: 8af9fa37b8a3 ("platform/x86: dell-privacy: Add support for Dell hardware privacy")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20221221220724.119594-1-hdegoede@redhat.com
---
drivers/platform/x86/dell/dell-wmi-privacy.c | 22 ++++++++++++++------
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/drivers/platform/x86/dell/dell-wmi-privacy.c b/drivers/platform/x86/dell/dell-wmi-privacy.c
index c82b3d6867c5b..915d5deeb971c 100644
--- a/drivers/platform/x86/dell/dell-wmi-privacy.c
+++ b/drivers/platform/x86/dell/dell-wmi-privacy.c
@@ -61,7 +61,7 @@ static const struct key_entry dell_wmi_keymap_type_0012[] = {
/* privacy mic mute */
{ KE_KEY, 0x0001, { KEY_MICMUTE } },
/* privacy camera mute */
- { KE_SW, 0x0002, { SW_CAMERA_LENS_COVER } },
+ { KE_VSW, 0x0002, { SW_CAMERA_LENS_COVER } },
{ KE_END, 0},
};
@@ -115,11 +115,15 @@ bool dell_privacy_process_event(int type, int code, int status)
switch (code) {
case DELL_PRIVACY_AUDIO_EVENT: /* Mic mute */
- case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
priv->last_status = status;
sparse_keymap_report_entry(priv->input_dev, key, 1, true);
ret = true;
break;
+ case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
+ priv->last_status = status;
+ sparse_keymap_report_entry(priv->input_dev, key, !(status & CAMERA_STATUS), false);
+ ret = true;
+ break;
default:
dev_dbg(&priv->wdev->dev, "unknown event type 0x%04x 0x%04x\n", type, code);
}
@@ -304,6 +308,11 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context)
dev_set_drvdata(&wdev->dev, priv);
priv->wdev = wdev;
+
+ ret = get_current_status(priv->wdev);
+ if (ret)
+ return ret;
+
/* create evdev passing interface */
priv->input_dev = devm_input_allocate_device(&wdev->dev);
if (!priv->input_dev)
@@ -331,11 +340,12 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context)
priv->input_dev->name = "Dell Privacy Driver";
priv->input_dev->id.bustype = BUS_HOST;
- ret = input_register_device(priv->input_dev);
- if (ret)
- return ret;
+ /* Report initial camera-cover status */
+ if (priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA))
+ input_report_switch(priv->input_dev, SW_CAMERA_LENS_COVER,
+ !(priv->last_status & CAMERA_STATUS));
- ret = get_current_status(priv->wdev);
+ ret = input_register_device(priv->input_dev);
if (ret)
return ret;
--
GitLab
From 6dc485f9940df8105ea729cbeb7a7d18d409dde5 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 21 Dec 2022 23:07:24 +0100
Subject: [PATCH 0736/1167] platform/x86: dell-privacy: Only register
SW_CAMERA_LENS_COVER if present
Unlike keys where userspace only reacts to keypresses, userspace may act
on switches in both (0 and 1) of their positions.
For example if a SW_TABLET_MODE switch is registered then GNOME will not
automatically show the onscreen keyboard when a text field gets focus on
touchscreen devices when SW_TABLET_MODE reports 0 and when SW_TABLET_MODE
reports 1 libinput will block (filter out) builtin keyboard and touchpad
events.
So to avoid unwanted side-effects EV_SW type inputs should only be
registered if they are actually present, only register SW_CAMERA_LENS_COVER
if it is actually there.
Fixes: 8af9fa37b8a3 ("platform/x86: dell-privacy: Add support for Dell hardware privacy")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20221221220724.119594-2-hdegoede@redhat.com
---
drivers/platform/x86/dell/dell-wmi-privacy.c | 19 +++++++++++++++----
1 file changed, 15 insertions(+), 4 deletions(-)
diff --git a/drivers/platform/x86/dell/dell-wmi-privacy.c b/drivers/platform/x86/dell/dell-wmi-privacy.c
index 915d5deeb971c..c517bd45dd32e 100644
--- a/drivers/platform/x86/dell/dell-wmi-privacy.c
+++ b/drivers/platform/x86/dell/dell-wmi-privacy.c
@@ -296,7 +296,7 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context)
{
struct privacy_wmi_data *priv;
struct key_entry *keymap;
- int ret, i;
+ int ret, i, j;
ret = wmi_has_guid(DELL_PRIVACY_GUID);
if (!ret)
@@ -327,9 +327,20 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context)
/* remap the keymap code with Dell privacy key type 0x12 as prefix
* KEY_MICMUTE scancode will be reported as 0x120001
*/
- for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
- keymap[i] = dell_wmi_keymap_type_0012[i];
- keymap[i].code |= (0x0012 << 16);
+ for (i = 0, j = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
+ /*
+ * Unlike keys where only presses matter, userspace may act
+ * on switches in both of their positions. Only register
+ * SW_CAMERA_LENS_COVER if it is actually there.
+ */
+ if (dell_wmi_keymap_type_0012[i].type == KE_VSW &&
+ dell_wmi_keymap_type_0012[i].sw.code == SW_CAMERA_LENS_COVER &&
+ !(priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA)))
+ continue;
+
+ keymap[j] = dell_wmi_keymap_type_0012[i];
+ keymap[j].code |= (0x0012 << 16);
+ j++;
}
ret = sparse_keymap_setup(priv->input_dev, keymap, NULL);
kfree(keymap);
--
GitLab
From b0907cadabcae6f1248f37a32a6e777f9ff6d4aa Mon Sep 17 00:00:00 2001
From: Adrian Huang <ahuang12@lenovo.com>
Date: Tue, 10 Jan 2023 09:45:12 +0800
Subject: [PATCH 0737/1167] md: fix incorrect declaration about claim_rdev in
md_import_device
Commit fb541ca4c365 ("md: remove lock_bdev / unlock_bdev") removes
wrappers for blkdev_get/blkdev_put. However, the uninitialized local
static variable of pointer type 'claim_rdev' in md_import_device()
is NULL, which leads to the following warning call trace:
WARNING: CPU: 22 PID: 1037 at block/bdev.c:577 bd_prepare_to_claim+0x131/0x150
CPU: 22 PID: 1037 Comm: mdadm Not tainted 6.2.0-rc3+ #69
..
RIP: 0010:bd_prepare_to_claim+0x131/0x150
..
Call Trace:
<TASK>
? _raw_spin_unlock+0x15/0x30
? iput+0x6a/0x220
blkdev_get_by_dev.part.0+0x4b/0x300
md_import_device+0x126/0x1d0
new_dev_store+0x184/0x240
md_attr_store+0x80/0xf0
kernfs_fop_write_iter+0x128/0x1c0
vfs_write+0x2be/0x3c0
ksys_write+0x5f/0xe0
do_syscall_64+0x38/0x90
entry_SYSCALL_64_after_hwframe+0x72/0xdc
It turns out the md device cannot be used:
md: could not open device unknown-block(259,0).
md: md127 stopped.
Fix the issue by declaring the local static variable of struct type
and passing the pointer of the variable to blkdev_get_by_dev().
Fixes: fb541ca4c365 ("md: remove lock_bdev / unlock_bdev")
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Song Liu <song@kernel.org>
---
drivers/md/md.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8af639296b3c8..02b0240e7c715 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3644,7 +3644,7 @@ EXPORT_SYMBOL_GPL(md_rdev_init);
*/
static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor)
{
- static struct md_rdev *claim_rdev; /* just for claiming the bdev */
+ static struct md_rdev claim_rdev; /* just for claiming the bdev */
struct md_rdev *rdev;
sector_t size;
int err;
@@ -3662,7 +3662,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
rdev->bdev = blkdev_get_by_dev(newdev,
FMODE_READ | FMODE_WRITE | FMODE_EXCL,
- super_format == -2 ? claim_rdev : rdev);
+ super_format == -2 ? &claim_rdev : rdev);
if (IS_ERR(rdev->bdev)) {
pr_warn("md: could not open device unknown-block(%u,%u).\n",
MAJOR(newdev), MINOR(newdev));
--
GitLab
From ed058eab22d64c00663563e8e1e112989c65c59f Mon Sep 17 00:00:00 2001
From: Henning Schild <henning.schild@siemens.com>
Date: Thu, 22 Dec 2022 11:37:19 +0100
Subject: [PATCH 0738/1167] platform/x86: simatic-ipc: correct name of a model
What we called IPC427G should be renamed to BX-39A to be more in line
with the actual product name.
Signed-off-by: Henning Schild <henning.schild@siemens.com>
Link: https://lore.kernel.org/r/20221222103720.8546-2-henning.schild@siemens.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/simatic-ipc.c | 2 +-
include/linux/platform_data/x86/simatic-ipc.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/platform/x86/simatic-ipc.c b/drivers/platform/x86/simatic-ipc.c
index ca76076fc706a..2ab1f8da32b01 100644
--- a/drivers/platform/x86/simatic-ipc.c
+++ b/drivers/platform/x86/simatic-ipc.c
@@ -46,7 +46,7 @@ static struct {
{SIMATIC_IPC_IPC427D, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_NONE},
{SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E},
{SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E},
- {SIMATIC_IPC_IPC427G, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCBX_39A, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
};
static int register_platform_devices(u32 station_id)
diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h
index 632320ec8f082..a4a6cba412cbb 100644
--- a/include/linux/platform_data/x86/simatic-ipc.h
+++ b/include/linux/platform_data/x86/simatic-ipc.h
@@ -32,7 +32,7 @@ enum simatic_ipc_station_ids {
SIMATIC_IPC_IPC477E = 0x00000A02,
SIMATIC_IPC_IPC127E = 0x00000D01,
SIMATIC_IPC_IPC227G = 0x00000F01,
- SIMATIC_IPC_IPC427G = 0x00001001,
+ SIMATIC_IPC_IPCBX_39A = 0x00001001,
};
static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len)
--
GitLab
From d348b1d761e358a4ba03fb34aa7e3dbd278db236 Mon Sep 17 00:00:00 2001
From: Henning Schild <henning.schild@siemens.com>
Date: Thu, 22 Dec 2022 11:37:20 +0100
Subject: [PATCH 0739/1167] platform/x86: simatic-ipc: add another model
Add IPC PX-39A support.
Signed-off-by: Henning Schild <henning.schild@siemens.com>
Link: https://lore.kernel.org/r/20221222103720.8546-3-henning.schild@siemens.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/simatic-ipc.c | 1 +
include/linux/platform_data/x86/simatic-ipc.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/drivers/platform/x86/simatic-ipc.c b/drivers/platform/x86/simatic-ipc.c
index 2ab1f8da32b01..b3622419cd1a4 100644
--- a/drivers/platform/x86/simatic-ipc.c
+++ b/drivers/platform/x86/simatic-ipc.c
@@ -47,6 +47,7 @@ static struct {
{SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E},
{SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E},
{SIMATIC_IPC_IPCBX_39A, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCPX_39A, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_227G},
};
static int register_platform_devices(u32 station_id)
diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h
index a4a6cba412cbb..a48bb52409777 100644
--- a/include/linux/platform_data/x86/simatic-ipc.h
+++ b/include/linux/platform_data/x86/simatic-ipc.h
@@ -33,6 +33,7 @@ enum simatic_ipc_station_ids {
SIMATIC_IPC_IPC127E = 0x00000D01,
SIMATIC_IPC_IPC227G = 0x00000F01,
SIMATIC_IPC_IPCBX_39A = 0x00001001,
+ SIMATIC_IPC_IPCPX_39A = 0x00001002,
};
static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len)
--
GitLab
From 6aa5207838ccf79879f212034435a5606f890eea Mon Sep 17 00:00:00 2001
From: Gayatri Kammela <gayatri.kammela@linux.intel.com>
Date: Wed, 28 Dec 2022 15:05:53 -0800
Subject: [PATCH 0740/1167] platform/x86: intel/pmc/core: Add Meteor Lake
mobile support
Add Meteor Lake mobile support to pmc core driver. Meteor Lake mobile
parts reuse all the Meteor Lake PCH IPs.
Cc: David E Box <david.e.box@linux.intel.com>
Signed-off-by: Gayatri Kammela <gayatri.kammela@linux.intel.com>
Link: https://lore.kernel.org/r/20221228230553.2497183-1-gayatri.kammela@linux.intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/intel/pmc/core.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index f1d802f6ec3f9..3a15d32d7644c 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -1029,6 +1029,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, mtl_core_init),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, mtl_core_init),
{}
};
--
GitLab
From ccb32e2be14271a60e9ba89c6d5660cc9998773c Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 29 Dec 2022 11:25:33 +0400
Subject: [PATCH 0741/1167] platform/x86/amd: Fix refcount leak in
amd_pmc_probe
pci_get_domain_bus_and_slot() takes reference, the caller should release
the reference by calling pci_dev_put() after use. Call pci_dev_put() in
the error path to fix this.
Fixes: 3d7d407dfb05 ("platform/x86: amd-pmc: Add support for AMD Spill to DRAM STB feature")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20221229072534.1381432-1-linmq006@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/amd/pmc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c
index 439d282aafd19..8d924986381be 100644
--- a/drivers/platform/x86/amd/pmc.c
+++ b/drivers/platform/x86/amd/pmc.c
@@ -932,7 +932,7 @@ static int amd_pmc_probe(struct platform_device *pdev)
if (enable_stb && (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB)) {
err = amd_pmc_s2d_init(dev);
if (err)
- return err;
+ goto err_pci_dev_put;
}
platform_set_drvdata(pdev, dev);
--
GitLab
From cf5ac2d45f6e4d11ad78e7b10ae9a4121ba5e995 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 11 Jan 2023 21:14:26 +0100
Subject: [PATCH 0742/1167] platform/x86: int3472/discrete: Ensure the
clk/power enable pins are in output mode
acpi_get_and_request_gpiod() does not take a gpio_lookup_flags argument
specifying that the pins direction should be initialized to a specific
value.
This means that in some cases the pins might be left in input mode, causing
the gpiod_set() calls made to enable the clk / regulator to not work.
One example of this problem is the clk-enable GPIO for the ov01a1s sensor
on a Dell Latitude 9420 being left in input mode causing the clk to
never get enabled.
Explicitly set the direction of the pins to output to fix this.
Fixes: 5de691bffe57 ("platform/x86: Add intel_skl_int3472 driver")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Reviewed-by: Daniel Scally <djrscally@gmail.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Link: https://lore.kernel.org/r/20230111201426.947853-1-hdegoede@redhat.com
---
drivers/platform/x86/intel/int3472/clk_and_regulator.c | 3 +++
drivers/platform/x86/intel/int3472/discrete.c | 4 ++++
2 files changed, 7 insertions(+)
diff --git a/drivers/platform/x86/intel/int3472/clk_and_regulator.c b/drivers/platform/x86/intel/int3472/clk_and_regulator.c
index b2342b3d78c72..74dc2cff799ee 100644
--- a/drivers/platform/x86/intel/int3472/clk_and_regulator.c
+++ b/drivers/platform/x86/intel/int3472/clk_and_regulator.c
@@ -181,6 +181,9 @@ int skl_int3472_register_regulator(struct int3472_discrete_device *int3472,
return PTR_ERR(int3472->regulator.gpio);
}
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->regulator.gpio, 0);
+
cfg.dev = &int3472->adev->dev;
cfg.init_data = &init_data;
cfg.ena_gpiod = int3472->regulator.gpio;
diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 974a132db6516..c42c3faa2c32d 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -168,6 +168,8 @@ static int skl_int3472_map_gpio_to_clk(struct int3472_discrete_device *int3472,
return (PTR_ERR(gpio));
int3472->clock.ena_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.ena_gpio, 0);
break;
case INT3472_GPIO_TYPE_PRIVACY_LED:
gpio = acpi_get_and_request_gpiod(path, pin, "int3472,privacy-led");
@@ -175,6 +177,8 @@ static int skl_int3472_map_gpio_to_clk(struct int3472_discrete_device *int3472,
return (PTR_ERR(gpio));
int3472->clock.led_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.led_gpio, 0);
break;
default:
dev_err(int3472->dev, "Invalid GPIO type 0x%02x for clock\n", type);
--
GitLab
From 9fdaca2c1e157dc0a3c0faecf3a6a68e7d8d0c7b Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 11 Jan 2023 22:33:07 +0000
Subject: [PATCH 0743/1167] kselftest: Fix error message for unconfigured LLVM
builds
We are missing a ) when we attempt to complain about not having enough
configuration for clang, resulting in the rather inscrutable error:
../lib.mk:23: *** unterminated call to function 'error': missing ')'. Stop.
Add the required ) so we print the message we were trying to print.
Signed-off-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
tools/testing/selftests/lib.mk | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 291144c284fbc..f7900e75d2306 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -20,7 +20,7 @@ CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH))
ifeq ($(CROSS_COMPILE),)
ifeq ($(CLANG_TARGET_FLAGS),)
-$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk
+$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk)
else
CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS)
endif # CLANG_TARGET_FLAGS
--
GitLab
From 9f907439dc80e4a2fcfb949927b36c036468dbb3 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <tong@infragraf.org>
Date: Wed, 11 Jan 2023 17:29:01 +0800
Subject: [PATCH 0744/1167] bpf: hash map, avoid deadlock with suitable hash
mask
The deadlock still may occur while accessed in NMI and non-NMI
context. Because in NMI, we still may access the same bucket but with
different map_locked index.
For example, on the same CPU, .max_entries = 2, we update the hash map,
with key = 4, while running bpf prog in NMI nmi_handle(), to update
hash map with key = 20, so it will have the same bucket index but have
different map_locked index.
To fix this issue, using min mask to hash again.
Fixes: 20b6cc34ea74 ("bpf: Avoid hashtab deadlock with map_locked")
Signed-off-by: Tonghao Zhang <tong@infragraf.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Song Liu <song@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Hou Tao <houtao1@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230111092903.92389-1-tong@infragraf.org
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
kernel/bpf/hashtab.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 5aa2b5525f793..66bded1443773 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -152,7 +152,7 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
{
unsigned long flags;
- hash = hash & HASHTAB_MAP_LOCK_MASK;
+ hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
preempt_disable();
if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
@@ -171,7 +171,7 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
struct bucket *b, u32 hash,
unsigned long flags)
{
- hash = hash & HASHTAB_MAP_LOCK_MASK;
+ hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
raw_spin_unlock_irqrestore(&b->raw_lock, flags);
__this_cpu_dec(*(htab->map_locked[hash]));
preempt_enable();
--
GitLab
From 579923d84b04abb6cd4cd1fd9974096a2dd1832b Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Wed, 11 Jan 2023 22:58:51 +0530
Subject: [PATCH 0745/1167] amd-xgbe: TX Flow Ctrl Registers are h/w ver
dependent
There is difference in the TX Flow Control registers (TFCR) between the
revisions of the hardware. The older revisions of hardware used to have
single register per queue. Whereas, the newer revision of hardware (from
ver 30H onwards) have one register per priority.
Update the driver to use the TFCR based on the reported version of the
hardware.
Fixes: c5aa9e3b8156 ("amd-xgbe: Initial AMD 10GbE platform driver")
Co-developed-by: Ajith Nayak <Ajith.Nayak@amd.com>
Signed-off-by: Ajith Nayak <Ajith.Nayak@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 23 +++++++++++++++--------
1 file changed, 15 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 3936543a74d8f..4030d619e84f5 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -524,19 +524,28 @@ static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata)
netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n");
}
+static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata)
+{
+ unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
+
+ /* From MAC ver 30H the TFCR is per priority, instead of per queue */
+ if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30)
+ return max_q_count;
+ else
+ return min_t(unsigned int, pdata->tx_q_count, max_q_count);
+}
+
static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata)
{
- unsigned int max_q_count, q_count;
unsigned int reg, reg_val;
- unsigned int i;
+ unsigned int i, q_count;
/* Clear MTL flow control */
for (i = 0; i < pdata->rx_q_count; i++)
XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0);
/* Clear MAC flow control */
- max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
- q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ q_count = xgbe_get_fc_queue_count(pdata);
reg = MAC_Q0TFCR;
for (i = 0; i < q_count; i++) {
reg_val = XGMAC_IOREAD(pdata, reg);
@@ -553,9 +562,8 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata)
{
struct ieee_pfc *pfc = pdata->pfc;
struct ieee_ets *ets = pdata->ets;
- unsigned int max_q_count, q_count;
unsigned int reg, reg_val;
- unsigned int i;
+ unsigned int i, q_count;
/* Set MTL flow control */
for (i = 0; i < pdata->rx_q_count; i++) {
@@ -579,8 +587,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata)
}
/* Set MAC flow control */
- max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
- q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count);
+ q_count = xgbe_get_fc_queue_count(pdata);
reg = MAC_Q0TFCR;
for (i = 0; i < q_count; i++) {
reg_val = XGMAC_IOREAD(pdata, reg);
--
GitLab
From 926446ae24c03311a480fb96eb78f0ce7ea6d091 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Wed, 11 Jan 2023 22:58:52 +0530
Subject: [PATCH 0746/1167] amd-xgbe: Delay AN timeout during KR training
AN restart triggered during KR training not only aborts the KR training
process but also move the HW to unstable state. Driver has to wait upto
500ms or until the KR training is completed before restarting AN cycle.
Fixes: 7c12aa08779c ("amd-xgbe: Move the PHY support into amd-xgbe")
Co-developed-by: Sudheesh Mavila <sudheesh.mavila@amd.com>
Signed-off-by: Sudheesh Mavila <sudheesh.mavila@amd.com>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 24 +++++++++++++++++++++++
drivers/net/ethernet/amd/xgbe/xgbe.h | 2 ++
2 files changed, 26 insertions(+)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 0c5c1b1556830..43fdd111235a6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -496,6 +496,7 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata,
reg |= XGBE_KR_TRAINING_ENABLE;
reg |= XGBE_KR_TRAINING_START;
XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg);
+ pdata->kr_start_time = jiffies;
netif_dbg(pdata, link, pdata->netdev,
"KR training initiated\n");
@@ -632,6 +633,8 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata)
xgbe_switch_mode(pdata);
+ pdata->an_result = XGBE_AN_READY;
+
xgbe_an_restart(pdata);
return XGBE_AN_INCOMPAT_LINK;
@@ -1275,9 +1278,30 @@ static bool xgbe_phy_aneg_done(struct xgbe_prv_data *pdata)
static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata)
{
unsigned long link_timeout;
+ unsigned long kr_time;
+ int wait;
link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ);
if (time_after(jiffies, link_timeout)) {
+ if ((xgbe_cur_mode(pdata) == XGBE_MODE_KR) &&
+ pdata->phy.autoneg == AUTONEG_ENABLE) {
+ /* AN restart should not happen while KR training is in progress.
+ * The while loop ensures no AN restart during KR training,
+ * waits up to 500ms and AN restart is triggered only if KR
+ * training is failed.
+ */
+ wait = XGBE_KR_TRAINING_WAIT_ITER;
+ while (wait--) {
+ kr_time = pdata->kr_start_time +
+ msecs_to_jiffies(XGBE_AN_MS_TIMEOUT);
+ if (time_after(jiffies, kr_time))
+ break;
+ /* AN restart is not required, if AN result is COMPLETE */
+ if (pdata->an_result == XGBE_AN_COMPLETE)
+ return;
+ usleep_range(10000, 11000);
+ }
+ }
netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n");
xgbe_phy_config_aneg(pdata);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 71f24cb479355..7a41367c437dd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -290,6 +290,7 @@
/* Auto-negotiation */
#define XGBE_AN_MS_TIMEOUT 500
#define XGBE_LINK_TIMEOUT 5
+#define XGBE_KR_TRAINING_WAIT_ITER 50
#define XGBE_SGMII_AN_LINK_STATUS BIT(1)
#define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3))
@@ -1280,6 +1281,7 @@ struct xgbe_prv_data {
unsigned int parallel_detect;
unsigned int fec_ability;
unsigned long an_start;
+ unsigned long kr_start_time;
enum xgbe_an_mode an_mode;
/* I2C support */
--
GitLab
From 01644a1f98ff45a4044395ce2bbfd534747e0676 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 11 Jan 2023 18:07:15 +0000
Subject: [PATCH 0747/1167] rxrpc: Fix wrong error return in
rxrpc_connect_call()
Fix rxrpc_connect_call() to return -ENOMEM rather than 0 if it fails to
look up a peer.
This generated a smatch warning:
net/rxrpc/call_object.c:303 rxrpc_connect_call() warn: missing error code 'ret'
I think this also fixes a syzbot-found bug:
rxrpc: Assertion failed - 1(0x1) == 11(0xb) is false
------------[ cut here ]------------
kernel BUG at net/rxrpc/call_object.c:645!
where the call being put is in the wrong state - as would be the case if we
failed to clear up correctly after the error in rxrpc_connect_call().
Fixes: 9d35d880e0e4 ("rxrpc: Move client call connection to the I/O thread")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Reported-and-tested-by: syzbot+4bb6356bb29d6299360e@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/202301111153.9eZRYLf1-lkp@intel.com/
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/2438405.1673460435@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/rxrpc/call_object.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 3ded5a24627c5..f3c9f0201c156 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -294,7 +294,7 @@ static void rxrpc_put_call_slot(struct rxrpc_call *call)
static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
{
struct rxrpc_local *local = call->local;
- int ret = 0;
+ int ret = -ENOMEM;
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
--
GitLab
From ea22f4319c3409d847d70eaaf149cc480a73220d Mon Sep 17 00:00:00 2001
From: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Date: Wed, 11 Jan 2023 15:56:07 -0800
Subject: [PATCH 0748/1167] ethtool: add netlink attr in rss get reply only if
value is not null
Current code for RSS_GET ethtool command includes netlink attributes
in reply message to user space even if they are null. Added checks
to include netlink attribute in reply message only if a value is
received from driver. Drivers might return null for RSS indirection
table or hash key. Instead of including attributes with empty value
in the reply message, add netlink attribute only if there is content.
Fixes: 7112a04664bf ("ethtool: add netlink based get rss support")
Signed-off-by: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Link: https://lore.kernel.org/r/20230111235607.85509-1-sudheer.mogilappagari@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ethtool/rss.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index ebe6145aed3f1..be260ab34e580 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -122,10 +122,13 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
{
const struct rss_reply_data *data = RSS_REPDATA(reply_base);
- if (nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc) ||
- nla_put(skb, ETHTOOL_A_RSS_INDIR,
- sizeof(u32) * data->indir_size, data->indir_table) ||
- nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))
+ if ((data->hfunc &&
+ nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
+ (data->indir_size &&
+ nla_put(skb, ETHTOOL_A_RSS_INDIR,
+ sizeof(u32) * data->indir_size, data->indir_table)) ||
+ (data->hkey_size &&
+ nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)))
return -EMSGSIZE;
return 0;
--
GitLab
From aedee9e8d9224de35081e73e63333a402907c53c Mon Sep 17 00:00:00 2001
From: Peter Foley <pefoley2@pefoley.com>
Date: Thu, 12 Jan 2023 23:23:59 -0500
Subject: [PATCH 0749/1167] kconfig: Update all declared targets
Currently qconf-cfg.sh is the only script that touches the "-bin"
target, even though all of the conf_cfg rules declare that they do.
Make the recipe unconditionally touch all declared targets to avoid
incompatibilities with upcoming versions of GNU make:
https://lists.gnu.org/archive/html/info-gnu/2022-10/msg00008.html
e.g.
scripts/kconfig/Makefile:215: warning: pattern recipe did not update peer target 'scripts/kconfig/nconf-bin'.
scripts/kconfig/Makefile:215: warning: pattern recipe did not update peer target 'scripts/kconfig/mconf-bin'.
scripts/kconfig/Makefile:215: warning: pattern recipe did not update peer target 'scripts/kconfig/gconf-bin'.
Signed-off-by: Peter Foley <pefoley2@pefoley.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/kconfig/.gitignore | 2 +-
scripts/kconfig/Makefile | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore
index c8a3f9cd52f02..0b2ff775b2e33 100644
--- a/scripts/kconfig/.gitignore
+++ b/scripts/kconfig/.gitignore
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
/conf
/[gmnq]conf
+/[gmnq]conf-bin
/[gmnq]conf-cflags
/[gmnq]conf-libs
-/qconf-bin
/qconf-moc.cc
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 0b1d15efaeb0c..af1c96198f491 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -209,7 +209,7 @@ $(obj)/gconf: | $(obj)/gconf-libs
$(obj)/gconf.o: | $(obj)/gconf-cflags
# check if necessary packages are available, and configure build flags
-cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin)
+cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin); touch $(obj)/$*conf-bin
$(obj)/%conf-cflags $(obj)/%conf-libs $(obj)/%conf-bin: $(src)/%conf-cfg.sh
$(call cmd,conf_cfg)
--
GitLab
From 92a9c0ad86d47ff4cce899012e355c400f02cfb8 Mon Sep 17 00:00:00 2001
From: Jaroslav Kysela <perex@perex.cz>
Date: Fri, 13 Jan 2023 09:53:11 +0100
Subject: [PATCH 0750/1167] ALSA: usb-audio: Fix possible NULL pointer
dereference in snd_usb_pcm_has_fixed_rate()
The subs function argument may be NULL, so do not use it before the NULL check.
Fixes: 291e9da91403 ("ALSA: usb-audio: Always initialize fixed_rate in snd_usb_find_implicit_fb_sync_format()")
Reported-by: coverity-bot <keescook@chromium.org>
Link: https://lore.kernel.org/alsa-devel/202301121424.4A79A485@keescook/
Signed-off-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20230113085311.623325-1-perex@perex.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/usb/pcm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 1f72960d0d536..d959da7a1afba 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -160,11 +160,12 @@ find_substream_format(struct snd_usb_substream *subs,
bool snd_usb_pcm_has_fixed_rate(struct snd_usb_substream *subs)
{
const struct audioformat *fp;
- struct snd_usb_audio *chip = subs->stream->chip;
+ struct snd_usb_audio *chip;
int rate = -1;
if (!subs)
return false;
+ chip = subs->stream->chip;
if (!(chip->quirk_flags & QUIRK_FLAG_FIXED_RATE))
return false;
list_for_each_entry(fp, &subs->fmt_list, list) {
--
GitLab
From e26fd28db82899be71b4b949527373d0a6be1e65 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qyousef@layalina.io>
Date: Thu, 12 Jan 2023 12:27:07 +0000
Subject: [PATCH 0751/1167] sched/uclamp: Fix a uninitialized variable warnings
Addresses the following warnings:
> config: riscv-randconfig-m031-20221111
> compiler: riscv64-linux-gcc (GCC) 12.1.0
>
> smatch warnings:
> kernel/sched/fair.c:7263 find_energy_efficient_cpu() error: uninitialized symbol 'util_min'.
> kernel/sched/fair.c:7263 find_energy_efficient_cpu() error: uninitialized symbol 'util_max'.
Fixes: 244226035a1f ("sched/uclamp: Fix fits_capacity() check in feec()")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230112122708.330667-2-qyousef@layalina.io
---
kernel/sched/fair.c | 35 ++++++++++++++++-------------------
1 file changed, 16 insertions(+), 19 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c36aa54ae071a..be43731b147da 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7229,10 +7229,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
eenv_task_busy_time(&eenv, p, prev_cpu);
for (; pd; pd = pd->next) {
+ unsigned long util_min = p_util_min, util_max = p_util_max;
unsigned long cpu_cap, cpu_thermal_cap, util;
unsigned long cur_delta, max_spare_cap = 0;
unsigned long rq_util_min, rq_util_max;
- unsigned long util_min, util_max;
unsigned long prev_spare_cap = 0;
int max_spare_cap_cpu = -1;
unsigned long base_energy;
@@ -7251,6 +7251,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
eenv.pd_cap = 0;
for_each_cpu(cpu, cpus) {
+ struct rq *rq = cpu_rq(cpu);
+
eenv.pd_cap += cpu_thermal_cap;
if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
@@ -7269,24 +7271,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
* much capacity we can get out of the CPU; this is
* aligned with sched_cpu_util().
*/
- if (uclamp_is_used()) {
- if (uclamp_rq_is_idle(cpu_rq(cpu))) {
- util_min = p_util_min;
- util_max = p_util_max;
- } else {
- /*
- * Open code uclamp_rq_util_with() except for
- * the clamp() part. Ie: apply max aggregation
- * only. util_fits_cpu() logic requires to
- * operate on non clamped util but must use the
- * max-aggregated uclamp_{min, max}.
- */
- rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
- rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
-
- util_min = max(rq_util_min, p_util_min);
- util_max = max(rq_util_max, p_util_max);
- }
+ if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
+ /*
+ * Open code uclamp_rq_util_with() except for
+ * the clamp() part. Ie: apply max aggregation
+ * only. util_fits_cpu() logic requires to
+ * operate on non clamped util but must use the
+ * max-aggregated uclamp_{min, max}.
+ */
+ rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX);
+
+ util_min = max(rq_util_min, p_util_min);
+ util_max = max(rq_util_max, p_util_max);
}
if (!util_fits_cpu(util, util_min, util_max, cpu))
continue;
--
GitLab
From da07d2f9c153e457e845d4dcfdd13568d71d18a4 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qyousef@layalina.io>
Date: Thu, 12 Jan 2023 12:27:08 +0000
Subject: [PATCH 0752/1167] sched/fair: Fixes for capacity inversion detection
Traversing the Perf Domains requires rcu_read_lock() to be held and is
conditional on sched_energy_enabled(). Ensure right protections applied.
Also skip capacity inversion detection for our own pd; which was an
error.
Fixes: 44c7b80bffc3 ("sched/fair: Detect capacity inversion")
Reported-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230112122708.330667-3-qyousef@layalina.io
---
kernel/sched/fair.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index be43731b147da..0f87369914274 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8868,16 +8868,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
* * Thermal pressure will impact all cpus in this perf domain
* equally.
*/
- if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+ if (sched_energy_enabled()) {
unsigned long inv_cap = capacity_orig - thermal_load_avg(rq);
- struct perf_domain *pd = rcu_dereference(rq->rd->pd);
+ struct perf_domain *pd;
+
+ rcu_read_lock();
+ pd = rcu_dereference(rq->rd->pd);
rq->cpu_capacity_inverted = 0;
for (; pd; pd = pd->next) {
struct cpumask *pd_span = perf_domain_span(pd);
unsigned long pd_cap_orig, pd_cap;
+ /* We can't be inverted against our own pd */
+ if (cpumask_test_cpu(cpu_of(rq), pd_span))
+ continue;
+
cpu = cpumask_any(pd_span);
pd_cap_orig = arch_scale_cpu_capacity(cpu);
@@ -8902,6 +8909,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
break;
}
}
+
+ rcu_read_unlock();
}
trace_sched_cpu_capacity_tp(rq);
--
GitLab
From fde5f74ccfc771941b018b5415fa9664426e10ad Mon Sep 17 00:00:00 2001
From: Mark Pearson <mpearson-lenovo@squebb.ca>
Date: Thu, 12 Jan 2023 17:12:28 -0500
Subject: [PATCH 0753/1167] platform/x86: thinkpad_acpi: Fix profile mode
display in AMT mode
Recently AMT mode was enabled (somewhat unexpectedly) on the Lenovo
Z13 platform. The FW is advertising it is available and the driver tries
to use it - unfortunately it reports the profile mode incorrectly.
Note, there is also some extra work needed to enable the dynamic aspect
of AMT support that I will be following up with; but more testing is
needed first. This patch just fixes things so the profiles are reported
correctly.
Link: https://gitlab.freedesktop.org/hadess/power-profiles-daemon/-/issues/115
Fixes: 46dcbc61b739 ("platform/x86: thinkpad-acpi: Add support for automatic mode transitions")
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://lore.kernel.org/r/20230112221228.490946-1-mpearson-lenovo@squebb.ca
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/thinkpad_acpi.c | 23 +++++++++++++++++------
1 file changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 1195293b22fdd..a95946800ae9d 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10311,9 +10311,11 @@ static DEFINE_MUTEX(dytc_mutex);
static int dytc_capabilities;
static bool dytc_mmc_get_available;
-static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *profile)
+static int convert_dytc_to_profile(int funcmode, int dytcmode,
+ enum platform_profile_option *profile)
{
- if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
+ switch (funcmode) {
+ case DYTC_FUNCTION_MMC:
switch (dytcmode) {
case DYTC_MODE_MMC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
@@ -10329,8 +10331,7 @@ static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *p
return -EINVAL;
}
return 0;
- }
- if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
+ case DYTC_FUNCTION_PSC:
switch (dytcmode) {
case DYTC_MODE_PSC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
@@ -10344,6 +10345,14 @@ static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *p
default: /* Unknown mode */
return -EINVAL;
}
+ return 0;
+ case DYTC_FUNCTION_AMT:
+ /* For now return balanced. It's the closest we have to 'auto' */
+ *profile = PLATFORM_PROFILE_BALANCED;
+ return 0;
+ default:
+ /* Unknown function */
+ return -EOPNOTSUPP;
}
return 0;
}
@@ -10492,6 +10501,7 @@ static int dytc_profile_set(struct platform_profile_handler *pprof,
err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output);
if (err)
goto unlock;
+
/* system supports AMT, activate it when on balanced */
if (dytc_capabilities & BIT(DYTC_FC_AMT))
dytc_control_amt(profile == PLATFORM_PROFILE_BALANCED);
@@ -10507,7 +10517,7 @@ static void dytc_profile_refresh(void)
{
enum platform_profile_option profile;
int output, err = 0;
- int perfmode;
+ int perfmode, funcmode;
mutex_lock(&dytc_mutex);
if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
@@ -10522,8 +10532,9 @@ static void dytc_profile_refresh(void)
if (err)
return;
+ funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF;
perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
- convert_dytc_to_profile(perfmode, &profile);
+ convert_dytc_to_profile(funcmode, perfmode, &profile);
if (profile != dytc_current_profile) {
dytc_current_profile = profile;
platform_profile_notify();
--
GitLab
From ac9c5e92dd15b9927e7355ccf79df76a58b44344 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Thu, 15 Dec 2022 16:51:55 +0000
Subject: [PATCH 0754/1167] iommu/arm-smmu: Report IOMMU_CAP_CACHE_COHERENCY
even betterer
Although it's vanishingly unlikely that anyone would integrate an SMMU
within a coherent interconnect without also making the pagetable walk
interface coherent, the same effect happens if a coherent SMMU fails to
advertise CTTW correctly. This turns out to be the case on some popular
NXP SoCs, where VFIO started failing the IOMMU_CAP_CACHE_COHERENCY test,
even though IOMMU_CACHE *was* previously achieving the desired effect
anyway thanks to the underlying integration.
While those SoCs stand to gain some more general benefits from a
firmware update to override CTTW correctly in DT/ACPI, it's also easy
to work around this in Linux as well, to avoid imposing too much on
affected users - since the upstream client devices *are* correctly
marked as coherent, we can trivially infer their coherent paths through
the SMMU as well.
Reported-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Fixes: df198b37e72c ("iommu/arm-smmu: Report IOMMU_CAP_CACHE_COHERENCY better")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/d6dc41952961e5c7b21acac08a8bf1eb0f69e124.1671123115.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm/arm-smmu/arm-smmu.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 719fbca1fe52a..443bc517277ba 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -1316,8 +1316,14 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
- /* Assume that a coherent TCU implies coherent TBUs */
- return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
+ /*
+ * It's overwhelmingly the case in practice that when the pagetable
+ * walk interface is connected to a coherent interconnect, all the
+ * translation interfaces are too. Furthermore if the device is
+ * natively coherent, then its translation interface must also be.
+ */
+ return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK ||
+ device_get_dma_attr(dev) == DEV_DMA_COHERENT;
case IOMMU_CAP_NOEXEC:
return true;
default:
--
GitLab
From ce31e6ca68bd7639bd3e5ef97be215031842bbab Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Dec 2022 16:12:50 +0200
Subject: [PATCH 0755/1167] iommu/arm-smmu: Don't unregister on shutdown
Michael Walle says he noticed the following stack trace while performing
a shutdown with "reboot -f". He suggests he got "lucky" and just hit the
correct spot for the reboot while there was a packet transmission in
flight.
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000098
CPU: 0 PID: 23 Comm: kworker/0:1 Not tainted 6.1.0-rc5-00088-gf3600ff8e322 #1930
Hardware name: Kontron KBox A-230-LS (DT)
pc : iommu_get_dma_domain+0x14/0x20
lr : iommu_dma_map_page+0x9c/0x254
Call trace:
iommu_get_dma_domain+0x14/0x20
dma_map_page_attrs+0x1ec/0x250
enetc_start_xmit+0x14c/0x10b0
enetc_xmit+0x60/0xdc
dev_hard_start_xmit+0xb8/0x210
sch_direct_xmit+0x11c/0x420
__dev_queue_xmit+0x354/0xb20
ip6_finish_output2+0x280/0x5b0
__ip6_finish_output+0x15c/0x270
ip6_output+0x78/0x15c
NF_HOOK.constprop.0+0x50/0xd0
mld_sendpack+0x1bc/0x320
mld_ifc_work+0x1d8/0x4dc
process_one_work+0x1e8/0x460
worker_thread+0x178/0x534
kthread+0xe0/0xe4
ret_from_fork+0x10/0x20
Code: d503201f f9416800 d503233f d50323bf (f9404c00)
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Oops: Fatal exception in interrupt
This appears to be reproducible when the board has a fixed IP address,
is ping flooded from another host, and "reboot -f" is used.
The following is one more manifestation of the issue:
$ reboot -f
kvm: exiting hardware virtualization
cfg80211: failed to load regulatory.db
arm-smmu 5000000.iommu: disabling translation
sdhci-esdhc 2140000.mmc: Removing from iommu group 11
sdhci-esdhc 2150000.mmc: Removing from iommu group 12
fsl-edma 22c0000.dma-controller: Removing from iommu group 17
dwc3 3100000.usb: Removing from iommu group 9
dwc3 3110000.usb: Removing from iommu group 10
ahci-qoriq 3200000.sata: Removing from iommu group 2
fsl-qdma 8380000.dma-controller: Removing from iommu group 20
platform f080000.display: Removing from iommu group 0
etnaviv-gpu f0c0000.gpu: Removing from iommu group 1
etnaviv etnaviv: Removing from iommu group 1
caam_jr 8010000.jr: Removing from iommu group 13
caam_jr 8020000.jr: Removing from iommu group 14
caam_jr 8030000.jr: Removing from iommu group 15
caam_jr 8040000.jr: Removing from iommu group 16
fsl_enetc 0000:00:00.0: Removing from iommu group 4
arm-smmu 5000000.iommu: Blocked unknown Stream ID 0x429; boot with "arm-smmu.disable_bypass=0" to allow, but this may have security implications
arm-smmu 5000000.iommu: GFSR 0x80000002, GFSYNR0 0x00000002, GFSYNR1 0x00000429, GFSYNR2 0x00000000
fsl_enetc 0000:00:00.1: Removing from iommu group 5
arm-smmu 5000000.iommu: Blocked unknown Stream ID 0x429; boot with "arm-smmu.disable_bypass=0" to allow, but this may have security implications
arm-smmu 5000000.iommu: GFSR 0x80000002, GFSYNR0 0x00000002, GFSYNR1 0x00000429, GFSYNR2 0x00000000
arm-smmu 5000000.iommu: Blocked unknown Stream ID 0x429; boot with "arm-smmu.disable_bypass=0" to allow, but this may have security implications
arm-smmu 5000000.iommu: GFSR 0x80000002, GFSYNR0 0x00000000, GFSYNR1 0x00000429, GFSYNR2 0x00000000
fsl_enetc 0000:00:00.2: Removing from iommu group 6
fsl_enetc_mdio 0000:00:00.3: Removing from iommu group 8
mscc_felix 0000:00:00.5: Removing from iommu group 3
fsl_enetc 0000:00:00.6: Removing from iommu group 7
pcieport 0001:00:00.0: Removing from iommu group 18
arm-smmu 5000000.iommu: Blocked unknown Stream ID 0x429; boot with "arm-smmu.disable_bypass=0" to allow, but this may have security implications
arm-smmu 5000000.iommu: GFSR 0x00000002, GFSYNR0 0x00000000, GFSYNR1 0x00000429, GFSYNR2 0x00000000
pcieport 0002:00:00.0: Removing from iommu group 19
Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a8
pc : iommu_get_dma_domain+0x14/0x20
lr : iommu_dma_unmap_page+0x38/0xe0
Call trace:
iommu_get_dma_domain+0x14/0x20
dma_unmap_page_attrs+0x38/0x1d0
enetc_unmap_tx_buff.isra.0+0x6c/0x80
enetc_poll+0x170/0x910
__napi_poll+0x40/0x1e0
net_rx_action+0x164/0x37c
__do_softirq+0x128/0x368
run_ksoftirqd+0x68/0x90
smpboot_thread_fn+0x14c/0x190
Code: d503201f f9416800 d503233f d50323bf (f9405400)
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Oops: Fatal exception in interrupt
---[ end Kernel panic - not syncing: Oops: Fatal exception in interrupt ]---
The problem seems to be that iommu_group_remove_device() is allowed to
run with no coordination whatsoever with the shutdown procedure of the
enetc PCI device. In fact, it almost seems as if it implies that the
pci_driver :: shutdown() method is mandatory if DMA is used with an
IOMMU, otherwise this is inevitable. That was never the case; shutdown
methods are optional in device drivers.
This is the call stack that leads to iommu_group_remove_device() during
reboot:
kernel_restart
-> device_shutdown
-> platform_shutdown
-> arm_smmu_device_shutdown
-> arm_smmu_device_remove
-> iommu_device_unregister
-> bus_for_each_dev
-> remove_iommu_group
-> iommu_release_device
-> iommu_group_remove_device
I don't know much about the arm_smmu driver, but
arm_smmu_device_shutdown() invoking arm_smmu_device_remove() looks
suspicious, since it causes the IOMMU device to unregister and that's
where everything starts to unravel. It forces all other devices which
depend on IOMMU groups to also point their ->shutdown() to ->remove(),
which will make reboot slower overall.
There are 2 moments relevant to this behavior. First was commit
b06c076ea962 ("Revert "iommu/arm-smmu: Make arm-smmu explicitly
non-modular"") when arm_smmu_device_shutdown() was made to run the exact
same thing as arm_smmu_device_remove(). Prior to that, there was no
iommu_device_unregister() call in arm_smmu_device_shutdown(). However,
that was benign until commit 57365a04c921 ("iommu: Move bus setup to
IOMMU device registration"), which made iommu_device_unregister() call
remove_iommu_group().
Restore the old shutdown behavior by making remove() call shutdown(),
but shutdown() does not call the remove() specific bits.
Fixes: 57365a04c921 ("iommu: Move bus setup to IOMMU device registration")
Reported-by: Michael Walle <michael@walle.cc>
Tested-by: Michael Walle <michael@walle.cc> # on kontron-sl28
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20221215141251.3688780-1-vladimir.oltean@nxp.com
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm/arm-smmu/arm-smmu.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 443bc517277ba..2ff7a72cf3772 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -2191,19 +2191,16 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
return 0;
}
-static int arm_smmu_device_remove(struct platform_device *pdev)
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
if (!smmu)
- return -ENODEV;
+ return;
if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
dev_notice(&pdev->dev, "disabling translation\n");
- iommu_device_unregister(&smmu->iommu);
- iommu_device_sysfs_remove(&smmu->iommu);
-
arm_smmu_rpm_get(smmu);
/* Turn the thing off */
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
@@ -2215,12 +2212,21 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
clk_bulk_disable(smmu->num_clks, smmu->clks);
clk_bulk_unprepare(smmu->num_clks, smmu->clks);
- return 0;
}
-static void arm_smmu_device_shutdown(struct platform_device *pdev)
+static int arm_smmu_device_remove(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ if (!smmu)
+ return -ENODEV;
+
+ iommu_device_unregister(&smmu->iommu);
+ iommu_device_sysfs_remove(&smmu->iommu);
+
+ arm_smmu_device_shutdown(pdev);
+
+ return 0;
}
static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
--
GitLab
From 32ea2c57dc216b6ad8125fa680d31daa5d421c95 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Dec 2022 16:12:51 +0200
Subject: [PATCH 0756/1167] iommu/arm-smmu-v3: Don't unregister on shutdown
Similar to SMMUv2, this driver calls iommu_device_unregister() from the
shutdown path, which removes the IOMMU groups with no coordination
whatsoever with their users - shutdown methods are optional in device
drivers. This can lead to NULL pointer dereferences in those drivers'
DMA API calls, or worse.
Instead of calling the full arm_smmu_device_remove() from
arm_smmu_device_shutdown(), let's pick only the relevant function call -
arm_smmu_device_disable() - more or less the reverse of
arm_smmu_device_reset() - and call just that from the shutdown path.
Fixes: 57365a04c921 ("iommu: Move bus setup to IOMMU device registration")
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://lore.kernel.org/r/20221215141251.3688780-2-vladimir.oltean@nxp.com
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index ab160198edd6b..f2425b0f0cd62 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -3858,7 +3858,9 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ arm_smmu_device_disable(smmu);
}
static const struct of_device_id arm_smmu_of_match[] = {
--
GitLab
From a6a9a5da68084d5eac6ef85ad09df7fc9c971de4 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Fri, 30 Dec 2022 12:31:00 +0400
Subject: [PATCH 0757/1167] iommu: Fix refcount leak in
iommu_device_claim_dma_owner
iommu_group_get() returns the group with the reference incremented.
Move iommu_group_get() after owner check to fix the refcount leak.
Fixes: 89395ccedbc1 ("iommu: Add device-centric DMA ownership interfaces")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20221230083100.1489569-1-linmq006@gmail.com
[ joro: Remove *group = NULL initialization ]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
drivers/iommu/iommu.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index de91dd88705bd..5f6a85aea501e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3185,14 +3185,16 @@ EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);
*/
int iommu_device_claim_dma_owner(struct device *dev, void *owner)
{
- struct iommu_group *group = iommu_group_get(dev);
+ struct iommu_group *group;
int ret = 0;
- if (!group)
- return -ENODEV;
if (WARN_ON(!owner))
return -EINVAL;
+ group = iommu_group_get(dev);
+ if (!group)
+ return -ENODEV;
+
mutex_lock(&group->mutex);
if (group->owner_cnt) {
if (group->owner != owner) {
--
GitLab
From dcdb3ba7e2a8caae7bfefd603bc22fd0ce9a389c Mon Sep 17 00:00:00 2001
From: Yunfei Wang <yf.wang@mediatek.com>
Date: Wed, 11 Jan 2023 14:38:00 +0800
Subject: [PATCH 0758/1167] iommu/iova: Fix alloc iova overflows issue
In __alloc_and_insert_iova_range, there is an issue that retry_pfn
overflows. The value of iovad->anchor.pfn_hi is ~0UL, then when
iovad->cached_node is iovad->anchor, curr_iova->pfn_hi + 1 will
overflow. As a result, if the retry logic is executed, low_pfn is
updated to 0, and then new_pfn < low_pfn returns false to make the
allocation successful.
This issue occurs in the following two situations:
1. The first iova size exceeds the domain size. When initializing
iova domain, iovad->cached_node is assigned as iovad->anchor. For
example, the iova domain size is 10M, start_pfn is 0x1_F000_0000,
and the iova size allocated for the first time is 11M. The
following is the log information, new->pfn_lo is smaller than
iovad->cached_node.
Example log as follows:
[ 223.798112][T1705487] sh: [name:iova&]__alloc_and_insert_iova_range
start_pfn:0x1f0000,retry_pfn:0x0,size:0xb00,limit_pfn:0x1f0a00
[ 223.799590][T1705487] sh: [name:iova&]__alloc_and_insert_iova_range
success start_pfn:0x1f0000,new->pfn_lo:0x1efe00,new->pfn_hi:0x1f08ff
2. The node with the largest iova->pfn_lo value in the iova domain
is deleted, iovad->cached_node will be updated to iovad->anchor,
and then the alloc iova size exceeds the maximum iova size that can
be allocated in the domain.
After judging that retry_pfn is less than limit_pfn, call retry_pfn+1
to fix the overflow issue.
Signed-off-by: jianjiao zeng <jianjiao.zeng@mediatek.com>
Signed-off-by: Yunfei Wang <yf.wang@mediatek.com>
Cc: <stable@vger.kernel.org> # 5.15.*
Fixes: 4e89dce72521 ("iommu/iova: Retry from last rb tree node if iova search fails")
Acked-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20230111063801.25107-1-yf.wang@mediatek.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
drivers/iommu/iova.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index a44ad92fc5eb7..fe452ce466429 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -197,7 +197,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
curr = __get_cached_rbnode(iovad, limit_pfn);
curr_iova = to_iova(curr);
- retry_pfn = curr_iova->pfn_hi + 1;
+ retry_pfn = curr_iova->pfn_hi;
retry:
do {
@@ -211,7 +211,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
if (high_pfn < size || new_pfn < low_pfn) {
if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
high_pfn = limit_pfn;
- low_pfn = retry_pfn;
+ low_pfn = retry_pfn + 1;
curr = iova_find_limit(iovad, limit_pfn);
curr_iova = to_iova(curr);
goto retry;
--
GitLab
From 142e821f68cf5da79ce722cb9c1323afae30e185 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 19 Dec 2022 19:06:22 +0100
Subject: [PATCH 0759/1167] iommu/mediatek-v1: Fix an error handling path in
mtk_iommu_v1_probe()
A clk, prepared and enabled in mtk_iommu_v1_hw_init(), is not released in
the error handling path of mtk_iommu_v1_probe().
Add the corresponding clk_disable_unprepare(), as already done in the
remove function.
Fixes: b17336c55d89 ("iommu/mediatek: add support for mtk iommu generation one HW")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Yong Wu <yong.wu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/593e7b7d97c6e064b29716b091a9d4fd122241fb.1671473163.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
drivers/iommu/mtk_iommu_v1.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 69682ee068d2b..ca581ff1c7696 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -683,7 +683,7 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev)
ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
dev_name(&pdev->dev));
if (ret)
- return ret;
+ goto out_clk_unprepare;
ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
if (ret)
@@ -698,6 +698,8 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev)
iommu_device_unregister(&data->iommu);
out_sysfs_remove:
iommu_device_sysfs_remove(&data->iommu);
+out_clk_unprepare:
+ clk_disable_unprepare(data->bclk);
return ret;
}
--
GitLab
From 56b88b50565cd8b946a2d00b0c83927b7ebb055e Mon Sep 17 00:00:00 2001
From: Clement Lecigne <clecigne@google.com>
Date: Fri, 13 Jan 2023 13:07:45 +0100
Subject: [PATCH 0760/1167] ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read
to prevent UAF
Takes rwsem lock inside snd_ctl_elem_read instead of snd_ctl_elem_read_user
like it was done for write in commit 1fa4445f9adf1 ("ALSA: control - introduce
snd_ctl_notify_one() helper"). Doing this way we are also fixing the following
locking issue happening in the compat path which can be easily triggered and
turned into an use-after-free.
64-bits:
snd_ctl_ioctl
snd_ctl_elem_read_user
[takes controls_rwsem]
snd_ctl_elem_read [lock properly held, all good]
[drops controls_rwsem]
32-bits:
snd_ctl_ioctl_compat
snd_ctl_elem_write_read_compat
ctl_elem_write_read
snd_ctl_elem_read [missing lock, not good]
CVE-2023-0266 was assigned for this issue.
Cc: stable@kernel.org # 5.13+
Signed-off-by: Clement Lecigne <clecigne@google.com>
Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Link: https://lore.kernel.org/r/20230113120745.25464-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
sound/core/control.c | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/sound/core/control.c b/sound/core/control.c
index 50e7ba66f1876..82aa1af1d1d87 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1203,14 +1203,19 @@ static int snd_ctl_elem_read(struct snd_card *card,
const u32 pattern = 0xdeadbeef;
int ret;
+ down_read(&card->controls_rwsem);
kctl = snd_ctl_find_id(card, &control->id);
- if (kctl == NULL)
- return -ENOENT;
+ if (kctl == NULL) {
+ ret = -ENOENT;
+ goto unlock;
+ }
index_offset = snd_ctl_get_ioff(kctl, &control->id);
vd = &kctl->vd[index_offset];
- if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL)
- return -EPERM;
+ if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) {
+ ret = -EPERM;
+ goto unlock;
+ }
snd_ctl_build_ioff(&control->id, kctl, index_offset);
@@ -1220,7 +1225,7 @@ static int snd_ctl_elem_read(struct snd_card *card,
info.id = control->id;
ret = __snd_ctl_elem_info(card, kctl, &info, NULL);
if (ret < 0)
- return ret;
+ goto unlock;
#endif
if (!snd_ctl_skip_validation(&info))
@@ -1230,7 +1235,7 @@ static int snd_ctl_elem_read(struct snd_card *card,
ret = kctl->get(kctl, control);
snd_power_unref(card);
if (ret < 0)
- return ret;
+ goto unlock;
if (!snd_ctl_skip_validation(&info) &&
sanity_check_elem_value(card, control, &info, pattern) < 0) {
dev_err(card->dev,
@@ -1238,8 +1243,11 @@ static int snd_ctl_elem_read(struct snd_card *card,
control->id.iface, control->id.device,
control->id.subdevice, control->id.name,
control->id.index);
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
+unlock:
+ up_read(&card->controls_rwsem);
return ret;
}
@@ -1253,9 +1261,7 @@ static int snd_ctl_elem_read_user(struct snd_card *card,
if (IS_ERR(control))
return PTR_ERR(control);
- down_read(&card->controls_rwsem);
result = snd_ctl_elem_read(card, control);
- up_read(&card->controls_rwsem);
if (result < 0)
goto error;
--
GitLab
From 1ed8a46256771de283772d482403691807214cf7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Fri, 13 Jan 2023 23:08:04 +0900
Subject: [PATCH 0761/1167] tomoyo: Remove "select SRCU"
Now that the SRCU Kconfig option is unconditionally selected, there is
no longer any point in selecting it. Therefore, remove the "select SRCU"
Kconfig statements.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
security/tomoyo/Kconfig | 1 -
1 file changed, 1 deletion(-)
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
index 772d2ab58fd14..ee0c1f48025bd 100644
--- a/security/tomoyo/Kconfig
+++ b/security/tomoyo/Kconfig
@@ -6,7 +6,6 @@ config SECURITY_TOMOYO
select SECURITYFS
select SECURITY_PATH
select SECURITY_NETWORK
- select SRCU
default n
help
This selects TOMOYO Linux, pathname-based access control.
--
GitLab
From fa17087e244263627a01d6a9b76b8fdaf410de34 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Fri, 13 Jan 2023 23:11:38 +0900
Subject: [PATCH 0762/1167] tomoyo: Update website link
SourceForge.JP was renamed to OSDN in May 2015.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
---
security/tomoyo/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
index ee0c1f48025bd..fad75be5f381d 100644
--- a/security/tomoyo/Kconfig
+++ b/security/tomoyo/Kconfig
@@ -10,7 +10,7 @@ config SECURITY_TOMOYO
help
This selects TOMOYO Linux, pathname-based access control.
Required userspace tools and further information may be
- found at <http://tomoyo.sourceforge.jp/>.
+ found at <https://tomoyo.osdn.jp/>.
If you are unsure how to answer this question, answer N.
config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY
--
GitLab
From 544d163d659d45a206d8929370d5a2984e546cb7 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Thu, 12 Jan 2023 13:08:56 +0000
Subject: [PATCH 0763/1167] io_uring: lock overflowing for IOPOLL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
syzbot reports an issue with overflow filling for IOPOLL:
WARNING: CPU: 0 PID: 28 at io_uring/io_uring.c:734 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734
CPU: 0 PID: 28 Comm: kworker/u4:1 Not tainted 6.2.0-rc3-syzkaller-16369-g358a161a6a9e #0
Workqueue: events_unbound io_ring_exit_work
Call trace:
 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734
 io_req_cqe_overflow+0x5c/0x70 io_uring/io_uring.c:773
 io_fill_cqe_req io_uring/io_uring.h:168 [inline]
 io_do_iopoll+0x474/0x62c io_uring/rw.c:1065
 io_iopoll_try_reap_events+0x6c/0x108 io_uring/io_uring.c:1513
 io_uring_try_cancel_requests+0x13c/0x258 io_uring/io_uring.c:3056
 io_ring_exit_work+0xec/0x390 io_uring/io_uring.c:2869
 process_one_work+0x2d8/0x504 kernel/workqueue.c:2289
 worker_thread+0x340/0x610 kernel/workqueue.c:2436
 kthread+0x12c/0x158 kernel/kthread.c:376
 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:863
There is no real problem for normal IOPOLL as flush is also called with
uring_lock taken, but it's getting more complicated for IOPOLL|SQPOLL,
for which __io_cqring_overflow_flush() happens from the CQ waiting path.
Reported-and-tested-by: syzbot+6805087452d72929404e@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org # 5.10+
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/rw.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 8227af2e1c0f5..9c3ddd46a1adc 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -1062,7 +1062,11 @@ int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
continue;
req->cqe.flags = io_put_kbuf(req, 0);
- io_fill_cqe_req(req->ctx, req);
+ if (unlikely(!__io_fill_cqe_req(ctx, req))) {
+ spin_lock(&ctx->completion_lock);
+ io_req_cqe_overflow(req);
+ spin_unlock(&ctx->completion_lock);
+ }
}
if (unlikely(!nr_events))
--
GitLab
From d3f450533bbcb6dd4d7d59cadc9b61b7321e4ac1 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 9 Jan 2023 10:44:31 +0100
Subject: [PATCH 0764/1167] efi: tpm: Avoid READ_ONCE() for accessing the event
log
Nathan reports that recent kernels built with LTO will crash when doing
EFI boot using Fedora's GRUB and SHIM. The culprit turns out to be a
misaligned load from the TPM event log, which is annotated with
READ_ONCE(), and under LTO, this gets translated into a LDAR instruction
which does not tolerate misaligned accesses.
Interestingly, this does not happen when booting the same kernel
straight from the UEFI shell, and so the fact that the event log may
appear misaligned in memory may be caused by a bug in GRUB or SHIM.
However, using READ_ONCE() to access firmware tables is slightly unusual
in any case, and here, we only need to ensure that 'event' is not
dereferenced again after it gets unmapped, but this is already taken
care of by the implicit barrier() semantics of the early_memunmap()
call.
Cc: <stable@vger.kernel.org>
Cc: Peter Jones <pjones@redhat.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Reported-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://github.com/ClangBuiltLinux/linux/issues/1782
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
include/linux/tpm_eventlog.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 20c0ff54b7a0d..7d68a5cc58816 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -198,8 +198,8 @@ static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *ev
* The loop below will unmap these fields if the log is larger than
* one page, so save them here for reference:
*/
- count = READ_ONCE(event->count);
- event_type = READ_ONCE(event->event_type);
+ count = event->count;
+ event_type = event->event_type;
/* Verify that it's the log header */
if (event_header->pcr_idx != 0 ||
--
GitLab
From e4f4db47794c9f474b184ee1418f42e6a07412b6 Mon Sep 17 00:00:00 2001
From: Luis Gerhorst <gerhorst@cs.fau.de>
Date: Mon, 9 Jan 2023 16:05:46 +0100
Subject: [PATCH 0765/1167] bpf: Fix pointer-leak due to insufficient
speculative store bypass mitigation
To mitigate Spectre v4, 2039f26f3aca ("bpf: Fix leakage due to
insufficient speculative store bypass mitigation") inserts lfence
instructions after 1) initializing a stack slot and 2) spilling a
pointer to the stack.
However, this does not cover cases where a stack slot is first
initialized with a pointer (subject to sanitization) but then
overwritten with a scalar (not subject to sanitization because
the slot was already initialized). In this case, the second write
may be subject to speculative store bypass (SSB) creating a
speculative pointer-as-scalar type confusion. This allows the
program to subsequently leak the numerical pointer value using,
for example, a branch-based cache side channel.
To fix this, also sanitize scalars if they write a stack slot
that previously contained a pointer. Assuming that pointer-spills
are only generated by LLVM on register-pressure, the performance
impact on most real-world BPF programs should be small.
The following unprivileged BPF bytecode drafts a minimal exploit
and the mitigation:
[...]
// r6 = 0 or 1 (skalar, unknown user input)
// r7 = accessible ptr for side channel
// r10 = frame pointer (fp), to be leaked
//
r9 = r10 # fp alias to encourage ssb
*(u64 *)(r9 - 8) = r10 // fp[-8] = ptr, to be leaked
// lfence added here because of pointer spill to stack.
//
// Ommitted: Dummy bpf_ringbuf_output() here to train alias predictor
// for no r9-r10 dependency.
//
*(u64 *)(r10 - 8) = r6 // fp[-8] = scalar, overwrites ptr
// 2039f26f3aca: no lfence added because stack slot was not STACK_INVALID,
// store may be subject to SSB
//
// fix: also add an lfence when the slot contained a ptr
//
r8 = *(u64 *)(r9 - 8)
// r8 = architecturally a scalar, speculatively a ptr
//
// leak ptr using branch-based cache side channel:
r8 &= 1 // choose bit to leak
if r8 == 0 goto SLOW // no mispredict
// architecturally dead code if input r6 is 0,
// only executes speculatively iff ptr bit is 1
r8 = *(u64 *)(r7 + 0) # encode bit in cache (0: slow, 1: fast)
SLOW:
[...]
After running this, the program can time the access to *(r7 + 0) to
determine whether the chosen pointer bit was 0 or 1. Repeat this 64
times to recover the whole address on amd64.
In summary, sanitization can only be skipped if one scalar is
overwritten with another scalar. Scalar-confusion due to speculative
store bypass can not lead to invalid accesses because the pointer
bounds deducted during verification are enforced using branchless
logic. See 979d63d50c0c ("bpf: prevent out of bounds speculation on
pointer arithmetic") for details.
Do not make the mitigation depend on !env->allow_{uninit_stack,ptr_leaks}
because speculative leaks are likely unexpected if these were enabled.
For example, leaking the address to a protected log file may be acceptable
while disabling the mitigation might unintentionally leak the address
into the cached-state of a map that is accessible to unprivileged
processes.
Fixes: 2039f26f3aca ("bpf: Fix leakage due to insufficient speculative store bypass mitigation")
Signed-off-by: Luis Gerhorst <gerhorst@cs.fau.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Henriette Hofmeier <henriette.hofmeier@rub.de>
Link: https://lore.kernel.org/bpf/edc95bad-aada-9cfc-ffe2-fa9bb206583c@cs.fau.de
Link: https://lore.kernel.org/bpf/20230109150544.41465-1-gerhorst@cs.fau.de
---
kernel/bpf/verifier.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4c0985daac02..dbef0b0967ae1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3295,7 +3295,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
bool sanitize = reg && is_spillable_regtype(reg->type);
for (i = 0; i < size; i++) {
- if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ u8 type = state->stack[spi].slot_type[i];
+
+ if (type != STACK_MISC && type != STACK_ZERO) {
sanitize = true;
break;
}
--
GitLab
From 83a7f8e4899fb4cd77c787a3373f3e82b49a080f Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Fri, 13 Jan 2023 16:46:37 +0100
Subject: [PATCH 0766/1167] drm/vc4: bo: Fix unused variable warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit 07a2975c65f2 ("drm/vc4: bo: Fix drmm_mutex_init memory hog")
removed the only use of the ret variable, but didn't remove the
variable itself leading to a unused variable warning.
Remove that variable.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 07a2975c65f2 ("drm/vc4: bo: Fix drmm_mutex_init memory hog")
Reviewed-by: MaÃra Canal <mcanal@igalia.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20230113154637.1704116-1-maxime@cerno.tech
---
drivers/gpu/drm/vc4/vc4_bo.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 29ce2fa72cc4c..c5947ed8cc812 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -395,7 +395,6 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
struct vc4_bo *bo;
- int ret;
if (WARN_ON_ONCE(vc4->is_vc5))
return ERR_PTR(-ENODEV);
--
GitLab
From 5daba914da0e48950e9407ea4d75fa57029c9adc Mon Sep 17 00:00:00 2001
From: Shang XiaoJing <shangxiaojing@huawei.com>
Date: Mon, 5 Dec 2022 19:58:23 +0800
Subject: [PATCH 0767/1167] phy: rockchip-inno-usb2: Fix missing
clk_disable_unprepare() in rockchip_usb2phy_power_on()
The clk_disable_unprepare() should be called in the error handling of
rockchip_usb2phy_power_on().
Fixes: 0e08d2a727e6 ("phy: rockchip-inno-usb2: add a new driver for Rockchip usb2phy")
Signed-off-by: Shang XiaoJing <shangxiaojing@huawei.com>
Link: https://lore.kernel.org/r/20221205115823.16957-1-shangxiaojing@huawei.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/rockchip/phy-rockchip-inno-usb2.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
index e6ededc515239..a0bc10aa79618 100644
--- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
+++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c
@@ -485,8 +485,10 @@ static int rockchip_usb2phy_power_on(struct phy *phy)
return ret;
ret = property_enable(base, &rport->port_cfg->phy_sus, false);
- if (ret)
+ if (ret) {
+ clk_disable_unprepare(rphy->clk480m);
return ret;
+ }
/* waiting for the utmi_clk to become stable */
usleep_range(1500, 2000);
--
GitLab
From d60c471a8670635b65b3d67b6e7aaa263d191cc3 Mon Sep 17 00:00:00 2001
From: Marijn Suijten <marijn.suijten@somainline.org>
Date: Wed, 14 Dec 2022 23:37:32 +0100
Subject: [PATCH 0768/1167] phy: Revert "phy: qualcomm: usb28nm: Add MDM9607
init sequence"
This reverts commit 557a28811c7e0286d3816842032db5eb7bb5f156.
This commit introduced an init sequence from downstream DT [1] in the
driver. As mentioned by the comment above the HSPHY_INIT_CFG macro for
this sequence:
/*
* The macro is used to define an initialization sequence. Each tuple
* is meant to program 'value' into phy register at 'offset' with 'delay'
* in us followed.
*/
Instead of corresponding to offsets into the phy register, the sequence
read by the downstream driver [2] is passed into ulpi_write [3] which
crafts the address-value pair into a new value and writes it into the
same register at USB_ULPI_VIEWPORT [4]. In other words, this init
sequence is programmed into the hardware in a totally different way than
downstream and is unlikely to achieve the desired result, if the hsphy
is working at all.
An alternative method needs to be found to write these init values at
the desired location. Fortunately mdm9607 did not land upstream yet [5]
and should have its compatible revised to use the generic one, instead
of a compatible that writes wrong data to the wrong registers.
[1]: https://android.googlesource.com/kernel/msm/+/android-7.1.0_r0.2/arch/arm/boot/dts/qcom/mdm9607.dtsi#585
[2]: https://android.googlesource.com/kernel/msm/+/android-7.1.0_r0.2/drivers/usb/phy/phy-msm-usb.c#4183
[3]: https://android.googlesource.com/kernel/msm/+/android-7.1.0_r0.2/drivers/usb/phy/phy-msm-usb.c#468
[4]: https://android.googlesource.com/kernel/msm/+/android-7.1.0_r0.2/drivers/usb/phy/phy-msm-usb.c#418
[5]: https://lore.kernel.org/linux-arm-msm/20210805222812.40731-1-konrad.dybcio@somainline.org/
Reported-by: Michael Srba <Michael.Srba@seznam.cz>
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Reviewed-by: Stephan Gerhold <stephan@gerhold.net>
Reviewed-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
Link: https://lore.kernel.org/r/20221214223733.648167-1-marijn.suijten@somainline.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
.../devicetree/bindings/phy/qcom,usb-hs-28nm.yaml | 1 -
drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c | 13 -------------
2 files changed, 14 deletions(-)
diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml
index abcc4373f39e1..ca6a0836b53c4 100644
--- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml
@@ -16,7 +16,6 @@ properties:
compatible:
enum:
- qcom,usb-hs-28nm-femtophy
- - qcom,usb-hs-28nm-mdm9607
reg:
maxItems: 1
diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
index 8807e59a1162c..a52a9bf13b758 100644
--- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
+++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c
@@ -401,26 +401,13 @@ static const struct hsphy_init_seq init_seq_femtophy[] = {
HSPHY_INIT_CFG(0x90, 0x60, 0),
};
-static const struct hsphy_init_seq init_seq_mdm9607[] = {
- HSPHY_INIT_CFG(0x80, 0x44, 0),
- HSPHY_INIT_CFG(0x81, 0x38, 0),
- HSPHY_INIT_CFG(0x82, 0x24, 0),
- HSPHY_INIT_CFG(0x83, 0x13, 0),
-};
-
static const struct hsphy_data hsphy_data_femtophy = {
.init_seq = init_seq_femtophy,
.init_seq_num = ARRAY_SIZE(init_seq_femtophy),
};
-static const struct hsphy_data hsphy_data_mdm9607 = {
- .init_seq = init_seq_mdm9607,
- .init_seq_num = ARRAY_SIZE(init_seq_mdm9607),
-};
-
static const struct of_device_id qcom_snps_hsphy_match[] = {
{ .compatible = "qcom,usb-hs-28nm-femtophy", .data = &hsphy_data_femtophy, },
- { .compatible = "qcom,usb-hs-28nm-mdm9607", .data = &hsphy_data_mdm9607, },
{ },
};
MODULE_DEVICE_TABLE(of, qcom_snps_hsphy_match);
--
GitLab
From fd3a8cff4d4a4acb0af49dd947c822717c053cf7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 10 Jan 2023 12:02:43 -0600
Subject: [PATCH 0769/1167] x86/pci: Treat EfiMemoryMappedIO as reservation of
ECAM space
Normally we reject ECAM space unless it is reported as reserved in the E820
table or via a PNP0C02 _CRS method (PCI Firmware, r3.3, sec 4.1.2).
07eab0901ede ("efi/x86: Remove EfiMemoryMappedIO from E820 map"), removes
E820 entries that correspond to EfiMemoryMappedIO regions because some
other firmware uses EfiMemoryMappedIO for PCI host bridge windows, and the
E820 entries prevent Linux from allocating BAR space for hot-added devices.
Some firmware doesn't report ECAM space via PNP0C02 _CRS methods, but does
mention it as an EfiMemoryMappedIO region via EFI GetMemoryMap(), which is
normally converted to an E820 entry by a bootloader or EFI stub. After
07eab0901ede, that E820 entry is removed, so we reject this ECAM space,
which makes PCI extended config space (offsets 0x100-0xfff) inaccessible.
The lack of extended config space breaks anything that relies on it,
including perf, VSEC telemetry, EDAC, QAT, SR-IOV, etc.
Allow use of ECAM for extended config space when the region is covered by
an EfiMemoryMappedIO region, even if it's not included in E820 or PNP0C02
_CRS.
Link: https://lore.kernel.org/r/ac2693d8-8ba3-72e0-5b66-b3ae008d539d@linux.intel.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216891
Fixes: 07eab0901ede ("efi/x86: Remove EfiMemoryMappedIO from E820 map")
Link: https://lore.kernel.org/r/20230110180243.1590045-3-helgaas@kernel.org
Reported-by: Kan Liang <kan.liang@linux.intel.com>
Reported-by: Tony Luck <tony.luck@intel.com>
Reported-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reported-by: Yunying Sun <yunying.sun@intel.com>
Reported-by: Baowen Zheng <baowen.zheng@corigine.com>
Reported-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reported-by: Yang Lixiao <lixiao.yang@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Yunying Sun <yunying.sun@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Rafael J. Wysocki <rafael@kernel.org>
---
arch/x86/pci/mmconfig-shared.c | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 51c951699b2ed..4b3efaa82ab7c 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -12,6 +12,7 @@
*/
#include <linux/acpi.h>
+#include <linux/efi.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/bitmap.h>
@@ -442,6 +443,32 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used)
return mcfg_res.flags;
}
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+ efi_memory_desc_t *md;
+ u64 size, mmio_start, mmio_end;
+
+ for_each_efi_memory_desc(md) {
+ if (md->type == EFI_MEMORY_MAPPED_IO) {
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ mmio_start = md->phys_addr;
+ mmio_end = mmio_start + size;
+
+ /*
+ * N.B. Caller supplies (start, start + size),
+ * so to match, mmio_end is the first address
+ * *past* the EFI_MEMORY_MAPPED_IO area.
+ */
+ if (mmio_start <= start && end <= mmio_end)
+ return true;
+ }
+ }
+#endif
+
+ return false;
+}
+
typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
@@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e
"MMCONFIG at %pR not reserved in "
"ACPI motherboard resources\n",
&cfg->res);
+
+ if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+ "EfiMemoryMappedIO"))
+ return true;
}
/*
--
GitLab
From b574baa64cf84e7793fe79f4491ae36c16e65a0b Mon Sep 17 00:00:00 2001
From: Richard Zhu <hongxing.zhu@nxp.com>
Date: Mon, 19 Dec 2022 15:12:21 +0800
Subject: [PATCH 0770/1167] phy: freescale: imx8m-pcie: Add one missing error
return
There should be one error return when fail to fetch the perst reset.
Add the missing error return.
Fixes: dce9edff16ee ("phy: freescale: imx8m-pcie: Add i.MX8MP PCIe PHY support")
Signed-off-by: Richard Zhu <hongxing.zhu@nxp.com>
Reviewed-by: Marek Vasut <marex@denx.de>
Link: https://lore.kernel.org/r/1671433941-2037-1-git-send-email-hongxing.zhu@nxp.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/freescale/phy-fsl-imx8m-pcie.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
index 7585e8080b77d..afc63552ecaf7 100644
--- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
+++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c
@@ -255,7 +255,7 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev)
imx8_phy->perst =
devm_reset_control_get_exclusive(dev, "perst");
if (IS_ERR(imx8_phy->perst))
- dev_err_probe(dev, PTR_ERR(imx8_phy->perst),
+ return dev_err_probe(dev, PTR_ERR(imx8_phy->perst),
"Failed to get PCIE PHY PERST control\n");
}
--
GitLab
From f5fe24ef17b5fbe6db49534163e77499fb10ae8c Mon Sep 17 00:00:00 2001
From: Mateusz Guzik <mjguzik@gmail.com>
Date: Fri, 13 Jan 2023 19:44:47 +0100
Subject: [PATCH 0771/1167] lockref: stop doing cpu_relax in the cmpxchg loop
On the x86-64 architecture even a failing cmpxchg grants exclusive
access to the cacheline, making it preferable to retry the failed op
immediately instead of stalling with the pause instruction.
To illustrate the impact, below are benchmark results obtained by
running various will-it-scale tests on top of the 6.2-rc3 kernel and
Cascade Lake (2 sockets * 24 cores * 2 threads) CPU.
All results in ops/s. Note there is some variance in re-runs, but the
code is consistently faster when contention is present.
open3 ("Same file open/close"):
proc stock no-pause
1 805603 814942 (+%1)
2 1054980 1054781 (-0%)
8 1544802 1822858 (+18%)
24 1191064 2199665 (+84%)
48 851582 1469860 (+72%)
96 609481 1427170 (+134%)
fstat2 ("Same file fstat"):
proc stock no-pause
1 3013872 3047636 (+1%)
2 4284687 4400421 (+2%)
8 3257721 5530156 (+69%)
24 2239819 5466127 (+144%)
48 1701072 5256609 (+209%)
96 1269157 6649326 (+423%)
Additionally, a kernel with a private patch to help access() scalability:
access2 ("Same file access"):
proc stock patched patched
+nopause
24 2378041 2005501 5370335 (-15% / +125%)
That is, fixing the problems in access itself *reduces* scalability
after the cacheline ping-pong only happens in lockref with the pause
instruction.
Note that fstat and access benchmarks are not currently integrated into
will-it-scale, but interested parties can find them in pull requests to
said project.
Code at hand has a rather tortured history. First modification showed
up in commit d472d9d98b46 ("lockref: Relax in cmpxchg loop"), written
with Itanium in mind. Later it got patched up to use an arch-dependent
macro to stop doing it on s390 where it caused a significant regression.
Said macro had undergone revisions and was ultimately eliminated later,
going back to cpu_relax.
While I intended to only remove cpu_relax for x86-64, I got the
following comment from Linus:
I would actually prefer just removing it entirely and see if
somebody else hollers. You have the numbers to prove it hurts on
real hardware, and I don't think we have any numbers to the
contrary.
So I think it's better to trust the numbers and remove it as a
failure, than say "let's just remove it on x86-64 and leave
everybody else with the potentially broken code"
Additionally, Will Deacon (maintainer of the arm64 port, one of the
architectures previously benchmarked):
So, from the arm64 side of the fence, I'm perfectly happy just
removing the cpu_relax() calls from lockref.
As such, come back full circle in history and whack it altogether.
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/all/CAGudoHHx0Nqg6DE70zAVA75eV-HXfWyhVMWZ-aSeOofkA_=WdA@mail.gmail.com/
Acked-by: Tony Luck <tony.luck@intel.com> # ia64
Acked-by: Nicholas Piggin <npiggin@gmail.com> # powerpc
Acked-by: Will Deacon <will@kernel.org> # arm64
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
lib/lockref.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/lockref.c b/lib/lockref.c
index 45e93ece8ba0d..2afe4c5d89191 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -23,7 +23,6 @@
} \
if (!--retry) \
break; \
- cpu_relax(); \
} \
} while (0)
--
GitLab
From 22eebaa631c40f3dac169ba781e0de471b83bf45 Mon Sep 17 00:00:00 2001
From: Peter Foley <pefoley2@pefoley.com>
Date: Thu, 12 Jan 2023 23:37:06 -0500
Subject: [PATCH 0772/1167] ata: pata_cs5535: Don't build on UML
This driver uses MSR functions that aren't implemented under UML.
Avoid building it to prevent tripping up allyesconfig.
e.g.
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x3a3): undefined reference to `__tracepoint_read_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x3d2): undefined reference to `__tracepoint_write_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x457): undefined reference to `__tracepoint_write_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x481): undefined reference to `do_trace_write_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x4d5): undefined reference to `do_trace_write_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x4f5): undefined reference to `do_trace_read_msr'
/usr/lib/gcc/x86_64-pc-linux-gnu/12/../../../../x86_64-pc-linux-gnu/bin/ld: pata_cs5535.c:(.text+0x51c): undefined reference to `do_trace_write_msr'
Signed-off-by: Peter Foley <pefoley2@pefoley.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
drivers/ata/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index eceaec33af65b..9695c4404e26a 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -640,6 +640,7 @@ config PATA_CS5530
config PATA_CS5535
tristate "CS5535 PATA support (Experimental)"
depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST))
+ depends on !UML
help
This option enables support for the NatSemi/AMD CS5535
companion chip used with the Geode processor family.
--
GitLab
From da35048f2600633a7f9ba5fa7d6e3b1d0195938b Mon Sep 17 00:00:00 2001
From: Nicholas Piggin <npiggin@gmail.com>
Date: Thu, 12 Jan 2023 20:54:26 +1000
Subject: [PATCH 0773/1167] kallsyms: Fix scheduling with interrupts disabled
in self-test
kallsyms_on_each* may schedule so must not be called with interrupts
disabled. The iteration function could disable interrupts, but this
also changes lookup_symbol() to match the change to the other timing
code.
Reported-by: Erhard F. <erhard_f@mailbox.org>
Link: https://lore.kernel.org/all/bug-216902-206035@https.bugzilla.kernel.org%2F/
Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/oe-lkp/202212251728.8d0872ff-oliver.sang@intel.com
Fixes: 30f3bb09778d ("kallsyms: Add self-test facility")
Tested-by: "Erhard F." <erhard_f@mailbox.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
kernel/kallsyms_selftest.c | 21 ++++++---------------
1 file changed, 6 insertions(+), 15 deletions(-)
diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
index f35d9cc1aab15..bfbc12da33267 100644
--- a/kernel/kallsyms_selftest.c
+++ b/kernel/kallsyms_selftest.c
@@ -157,14 +157,11 @@ static void test_kallsyms_compression_ratio(void)
static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr)
{
u64 t0, t1, t;
- unsigned long flags;
struct test_stat *stat = (struct test_stat *)data;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
(void)kallsyms_lookup_name(name);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
t = t1 - t0;
if (t < stat->min)
@@ -234,18 +231,15 @@ static int find_symbol(void *data, const char *name, struct module *mod, unsigne
static void test_perf_kallsyms_on_each_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
stat.perf = 1;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_symbol(find_symbol, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0);
}
@@ -270,17 +264,14 @@ static int match_symbol(void *data, unsigned long addr)
static void test_perf_kallsyms_on_each_match_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0);
}
--
GitLab
From 3b293487b8752cc42c1cbf8a0447bc6076c075fa Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 12 Jan 2023 15:03:16 -0800
Subject: [PATCH 0774/1167] firmware: coreboot: Check size of table entry and
use flex-array
The memcpy() of the data following a coreboot_table_entry couldn't
be evaluated by the compiler under CONFIG_FORTIFY_SOURCE. To make it
easier to reason about, add an explicit flexible array member to struct
coreboot_device so the entire entry can be copied at once. Additionally,
validate the sizes before copying. Avoids this run-time false positive
warning:
memcpy: detected field-spanning write (size 168) of single field "&device->entry" at drivers/firmware/google/coreboot_table.c:103 (size 8)
Reported-by: Paul Menzel <pmenzel@molgen.mpg.de>
Link: https://lore.kernel.org/all/03ae2704-8c30-f9f0-215b-7cdf4ad35a9a@molgen.mpg.de/
Cc: Jack Rosenthal <jrosenth@chromium.org>
Cc: Guenter Roeck <groeck@chromium.org>
Cc: Julius Werner <jwerner@chromium.org>
Cc: Brian Norris <briannorris@chromium.org>
Cc: Stephen Boyd <swboyd@chromium.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Julius Werner <jwerner@chromium.org>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Link: https://lore.kernel.org/r/20230107031406.gonna.761-kees@kernel.org
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Jack Rosenthal <jrosenth@chromium.org>
Link: https://lore.kernel.org/r/20230112230312.give.446-kees@kernel.org
---
drivers/firmware/google/coreboot_table.c | 9 +++++++--
drivers/firmware/google/coreboot_table.h | 1 +
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c
index 2652c396c4236..33ae94745aef9 100644
--- a/drivers/firmware/google/coreboot_table.c
+++ b/drivers/firmware/google/coreboot_table.c
@@ -93,14 +93,19 @@ static int coreboot_table_populate(struct device *dev, void *ptr)
for (i = 0; i < header->table_entries; i++) {
entry = ptr_entry;
- device = kzalloc(sizeof(struct device) + entry->size, GFP_KERNEL);
+ if (entry->size < sizeof(*entry)) {
+ dev_warn(dev, "coreboot table entry too small!\n");
+ return -EINVAL;
+ }
+
+ device = kzalloc(sizeof(device->dev) + entry->size, GFP_KERNEL);
if (!device)
return -ENOMEM;
device->dev.parent = dev;
device->dev.bus = &coreboot_bus_type;
device->dev.release = coreboot_device_release;
- memcpy(&device->entry, ptr_entry, entry->size);
+ memcpy(device->raw, ptr_entry, entry->size);
switch (device->entry.tag) {
case LB_TAG_CBMEM_ENTRY:
diff --git a/drivers/firmware/google/coreboot_table.h b/drivers/firmware/google/coreboot_table.h
index 37f4d335a606d..d814dca33a084 100644
--- a/drivers/firmware/google/coreboot_table.h
+++ b/drivers/firmware/google/coreboot_table.h
@@ -79,6 +79,7 @@ struct coreboot_device {
struct lb_cbmem_ref cbmem_ref;
struct lb_cbmem_entry cbmem_entry;
struct lb_framebuffer framebuffer;
+ DECLARE_FLEX_ARRAY(u8, raw);
};
};
--
GitLab
From 42633ed852deadc14d44660ad71e2f6640239120 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Thu, 12 Jan 2023 22:49:48 +0000
Subject: [PATCH 0775/1167] kbuild: Fix CFI hash randomization with KASAN
Clang emits a asan.module_ctor constructor to each object file
when KASAN is enabled, and these functions are indirectly called
in do_ctors. With CONFIG_CFI_CLANG, the compiler also emits a CFI
type hash before each address-taken global function so they can
pass indirect call checks.
However, in commit 0c3e806ec0f9 ("x86/cfi: Add boot time hash
randomization"), x86 implemented boot time hash randomization,
which relies on the .cfi_sites section generated by objtool. As
objtool is run against vmlinux.o instead of individual object
files with X86_KERNEL_IBT (enabled by default), CFI types in
object files that are not part of vmlinux.o end up not being
included in .cfi_sites, and thus won't get randomized and trip
CFI when called.
Only .vmlinux.export.o and init/version-timestamp.o are linked
into vmlinux separately from vmlinux.o. As these files don't
contain any functions, disable KASAN for both of them to avoid
breaking hash randomization.
Link: https://github.com/ClangBuiltLinux/linux/issues/1742
Fixes: 0c3e806ec0f9 ("x86/cfi: Add boot time hash randomization")
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20230112224948.1479453-2-samitolvanen@google.com
---
init/Makefile | 1 +
scripts/Makefile.vmlinux | 1 +
2 files changed, 2 insertions(+)
diff --git a/init/Makefile b/init/Makefile
index 8316c23bead26..26de459006c4e 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -59,3 +59,4 @@ include/generated/utsversion.h: FORCE
$(obj)/version-timestamp.o: include/generated/utsversion.h
CFLAGS_version-timestamp.o := -include include/generated/utsversion.h
+KASAN_SANITIZE_version-timestamp.o := n
diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
index 49946cb968440..10176dec97eac 100644
--- a/scripts/Makefile.vmlinux
+++ b/scripts/Makefile.vmlinux
@@ -18,6 +18,7 @@ quiet_cmd_cc_o_c = CC $@
$(call if_changed_dep,cc_o_c)
ifdef CONFIG_MODULES
+KASAN_SANITIZE_.vmlinux.export.o := n
targets += .vmlinux.export.o
vmlinux: .vmlinux.export.o
endif
--
GitLab
From 84ed64b1a7a7fcd507598dee7708c1f225123711 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Tue, 10 Jan 2023 13:53:10 +0100
Subject: [PATCH 0776/1167] scsi: target: core: Fix warning on RT kernels
Calling spin_lock_irqsave() does not disable the interrupts on realtime
kernels, remove the warning and replace assert_spin_locked() with
lockdep_assert_held().
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230110125310.55884-1-mlombard@redhat.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/target/target_core_tmr.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index bac111456fa1d..2b95b4550a637 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -73,8 +73,8 @@ static bool __target_check_io_state(struct se_cmd *se_cmd,
{
struct se_session *sess = se_cmd->se_sess;
- assert_spin_locked(&sess->sess_cmd_lock);
- WARN_ON_ONCE(!irqs_disabled());
+ lockdep_assert_held(&sess->sess_cmd_lock);
+
/*
* If command already reached CMD_T_COMPLETE state within
* target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
--
GitLab
From 4bb4db7f3187c6e3de6b229ffc87cdb30a2d22b6 Mon Sep 17 00:00:00 2001
From: Jisoo Jang <jisoo.jang@yonsei.ac.kr>
Date: Wed, 11 Jan 2023 22:19:14 +0900
Subject: [PATCH 0777/1167] net: nfc: Fix use-after-free in local_cleanup()
Fix a use-after-free that occurs in kfree_skb() called from
local_cleanup(). This could happen when killing nfc daemon (e.g. neard)
after detaching an nfc device.
When detaching an nfc device, local_cleanup() called from
nfc_llcp_unregister_device() frees local->rx_pending and decreases
local->ref by kref_put() in nfc_llcp_local_put().
In the terminating process, nfc daemon releases all sockets and it leads
to decreasing local->ref. After the last release of local->ref,
local_cleanup() called from local_release() frees local->rx_pending
again, which leads to the bug.
Setting local->rx_pending to NULL in local_cleanup() could prevent
use-after-free when local_cleanup() is called twice.
Found by a modified version of syzkaller.
BUG: KASAN: use-after-free in kfree_skb()
Call Trace:
dump_stack_lvl (lib/dump_stack.c:106)
print_address_description.constprop.0.cold (mm/kasan/report.c:306)
kasan_check_range (mm/kasan/generic.c:189)
kfree_skb (net/core/skbuff.c:955)
local_cleanup (net/nfc/llcp_core.c:159)
nfc_llcp_local_put.part.0 (net/nfc/llcp_core.c:172)
nfc_llcp_local_put (net/nfc/llcp_core.c:181)
llcp_sock_destruct (net/nfc/llcp_sock.c:959)
__sk_destruct (net/core/sock.c:2133)
sk_destruct (net/core/sock.c:2181)
__sk_free (net/core/sock.c:2192)
sk_free (net/core/sock.c:2203)
llcp_sock_release (net/nfc/llcp_sock.c:646)
__sock_release (net/socket.c:650)
sock_close (net/socket.c:1365)
__fput (fs/file_table.c:306)
task_work_run (kernel/task_work.c:179)
ptrace_notify (kernel/signal.c:2354)
syscall_exit_to_user_mode_prepare (kernel/entry/common.c:278)
syscall_exit_to_user_mode (kernel/entry/common.c:296)
do_syscall_64 (arch/x86/entry/common.c:86)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:106)
Allocated by task 4719:
kasan_save_stack (mm/kasan/common.c:45)
__kasan_slab_alloc (mm/kasan/common.c:325)
slab_post_alloc_hook (mm/slab.h:766)
kmem_cache_alloc_node (mm/slub.c:3497)
__alloc_skb (net/core/skbuff.c:552)
pn533_recv_response (drivers/nfc/pn533/usb.c:65)
__usb_hcd_giveback_urb (drivers/usb/core/hcd.c:1671)
usb_giveback_urb_bh (drivers/usb/core/hcd.c:1704)
tasklet_action_common.isra.0 (kernel/softirq.c:797)
__do_softirq (kernel/softirq.c:571)
Freed by task 1901:
kasan_save_stack (mm/kasan/common.c:45)
kasan_set_track (mm/kasan/common.c:52)
kasan_save_free_info (mm/kasan/genericdd.c:518)
__kasan_slab_free (mm/kasan/common.c:236)
kmem_cache_free (mm/slub.c:3809)
kfree_skbmem (net/core/skbuff.c:874)
kfree_skb (net/core/skbuff.c:931)
local_cleanup (net/nfc/llcp_core.c:159)
nfc_llcp_unregister_device (net/nfc/llcp_core.c:1617)
nfc_unregister_device (net/nfc/core.c:1179)
pn53x_unregister_nfc (drivers/nfc/pn533/pn533.c:2846)
pn533_usb_disconnect (drivers/nfc/pn533/usb.c:579)
usb_unbind_interface (drivers/usb/core/driver.c:458)
device_release_driver_internal (drivers/base/dd.c:1279)
bus_remove_device (drivers/base/bus.c:529)
device_del (drivers/base/core.c:3665)
usb_disable_device (drivers/usb/core/message.c:1420)
usb_disconnect (drivers/usb/core.c:2261)
hub_event (drivers/usb/core/hub.c:5833)
process_one_work (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:212 include/trace/events/workqueue.h:108 kernel/workqueue.c:2281)
worker_thread (include/linux/list.h:282 kernel/workqueue.c:2423)
kthread (kernel/kthread.c:319)
ret_from_fork (arch/x86/entry/entry_64.S:301)
Fixes: 3536da06db0b ("NFC: llcp: Clean local timers and works when removing a device")
Signed-off-by: Jisoo Jang <jisoo.jang@yonsei.ac.kr>
Link: https://lore.kernel.org/r/20230111131914.3338838-1-jisoo.jang@yonsei.ac.kr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/nfc/llcp_core.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index 3364caabef8b1..a27e1842b2a09 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -157,6 +157,7 @@ static void local_cleanup(struct nfc_llcp_local *local)
cancel_work_sync(&local->rx_work);
cancel_work_sync(&local->timeout_work);
kfree_skb(local->rx_pending);
+ local->rx_pending = NULL;
del_timer_sync(&local->sdreq_timer);
cancel_work_sync(&local->sdreq_timeout_work);
nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs);
--
GitLab
From 488e0bf7f34af3d42d1d5e56f7a5a7beaff188a3 Mon Sep 17 00:00:00 2001
From: Esina Ekaterina <eesina@astralinux.ru>
Date: Thu, 12 Jan 2023 10:47:03 +0300
Subject: [PATCH 0778/1167] net: wan: Add checks for NULL for utdm in
undo_uhdlc_init and unmap_si_regs
If uhdlc_priv_tsa != 1 then utdm is not initialized.
And if ret != NULL then goto undo_uhdlc_init, where
utdm is dereferenced. Same if dev == NULL.
Found by Astra Linux on behalf of Linux Verification Center
(linuxtesting.org) with SVACE.
Fixes: 8d68100ab4ad ("soc/fsl/qe: fix err handling of ucc_of_parse_tdm")
Signed-off-by: Esina Ekaterina <eesina@astralinux.ru>
Link: https://lore.kernel.org/r/20230112074703.13558-1-eesina@astralinux.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/wan/fsl_ucc_hdlc.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 22edea6ca4b81..1c53b55469270 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -1243,9 +1243,11 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
free_dev:
free_netdev(dev);
undo_uhdlc_init:
- iounmap(utdm->siram);
+ if (utdm)
+ iounmap(utdm->siram);
unmap_si_regs:
- iounmap(utdm->si_regs);
+ if (utdm)
+ iounmap(utdm->si_regs);
free_utdm:
if (uhdlc_priv->tsa)
kfree(utdm);
--
GitLab
From 3c463721a73bdb57a913e0d3124677a3758886fc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 12 Jan 2023 12:54:40 +0200
Subject: [PATCH 0779/1167] net: enetc: avoid deadlock in
enetc_tx_onestep_tstamp()
This lockdep splat says it better than I could:
================================
WARNING: inconsistent lock state
6.2.0-rc2-07010-ga9b9500ffaac-dirty #967 Not tainted
--------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
kworker/1:3/179 [HC0[0]:SC0[0]:HE1:SE1] takes:
ffff3ec4036ce098 (_xmit_ETHER#2){+.?.}-{3:3}, at: netif_freeze_queues+0x5c/0xc0
{IN-SOFTIRQ-W} state was registered at:
_raw_spin_lock+0x5c/0xc0
sch_direct_xmit+0x148/0x37c
__dev_queue_xmit+0x528/0x111c
ip6_finish_output2+0x5ec/0xb7c
ip6_finish_output+0x240/0x3f0
ip6_output+0x78/0x360
ndisc_send_skb+0x33c/0x85c
ndisc_send_rs+0x54/0x12c
addrconf_rs_timer+0x154/0x260
call_timer_fn+0xb8/0x3a0
__run_timers.part.0+0x214/0x26c
run_timer_softirq+0x3c/0x74
__do_softirq+0x14c/0x5d8
____do_softirq+0x10/0x20
call_on_irq_stack+0x2c/0x5c
do_softirq_own_stack+0x1c/0x30
__irq_exit_rcu+0x168/0x1a0
irq_exit_rcu+0x10/0x40
el1_interrupt+0x38/0x64
irq event stamp: 7825
hardirqs last enabled at (7825): [<ffffdf1f7200cae4>] exit_to_kernel_mode+0x34/0x130
hardirqs last disabled at (7823): [<ffffdf1f708105f0>] __do_softirq+0x550/0x5d8
softirqs last enabled at (7824): [<ffffdf1f7081050c>] __do_softirq+0x46c/0x5d8
softirqs last disabled at (7811): [<ffffdf1f708166e0>] ____do_softirq+0x10/0x20
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(_xmit_ETHER#2);
<Interrupt>
lock(_xmit_ETHER#2);
*** DEADLOCK ***
3 locks held by kworker/1:3/179:
#0: ffff3ec400004748 ((wq_completion)events){+.+.}-{0:0}, at: process_one_work+0x1f4/0x6c0
#1: ffff80000a0bbdc8 ((work_completion)(&priv->tx_onestep_tstamp)){+.+.}-{0:0}, at: process_one_work+0x1f4/0x6c0
#2: ffff3ec4036cd438 (&dev->tx_global_lock){+.+.}-{3:3}, at: netif_tx_lock+0x1c/0x34
Workqueue: events enetc_tx_onestep_tstamp
Call trace:
print_usage_bug.part.0+0x208/0x22c
mark_lock+0x7f0/0x8b0
__lock_acquire+0x7c4/0x1ce0
lock_acquire.part.0+0xe0/0x220
lock_acquire+0x68/0x84
_raw_spin_lock+0x5c/0xc0
netif_freeze_queues+0x5c/0xc0
netif_tx_lock+0x24/0x34
enetc_tx_onestep_tstamp+0x20/0x100
process_one_work+0x28c/0x6c0
worker_thread+0x74/0x450
kthread+0x118/0x11c
but I'll say it anyway: the enetc_tx_onestep_tstamp() work item runs in
process context, therefore with softirqs enabled (i.o.w., it can be
interrupted by a softirq). If we hold the netif_tx_lock() when there is
an interrupt, and the NET_TX softirq then gets scheduled, this will take
the netif_tx_lock() a second time and deadlock the kernel.
To solve this, use netif_tx_lock_bh(), which blocks softirqs from
running.
Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230112105440.1786799-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/freescale/enetc/enetc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 3a79ead5219ae..e96449eedfb54 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2290,14 +2290,14 @@ static void enetc_tx_onestep_tstamp(struct work_struct *work)
priv = container_of(work, struct enetc_ndev_priv, tx_onestep_tstamp);
- netif_tx_lock(priv->ndev);
+ netif_tx_lock_bh(priv->ndev);
clear_bit_unlock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS, &priv->flags);
skb = skb_dequeue(&priv->tx_skbs);
if (skb)
enetc_start_xmit(skb, priv->ndev);
- netif_tx_unlock(priv->ndev);
+ netif_tx_unlock_bh(priv->ndev);
}
static void enetc_tx_onestep_tstamp_init(struct enetc_ndev_priv *priv)
--
GitLab
From 925f3deb45df73173a33e1e81db77575f4ffde39 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <clement.leger@bootlin.com>
Date: Thu, 12 Jan 2023 17:13:11 +0100
Subject: [PATCH 0780/1167] net: lan966x: add missing fwnode_handle_put() for
ports node
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Since the "ethernet-ports" node is retrieved using
device_get_named_child_node(), it should be release after using it. Add
missing fwnode_handle_put() and move the code that retrieved the node
from device-tree to avoid complicated handling in case of error.
Fixes: db8bcaad5393 ("net: lan966x: add the basic lan966x driver")
Signed-off-by: Clément Léger <clement.leger@bootlin.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://lore.kernel.org/r/20230112161311.495124-1-clement.leger@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../net/ethernet/microchip/lan966x/lan966x_main.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index cadde20505ba0..580c91d24a528 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -1043,11 +1043,6 @@ static int lan966x_probe(struct platform_device *pdev)
lan966x->base_mac[5] &= 0xf0;
}
- ports = device_get_named_child_node(&pdev->dev, "ethernet-ports");
- if (!ports)
- return dev_err_probe(&pdev->dev, -ENODEV,
- "no ethernet-ports child found\n");
-
err = lan966x_create_targets(pdev, lan966x);
if (err)
return dev_err_probe(&pdev->dev, err,
@@ -1125,6 +1120,11 @@ static int lan966x_probe(struct platform_device *pdev)
}
}
+ ports = device_get_named_child_node(&pdev->dev, "ethernet-ports");
+ if (!ports)
+ return dev_err_probe(&pdev->dev, -ENODEV,
+ "no ethernet-ports child found\n");
+
/* init switch */
lan966x_init(lan966x);
lan966x_stats_init(lan966x);
@@ -1162,6 +1162,8 @@ static int lan966x_probe(struct platform_device *pdev)
goto cleanup_ports;
}
+ fwnode_handle_put(ports);
+
lan966x_mdb_init(lan966x);
err = lan966x_fdb_init(lan966x);
if (err)
@@ -1191,6 +1193,7 @@ static int lan966x_probe(struct platform_device *pdev)
lan966x_fdb_deinit(lan966x);
cleanup_ports:
+ fwnode_handle_put(ports);
fwnode_handle_put(portnp);
lan966x_cleanup_ports(lan966x);
--
GitLab
From 6bc1fe7dd748ba5e76e7917d110837cafe7b931c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 12 Jan 2023 18:42:51 +0100
Subject: [PATCH 0781/1167] mptcp: explicitly specify sock family at subflow
creation time
Let the caller specify the to-be-created subflow family.
For a given MPTCP socket created with the AF_INET6 family, the current
userspace PM can already ask the kernel to create subflows in v4 and v6.
If "plain" IPv4 addresses are passed to the kernel, they are
automatically mapped in v6 addresses "by accident". This can be
problematic because the userspace will need to pass different addresses,
now the v4-mapped-v6 addresses to destroy this new subflow.
On the other hand, if the MPTCP socket has been created with the AF_INET
family, the command to create a subflow in v6 will be accepted but the
result will not be the one as expected as new subflow will be created in
IPv4 using part of the v6 addresses passed to the kernel: not creating
the expected subflow then.
No functional change intended for the in-kernel PM where an explicit
enforcement is currently in place. This arbitrary enforcement will be
leveraged by other patches in a future version.
Fixes: 702c2f646d42 ("mptcp: netlink: allow userspace-driven subflow establishment")
Cc: stable@vger.kernel.org
Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/mptcp/protocol.c | 2 +-
net/mptcp/protocol.h | 3 ++-
net/mptcp/subflow.c | 9 +++++----
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index b7ad030dfe891..8cd6cc67c2c5c 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -98,7 +98,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
struct socket *ssock;
int err;
- err = mptcp_subflow_create_socket(sk, &ssock);
+ err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock);
if (err)
return err;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a0d1658ce59ee..a9e0355744b6a 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -641,7 +641,8 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
const struct mptcp_addr_info *remote);
-int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
+int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
+ struct socket **new_sock);
void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
struct sockaddr_storage *addr,
unsigned short family);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index bd387d4b5a38f..ec54413fb31f7 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1547,7 +1547,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
if (!mptcp_is_fully_established(sk))
goto err_out;
- err = mptcp_subflow_create_socket(sk, &sf);
+ err = mptcp_subflow_create_socket(sk, loc->family, &sf);
if (err)
goto err_out;
@@ -1660,7 +1660,9 @@ static void mptcp_subflow_ops_undo_override(struct sock *ssk)
#endif
ssk->sk_prot = &tcp_prot;
}
-int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
+
+int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
+ struct socket **new_sock)
{
struct mptcp_subflow_context *subflow;
struct net *net = sock_net(sk);
@@ -1673,8 +1675,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
if (unlikely(!sk->sk_socket))
return -EINVAL;
- err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
- &sf);
+ err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf);
if (err)
return err;
--
GitLab
From fb00ee4f3343acb2b9222ca9b73b47dd1e1a8efc Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 12 Jan 2023 18:42:52 +0100
Subject: [PATCH 0782/1167] mptcp: netlink: respect v4/v6-only sockets
If an MPTCP socket has been created with AF_INET6 and the IPV6_V6ONLY
option has been set, the userspace PM would allow creating subflows
using IPv4 addresses, e.g. mapped in v6.
The kernel side of userspace PM will also accept creating subflows with
local and remote addresses having different families. Depending on the
subflow socket's family, different behaviours are expected:
- If AF_INET is forced with a v6 address, the kernel will take the last
byte of the IP and try to connect to that: a new subflow is created
but to a non expected address.
- If AF_INET6 is forced with a v4 address, the kernel will try to
connect to a v4 address (v4-mapped-v6). A -EBADF error from the
connect() part is then expected.
It is then required to check the given families can be accepted. This is
done by using a new helper for addresses family matching, taking care of
IPv4 vs IPv4-mapped-IPv6 addresses. This helper will be re-used later by
the in-kernel path-manager to use mixed IPv4 and IPv6 addresses.
While at it, a clear error message is now reported if there are some
conflicts with the families that have been passed by the userspace.
Fixes: 702c2f646d42 ("mptcp: netlink: allow userspace-driven subflow establishment")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/mptcp/pm.c | 25 +++++++++++++++++++++++++
net/mptcp/pm_userspace.c | 7 +++++++
net/mptcp/protocol.h | 3 +++
3 files changed, 35 insertions(+)
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 45e2a48397b95..70f0ced3ca86e 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -420,6 +420,31 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
}
}
+/* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
+ * otherwise allow any matching local/remote pair
+ */
+bool mptcp_pm_addr_families_match(const struct sock *sk,
+ const struct mptcp_addr_info *loc,
+ const struct mptcp_addr_info *rem)
+{
+ bool mptcp_is_v4 = sk->sk_family == AF_INET;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+ bool loc_is_v4 = loc->family == AF_INET || ipv6_addr_v4mapped(&loc->addr6);
+ bool rem_is_v4 = rem->family == AF_INET || ipv6_addr_v4mapped(&rem->addr6);
+
+ if (mptcp_is_v4)
+ return loc_is_v4 && rem_is_v4;
+
+ if (ipv6_only_sock(sk))
+ return !loc_is_v4 && !rem_is_v4;
+
+ return loc_is_v4 == rem_is_v4;
+#else
+ return mptcp_is_v4 && loc->family == AF_INET && rem->family == AF_INET;
+#endif
+}
+
void mptcp_pm_data_reset(struct mptcp_sock *msk)
{
u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 65dcc55a8ad89..ea6ad9da74930 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -294,6 +294,13 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info)
}
sk = (struct sock *)msk;
+
+ if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) {
+ GENL_SET_ERR_MSG(info, "families mismatch");
+ err = -EINVAL;
+ goto create_err;
+ }
+
lock_sock(sk);
err = __mptcp_subflow_connect(sk, &addr_l, &addr_r);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a9e0355744b6a..601469249da80 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -777,6 +777,9 @@ int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
bool require_family,
struct mptcp_pm_addr_entry *entry);
+bool mptcp_pm_addr_families_match(const struct sock *sk,
+ const struct mptcp_addr_info *loc,
+ const struct mptcp_addr_info *rem);
void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
--
GitLab
From 4656d72c1efa495a58ad6d8b073a60907073e4e6 Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 12 Jan 2023 18:42:53 +0100
Subject: [PATCH 0783/1167] selftests: mptcp: userspace: validate v4-v6
subflows mix
MPTCP protocol supports having subflows in both IPv4 and IPv6. In Linux,
it is possible to have that if the MPTCP socket has been created with
AF_INET6 family without the IPV6_V6ONLY option.
Here, a new IPv4 subflow is being added to the initial IPv6 connection,
then being removed using Netlink commands.
Cc: stable@vger.kernel.org # v5.19+
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../selftests/net/mptcp/userspace_pm.sh | 47 +++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index a29deb9fa024c..ab2d581f28a1d 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -752,6 +752,52 @@ test_subflows()
"$server4_token" > /dev/null 2>&1
}
+test_subflows_v4_v6_mix()
+{
+ # Attempt to add a listener at 10.0.2.1:<subflow-port>
+ ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\
+ $app6_port > /dev/null 2>&1 &
+ local listener_pid=$!
+
+ # ADD_ADDR4 from server to client machine reusing the subflow port on
+ # the established v6 connection
+ :>"$client_evts"
+ ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\
+ $server_addr_id dev ns1eth2 > /dev/null 2>&1
+ stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id
+ sleep 0.5
+ verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\
+ "$server_addr_id" "$app6_port"
+
+ # CREATE_SUBFLOW from client to server machine
+ :>"$client_evts"
+ ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\
+ $app6_port token "$client6_token" > /dev/null 2>&1
+ sleep 0.5
+ verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\
+ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+ "$server_addr_id" "ns2" "ns1"
+
+ # Delete the listener from the server ns, if one was created
+ kill_wait $listener_pid
+
+ sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts")
+
+ # DESTROY_SUBFLOW from client to server machine
+ :>"$client_evts"
+ ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\
+ $app6_port token "$client6_token" > /dev/null 2>&1
+ sleep 0.5
+ verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \
+ "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\
+ "$server_addr_id" "ns2" "ns1"
+
+ # RM_ADDR from server to client machine
+ ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\
+ "$server6_token" > /dev/null 2>&1
+ sleep 0.5
+}
+
test_prio()
{
local count
@@ -861,6 +907,7 @@ make_connection "v6"
test_announce
test_remove
test_subflows
+test_subflows_v4_v6_mix
test_prio
test_listener
--
GitLab
From a22b7388d658ecfcd226600c8c34ce4481e88655 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Thu, 12 Jan 2023 16:55:29 -0800
Subject: [PATCH 0784/1167] sch_htb: Avoid grafting on
htb_destroy_class_offload when destroying htb
Peek at old qdisc and graft only when deleting a leaf class in the htb,
rather than when deleting the htb itself. Do not peek at the qdisc of the
netdev queue when destroying the htb. The caller may already have grafted a
new qdisc that is not part of the htb structure being destroyed.
This fix resolves two use cases.
1. Using tc to destroy the htb.
- Netdev was being prematurely activated before the htb was fully
destroyed.
2. Using tc to replace the htb with another qdisc (which also leads to
the htb being destroyed).
- Premature netdev activation like previous case. Newly grafted qdisc
was also getting accidentally overwritten when destroying the htb.
Fixes: d03b195b5aa0 ("sch_htb: Hierarchical QoS hardware offload")
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Maxim Mikityanskiy <maxtram95@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20230113005528.302625-1-rrameshbabu@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/sch_htb.c | 27 ++++++++++++++++-----------
1 file changed, 16 insertions(+), 11 deletions(-)
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 2238edece1a46..f46643850df84 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1549,7 +1549,7 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl,
struct tc_htb_qopt_offload offload_opt;
struct netdev_queue *dev_queue;
struct Qdisc *q = cl->leaf.q;
- struct Qdisc *old = NULL;
+ struct Qdisc *old;
int err;
if (cl->level)
@@ -1557,14 +1557,17 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl,
WARN_ON(!q);
dev_queue = htb_offload_get_queue(cl);
- old = htb_graft_helper(dev_queue, NULL);
- if (destroying)
- /* Before HTB is destroyed, the kernel grafts noop_qdisc to
- * all queues.
+ /* When destroying, caller qdisc_graft grafts the new qdisc and invokes
+ * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload
+ * does not need to graft or qdisc_put the qdisc being destroyed.
+ */
+ if (!destroying) {
+ old = htb_graft_helper(dev_queue, NULL);
+ /* Last qdisc grafted should be the same as cl->leaf.q when
+ * calling htb_delete.
*/
- WARN_ON(!(old->flags & TCQ_F_BUILTIN));
- else
WARN_ON(old != q);
+ }
if (cl->parent) {
_bstats_update(&cl->parent->bstats_bias,
@@ -1581,10 +1584,12 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl,
};
err = htb_offload(qdisc_dev(sch), &offload_opt);
- if (!err || destroying)
- qdisc_put(old);
- else
- htb_graft_helper(dev_queue, old);
+ if (!destroying) {
+ if (!err)
+ qdisc_put(old);
+ else
+ htb_graft_helper(dev_queue, old);
+ }
if (last_child)
return err;
--
GitLab
From 5dc4c995db9eb45f6373a956eb1f69460e69e6d4 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 15 Jan 2023 09:22:43 -0600
Subject: [PATCH 0785/1167] Linux 6.2-rc4
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index 460716314fb3c..e09fe100efb21 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
--
GitLab
From a608da3bd730d718f2d3ebec1c26f9865f8f17ce Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Date: Fri, 6 Jan 2023 17:43:06 +0900
Subject: [PATCH 0786/1167] zonefs: Detect append writes at invalid locations
Using REQ_OP_ZONE_APPEND operations for synchronous writes to sequential
files succeeds regardless of the zone write pointer position, as long as
the target zone is not full. This means that if an external (buggy)
application writes to the zone of a sequential file underneath the file
system, subsequent file write() operation will succeed but the file size
will not be correct and the file will contain invalid data written by
another application.
Modify zonefs_file_dio_append() to check the written sector of an append
write (returned in bio->bi_iter.bi_sector) and return -EIO if there is a
mismatch with the file zone wp offset field. This change triggers a call
to zonefs_io_error() and a zone check. Modify zonefs_io_error_cb() to
not expose the unexpected data after the current inode size when the
errors=remount-ro mode is used. Other error modes are correctly handled
already.
Fixes: 02ef12a663c7 ("zonefs: use REQ_OP_ZONE_APPEND for sync DIO")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
fs/zonefs/super.c | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 2c53fbb8d918e..a9c5c3f720adf 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -442,6 +442,10 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
data_size = zonefs_check_zone_condition(inode, zone,
false, false);
}
+ } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
+ data_size > isize) {
+ /* Do not expose garbage data */
+ data_size = isize;
}
/*
@@ -805,6 +809,24 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
ret = submit_bio_wait(bio);
+ /*
+ * If the file zone was written underneath the file system, the zone
+ * write pointer may not be where we expect it to be, but the zone
+ * append write can still succeed. So check manually that we wrote where
+ * we intended to, that is, at zi->i_wpoffset.
+ */
+ if (!ret) {
+ sector_t wpsector =
+ zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT);
+
+ if (bio->bi_iter.bi_sector != wpsector) {
+ zonefs_warn(inode->i_sb,
+ "Corrupted write pointer %llu for zone at %llu\n",
+ wpsector, zi->i_zsector);
+ ret = -EIO;
+ }
+ }
+
zonefs_file_write_dio_end_io(iocb, size, ret, 0);
trace_zonefs_file_dio_append(inode, size, ret);
--
GitLab
From 6618d69aa129a8fc613e64775d5019524c6f231b Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Tue, 13 Dec 2022 19:03:55 +0100
Subject: [PATCH 0787/1167] rust: print: avoid evaluating arguments in `pr_*`
macros in `unsafe` blocks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
At the moment it is possible to perform unsafe operations in
the arguments of `pr_*` macros since they are evaluated inside
an `unsafe` block:
let x = &10u32 as *const u32;
pr_info!("{}", *x);
In other words, this is a soundness issue.
Fix it so that it requires an explicit `unsafe` block.
Reported-by: Wedson Almeida Filho <wedsonaf@gmail.com>
Reported-by: Domen Puncer Kugler <domen.puncerkugler@nccgroup.com>
Link: https://github.com/Rust-for-Linux/linux/issues/479
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Reviewed-by: Björn Roy Baron <bjorn3_gh@protonmail.com>
Reviewed-by: Vincenzo Palazzo <vincenzopalazzodev@gmail.com>
---
rust/kernel/print.rs | 29 ++++++++++++++++++-----------
1 file changed, 18 insertions(+), 11 deletions(-)
diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs
index 29bf9c2e8aee6..30103325696d8 100644
--- a/rust/kernel/print.rs
+++ b/rust/kernel/print.rs
@@ -142,17 +142,24 @@ pub fn call_printk_cont(args: fmt::Arguments<'_>) {
macro_rules! print_macro (
// The non-continuation cases (most of them, e.g. `INFO`).
($format_string:path, false, $($arg:tt)+) => (
- // SAFETY: This hidden macro should only be called by the documented
- // printing macros which ensure the format string is one of the fixed
- // ones. All `__LOG_PREFIX`s are null-terminated as they are generated
- // by the `module!` proc macro or fixed values defined in a kernel
- // crate.
- unsafe {
- $crate::print::call_printk(
- &$format_string,
- crate::__LOG_PREFIX,
- format_args!($($arg)+),
- );
+ // To remain sound, `arg`s must be expanded outside the `unsafe` block.
+ // Typically one would use a `let` binding for that; however, `format_args!`
+ // takes borrows on the arguments, but does not extend the scope of temporaries.
+ // Therefore, a `match` expression is used to keep them around, since
+ // the scrutinee is kept until the end of the `match`.
+ match format_args!($($arg)+) {
+ // SAFETY: This hidden macro should only be called by the documented
+ // printing macros which ensure the format string is one of the fixed
+ // ones. All `__LOG_PREFIX`s are null-terminated as they are generated
+ // by the `module!` proc macro or fixed values defined in a kernel
+ // crate.
+ args => unsafe {
+ $crate::print::call_printk(
+ &$format_string,
+ crate::__LOG_PREFIX,
+ args,
+ );
+ }
}
);
--
GitLab
From 216f764716f34fe68cedc7296ae2043a7727e640 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Tue, 3 Jan 2023 16:47:55 +0800
Subject: [PATCH 0788/1167] block, bfq: switch 'bfqg->ref' to use atomic
refcount apis
The updating of 'bfqg->ref' should be protected by 'bfqd->lock', however,
during code review, we found that bfq_pd_free() update 'bfqg->ref'
without holding the lock, which is problematic:
1) bfq_pd_free() triggered by removing cgroup is called asynchronously;
2) bfqq will grab bfqg reference, and exit bfqq will drop the reference,
which can concurrent with 1).
Unfortunately, 'bfqd->lock' can't be held here because 'bfqd' might already
be freed in bfq_pd_free(). Fix the problem by using atomic refcount apis.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20230103084755.1256479-1-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/bfq-cgroup.c | 8 +++-----
block/bfq-iosched.h | 2 +-
2 files changed, 4 insertions(+), 6 deletions(-)
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 1b2829e99dad0..7d9b15f0dbd57 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -316,14 +316,12 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
static void bfqg_get(struct bfq_group *bfqg)
{
- bfqg->ref++;
+ refcount_inc(&bfqg->ref);
}
static void bfqg_put(struct bfq_group *bfqg)
{
- bfqg->ref--;
-
- if (bfqg->ref == 0)
+ if (refcount_dec_and_test(&bfqg->ref))
kfree(bfqg);
}
@@ -530,7 +528,7 @@ static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
}
/* see comments in bfq_bic_update_cgroup for why refcounting */
- bfqg_get(bfqg);
+ refcount_set(&bfqg->ref, 1);
return &bfqg->pd;
}
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 41aa151ccc223..466e4865ace63 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -928,7 +928,7 @@ struct bfq_group {
char blkg_path[128];
/* reference counter (see comments in bfq_bic_update_cgroup) */
- int ref;
+ refcount_t ref;
/* Is bfq_group still online? */
bool online;
--
GitLab
From b72d13977689f0c717444010e108c4f20658dfee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?=
<duke_xinanwen@163.com>
Date: Tue, 27 Dec 2022 01:51:27 -0800
Subject: [PATCH 0789/1167] USB: serial: option: add Quectel EM05-G (RS) modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The EM05-G (RS) modem has 2 USB configurations that are configurable via
the AT command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate
with the following interfaces, respectively:
"RMNET" : AT + DIAG + NMEA + Modem + QMI
"MBIM" : MBIM + AT + DIAG + NMEA + Modem
The detailed description of the USB configuration for each mode as follows:
RMNET Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 21 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0314 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
MBIM Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 16 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0314 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-G
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms
I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Duke Xin(辛安文) <duke_xinanwen@163.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 07ffff889ed1e..58df076b69444 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -258,6 +258,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EM05G_CS 0x030c
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
#define QUECTEL_PRODUCT_EM05G_GR 0x0313
+#define QUECTEL_PRODUCT_EM05G_RS 0x0314
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
#define QUECTEL_PRODUCT_RM520N 0x0801
@@ -1167,6 +1168,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff),
.driver_info = RSVD(6) | ZLP },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) },
--
GitLab
From d9bbb15881046bd76f8710c76e26a740eee997ef Mon Sep 17 00:00:00 2001
From: Ali Mirghasemi <ali.mirghasemi1376@gmail.com>
Date: Wed, 28 Dec 2022 15:08:47 +0330
Subject: [PATCH 0790/1167] USB: serial: option: add Quectel EC200U modem
Add support for EC200U modem
0x0901: EC200U - AT + AP + CP + NMEA + DIAG + MOS
usb-device output:
T: Bus=01 Lev=02 Prnt=02 Port=02 Cnt=01 Dev#= 4 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0901 Rev= 3.18
S: Manufacturer=Android
S: Product=Android
C:* #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=400mA
A: FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=06 Prot=00
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=06 Prot=00 Driver=cdc_ether
E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=32ms
I: If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=83(I) Atr=03(Int.) MxPS= 512 Ivl=4096ms
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=89(I) Atr=03(Int.) MxPS= 512 Ivl=4096ms
I:* If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Ali Mirghasemi <ali.mirghasemi1376@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 58df076b69444..f00eaff4c9130 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -262,6 +262,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EM12 0x0512
#define QUECTEL_PRODUCT_RM500Q 0x0800
#define QUECTEL_PRODUCT_RM520N 0x0801
+#define QUECTEL_PRODUCT_EC200U 0x0901
#define QUECTEL_PRODUCT_EC200S_CN 0x6002
#define QUECTEL_PRODUCT_EC200T 0x6026
#define QUECTEL_PRODUCT_RM500K 0x7001
@@ -1189,6 +1190,7 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
--
GitLab
From 3f9e76e31704a325170e5aec2243c8d084d74854 Mon Sep 17 00:00:00 2001
From: Michael Adler <michael.adler@siemens.com>
Date: Tue, 3 Jan 2023 14:48:50 +0100
Subject: [PATCH 0791/1167] USB: serial: cp210x: add SCALANCE LPE-9000 device
id
Add the USB serial console device ID for Siemens SCALANCE LPE-9000
which have a USB port for their serial console.
Signed-off-by: Michael Adler <michael.adler@siemens.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/cp210x.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 67372acc23529..832ad592b7ef3 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -60,6 +60,7 @@ static const struct usb_device_id id_table[] = {
{ USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */
{ USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */
{ USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */
+ { USB_DEVICE(0x0908, 0x0070) }, /* Siemens SCALANCE LPE-9000 USB Serial Console */
{ USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */
{ USB_DEVICE(0x0988, 0x0578) }, /* Teraoka AD2000 */
{ USB_DEVICE(0x0B00, 0x3070) }, /* Ingenico 3070 */
--
GitLab
From 1541dd0097c0f8f470e76eddf5120fc55a7e3101 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?=
<duke_xinanwen@163.com>
Date: Sun, 15 Jan 2023 18:07:27 -0800
Subject: [PATCH 0792/1167] USB: serial: option: add Quectel EM05CN (SG) modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The EM05CN (SG) modem has 2 USB configurations that are configurable via the AT
command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with
the following interfaces, respectively:
"MBIM" : AT + MBIM + DIAG + NMEA + MODEM
"RMNET" : AT + DIAG + NMEA + Modem + QMI
The detailed description of the USB configuration for each mode as follows:
MBIM Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0310 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-CN
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A: FirstIf#= 1 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms
I: If#= 2 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 2 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
RMNET Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 3 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0310 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-CN
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Duke Xin(辛安文) <duke_xinanwen@163.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index f00eaff4c9130..2b1d5472f5788 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -256,6 +256,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EM05G 0x030a
#define QUECTEL_PRODUCT_EM060K 0x030b
#define QUECTEL_PRODUCT_EM05G_CS 0x030c
+#define QUECTEL_PRODUCT_EM05CN_SG 0x0310
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
#define QUECTEL_PRODUCT_EM05G_GR 0x0313
#define QUECTEL_PRODUCT_EM05G_RS 0x0314
@@ -1163,6 +1164,8 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff),
--
GitLab
From 71dfd381a7c051f16a61f82fbd38a4cca563bdca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duke=20Xin=28=E8=BE=9B=E5=AE=89=E6=96=87=29?=
<duke_xinanwen@163.com>
Date: Sun, 15 Jan 2023 18:33:28 -0800
Subject: [PATCH 0793/1167] USB: serial: option: add Quectel EM05CN modem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The EM05CN modem has 2 USB configurations that are configurable via the AT
command AT+QCFG="usbnet",[ 0 | 2 ] which make the modem enumerate with
the following interfaces, respectively:
"MBIM" : AT + MBIM + DIAG + NMEA + MODEM
"RMNET" : AT + DIAG + NMEA + Modem + QMI
The detailed description of the USB configuration for each mode as follows:
MBIM Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 2 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0312 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-CN
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A: FirstIf#= 1 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E: Ad=89(I) Atr=03(Int.) MxPS= 64 Ivl=32ms
I: If#= 2 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 2 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
RMNET Mode
--------------
T: Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 3 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=2c7c ProdID=0312 Rev= 3.18
S: Manufacturer=Quectel
S: Product=Quectel EM05-CN
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E: Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=83(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=85(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E: Ad=87(I) Atr=03(Int.) MxPS= 10 Ivl=32ms
E: Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)
E: Ad=89(I) Atr=03(Int.) MxPS= 8 Ivl=32ms
E: Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E: Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Signed-off-by: Duke Xin(辛安文) <duke_xinanwen@163.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
drivers/usb/serial/option.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 2b1d5472f5788..ee5ac4ef7e162 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -258,6 +258,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_EM05G_CS 0x030c
#define QUECTEL_PRODUCT_EM05CN_SG 0x0310
#define QUECTEL_PRODUCT_EM05G_SG 0x0311
+#define QUECTEL_PRODUCT_EM05CN 0x0312
#define QUECTEL_PRODUCT_EM05G_GR 0x0313
#define QUECTEL_PRODUCT_EM05G_RS 0x0314
#define QUECTEL_PRODUCT_EM12 0x0512
@@ -1164,6 +1165,8 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
.driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
+ { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN, 0xff),
+ .driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff),
.driver_info = RSVD(6) | ZLP },
{ USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff),
--
GitLab
From 5657c116783545fb49cd7004994c187128552b12 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Sun, 15 Jan 2023 14:31:22 -0500
Subject: [PATCH 0794/1167] sched/core: Fix NULL pointer access fault in
sched_setaffinity() with non-SMP configs
The kernel commit 9a5418bc48ba ("sched/core: Use kfree_rcu() in
do_set_cpus_allowed()") introduces a bug for kernels built with non-SMP
configs. Calling sched_setaffinity() on such a uniprocessor kernel will
cause cpumask_copy() to be called with a NULL pointer leading to general
protection fault. This is not really a problem in real use cases as
there aren't that many uniprocessor kernel configs in use and calling
sched_setaffinity() on such a uniprocessor system doesn't make sense.
Fix this problem by making sure cpumask_copy() will not be called in
such a case.
Fixes: 9a5418bc48ba ("sched/core: Use kfree_rcu() in do_set_cpus_allowed()")
Reported-by: kernel test robot <yujie.liu@intel.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230115193122.563036-1-longman@redhat.com
---
kernel/sched/core.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bb1ee6d7bddea..e838feb6adc50 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8290,12 +8290,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_put_task;
+ /*
+ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
+ * alloc_user_cpus_ptr() returns NULL.
+ */
user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
- if (IS_ENABLED(CONFIG_SMP) && !user_mask) {
+ if (user_mask) {
+ cpumask_copy(user_mask, in_mask);
+ } else if (IS_ENABLED(CONFIG_SMP)) {
retval = -ENOMEM;
goto out_put_task;
}
- cpumask_copy(user_mask, in_mask);
+
ac = (struct affinity_context){
.new_mask = in_mask,
.user_mask = user_mask,
--
GitLab
From 5f5cc9ed992cbab6361f198966f0edba5fc52688 Mon Sep 17 00:00:00 2001
From: Yair Podemsky <ypodemsk@redhat.com>
Date: Tue, 10 Jan 2023 18:02:06 +0200
Subject: [PATCH 0795/1167] x86/aperfmperf: Erase stale arch_freq_scale values
when disabling frequency invariance readings
Once disable_freq_invariance_work is called the scale_freq_tick function
will not compute or update the arch_freq_scale values.
However the scheduler will still read these values and use them.
The result is that the scheduler might perform unfair decisions based on stale
values.
This patch adds the step of setting the arch_freq_scale values for all
cpus to the default (max) value SCHED_CAPACITY_SCALE, Once all cpus
have the same arch_freq_scale value the scaling is meaningless.
Signed-off-by: Yair Podemsky <ypodemsk@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230110160206.75912-1-ypodemsk@redhat.com
---
arch/x86/kernel/cpu/aperfmperf.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 1f60a2b279368..fdbb5f07448fa 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void)
static void disable_freq_invariance_workfn(struct work_struct *work)
{
+ int cpu;
+
static_branch_disable(&arch_scale_freq_key);
+
+ /*
+ * Set arch_freq_scale to a default value on all cpus
+ * This negates the effect of scaling
+ */
+ for_each_possible_cpu(cpu)
+ per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE;
}
static DECLARE_WORK(disable_freq_invariance_work,
--
GitLab
From e5464277625c1aca5c002e0f470377cdd6816dcf Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 16 Jan 2023 10:49:56 +0100
Subject: [PATCH 0796/1167] gpio: mxc: Protect GPIO irqchip RMW with bgpio
spinlock
The driver currently performs register read-modify-write without locking
in its irqchip part, this could lead to a race condition when configuring
interrupt mode setting. Add the missing bgpio spinlock lock/unlock around
the register read-modify-write.
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Fixes: 07bd1a6cc7cbb ("MXC arch: Add gpio support for the whole platform")
Signed-off-by: Marek Vasut <marex@denx.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-mxc.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index d5626c572d24e..2d9d498727f10 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -18,6 +18,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/spinlock.h>
#include <linux/syscore_ops.h>
#include <linux/gpio/driver.h>
#include <linux/of.h>
@@ -159,6 +160,7 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type)
{
struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
struct mxc_gpio_port *port = gc->private;
+ unsigned long flags;
u32 bit, val;
u32 gpio_idx = d->hwirq;
int edge;
@@ -197,6 +199,8 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type)
return -EINVAL;
}
+ raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags);
+
if (GPIO_EDGE_SEL >= 0) {
val = readl(port->base + GPIO_EDGE_SEL);
if (edge == GPIO_INT_BOTH_EDGES)
@@ -217,15 +221,20 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type)
writel(1 << gpio_idx, port->base + GPIO_ISR);
port->pad_type[gpio_idx] = type;
+ raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
+
return 0;
}
static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)
{
void __iomem *reg = port->base;
+ unsigned long flags;
u32 bit, val;
int edge;
+ raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags);
+
reg += GPIO_ICR1 + ((gpio & 0x10) >> 2); /* lower or upper register */
bit = gpio & 0xf;
val = readl(reg);
@@ -243,6 +252,8 @@ static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)
return;
}
writel(val | (edge << (bit << 1)), reg);
+
+ raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
}
/* handle 32 interrupts in one status register */
--
GitLab
From 8e88a0feebb241cab0253698b2f7358b6ebec802 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 16 Jan 2023 10:49:57 +0100
Subject: [PATCH 0797/1167] gpio: mxc: Always set GPIOs used as interrupt
source to INPUT mode
Always configure GPIO pins which are used as interrupt source as INPUTs.
In case the default pin configuration is OUTPUT, or the prior stage does
configure the pins as OUTPUT, then Linux will not reconfigure the pin as
INPUT and no interrupts are received.
Always configure the interrupt source GPIO pin as input to fix the above case.
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Fixes: 07bd1a6cc7cbb ("MXC arch: Add gpio support for the whole platform")
Signed-off-by: Marek Vasut <marex@denx.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-mxc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 2d9d498727f10..6f673b2f2a1bf 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -223,7 +223,7 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type)
raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
- return 0;
+ return port->gc.direction_input(&port->gc, gpio_idx);
}
static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)
--
GitLab
From 8c0089882a62da2d75fb655e781cc33cc1351f6a Mon Sep 17 00:00:00 2001
From: Martin Liska <mliska@suse.cz>
Date: Mon, 16 Jan 2023 11:45:33 +0100
Subject: [PATCH 0798/1167] scripts: support GNU make 4.4 in jobserver-exec
Starting with GNU make 4.4, --jobserver-auth newly uses named
pipe (fifo) instead of part of opened file descriptors:
https://www.gnu.org/software/make/manual/html_node/POSIX-Jobserver.html
Support also the new format.
Signed-off-by: Martin Liska <mliska@suse.cz>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
scripts/jobserver-exec | 19 ++++++++++++++-----
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/scripts/jobserver-exec b/scripts/jobserver-exec
index 4192855f5b8b5..7eca035472d30 100755
--- a/scripts/jobserver-exec
+++ b/scripts/jobserver-exec
@@ -26,11 +26,20 @@ try:
# If the MAKEFLAGS variable contains multiple instances of the
# --jobserver-auth= option, the last one is relevant.
fds = opts[-1].split("=", 1)[1]
- reader, writer = [int(x) for x in fds.split(",", 1)]
- # Open a private copy of reader to avoid setting nonblocking
- # on an unexpecting process with the same reader fd.
- reader = os.open("/proc/self/fd/%d" % (reader),
- os.O_RDONLY | os.O_NONBLOCK)
+
+ # Starting with GNU Make 4.4, named pipes are used for reader and writer.
+ # Example argument: --jobserver-auth=fifo:/tmp/GMfifo8134
+ _, _, path = fds.partition('fifo:')
+
+ if path:
+ reader = os.open(path, os.O_RDONLY | os.O_NONBLOCK)
+ writer = os.open(path, os.O_WRONLY)
+ else:
+ reader, writer = [int(x) for x in fds.split(",", 1)]
+ # Open a private copy of reader to avoid setting nonblocking
+ # on an unexpecting process with the same reader fd.
+ reader = os.open("/proc/self/fd/%d" % (reader),
+ os.O_RDONLY | os.O_NONBLOCK)
# Read out as many jobserver slots as possible.
while True:
--
GitLab
From e5d1ab1a73ad275c0205cbc09a0a9f9f42bbb87f Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Tue, 3 Jan 2023 13:41:15 +0100
Subject: [PATCH 0799/1167] wifi: brcmfmac: avoid handling disabled channels
for survey dump
An issue was reported in which periodically error messages are
printed in the kernel log:
[ 26.303445] brcmfmac: brcmf_fw_alloc_request: using brcm/brcmfmac43455-sdio for chip BCM4345/6
[ 26.303554] brcmfmac mmc1:0001:1: Direct firmware load for brcm/brcmfmac43455-sdio.raspberrypi,3-model-b-plus.bin failed with error -2
[ 26.516752] brcmfmac_wcc: brcmf_wcc_attach: executing
[ 26.528264] brcmfmac: brcmf_c_preinit_dcmds: Firmware: BCM4345/6 wl0: Jan 4 2021 19:56:29 version 7.45.229 (617f1f5 CY) FWID 01-2dbd9d2e
[ 27.076829] Bluetooth: hci0: BCM: features 0x2f
[ 27.078592] Bluetooth: hci0: BCM43455 37.4MHz Raspberry Pi 3+
[ 27.078601] Bluetooth: hci0: BCM4345C0 (003.001.025) build 0342
[ 30.142104] Adding 102396k swap on /var/swap. Priority:-2 extents:1 across:102396k SS
[ 30.590017] Bluetooth: MGMT ver 1.22
[ 104.897615] brcmfmac: cfg80211_set_channel: set chanspec 0x100e fail, reason -52
[ 104.897992] brcmfmac: cfg80211_set_channel: set chanspec 0xd022 fail, reason -52
[ 105.007672] brcmfmac: cfg80211_set_channel: set chanspec 0xd026 fail, reason -52
[ 105.117654] brcmfmac: cfg80211_set_channel: set chanspec 0xd02a fail, reason -52
[ 105.227636] brcmfmac: cfg80211_set_channel: set chanspec 0xd02e fail, reason -52
[ 106.987552] brcmfmac: cfg80211_set_channel: set chanspec 0xd090 fail, reason -52
[ 106.987911] brcmfmac: cfg80211_set_channel: set chanspec 0xd095 fail, reason -52
[ 106.988233] brcmfmac: cfg80211_set_channel: set chanspec 0xd099 fail, reason -52
[ 106.988565] brcmfmac: cfg80211_set_channel: set chanspec 0xd09d fail, reason -52
[ 106.988909] brcmfmac: cfg80211_set_channel: set chanspec 0xd0a1 fail, reason -52
This happens in brcmf_cfg80211_dump_survey() because we try a disabled
channel. When channel is marked as disabled we do not need to fill any
other info so bail out.
Fixes: 6c04deae1438 ("brcmfmac: Add dump_survey cfg80211 ops for HostApd AutoChannelSelection")
Reported-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230103124117.271988-2-arend.vanspriel@broadcom.com
---
.../broadcom/brcm80211/brcmfmac/cfg80211.c | 16 +++++++---------
1 file changed, 7 insertions(+), 9 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index bff3128c2f261..478ca3848c64e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -7937,6 +7937,9 @@ cfg80211_set_channel(struct wiphy *wiphy, struct net_device *dev,
struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
+ if (chan->flags & IEEE80211_CHAN_DISABLED)
+ return -EINVAL;
+
/* set_channel */
chspec = channel_to_chanspec(&cfg->d11inf, chan);
if (chspec != INVCHANSPEC) {
@@ -7961,7 +7964,6 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
struct brcmf_dump_survey survey = {};
struct ieee80211_supported_band *band;
- struct ieee80211_channel *chan;
struct cca_msrmnt_query req;
u32 noise;
int err;
@@ -7987,13 +7989,10 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
}
/* Setting current channel to the requested channel */
- chan = &band->channels[idx];
- err = cfg80211_set_channel(wiphy, ndev, chan, NL80211_CHAN_HT20);
- if (err) {
- info->channel = chan;
- info->filled = 0;
+ info->filled = 0;
+ info->channel = &band->channels[idx];
+ if (cfg80211_set_channel(wiphy, ndev, info->channel, NL80211_CHAN_HT20))
return 0;
- }
/* Disable mpc */
brcmf_set_mpc(ifp, 0);
@@ -8028,7 +8027,6 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
if (err)
goto exit;
- info->channel = chan;
info->noise = noise;
info->time = ACS_MSRMNT_DELAY;
info->time_busy = ACS_MSRMNT_DELAY - survey.idle;
@@ -8040,7 +8038,7 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
SURVEY_INFO_TIME_TX;
brcmf_dbg(INFO, "OBSS dump: channel %d: survey duration %d\n",
- ieee80211_frequency_to_channel(chan->center_freq),
+ ieee80211_frequency_to_channel(info->channel->center_freq),
ACS_MSRMNT_DELAY);
brcmf_dbg(INFO, "noise(%d) busy(%llu) rx(%llu) tx(%llu)\n",
info->noise, info->time_busy, info->time_rx, info->time_tx);
--
GitLab
From aadb50d1571211c73248605bcc1f4b9f8e3d1364 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Tue, 3 Jan 2023 13:41:16 +0100
Subject: [PATCH 0800/1167] wifi: brcmfmac: avoid NULL-deref in survey dump for
2G only device
When dealing with a device for 2GHz band only the wiphy->bands for
5GHz will be NULL. This would result in a NULL-deref in the
brcmf_cfg80211_dump_survey() function. Rework the code with a
for-loop to make it easier to add another band.
Fixes: 6c04deae1438 ("brcmfmac: Add dump_survey cfg80211 ops for HostApd AutoChannelSelection")
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230103124117.271988-3-arend.vanspriel@broadcom.com
---
.../broadcom/brcm80211/brcmfmac/cfg80211.c | 23 +++++++++++--------
1 file changed, 13 insertions(+), 10 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 478ca3848c64e..b115902eb475e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -7964,6 +7964,7 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
struct brcmf_dump_survey survey = {};
struct ieee80211_supported_band *band;
+ enum nl80211_band band_id;
struct cca_msrmnt_query req;
u32 noise;
int err;
@@ -7976,21 +7977,23 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev,
return -EBUSY;
}
- band = wiphy->bands[NL80211_BAND_2GHZ];
- if (band && idx >= band->n_channels) {
- idx -= band->n_channels;
- band = NULL;
- }
+ for (band_id = 0; band_id < NUM_NL80211_BANDS; band_id++) {
+ band = wiphy->bands[band_id];
+ if (!band)
+ continue;
+ if (idx >= band->n_channels) {
+ idx -= band->n_channels;
+ continue;
+ }
- if (!band || idx >= band->n_channels) {
- band = wiphy->bands[NL80211_BAND_5GHZ];
- if (idx >= band->n_channels)
- return -ENOENT;
+ info->channel = &band->channels[idx];
+ break;
}
+ if (band_id == NUM_NL80211_BANDS)
+ return -ENOENT;
/* Setting current channel to the requested channel */
info->filled = 0;
- info->channel = &band->channels[idx];
if (cfg80211_set_channel(wiphy, ndev, info->channel, NL80211_CHAN_HT20))
return 0;
--
GitLab
From ed05cb177ae5cd7f02f1d6e7706ba627d30f1696 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Wed, 11 Jan 2023 12:24:19 +0100
Subject: [PATCH 0801/1167] wifi: brcmfmac: fix regression for Broadcom PCIe
wifi devices
A sanity check was introduced considering maximum flowrings above
256 as insane and effectively aborting the device probe. This
resulted in regression for number of users as the value turns out
to be sane after all.
Fixes: 2aca4f3734bd ("brcmfmac: return error when getting invalid max_flowrings from dongle")
Reported-by: chainofflowers <chainofflowers@posteo.net>
Link: https://lore.kernel.org/all/4781984.GXAFRqVoOG@luna/
Reported-by: Christian Marillat <marillat@debian.org>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216894
Cc: stable@vger.kernel.org
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230111112419.24185-1-arend.vanspriel@broadcom.com
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index ae57a9a3ab055..b67f6d0810b6c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1228,7 +1228,7 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
BRCMF_NROF_H2D_COMMON_MSGRINGS;
max_completionrings = BRCMF_NROF_D2H_COMMON_MSGRINGS;
}
- if (max_flowrings > 256) {
+ if (max_flowrings > 512) {
brcmf_err(bus, "invalid max_flowrings(%d)\n", max_flowrings);
return -EIO;
}
--
GitLab
From b870e73a56c4cccbec33224233eaf295839f228c Mon Sep 17 00:00:00 2001
From: Szymon Heidrich <szymon.heidrich@gmail.com>
Date: Wed, 11 Jan 2023 18:50:31 +0100
Subject: [PATCH 0802/1167] wifi: rndis_wlan: Prevent buffer overflow in
rndis_query_oid
Since resplen and respoffs are signed integers sufficiently
large values of unsigned int len and offset members of RNDIS
response will result in negative values of prior variables.
This may be utilized to bypass implemented security checks
to either extract memory contents by manipulating offset or
overflow the data buffer via memcpy by manipulating both
offset and len.
Additionally assure that sum of resplen and respoffs does not
overflow so buffer boundaries are kept.
Fixes: 80f8c5b434f9 ("rndis_wlan: copy only useful data from rndis_command respond")
Signed-off-by: Szymon Heidrich <szymon.heidrich@gmail.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230111175031.7049-1-szymon.heidrich@gmail.com
---
drivers/net/wireless/rndis_wlan.c | 19 ++++++-------------
1 file changed, 6 insertions(+), 13 deletions(-)
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 82a7458e01aec..bf72e5fd39cf4 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -696,8 +696,8 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len)
struct rndis_query *get;
struct rndis_query_c *get_c;
} u;
- int ret, buflen;
- int resplen, respoffs, copylen;
+ int ret;
+ size_t buflen, resplen, respoffs, copylen;
buflen = *len + sizeof(*u.get);
if (buflen < CONTROL_BUFFER_SIZE)
@@ -732,22 +732,15 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len)
if (respoffs > buflen) {
/* Device returned data offset outside buffer, error. */
- netdev_dbg(dev->net, "%s(%s): received invalid "
- "data offset: %d > %d\n", __func__,
- oid_to_string(oid), respoffs, buflen);
+ netdev_dbg(dev->net,
+ "%s(%s): received invalid data offset: %zu > %zu\n",
+ __func__, oid_to_string(oid), respoffs, buflen);
ret = -EINVAL;
goto exit_unlock;
}
- if ((resplen + respoffs) > buflen) {
- /* Device would have returned more data if buffer would
- * have been big enough. Copy just the bits that we got.
- */
- copylen = buflen - respoffs;
- } else {
- copylen = resplen;
- }
+ copylen = min(resplen, buflen - respoffs);
if (copylen > *len)
copylen = *len;
--
GitLab
From 31b62a98de42cf65d76e4dcfb571af067d27d83a Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Tue, 10 Jan 2023 17:29:58 +0000
Subject: [PATCH 0803/1167] pinctrl: rockchip: fix reading pull type on rk3568
When reading pinconf-pins from debugfs it fails to get the configured pull
type on RK3568, "unsupported pinctrl type" error messages is also reported.
Fix this by adding support for RK3568 in rockchip_get_pull, including a
reverse of the pull-up value swap applied in rockchip_set_pull so that
pull-up is correctly reported in pinconf-pins.
Also update the workaround comment to reflect affected pins, GPIO0_D3-D6.
Fixes: c0dadc0e47a8 ("pinctrl: rockchip: add support for rk3568")
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Jianqun Xu <jay.xu@rock-chips.com>
Link: https://lore.kernel.org/r/20230110172955.1258840-1-jonas@kwiboo.se
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/pinctrl/pinctrl-rockchip.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index da974ff2d75d0..c3b9313e5be17 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -2436,10 +2436,19 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num)
case RK3308:
case RK3368:
case RK3399:
+ case RK3568:
case RK3588:
pull_type = bank->pull_type[pin_num / 8];
data >>= bit;
data &= (1 << RK3188_PULL_BITS_PER_PIN) - 1;
+ /*
+ * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6,
+ * where that pull up value becomes 3.
+ */
+ if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) {
+ if (data == 3)
+ data = 1;
+ }
return rockchip_pull_list[pull_type][data];
default:
@@ -2497,7 +2506,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank,
}
}
/*
- * In the TRM, pull-up being 1 for everything except the GPIO0_D0-D6,
+ * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6,
* where that pull up value becomes 3.
*/
if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) {
--
GitLab
From c296c77efb66994d94d9f706446a115581226550 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Sat, 14 Jan 2023 13:04:37 +0100
Subject: [PATCH 0804/1167] net: stmmac: Fix queue statistics reading
Correct queue statistics reading. All queue statistics are stored as unsigned
long values. The retrieval for ethtool fetches these values as u64. However, on
some systems the size of the counters are 32 bit. That yields wrong queue
statistic counters e.g., on arm32 systems such as the stm32mp157. Fix it by
using the correct data type.
Tested on Olimex STMP157-OLinuXino-LIME2 by simple running linuxptp for a short
period of time:
Non-patched kernel:
|root@st1:~# ethtool -S eth0 | grep q0
| q0_tx_pkt_n: 3775276254951 # ???
| q0_tx_irq_n: 879
| q0_rx_pkt_n: 1194000908909 # ???
| q0_rx_irq_n: 278
Patched kernel:
|root@st1:~# ethtool -S eth0 | grep q0
| q0_tx_pkt_n: 2434
| q0_tx_irq_n: 1274
| q0_rx_pkt_n: 1604
| q0_rx_irq_n: 846
Fixes: 68e9c5dee1cf ("net: stmmac: add ethtool per-queue statistic framework")
Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Cc: Vijayakannan Ayyathurai <vijayakannan.ayyathurai@intel.com>
Cc: Wong Vee Khee <vee.khee.wong@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index f453b0d093663..35c8dd92d3692 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -551,16 +551,16 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data)
p = (char *)priv + offsetof(struct stmmac_priv,
xstats.txq_stats[q].tx_pkt_n);
for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64 *);
+ *data++ = (*(unsigned long *)p);
+ p += sizeof(unsigned long);
}
}
for (q = 0; q < rx_cnt; q++) {
p = (char *)priv + offsetof(struct stmmac_priv,
xstats.rxq_stats[q].rx_pkt_n);
for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) {
- *data++ = (*(u64 *)p);
- p += sizeof(u64 *);
+ *data++ = (*(unsigned long *)p);
+ p += sizeof(unsigned long);
}
}
}
--
GitLab
From 3a415d59c1dbec9d772dbfab2d2520d98360caae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Jan 2023 16:48:49 +0000
Subject: [PATCH 0805/1167] net/sched: sch_taprio: fix possible use-after-free
syzbot reported a nasty crash [1] in net_tx_action() which
made little sense until we got a repro.
This repro installs a taprio qdisc, but providing an
invalid TCA_RATE attribute.
qdisc_create() has to destroy the just initialized
taprio qdisc, and taprio_destroy() is called.
However, the hrtimer used by taprio had already fired,
therefore advance_sched() called __netif_schedule().
Then net_tx_action was trying to use a destroyed qdisc.
We can not undo the __netif_schedule(), so we must wait
until one cpu serviced the qdisc before we can proceed.
Many thanks to Alexander Potapenko for his help.
[1]
BUG: KMSAN: uninit-value in queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline]
BUG: KMSAN: uninit-value in do_raw_spin_trylock include/linux/spinlock.h:191 [inline]
BUG: KMSAN: uninit-value in __raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline]
BUG: KMSAN: uninit-value in _raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138
queued_spin_trylock include/asm-generic/qspinlock.h:94 [inline]
do_raw_spin_trylock include/linux/spinlock.h:191 [inline]
__raw_spin_trylock include/linux/spinlock_api_smp.h:89 [inline]
_raw_spin_trylock+0x92/0xa0 kernel/locking/spinlock.c:138
spin_trylock include/linux/spinlock.h:359 [inline]
qdisc_run_begin include/net/sch_generic.h:187 [inline]
qdisc_run+0xee/0x540 include/net/pkt_sched.h:125
net_tx_action+0x77c/0x9a0 net/core/dev.c:5086
__do_softirq+0x1cc/0x7fb kernel/softirq.c:571
run_ksoftirqd+0x2c/0x50 kernel/softirq.c:934
smpboot_thread_fn+0x554/0x9f0 kernel/smpboot.c:164
kthread+0x31b/0x430 kernel/kthread.c:376
ret_from_fork+0x1f/0x30
Uninit was created at:
slab_post_alloc_hook mm/slab.h:732 [inline]
slab_alloc_node mm/slub.c:3258 [inline]
__kmalloc_node_track_caller+0x814/0x1250 mm/slub.c:4970
kmalloc_reserve net/core/skbuff.c:358 [inline]
__alloc_skb+0x346/0xcf0 net/core/skbuff.c:430
alloc_skb include/linux/skbuff.h:1257 [inline]
nlmsg_new include/net/netlink.h:953 [inline]
netlink_ack+0x5f3/0x12b0 net/netlink/af_netlink.c:2436
netlink_rcv_skb+0x55d/0x6c0 net/netlink/af_netlink.c:2507
rtnetlink_rcv+0x30/0x40 net/core/rtnetlink.c:6108
netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
netlink_unicast+0xf3b/0x1270 net/netlink/af_netlink.c:1345
netlink_sendmsg+0x1288/0x1440 net/netlink/af_netlink.c:1921
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg net/socket.c:734 [inline]
____sys_sendmsg+0xabc/0xe90 net/socket.c:2482
___sys_sendmsg+0x2a1/0x3f0 net/socket.c:2536
__sys_sendmsg net/socket.c:2565 [inline]
__do_sys_sendmsg net/socket.c:2574 [inline]
__se_sys_sendmsg net/socket.c:2572 [inline]
__x64_sys_sendmsg+0x367/0x540 net/socket.c:2572
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
CPU: 0 PID: 13 Comm: ksoftirqd/0 Not tainted 6.0.0-rc2-syzkaller-47461-gac3859c02d7f #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/22/2022
Fixes: 5a781ccbd19e ("tc: Add support for configuring the taprio scheduler")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/sch_generic.h | 7 +++++++
net/sched/sch_taprio.c | 3 +++
2 files changed, 10 insertions(+)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d5517719af4ef..af4aa66aaa4eb 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1288,4 +1288,11 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx);
int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb));
+/* Make sure qdisc is no longer in SCHED state. */
+static inline void qdisc_synchronize(const struct Qdisc *q)
+{
+ while (test_bit(__QDISC_STATE_SCHED, &q->state))
+ msleep(1);
+}
+
#endif
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 570389f6cdd7d..9a11a499ea2df 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1700,6 +1700,8 @@ static void taprio_reset(struct Qdisc *sch)
int i;
hrtimer_cancel(&q->advance_timer);
+ qdisc_synchronize(sch);
+
if (q->qdiscs) {
for (i = 0; i < dev->num_tx_queues; i++)
if (q->qdiscs[i])
@@ -1720,6 +1722,7 @@ static void taprio_destroy(struct Qdisc *sch)
* happens in qdisc_create(), after taprio_init() has been called.
*/
hrtimer_cancel(&q->advance_timer);
+ qdisc_synchronize(sch);
taprio_disable_offload(dev, q, NULL);
--
GitLab
From c4d48a58f32c5972174a1d01c33b296fe378cce0 Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Fri, 13 Jan 2023 19:01:36 -0800
Subject: [PATCH 0806/1167] l2tp: convert l2tp_tunnel_list to idr
l2tp uses l2tp_tunnel_list to track all registered tunnels and
to allocate tunnel ID's. IDR can do the same job.
More importantly, with IDR we can hold the ID before a successful
registration so that we don't need to worry about late error
handling, it is not easy to rollback socket changes.
This is a preparation for the following fix.
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Guillaume Nault <gnault@redhat.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Parkin <tparkin@katalix.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_core.c | 85 ++++++++++++++++++++++----------------------
1 file changed, 42 insertions(+), 43 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 9a1415fe3fa78..e9c0ce0b7972d 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -104,9 +104,9 @@ static struct workqueue_struct *l2tp_wq;
/* per-net private data for this module */
static unsigned int l2tp_net_id;
struct l2tp_net {
- struct list_head l2tp_tunnel_list;
- /* Lock for write access to l2tp_tunnel_list */
- spinlock_t l2tp_tunnel_list_lock;
+ /* Lock for write access to l2tp_tunnel_idr */
+ spinlock_t l2tp_tunnel_idr_lock;
+ struct idr l2tp_tunnel_idr;
struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
/* Lock for write access to l2tp_session_hlist */
spinlock_t l2tp_session_hlist_lock;
@@ -208,13 +208,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
struct l2tp_tunnel *tunnel;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (tunnel->tunnel_id == tunnel_id &&
- refcount_inc_not_zero(&tunnel->ref_count)) {
- rcu_read_unlock_bh();
-
- return tunnel;
- }
+ tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id);
+ if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) {
+ rcu_read_unlock_bh();
+ return tunnel;
}
rcu_read_unlock_bh();
@@ -224,13 +221,14 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
{
- const struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_net *pn = l2tp_pernet(net);
+ unsigned long tunnel_id, tmp;
struct l2tp_tunnel *tunnel;
int count = 0;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- if (++count > nth &&
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel && ++count > nth &&
refcount_inc_not_zero(&tunnel->ref_count)) {
rcu_read_unlock_bh();
return tunnel;
@@ -1227,6 +1225,15 @@ static void l2tp_udp_encap_destroy(struct sock *sk)
l2tp_tunnel_delete(tunnel);
}
+static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+}
+
/* Workqueue tunnel deletion function */
static void l2tp_tunnel_del_work(struct work_struct *work)
{
@@ -1234,7 +1241,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
del_work);
struct sock *sk = tunnel->sock;
struct socket *sock = sk->sk_socket;
- struct l2tp_net *pn;
l2tp_tunnel_closeall(tunnel);
@@ -1248,12 +1254,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
}
}
- /* Remove the tunnel struct from the tunnel list */
- pn = l2tp_pernet(tunnel->l2tp_net);
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_del_rcu(&tunnel->list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-
+ l2tp_tunnel_remove(tunnel->l2tp_net, tunnel);
/* drop initial ref */
l2tp_tunnel_dec_refcount(tunnel);
@@ -1455,12 +1456,19 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
struct l2tp_tunnel_cfg *cfg)
{
- struct l2tp_tunnel *tunnel_walk;
- struct l2tp_net *pn;
+ struct l2tp_net *pn = l2tp_pernet(net);
+ u32 tunnel_id = tunnel->tunnel_id;
struct socket *sock;
struct sock *sk;
int ret;
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id,
+ GFP_ATOMIC);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
+ if (ret)
+ return ret == -ENOSPC ? -EEXIST : ret;
+
if (tunnel->fd < 0) {
ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id,
tunnel->peer_tunnel_id, cfg,
@@ -1481,23 +1489,13 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
rcu_assign_sk_user_data(sk, tunnel);
write_unlock_bh(&sk->sk_callback_lock);
- tunnel->l2tp_net = net;
- pn = l2tp_pernet(net);
-
sock_hold(sk);
tunnel->sock = sk;
+ tunnel->l2tp_net = net;
- spin_lock_bh(&pn->l2tp_tunnel_list_lock);
- list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) {
- if (tunnel_walk->tunnel_id == tunnel->tunnel_id) {
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
- sock_put(sk);
- ret = -EEXIST;
- goto err_sock;
- }
- }
- list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
- spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
struct udp_tunnel_sock_cfg udp_cfg = {
@@ -1523,9 +1521,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
return 0;
-err_sock:
- write_lock_bh(&sk->sk_callback_lock);
- rcu_assign_sk_user_data(sk, NULL);
err_inval_sock:
write_unlock_bh(&sk->sk_callback_lock);
@@ -1534,6 +1529,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
else
sockfd_put(sock);
err:
+ l2tp_tunnel_remove(net, tunnel);
return ret;
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
@@ -1647,8 +1643,8 @@ static __net_init int l2tp_init_net(struct net *net)
struct l2tp_net *pn = net_generic(net, l2tp_net_id);
int hash;
- INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
- spin_lock_init(&pn->l2tp_tunnel_list_lock);
+ idr_init(&pn->l2tp_tunnel_idr);
+ spin_lock_init(&pn->l2tp_tunnel_idr_lock);
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]);
@@ -1662,11 +1658,13 @@ static __net_exit void l2tp_exit_net(struct net *net)
{
struct l2tp_net *pn = l2tp_pernet(net);
struct l2tp_tunnel *tunnel = NULL;
+ unsigned long tunnel_id, tmp;
int hash;
rcu_read_lock_bh();
- list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
- l2tp_tunnel_delete(tunnel);
+ idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+ if (tunnel)
+ l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
@@ -1676,6 +1674,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash]));
+ idr_destroy(&pn->l2tp_tunnel_idr);
}
static struct pernet_operations l2tp_net_ops = {
--
GitLab
From 0b2c59720e65885a394a017d0cf9cab118914682 Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Fri, 13 Jan 2023 19:01:37 -0800
Subject: [PATCH 0807/1167] l2tp: close all race conditions in
l2tp_tunnel_register()
The code in l2tp_tunnel_register() is racy in several ways:
1. It modifies the tunnel socket _after_ publishing it.
2. It calls setup_udp_tunnel_sock() on an existing socket without
locking.
3. It changes sock lock class on fly, which triggers many syzbot
reports.
This patch amends all of them by moving socket initialization code
before publishing and under sock lock. As suggested by Jakub, the
l2tp lockdep class is not necessary as we can just switch to
bh_lock_sock_nested().
Fixes: 37159ef2c1ae ("l2tp: fix a lockdep splat")
Fixes: 6b9f34239b00 ("l2tp: fix races in tunnel creation")
Reported-by: syzbot+52866e24647f9a23403f@syzkaller.appspotmail.com
Reported-by: syzbot+94cc2a66fc228b23f360@syzkaller.appspotmail.com
Reported-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Guillaume Nault <gnault@redhat.com>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Parkin <tparkin@katalix.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_core.c | 28 ++++++++++++++--------------
1 file changed, 14 insertions(+), 14 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index e9c0ce0b7972d..b6554e32bb12a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1041,7 +1041,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
nf_reset_ct(skb);
- bh_lock_sock(sk);
+ bh_lock_sock_nested(sk);
if (sock_owned_by_user(sk)) {
kfree_skb(skb);
ret = NET_XMIT_DROP;
@@ -1385,8 +1385,6 @@ static int l2tp_tunnel_sock_create(struct net *net,
return err;
}
-static struct lock_class_key l2tp_socket_class;
-
int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
{
@@ -1482,21 +1480,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
}
sk = sock->sk;
+ lock_sock(sk);
write_lock_bh(&sk->sk_callback_lock);
ret = l2tp_validate_socket(sk, net, tunnel->encap);
- if (ret < 0)
+ if (ret < 0) {
+ release_sock(sk);
goto err_inval_sock;
+ }
rcu_assign_sk_user_data(sk, tunnel);
write_unlock_bh(&sk->sk_callback_lock);
- sock_hold(sk);
- tunnel->sock = sk;
- tunnel->l2tp_net = net;
-
- spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
- idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id);
- spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
-
if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
struct udp_tunnel_sock_cfg udp_cfg = {
.sk_user_data = tunnel,
@@ -1510,9 +1503,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
tunnel->old_sk_destruct = sk->sk_destruct;
sk->sk_destruct = &l2tp_tunnel_destruct;
- lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class,
- "l2tp_sock");
sk->sk_allocation = GFP_ATOMIC;
+ release_sock(sk);
+
+ sock_hold(sk);
+ tunnel->sock = sk;
+ tunnel->l2tp_net = net;
+
+ spin_lock_bh(&pn->l2tp_tunnel_idr_lock);
+ idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id);
+ spin_unlock_bh(&pn->l2tp_tunnel_idr_lock);
trace_register_tunnel(tunnel);
--
GitLab
From 87b93b678e95c7d93fe6a55b0e0fbda26d8c7760 Mon Sep 17 00:00:00 2001
From: Geetha sowjanya <gakula@marvell.com>
Date: Fri, 13 Jan 2023 11:49:02 +0530
Subject: [PATCH 0808/1167] octeontx2-pf: Avoid use of GFP_KERNEL in atomic
context
Using GFP_KERNEL in preemption disable context, causing below warning
when CONFIG_DEBUG_ATOMIC_SLEEP is enabled.
[ 32.542271] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:274
[ 32.550883] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
[ 32.558707] preempt_count: 1, expected: 0
[ 32.562710] RCU nest depth: 0, expected: 0
[ 32.566800] CPU: 3 PID: 1 Comm: swapper/0 Tainted: G W 6.2.0-rc2-00269-gae9dcb91c606 #7
[ 32.576188] Hardware name: Marvell CN106XX board (DT)
[ 32.581232] Call trace:
[ 32.583670] dump_backtrace.part.0+0xe0/0xf0
[ 32.587937] show_stack+0x18/0x30
[ 32.591245] dump_stack_lvl+0x68/0x84
[ 32.594900] dump_stack+0x18/0x34
[ 32.598206] __might_resched+0x12c/0x160
[ 32.602122] __might_sleep+0x48/0xa0
[ 32.605689] __kmem_cache_alloc_node+0x2b8/0x2e0
[ 32.610301] __kmalloc+0x58/0x190
[ 32.613610] otx2_sq_aura_pool_init+0x1a8/0x314
[ 32.618134] otx2_open+0x1d4/0x9d0
To avoid use of GFP_ATOMIC for memory allocation, disable preemption
after all memory allocation is done.
Fixes: 4af1b64f80fb ("octeontx2-pf: Fix lmtst ID used in aura free")
Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 88f8772a61cd5..497b777b6a34f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1370,7 +1370,6 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
if (err)
goto fail;
- get_cpu();
/* Allocate pointers and free them to aura/pool */
for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) {
pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx);
@@ -1388,13 +1387,14 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
if (err)
goto err_mem;
+ get_cpu();
pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
+ put_cpu();
sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
}
}
err_mem:
- put_cpu();
return err ? -ENOMEM : 0;
fail:
--
GitLab
From 8a9a1a18731eb123e35f48176380a18b9782845e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 28 Oct 2022 16:39:14 +0200
Subject: [PATCH 0809/1167] arm64: efi: Avoid workqueue to check whether EFI
runtime is live
Comparing current_work() against efi_rts_work.work is sufficient to
decide whether current is currently running EFI runtime services code at
any level in its call stack.
However, there are other potential users of the EFI runtime stack, such
as the ACPI subsystem, which may invoke efi_call_virt_pointer()
directly, and so any sync exceptions occurring in firmware during those
calls are currently misidentified.
So instead, let's check whether the stashed value of the thread stack
pointer points into current's thread stack. This can only be the case if
current was interrupted while running EFI runtime code. Note that this
implies that we should clear the stashed value after switching back, to
avoid false positives.
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
arch/arm64/include/asm/efi.h | 9 +++++++++
arch/arm64/kernel/efi-rt-wrapper.S | 6 ++++++
arch/arm64/kernel/efi.c | 3 ++-
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 31d13a6001df4..de4ff90785b2c 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -48,8 +48,17 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
})
extern spinlock_t efi_rt_lock;
+extern u64 *efi_rt_stack_top;
efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
+/*
+ * efi_rt_stack_top[-1] contains the value the stack pointer had before
+ * switching to the EFI runtime stack.
+ */
+#define current_in_efi() \
+ (!preemptible() && efi_rt_stack_top != NULL && \
+ on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1))
+
#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
/*
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index d872d18101d83..e8ae803662cf1 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -46,7 +46,10 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
mov x4, x6
blr x8
+ mov x16, sp
mov sp, x29
+ str xzr, [x16, #8] // clear recorded task SP value
+
ldp x1, x2, [sp, #16]
cmp x2, x18
ldp x29, x30, [sp], #112
@@ -71,6 +74,9 @@ SYM_FUNC_END(__efi_rt_asm_wrapper)
SYM_CODE_START(__efi_rt_asm_recover)
mov sp, x30
+ ldr_l x16, efi_rt_stack_top // clear recorded task SP value
+ str xzr, [x16, #-8]
+
ldp x19, x20, [sp, #32]
ldp x21, x22, [sp, #48]
ldp x23, x24, [sp, #64]
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index fab05de2e12dd..b273900f45668 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -11,6 +11,7 @@
#include <linux/init.h>
#include <asm/efi.h>
+#include <asm/stacktrace.h>
static bool region_is_misaligned(const efi_memory_desc_t *md)
{
@@ -154,7 +155,7 @@ asmlinkage efi_status_t __efi_rt_asm_recover(void);
bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
{
/* Check whether the exception occurred while running the firmware */
- if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64)
+ if (!current_in_efi() || regs->pc >= TASK_SIZE_64)
return false;
pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg);
--
GitLab
From 7ea55715c421d22c1b63f7129cae6a654091b695 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 9 Dec 2022 12:10:13 +0100
Subject: [PATCH 0810/1167] arm64: efi: Account for the EFI runtime stack in
stack unwinder
The EFI runtime services run from a dedicated stack now, and so the
stack unwinder needs to be informed about this.
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
arch/arm64/include/asm/stacktrace.h | 15 +++++++++++++++
arch/arm64/kernel/stacktrace.c | 12 ++++++++++++
2 files changed, 27 insertions(+)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 4e5354beafb01..66ec8caa6ac07 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -106,4 +106,19 @@ static inline struct stack_info stackinfo_get_sdei_critical(void)
#define stackinfo_get_sdei_critical() stackinfo_get_unknown()
#endif
+#ifdef CONFIG_EFI
+extern u64 *efi_rt_stack_top;
+
+static inline struct stack_info stackinfo_get_efi(void)
+{
+ unsigned long high = (u64)efi_rt_stack_top;
+ unsigned long low = high - THREAD_SIZE;
+
+ return (struct stack_info) {
+ .low = low,
+ .high = high,
+ };
+}
+#endif
+
#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 117e2c180f3c7..83154303e682c 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -5,6 +5,7 @@
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/kernel.h>
+#include <linux/efi.h>
#include <linux/export.h>
#include <linux/ftrace.h>
#include <linux/sched.h>
@@ -12,6 +13,7 @@
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
+#include <asm/efi.h>
#include <asm/irq.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
@@ -186,6 +188,13 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
: stackinfo_get_unknown(); \
})
+#define STACKINFO_EFI \
+ ({ \
+ ((task == current) && current_in_efi()) \
+ ? stackinfo_get_efi() \
+ : stackinfo_get_unknown(); \
+ })
+
noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
@@ -199,6 +208,9 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_ARM_SDE_INTERFACE)
STACKINFO_SDEI(normal),
STACKINFO_SDEI(critical),
+#endif
+#ifdef CONFIG_EFI
+ STACKINFO_EFI,
#endif
};
struct unwind_state state = {
--
GitLab
From b22c7b97189d461d7143052da83b36390c623b54 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Thu, 12 Jan 2023 14:54:30 +0800
Subject: [PATCH 0811/1167] erofs: add documentation for 'domain_id' mount
option
Since the EROFS share domain feature for fscache mode has been available
since Linux v6.1, let's add documentation for 'domain_id' mount option.
Cc: linux-doc@vger.kernel.org
Reviewed-by: Jia Zhu <zhujia.zj@bytedance.com>
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20230112065431.124926-2-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
Documentation/filesystems/erofs.rst | 2 ++
1 file changed, 2 insertions(+)
diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst
index 067fd1670b1f1..a43aacf1494e7 100644
--- a/Documentation/filesystems/erofs.rst
+++ b/Documentation/filesystems/erofs.rst
@@ -120,6 +120,8 @@ dax={always,never} Use direct access (no page cache). See
dax A legacy option which is an alias for ``dax=always``.
device=%s Specify a path to an extra device to be used together.
fsid=%s Specify a filesystem image ID for Fscache back-end.
+domain_id=%s Specify a domain ID in fscache mode so that different images
+ with the same blobs under a given domain ID can share storage.
=================== =========================================================
Sysfs Entries
--
GitLab
From e02ac3e7329f76c5de40cba2746cbe165f571dff Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Thu, 12 Jan 2023 14:54:31 +0800
Subject: [PATCH 0812/1167] erofs: clean up parsing of fscache related options
... to avoid the mess of conditional preprocessing as we are continually
adding fscache related mount options.
Reviewd-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Yue Hu <huyue2@coolpad.com>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230112065431.124926-3-jefflexu@linux.alibaba.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
fs/erofs/super.c | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 481788c24a68b..626a615dafc2f 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -577,26 +577,25 @@ static int erofs_fc_parse_param(struct fs_context *fc,
}
++ctx->devs->extra_devices;
break;
- case Opt_fsid:
#ifdef CONFIG_EROFS_FS_ONDEMAND
+ case Opt_fsid:
kfree(ctx->fsid);
ctx->fsid = kstrdup(param->string, GFP_KERNEL);
if (!ctx->fsid)
return -ENOMEM;
-#else
- errorfc(fc, "fsid option not supported");
-#endif
break;
case Opt_domain_id:
-#ifdef CONFIG_EROFS_FS_ONDEMAND
kfree(ctx->domain_id);
ctx->domain_id = kstrdup(param->string, GFP_KERNEL);
if (!ctx->domain_id)
return -ENOMEM;
+ break;
#else
- errorfc(fc, "domain_id option not supported");
-#endif
+ case Opt_fsid:
+ case Opt_domain_id:
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
+#endif
default:
return -ENOPARAM;
}
--
GitLab
From 1132d1c834d6185c89aef07c860fc143a6f2db93 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 13 Jan 2023 11:58:46 +0100
Subject: [PATCH 0813/1167] wifi: mt76: dma: do not increment queue head if
mt76_dma_add_buf fails
Do not increment queue head if mt76_dma_add_buf fails for Wireless
Ethernet Dispatcher rx queues.
Fixes: cd372b8c99c5 ("wifi: mt76: add WED RX support to mt76_dma_{add,get}_buf")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
(cherry picked from commit fe13dad8992be0b26c1be390bcd111acf9892c17)
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230113105848.34642-1-nbd@nbd.name
---
drivers/net/wireless/mediatek/mt76/dma.c | 9 +++++----
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index f795548562f55..c058a02e9ba55 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -212,14 +212,14 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
{
struct mt76_queue_entry *entry;
struct mt76_desc *desc;
- u32 ctrl;
int i, idx = -1;
+ u32 ctrl, next;
for (i = 0; i < nbufs; i += 2, buf += 2) {
u32 buf0 = buf[0].addr, buf1 = 0;
idx = q->head;
- q->head = (q->head + 1) % q->ndesc;
+ next = (q->head + 1) % q->ndesc;
desc = &q->desc[idx];
entry = &q->entry[idx];
@@ -239,8 +239,8 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
MT_DMA_CTL_TO_HOST;
} else {
if (txwi) {
- q->entry[q->head].txwi = DMA_DUMMY_DATA;
- q->entry[q->head].skip_buf0 = true;
+ q->entry[next].txwi = DMA_DUMMY_DATA;
+ q->entry[next].skip_buf0 = true;
}
if (buf[0].skip_unmap)
@@ -271,6 +271,7 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
WRITE_ONCE(desc->info, cpu_to_le32(info));
WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl));
+ q->head = next;
q->queued++;
}
--
GitLab
From e5c3ac895750b39ef53b84ff4814617ecd69d556 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 13 Jan 2023 11:58:47 +0100
Subject: [PATCH 0814/1167] wifi: mt76: handle possible mt76_rx_token_consume
failures
Take into account possible error conditions of mt76_rx_token_consume
routine in mt7915_mmio_wed_init_rx_buf() and mt76_dma_add_buf()
Fixes: cd372b8c99c5 ("wifi: mt76: add WED RX support to mt76_dma_{add,get}_buf")
Fixes: 4f831d18d12d ("wifi: mt76: mt7915: enable WED RX support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
(cherry picked from commit 96f134dc19645be4994e89a2f68fa89309becbee)
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230113105848.34642-2-nbd@nbd.name
---
drivers/net/wireless/mediatek/mt76/dma.c | 10 +++++++++-
drivers/net/wireless/mediatek/mt76/mt7915/mmio.c | 7 +++++++
drivers/net/wireless/mediatek/mt76/tx.c | 7 ++++---
3 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index c058a02e9ba55..61a8ab9e1db55 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -234,6 +234,9 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
rx_token = mt76_rx_token_consume(dev, (void *)skb, t,
buf[0].addr);
+ if (rx_token < 0)
+ return -ENOMEM;
+
buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token);
ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len) |
MT_DMA_CTL_TO_HOST;
@@ -602,7 +605,12 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q)
qbuf.addr = addr + offset;
qbuf.len = len - offset;
qbuf.skip_unmap = false;
- mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, t);
+ if (mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, t) < 0) {
+ dma_unmap_single(dev->dma_dev, addr, len,
+ DMA_FROM_DEVICE);
+ skb_free_frag(buf);
+ break;
+ }
frames++;
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 0a95c3da241b5..8388e2a658535 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -653,6 +653,13 @@ static u32 mt7915_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size)
desc->buf0 = cpu_to_le32(phy_addr);
token = mt76_rx_token_consume(&dev->mt76, ptr, t, phy_addr);
+ if (token < 0) {
+ dma_unmap_single(dev->mt76.dma_dev, phy_addr,
+ wed->wlan.rx_size, DMA_TO_DEVICE);
+ skb_free_frag(ptr);
+ goto unmap;
+ }
+
desc->token |= cpu_to_le32(FIELD_PREP(MT_DMA_CTL_TOKEN,
token));
desc++;
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 24568b98ed9df..1f309d05380ad 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -764,11 +764,12 @@ int mt76_rx_token_consume(struct mt76_dev *dev, void *ptr,
spin_lock_bh(&dev->rx_token_lock);
token = idr_alloc(&dev->rx_token, t, 0, dev->rx_token_size,
GFP_ATOMIC);
+ if (token >= 0) {
+ t->ptr = ptr;
+ t->dma_addr = phys;
+ }
spin_unlock_bh(&dev->rx_token_lock);
- t->ptr = ptr;
- t->dma_addr = phys;
-
return token;
}
EXPORT_SYMBOL_GPL(mt76_rx_token_consume);
--
GitLab
From 953519b35227d5dbbb5c5724f1f539735fbf7781 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 13 Jan 2023 11:58:48 +0100
Subject: [PATCH 0815/1167] wifi: mt76: dma: fix a regression in adding rx
buffers
When adding WED support, mt76_dma_add_buf was accidentally changed to set
the skip_buf0 flag for tx buffers on the wrong queue descriptor entry.
Additionally, there is a rxwi leak when rx buffer allocation fails.
Fix this and make the code more readable by adding a separate function for
adding rx buffers.
Reported-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Link: https://lore.kernel.org/r/CABXGCsMEnQd=gYKTd1knRsWuxCb=Etv5nAre%2BXJS_s5FgVteYA@mail.gmail.com/
Reported-by: Mike Lothian <mike@fireburn.co.uk>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216829
Reported-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/lkml/20230112171706.294550-1-angelogioacchino.delregno@collabora.com/
Fixes: cd372b8c99c5 ("wifi: mt76: add WED RX support to mt76_dma_{add,get}_buf")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230113105848.34642-3-nbd@nbd.name
---
drivers/net/wireless/mediatek/mt76/dma.c | 124 +++++++++++++----------
1 file changed, 72 insertions(+), 52 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 61a8ab9e1db55..06161815c180e 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -205,6 +205,52 @@ mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q)
mt76_dma_sync_idx(dev, q);
}
+static int
+mt76_dma_add_rx_buf(struct mt76_dev *dev, struct mt76_queue *q,
+ struct mt76_queue_buf *buf, void *data)
+{
+ struct mt76_desc *desc = &q->desc[q->head];
+ struct mt76_queue_entry *entry = &q->entry[q->head];
+ struct mt76_txwi_cache *txwi = NULL;
+ u32 buf1 = 0, ctrl;
+ int idx = q->head;
+ int rx_token;
+
+ ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+
+ if ((q->flags & MT_QFLAG_WED) &&
+ FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
+ txwi = mt76_get_rxwi(dev);
+ if (!txwi)
+ return -ENOMEM;
+
+ rx_token = mt76_rx_token_consume(dev, data, txwi, buf->addr);
+ if (rx_token < 0) {
+ mt76_put_rxwi(dev, txwi);
+ return -ENOMEM;
+ }
+
+ buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token);
+ ctrl |= MT_DMA_CTL_TO_HOST;
+ }
+
+ WRITE_ONCE(desc->buf0, cpu_to_le32(buf->addr));
+ WRITE_ONCE(desc->buf1, cpu_to_le32(buf1));
+ WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl));
+ WRITE_ONCE(desc->info, 0);
+
+ entry->dma_addr[0] = buf->addr;
+ entry->dma_len[0] = buf->len;
+ entry->txwi = txwi;
+ entry->buf = data;
+ entry->wcid = 0xffff;
+ entry->skip_buf1 = true;
+ q->head = (q->head + 1) % q->ndesc;
+ q->queued++;
+
+ return idx;
+}
+
static int
mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
struct mt76_queue_buf *buf, int nbufs, u32 info,
@@ -215,6 +261,11 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
int i, idx = -1;
u32 ctrl, next;
+ if (txwi) {
+ q->entry[q->head].txwi = DMA_DUMMY_DATA;
+ q->entry[q->head].skip_buf0 = true;
+ }
+
for (i = 0; i < nbufs; i += 2, buf += 2) {
u32 buf0 = buf[0].addr, buf1 = 0;
@@ -224,51 +275,28 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
desc = &q->desc[idx];
entry = &q->entry[idx];
- if ((q->flags & MT_QFLAG_WED) &&
- FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
- struct mt76_txwi_cache *t = txwi;
- int rx_token;
-
- if (!t)
- return -ENOMEM;
-
- rx_token = mt76_rx_token_consume(dev, (void *)skb, t,
- buf[0].addr);
- if (rx_token < 0)
- return -ENOMEM;
-
- buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token);
- ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len) |
- MT_DMA_CTL_TO_HOST;
- } else {
- if (txwi) {
- q->entry[next].txwi = DMA_DUMMY_DATA;
- q->entry[next].skip_buf0 = true;
- }
-
- if (buf[0].skip_unmap)
- entry->skip_buf0 = true;
- entry->skip_buf1 = i == nbufs - 1;
-
- entry->dma_addr[0] = buf[0].addr;
- entry->dma_len[0] = buf[0].len;
-
- ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
- if (i < nbufs - 1) {
- entry->dma_addr[1] = buf[1].addr;
- entry->dma_len[1] = buf[1].len;
- buf1 = buf[1].addr;
- ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
- if (buf[1].skip_unmap)
- entry->skip_buf1 = true;
- }
-
- if (i == nbufs - 1)
- ctrl |= MT_DMA_CTL_LAST_SEC0;
- else if (i == nbufs - 2)
- ctrl |= MT_DMA_CTL_LAST_SEC1;
+ if (buf[0].skip_unmap)
+ entry->skip_buf0 = true;
+ entry->skip_buf1 = i == nbufs - 1;
+
+ entry->dma_addr[0] = buf[0].addr;
+ entry->dma_len[0] = buf[0].len;
+
+ ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len);
+ if (i < nbufs - 1) {
+ entry->dma_addr[1] = buf[1].addr;
+ entry->dma_len[1] = buf[1].len;
+ buf1 = buf[1].addr;
+ ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len);
+ if (buf[1].skip_unmap)
+ entry->skip_buf1 = true;
}
+ if (i == nbufs - 1)
+ ctrl |= MT_DMA_CTL_LAST_SEC0;
+ else if (i == nbufs - 2)
+ ctrl |= MT_DMA_CTL_LAST_SEC1;
+
WRITE_ONCE(desc->buf0, cpu_to_le32(buf0));
WRITE_ONCE(desc->buf1, cpu_to_le32(buf1));
WRITE_ONCE(desc->info, cpu_to_le32(info));
@@ -581,17 +609,9 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q)
spin_lock_bh(&q->lock);
while (q->queued < q->ndesc - 1) {
- struct mt76_txwi_cache *t = NULL;
struct mt76_queue_buf qbuf;
void *buf = NULL;
- if ((q->flags & MT_QFLAG_WED) &&
- FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) {
- t = mt76_get_rxwi(dev);
- if (!t)
- break;
- }
-
buf = page_frag_alloc(rx_page, q->buf_size, GFP_ATOMIC);
if (!buf)
break;
@@ -605,7 +625,7 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q)
qbuf.addr = addr + offset;
qbuf.len = len - offset;
qbuf.skip_unmap = false;
- if (mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, t) < 0) {
+ if (mt76_dma_add_rx_buf(dev, q, &qbuf, buf) < 0) {
dma_unmap_single(dev->dma_dev, addr, len,
DMA_FROM_DEVICE);
skb_free_frag(buf);
--
GitLab
From 80f8a66dede0a4b4e9e846765a97809c6fe49ce5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Jan 2023 12:43:26 +0000
Subject: [PATCH 0816/1167] Revert "wifi: mac80211: fix memory leak in
ieee80211_if_add()"
This reverts commit 13e5afd3d773c6fc6ca2b89027befaaaa1ea7293.
ieee80211_if_free() is already called from free_netdev(ndev)
because ndev->priv_destructor == ieee80211_if_free
syzbot reported:
general protection fault, probably for non-canonical address 0xdffffc0000000004: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000020-0x0000000000000027]
CPU: 0 PID: 10041 Comm: syz-executor.0 Not tainted 6.2.0-rc2-syzkaller-00388-g55b98837e37d #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
RIP: 0010:pcpu_get_page_chunk mm/percpu.c:262 [inline]
RIP: 0010:pcpu_chunk_addr_search mm/percpu.c:1619 [inline]
RIP: 0010:free_percpu mm/percpu.c:2271 [inline]
RIP: 0010:free_percpu+0x186/0x10f0 mm/percpu.c:2254
Code: 80 3c 02 00 0f 85 f5 0e 00 00 48 8b 3b 48 01 ef e8 cf b3 0b 00 48 ba 00 00 00 00 00 fc ff df 48 8d 78 20 48 89 f9 48 c1 e9 03 <80> 3c 11 00 0f 85 3b 0e 00 00 48 8b 58 20 48 b8 00 00 00 00 00 fc
RSP: 0018:ffffc90004ba7068 EFLAGS: 00010002
RAX: 0000000000000000 RBX: ffff88823ffe2b80 RCX: 0000000000000004
RDX: dffffc0000000000 RSI: ffffffff81c1f4e7 RDI: 0000000000000020
RBP: ffffe8fffe8fc220 R08: 0000000000000005 R09: 0000000000000000
R10: 0000000000000000 R11: 1ffffffff2179ab2 R12: ffff8880b983d000
R13: 0000000000000003 R14: 0000607f450fc220 R15: ffff88823ffe2988
FS: 00007fcb349de700(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b32220000 CR3: 000000004914f000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
netdev_run_todo+0x6bf/0x1100 net/core/dev.c:10352
ieee80211_register_hw+0x2663/0x4040 net/mac80211/main.c:1411
mac80211_hwsim_new_radio+0x2537/0x4d80 drivers/net/wireless/mac80211_hwsim.c:4583
hwsim_new_radio_nl+0xa09/0x10f0 drivers/net/wireless/mac80211_hwsim.c:5176
genl_family_rcv_msg_doit.isra.0+0x1e6/0x2d0 net/netlink/genetlink.c:968
genl_family_rcv_msg net/netlink/genetlink.c:1048 [inline]
genl_rcv_msg+0x4ff/0x7e0 net/netlink/genetlink.c:1065
netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564
genl_rcv+0x28/0x40 net/netlink/genetlink.c:1076
netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline]
netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356
netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg+0xd3/0x120 net/socket.c:734
____sys_sendmsg+0x712/0x8c0 net/socket.c:2476
___sys_sendmsg+0x110/0x1b0 net/socket.c:2530
__sys_sendmsg+0xf7/0x1c0 net/socket.c:2559
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: 13e5afd3d773 ("wifi: mac80211: fix memory leak in ieee80211_if_add()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Zhengchao Shao <shaozhengchao@huawei.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/20230113124326.3533978-1-edumazet@google.com
---
net/mac80211/iface.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e20c3fe9a0b19..23ed13f150675 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -2197,7 +2197,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
ret = cfg80211_register_netdevice(ndev);
if (ret) {
- ieee80211_if_free(ndev);
free_netdev(ndev);
return ret;
}
--
GitLab
From 3ef5abd9b5c738bc6fa9a65e40331ef2cb03ad9c Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Thu, 12 Jan 2023 17:18:13 +0106
Subject: [PATCH 0817/1167] tty: serial: kgdboc: fix mutex locking order for
configure_kgdboc()
Several mutexes are taken while setting up console serial ports. In
particular, the tty_port->mutex and @console_mutex are taken:
serial_pnp_probe
serial8250_register_8250_port
uart_add_one_port (locks tty_port->mutex)
uart_configure_port
register_console (locks @console_mutex)
In order to synchronize kgdb's tty_find_polling_driver() with
register_console(), commit 6193bc90849a ("tty: serial: kgdboc:
synchronize tty_find_polling_driver() and register_console()") takes
the @console_mutex. However, this leads to the following call chain
(with locking):
platform_probe
kgdboc_probe
configure_kgdboc (locks @console_mutex)
tty_find_polling_driver
uart_poll_init (locks tty_port->mutex)
uart_set_options
This is clearly deadlock potential due to the reverse lock ordering.
Since uart_set_options() requires holding @console_mutex in order to
serialize early initialization of the serial-console lock, take the
@console_mutex in uart_poll_init() instead of configure_kgdboc().
Since configure_kgdboc() was using @console_mutex for safe traversal
of the console list, change it to use the SRCU iterator instead.
Add comments to uart_set_options() kerneldoc mentioning that it
requires holding @console_mutex (aka the console_list_lock).
Fixes: 6193bc90849a ("tty: serial: kgdboc: synchronize tty_find_polling_driver() and register_console()")
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
[pmladek@suse.com: Export console_srcu_read_lock_is_held() to fix build kgdboc as a module.]
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20230112161213.1434854-1-john.ogness@linutronix.de
---
drivers/tty/serial/kgdboc.c | 20 +++++---------------
drivers/tty/serial/serial_core.c | 5 +++++
kernel/printk/printk.c | 1 +
3 files changed, 11 insertions(+), 15 deletions(-)
diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c
index a3ed9b34e2abb..7ce7bb1640054 100644
--- a/drivers/tty/serial/kgdboc.c
+++ b/drivers/tty/serial/kgdboc.c
@@ -171,6 +171,7 @@ static int configure_kgdboc(void)
int err = -ENODEV;
char *cptr = config;
struct console *cons;
+ int cookie;
if (!strlen(config) || isspace(config[0])) {
err = 0;
@@ -189,20 +190,9 @@ static int configure_kgdboc(void)
if (kgdboc_register_kbd(&cptr))
goto do_register;
- /*
- * tty_find_polling_driver() can call uart_set_options()
- * (via poll_init) to configure the uart. Take the console_list_lock
- * in order to synchronize against register_console(), which can also
- * configure the uart via uart_set_options(). This also allows safe
- * traversal of the console list.
- */
- console_list_lock();
-
p = tty_find_polling_driver(cptr, &tty_line);
- if (!p) {
- console_list_unlock();
+ if (!p)
goto noconfig;
- }
/*
* Take console_lock to serialize device() callback with
@@ -211,7 +201,8 @@ static int configure_kgdboc(void)
*/
console_lock();
- for_each_console(cons) {
+ cookie = console_srcu_read_lock();
+ for_each_console_srcu(cons) {
int idx;
if (cons->device && cons->device(cons, &idx) == p &&
idx == tty_line) {
@@ -219,11 +210,10 @@ static int configure_kgdboc(void)
break;
}
}
+ console_srcu_read_unlock(cookie);
console_unlock();
- console_list_unlock();
-
kgdb_tty_driver = p;
kgdb_tty_line = tty_line;
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index b9fbbee598b81..ec874f3a567ca 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2212,6 +2212,9 @@ EXPORT_SYMBOL_GPL(uart_parse_options);
* @parity: parity character - 'n' (none), 'o' (odd), 'e' (even)
* @bits: number of data bits
* @flow: flow control character - 'r' (rts)
+ *
+ * Locking: Caller must hold console_list_lock in order to serialize
+ * early initialization of the serial-console lock.
*/
int
uart_set_options(struct uart_port *port, struct console *co,
@@ -2619,7 +2622,9 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options)
if (!ret && options) {
uart_parse_options(options, &baud, &parity, &bits, &flow);
+ console_list_lock();
ret = uart_set_options(port, NULL, baud, parity, bits, flow);
+ console_list_unlock();
}
out:
mutex_unlock(&tport->mutex);
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9ec1017664718..3f7c8ed96512b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -123,6 +123,7 @@ bool console_srcu_read_lock_is_held(void)
{
return srcu_read_lock_held(&console_srcu);
}
+EXPORT_SYMBOL(console_srcu_read_lock_is_held);
#endif
enum devkmsg_log_bits {
--
GitLab
From 3e9900f3bd7ba30d60f82b162b70a1dffe4e8e24 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 16 Jan 2023 08:51:05 -0700
Subject: [PATCH 0818/1167] pktcdvd: check for NULL returna fter calling
bio_split_to_limits()
The revert of the removal of this driver happened after we fixed up
the split limits for NOWAIT issue, hence it got missed. Ensure that
we check for a NULL bio after splitting, in case it should be retried.
Marking this as fixing both commits, so that stable backport will do
this correctly.
Cc: stable@vger.kernel.org
Fixes: 9cea62b2cbab ("block: don't allow splitting of a REQ_NOWAIT bio")
Fixes: 4b83e99ee709 ("Revert "pktcdvd: remove driver."")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/block/pktcdvd.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 4cea3b08087ed..2f1a92509271c 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2400,6 +2400,8 @@ static void pkt_submit_bio(struct bio *bio)
struct bio *split;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
(unsigned long long)bio->bi_iter.bi_sector,
--
GitLab
From 4fe59a130c112460626a6a8b9232aa580d9b8efc Mon Sep 17 00:00:00 2001
From: Anuradha Weeraman <anuradha@debian.org>
Date: Mon, 16 Jan 2023 18:26:34 +0530
Subject: [PATCH 0819/1167] kernel/printk/printk.c: Fix W=1 kernel-doc warning
Fix W=1 kernel-doc warning:
kernel/printk/printk.c:
- Include function parameter in console_lock_spinning_disable_and_check()
Signed-off-by: Anuradha Weeraman <anuradha@debian.org>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20230116125635.374567-1-anuradha@debian.org
---
kernel/printk/printk.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 3f7c8ed96512b..39221b0f918db 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1892,6 +1892,7 @@ static void console_lock_spinning_enable(void)
/**
* console_lock_spinning_disable_and_check - mark end of code where another
* thread was able to busy wait and check if there is a waiter
+ * @cookie: cookie returned from console_srcu_read_lock()
*
* This is called at the end of the section where spinning is allowed.
* It has two functions. First, it is a signal that it is no longer
--
GitLab
From 0f097f08c9b3c1fdb6cc9f2dd423abc17d13f1a2 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Wed, 11 Jan 2023 12:10:54 +0200
Subject: [PATCH 0820/1167] lib/scatterlist: Fix to calculate the last_pg
properly
The last_pg is wrong, it is actually the first page of the last
scatterlist element. To get the last page of the last scatterlist element
we have to add prv->length. So it is checking mergability against the
wrong page, Further, a SG element is not guaranteed to end on a page
boundary, so we have to check the sub page location also for merge
eligibility.
Fix the above by checking physical contiguity based on PFNs, compute the
actual last page and then call pages_are_mergable().
Fixes: 1567b49d1a40 ("lib/scatterlist: add check when merging zone device pages")
Link: https://lore.kernel.org/r/20230111101054.188136-1-yishaih@nvidia.com
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
lib/scatterlist.c | 25 +++++++++++++++----------
1 file changed, 15 insertions(+), 10 deletions(-)
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index f72aa50c6654b..8d7519a8f308d 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -470,22 +470,27 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append,
return -EOPNOTSUPP;
if (sgt_append->prv) {
+ unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) +
+ sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE;
+
if (WARN_ON(offset))
return -EINVAL;
/* Merge contiguous pages into the last SG */
prv_len = sgt_append->prv->length;
- last_pg = sg_page(sgt_append->prv);
- while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
- if (sgt_append->prv->length + PAGE_SIZE > max_segment)
- break;
- sgt_append->prv->length += PAGE_SIZE;
- last_pg = pages[0];
- pages++;
- n_pages--;
+ if (page_to_pfn(pages[0]) == next_pfn) {
+ last_pg = pfn_to_page(next_pfn - 1);
+ while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
+ if (sgt_append->prv->length + PAGE_SIZE > max_segment)
+ break;
+ sgt_append->prv->length += PAGE_SIZE;
+ last_pg = pages[0];
+ pages++;
+ n_pages--;
+ }
+ if (!n_pages)
+ goto out;
}
- if (!n_pages)
- goto out;
}
/* compute number of contiguous chunks */
--
GitLab
From 5fa55950729d0762a787451dc52862c3f850f859 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 9 Jan 2023 22:57:13 +0100
Subject: [PATCH 0821/1167] x86/i8259: Mark legacy PIC interrupts with
IRQ_LEVEL
Baoquan reported that after triggering a crash the subsequent crash-kernel
fails to boot about half of the time. It triggers a NULL pointer
dereference in the periodic tick code.
This happens because the legacy timer interrupt (IRQ0) is resent in
software which happens in soft interrupt (tasklet) context. In this context
get_irq_regs() returns NULL which leads to the NULL pointer dereference.
The reason for the resend is a spurious APIC interrupt on the IRQ0 vector
which is captured and leads to a resend when the legacy timer interrupt is
enabled. This is wrong because the legacy PIC interrupts are level
triggered and therefore should never be resent in software, but nothing
ever sets the IRQ_LEVEL flag on those interrupts, so the core code does not
know about their trigger type.
Ensure that IRQ_LEVEL is set when the legacy PCI interrupts are set up.
Fixes: a4633adcdbc1 ("[PATCH] genirq: add genirq sw IRQ-retrigger")
Reported-by: Baoquan He <bhe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Baoquan He <bhe@redhat.com>
Link: https://lore.kernel.org/r/87mt6rjrra.ffs@tglx
---
arch/x86/kernel/i8259.c | 1 +
arch/x86/kernel/irqinit.c | 4 +++-
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 3aa5304200c50..4d8aff05a509e 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq)
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+ irq_set_status_flags(irq, IRQ_LEVEL);
enable_irq(irq);
lapic_assign_legacy_vector(irq, true);
}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index beb1bada1b0ab..c683666876f1c 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -65,8 +65,10 @@ void __init init_ISA_irqs(void)
legacy_pic->init(0);
- for (i = 0; i < nr_legacy_irqs(); i++)
+ for (i = 0; i < nr_legacy_irqs(); i++) {
irq_set_chip_and_handler(i, chip, handle_level_irq);
+ irq_set_status_flags(i, IRQ_LEVEL);
+ }
}
void __init init_IRQ(void)
--
GitLab
From 0e0078f72be81bbb2a02b229fd2cec8ad63e4fb1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Nov 2022 18:47:48 +0100
Subject: [PATCH 0822/1167] btrfs: factor out scratching of one regular super
block
btrfs_scratch_superblocks open codes scratching super block of a
non-zoned super block. Split the code to read, zero and write the
superblock for regular devices into a separate helper.
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/volumes.c | 51 +++++++++++++++++++++++-----------------------
1 file changed, 26 insertions(+), 25 deletions(-)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bf0decaac7f30..119dc26ca141c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2014,42 +2014,43 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info)
return num_devices;
}
+static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev, int copy_num)
+{
+ struct btrfs_super_block *disk_super;
+ struct page *page;
+ int ret;
+
+ disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
+ if (IS_ERR(disk_super))
+ return;
+
+ memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+ page = virt_to_page(disk_super);
+ set_page_dirty(page);
+ lock_page(page);
+ /* write_on_page() unlocks the page */
+ ret = write_one_page(page);
+ if (ret)
+ btrfs_warn(fs_info, "error clearing superblock number %d (%d)",
+ copy_num, ret);
+ btrfs_release_disk_super(disk_super);
+}
+
void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
struct block_device *bdev,
const char *device_path)
{
- struct btrfs_super_block *disk_super;
int copy_num;
if (!bdev)
return;
for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) {
- struct page *page;
- int ret;
-
- disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
- if (IS_ERR(disk_super))
- continue;
-
- if (bdev_is_zoned(bdev)) {
+ if (bdev_is_zoned(bdev))
btrfs_reset_sb_log_zones(bdev, copy_num);
- continue;
- }
-
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-
- page = virt_to_page(disk_super);
- set_page_dirty(page);
- lock_page(page);
- /* write_on_page() unlocks the page */
- ret = write_one_page(page);
- if (ret)
- btrfs_warn(fs_info,
- "error clearing superblock number %d (%d)",
- copy_num, ret);
- btrfs_release_disk_super(disk_super);
-
+ else
+ btrfs_scratch_superblock(fs_info, bdev, copy_num);
}
/* Notify udev that device has changed */
--
GitLab
From 26ecf243e407be54807ad67210f7e83b9fad71ea Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 21 Nov 2022 18:47:49 +0100
Subject: [PATCH 0823/1167] btrfs: stop using write_one_page in
btrfs_scratch_superblock
write_one_page is an awkward interface that expects the page locked and
->writepage to be implemented. Replace that by zeroing the signature
bytes and synchronize the block device page using the proper bdev
helpers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/volumes.c | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 119dc26ca141c..bcfef75b97da0 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2018,23 +2018,22 @@ static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
struct block_device *bdev, int copy_num)
{
struct btrfs_super_block *disk_super;
- struct page *page;
+ const size_t len = sizeof(disk_super->magic);
+ const u64 bytenr = btrfs_sb_offset(copy_num);
int ret;
- disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
+ disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr);
if (IS_ERR(disk_super))
return;
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
- page = virt_to_page(disk_super);
- set_page_dirty(page);
- lock_page(page);
- /* write_on_page() unlocks the page */
- ret = write_one_page(page);
+ memset(&disk_super->magic, 0, len);
+ folio_mark_dirty(virt_to_folio(disk_super));
+ btrfs_release_disk_super(disk_super);
+
+ ret = sync_blockdev_range(bdev, bytenr, bytenr + len - 1);
if (ret)
btrfs_warn(fs_info, "error clearing superblock number %d (%d)",
copy_num, ret);
- btrfs_release_disk_super(disk_super);
}
void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
--
GitLab
From 1f55ee6d0901d915801618bda0af4e5b937e3db7 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 12 Jan 2023 14:17:20 +0000
Subject: [PATCH 0824/1167] btrfs: fix invalid leaf access due to inline extent
during lseek
During lseek, for SEEK_DATA and SEEK_HOLE modes, we access the disk_bytenr
of an extent without checking its type. However inline extents have their
data starting the offset of the disk_bytenr field, so accessing that field
when we have an inline extent can result in either of the following:
1) Interpret the inline extent's data as a disk_bytenr value;
2) In case the inline data is less than 8 bytes, we access part of some
other item in the leaf, or unused space in the leaf;
3) In case the inline data is less than 8 bytes and the extent item is
the first item in the leaf, we can access beyond the leaf's limit.
So fix this by not accessing the disk_bytenr field if we have an inline
extent.
Fixes: b6e833567ea1 ("btrfs: make hole and data seeking a lot more efficient")
Reported-by: Matthias Schoepfer <matthias.schoepfer@googlemail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=216908
Link: https://lore.kernel.org/linux-btrfs/7f25442f-b121-2a3a-5a3d-22bcaae83cd4@leemhuis.info/
CC: stable@vger.kernel.org # 6.1
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/file.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 834bbcb91102f..af046d22300e2 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3541,6 +3541,7 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
struct extent_buffer *leaf = path->nodes[0];
struct btrfs_file_extent_item *extent;
u64 extent_end;
+ u8 type;
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
@@ -3596,10 +3597,16 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(leaf, extent);
- if (btrfs_file_extent_disk_bytenr(leaf, extent) == 0 ||
- btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_PREALLOC) {
+ /*
+ * Can't access the extent's disk_bytenr field if this is an
+ * inline extent, since at that offset, it's where the extent
+ * data starts.
+ */
+ if (type == BTRFS_FILE_EXTENT_PREALLOC ||
+ (type == BTRFS_FILE_EXTENT_REG &&
+ btrfs_file_extent_disk_bytenr(leaf, extent) == 0)) {
/*
* Explicit hole or prealloc extent, search for delalloc.
* A prealloc extent is treated like a hole.
--
GitLab
From b7adbf9ada3513d2092362c8eac5cddc5b651f5c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 12 Jan 2023 16:31:08 +0000
Subject: [PATCH 0825/1167] btrfs: fix race between quota rescan and disable
leading to NULL pointer deref
If we have one task trying to start the quota rescan worker while another
one is trying to disable quotas, we can end up hitting a race that results
in the quota rescan worker doing a NULL pointer dereference. The steps for
this are the following:
1) Quotas are enabled;
2) Task A calls the quota rescan ioctl and enters btrfs_qgroup_rescan().
It calls qgroup_rescan_init() which returns 0 (success) and then joins a
transaction and commits it;
3) Task B calls the quota disable ioctl and enters btrfs_quota_disable().
It clears the bit BTRFS_FS_QUOTA_ENABLED from fs_info->flags and calls
btrfs_qgroup_wait_for_completion(), which returns immediately since the
rescan worker is not yet running.
Then it starts a transaction and locks fs_info->qgroup_ioctl_lock;
4) Task A queues the rescan worker, by calling btrfs_queue_work();
5) The rescan worker starts, and calls rescan_should_stop() at the start
of its while loop, which results in 0 iterations of the loop, since
the flag BTRFS_FS_QUOTA_ENABLED was cleared from fs_info->flags by
task B at step 3);
6) Task B sets fs_info->quota_root to NULL;
7) The rescan worker tries to start a transaction and uses
fs_info->quota_root as the root argument for btrfs_start_transaction().
This results in a NULL pointer dereference down the call chain of
btrfs_start_transaction(). The stack trace is something like the one
reported in Link tag below:
general protection fault, probably for non-canonical address 0xdffffc0000000041: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000208-0x000000000000020f]
CPU: 1 PID: 34 Comm: kworker/u4:2 Not tainted 6.1.0-syzkaller-13872-gb6bb9676f216 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
Workqueue: btrfs-qgroup-rescan btrfs_work_helper
RIP: 0010:start_transaction+0x48/0x10f0 fs/btrfs/transaction.c:564
Code: 48 89 fb 48 (...)
RSP: 0018:ffffc90000ab7ab0 EFLAGS: 00010206
RAX: 0000000000000041 RBX: 0000000000000208 RCX: ffff88801779ba80
RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000
RBP: dffffc0000000000 R08: 0000000000000001 R09: fffff52000156f5d
R10: fffff52000156f5d R11: 1ffff92000156f5c R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000003
FS: 0000000000000000(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f2bea75b718 CR3: 000000001d0cc000 CR4: 00000000003506e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
btrfs_qgroup_rescan_worker+0x3bb/0x6a0 fs/btrfs/qgroup.c:3402
btrfs_work_helper+0x312/0x850 fs/btrfs/async-thread.c:280
process_one_work+0x877/0xdb0 kernel/workqueue.c:2289
worker_thread+0xb14/0x1330 kernel/workqueue.c:2436
kthread+0x266/0x300 kernel/kthread.c:376
ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308
</TASK>
Modules linked in:
So fix this by having the rescan worker function not attempt to start a
transaction if it didn't do any rescan work.
Reported-by: syzbot+96977faa68092ad382c4@syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/000000000000e5454b05f065a803@google.com/
Fixes: e804861bd4e6 ("btrfs: fix deadlock between quota disable and qgroup rescan worker")
CC: stable@vger.kernel.org # 5.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/qgroup.c | 25 +++++++++++++++++--------
1 file changed, 17 insertions(+), 8 deletions(-)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 00851c86aa8aa..af97413abcf43 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3367,6 +3367,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
int err = -ENOMEM;
int ret = 0;
bool stopped = false;
+ bool did_leaf_rescans = false;
path = btrfs_alloc_path();
if (!path)
@@ -3387,6 +3388,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
}
err = qgroup_rescan_leaf(trans, path);
+ did_leaf_rescans = true;
if (err > 0)
btrfs_commit_transaction(trans);
@@ -3407,16 +3409,23 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
mutex_unlock(&fs_info->qgroup_rescan_lock);
/*
- * only update status, since the previous part has already updated the
- * qgroup info.
+ * Only update status, since the previous part has already updated the
+ * qgroup info, and only if we did any actual work. This also prevents
+ * race with a concurrent quota disable, which has already set
+ * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at
+ * btrfs_quota_disable().
*/
- trans = btrfs_start_transaction(fs_info->quota_root, 1);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
+ if (did_leaf_rescans) {
+ trans = btrfs_start_transaction(fs_info->quota_root, 1);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ trans = NULL;
+ btrfs_err(fs_info,
+ "fail to start transaction for status update: %d",
+ err);
+ }
+ } else {
trans = NULL;
- btrfs_err(fs_info,
- "fail to start transaction for status update: %d",
- err);
}
mutex_lock(&fs_info->qgroup_rescan_lock);
--
GitLab
From 0a3a58de319552525507a3497da86df039a5e4e0 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw2@infradead.org>
Date: Sun, 15 Jan 2023 22:14:19 +0000
Subject: [PATCH 0826/1167] x86/pci/xen: Set MSI_FLAG_PCI_MSIX support in Xen
MSI domain
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The Xen MSI → PIRQ magic does support MSI-X, so advertise it.
(In fact it's better off with MSI-X than MSI, because it's actually
broken by design for 32-bit MSI, since it puts the high bits of the
PIRQ# into the high 32 bits of the MSI message address, instead of the
Extended Destination ID field which is in bits 4-11.
Strictly speaking, this really fixes a much older commit 2e4386eba0c0
("x86/xen: Wrap XEN MSI management into irqdomain") which failed to set
the flag. But that never really mattered until __pci_enable_msix_range()
started to check and bail out early. So in 6.2-rc we see failures e.g.
to bring up networking on an Amazon EC2 m4.16xlarge instance:
[ 41.498694] ena 0000:00:03.0 (unnamed net_device) (uninitialized): Failed to enable MSI-X. irq_cnt -524
[ 41.498705] ena 0000:00:03.0: Can not reserve msix vectors
[ 41.498712] ena 0000:00:03.0: Failed to enable and set the admin interrupts
Side note: This is the first bug found, and first patch tested, by running
Xen guests under QEMU/KVM instead of running under actual Xen.
Fixes: 99f3d2797657 ("PCI/MSI: Reject MSI-X early")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/4bffa69a949bfdc92c4a18e5a1c3cbb3b94a0d32.camel@infradead.org
---
arch/x86/pci/xen.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index b94f727251b64..790550479831f 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -433,6 +433,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = {
};
static struct msi_domain_info xen_pci_msi_domain_info = {
+ .flags = MSI_FLAG_PCI_MSIX,
.ops = &xen_pci_msi_domain_ops,
};
--
GitLab
From 6c796996ee7033bcbbc3cd733513eb43f8160f5e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 16 Jan 2023 19:11:32 +0100
Subject: [PATCH 0827/1167] x86/pci/xen: Fixup fallout from the PCI/MSI
overhaul
David reported that the recent PCI/MSI rework results in MSI descriptor
leakage under XEN.
This is caused by:
1) The missing MSI_FLAG_FREE_MSI_DESCS flag in the XEN MSI domain info,
which is required now that PCI/MSI delegates descriptor freeing to
the core MSI code.
2) Not disassociating the interrupts on teardown, by setting the
msi_desc::irq to 0. This was not required before because the teardown
was unconditional and did not check whether a MSI descriptor was still
connected to a Linux interrupt.
On further inspection it came to light that the MSI_FLAG_DEV_SYSFS is
missing in the XEN MSI domain info as well to restore the pre 6.2 status
quo.
Add the missing MSI flags and disassociate the MSI descriptor from the
Linux interrupt in the XEN specific teardown function.
Fixes: b2bdda205c0c ("PCI/MSI: Let the MSI core free descriptors")
Fixes: 2f2940d16823 ("genirq/msi: Remove filter from msi_free_descs_free_range()")
Fixes: ffd84485e6be ("PCI/MSI: Let the irq code handle sysfs groups")
Reported-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/871qnunycr.ffs@tglx
---
arch/x86/pci/xen.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 790550479831f..8babce71915fe 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev)
msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
for (i = 0; i < msidesc->nvec_used; i++)
xen_destroy_irq(msidesc->irq + i);
+ msidesc->irq = 0;
}
}
@@ -433,7 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = {
};
static struct msi_domain_info xen_pci_msi_domain_info = {
- .flags = MSI_FLAG_PCI_MSIX,
+ .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
.ops = &xen_pci_msi_domain_ops,
};
--
GitLab
From ef7592e466ef7b2595fdfdfd23559a779f4b211a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 16 Jan 2023 15:22:57 -0800
Subject: [PATCH 0828/1167] MAINTAINERS: update fsverity git repo, list, and
patchwork
We're moving fsverity development to use its own git repo, mailing list,
and patchwork project, instead of reusing the fscrypt ones. Update the
MAINTAINERS file accordingly.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20230116232257.64377-1-ebiggers@kernel.org
---
MAINTAINERS | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 42fc47c6edfd7..936cbdbc60eb1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8520,10 +8520,10 @@ F: include/linux/fsnotify*.h
FSVERITY: READ-ONLY FILE-BASED AUTHENTICITY PROTECTION
M: Eric Biggers <ebiggers@kernel.org>
M: Theodore Y. Ts'o <tytso@mit.edu>
-L: linux-fscrypt@vger.kernel.org
+L: fsverity@lists.linux.dev
S: Supported
-Q: https://patchwork.kernel.org/project/linux-fscrypt/list/
-T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git fsverity
+Q: https://patchwork.kernel.org/project/fsverity/list/
+T: git https://git.kernel.org/pub/scm/fs/fsverity/linux.git
F: Documentation/filesystems/fsverity.rst
F: fs/verity/
F: include/linux/fsverity.h
--
GitLab
From 31e1be62abdebc28bd51d0999a25f0eea535b5af Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 16 Jan 2023 15:34:24 -0800
Subject: [PATCH 0829/1167] MAINTAINERS: update fscrypt git repo
fscrypt.git is being renamed to linux.git, so update MAINTAINERS
accordingly. (The reasons for the rename are to match what I'm doing
for the new fsverity repo, which also involves the branch names changing
to be clearer; and to avoid ambiguity with userspace tools.)
As long as I'm updating the fscrypt MAINTAINERS entry anyway, also:
- Move my name to the top, so that people bother me first if they just
choose the first person. (In practice I'm the primary maintainer, and
Ted and Jaegeuk are backups.)
- Remove an unnecessary wildcard.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20230116233424.65657-1-ebiggers@kernel.org
---
MAINTAINERS | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 42fc47c6edfd7..8d0ee9f17b4d4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8468,16 +8468,16 @@ F: fs/fscache/
F: include/linux/fscache*.h
FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
+M: Eric Biggers <ebiggers@kernel.org>
M: Theodore Y. Ts'o <tytso@mit.edu>
M: Jaegeuk Kim <jaegeuk@kernel.org>
-M: Eric Biggers <ebiggers@kernel.org>
L: linux-fscrypt@vger.kernel.org
S: Supported
Q: https://patchwork.kernel.org/project/linux-fscrypt/list/
-T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git
+T: git https://git.kernel.org/pub/scm/fs/fscrypt/linux.git
F: Documentation/filesystems/fscrypt.rst
F: fs/crypto/
-F: include/linux/fscrypt*.h
+F: include/linux/fscrypt.h
F: include/uapi/linux/fscrypt.h
FSI SUBSYSTEM
--
GitLab
From e3ff8887e7db757360f97634e0d6f4b8e27a8c46 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Tue, 3 Jan 2023 19:28:33 +0800
Subject: [PATCH 0830/1167] blk-cgroup: fix missing pd_online_fn() while
activating policy
If the policy defines pd_online_fn(), it should be called after
pd_init_fn(), like blkg_create().
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230103112833.2013432-1-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-cgroup.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ce6a2b7d3dfb2..4c94a6560f625 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1455,6 +1455,10 @@ int blkcg_activate_policy(struct request_queue *q,
list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
pol->pd_init_fn(blkg->pd[pol->plid]);
+ if (pol->pd_online_fn)
+ list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+ pol->pd_online_fn(blkg->pd[pol->plid]);
+
__set_bit(pol->plid, q->blkcg_pols);
ret = 0;
--
GitLab
From d52fec86a465355b379e839fa372ead0334d62e6 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0831/1167] LoongArch: Add HWCAP_LOONGARCH_CPUCFG to elf_hwcap
HWCAP_LOONGARCH_CPUCFG is missing in elf_hwcap, so add it for glibc's
later use.
Cc: stable@vger.kernel.org
Reported-by: Yinyu Cai <caiyinyu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/kernel/cpu-probe.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index 255a09876ef28..3a3fce2d78461 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -94,7 +94,7 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR |
LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH;
- elf_hwcap |= HWCAP_LOONGARCH_CRC32;
+ elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32;
config = read_cpucfg(LOONGARCH_CPUCFG1);
if (config & CPUCFG1_UAL) {
--
GitLab
From 2959fce7fdb73fc784aefd58cc34b1ba700826aa Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0832/1167] LoongArch: Use common function sign_extend64()
There exists a common function sign_extend64() to sign extend a 64-bit
value using specified bit as sign-bit in include/linux/bitops.h, it is
more efficient, let us use it and remove the arch-specific sign_extend()
under arch/loongarch.
Suggested-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/inst.h | 8 --------
arch/loongarch/kernel/alternative.c | 6 +++---
2 files changed, 3 insertions(+), 11 deletions(-)
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index c00e1512d4fa3..6cd994d6d9d08 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -377,14 +377,6 @@ static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
return val < (1UL << bit);
}
-static inline unsigned long sign_extend(unsigned long val, unsigned int idx)
-{
- if (!is_imm_negative(val, idx + 1))
- return ((1UL << idx) - 1) & val;
- else
- return ~((1UL << idx) - 1) | val;
-}
-
#define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
int offset) \
diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c
index c5aebeac960b6..4ad13847e9626 100644
--- a/arch/loongarch/kernel/alternative.c
+++ b/arch/loongarch/kernel/alternative.c
@@ -74,7 +74,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf,
switch (src->reg0i26_format.opcode) {
case b_op:
case bl_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 27);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
@@ -93,7 +93,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf,
fallthrough;
case beqz_op:
case bnez_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
@@ -112,7 +112,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf,
case bge_op:
case bltu_op:
case bgeu_op:
- jump_addr = cur_pc + sign_extend(si << 2, 17);
+ jump_addr = cur_pc + sign_extend64(si << 2, 17);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
--
GitLab
From 3200983fa8e2c8aa17ed911b617b4a248bcb1267 Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0833/1167] LoongArch: Simplify larch_insn_gen_xxx
implementation
Simplify larch_insn_gen_xxx implementation by reusing emit_xxx.
Signed-off-by: Youling Tang <tangyouling@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/inst.h | 1 +
arch/loongarch/kernel/inst.c | 45 +++++--------------------------
2 files changed, 8 insertions(+), 38 deletions(-)
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 6cd994d6d9d08..7eedd83fd0d72 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -393,6 +393,7 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \
}
DEF_EMIT_REG0I26_FORMAT(b, b_op)
+DEF_EMIT_REG0I26_FORMAT(bl, bl_op)
#define DEF_EMIT_REG1I20_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c
index 512579d79b221..badc590870423 100644
--- a/arch/loongarch/kernel/inst.c
+++ b/arch/loongarch/kernel/inst.c
@@ -58,7 +58,6 @@ u32 larch_insn_gen_nop(void)
u32 larch_insn_gen_b(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
@@ -66,15 +65,7 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest)
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = b_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_b(&insn, offset >> 2);
return insn.word;
}
@@ -82,7 +73,6 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest)
u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
@@ -90,15 +80,7 @@ u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest)
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = bl_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_bl(&insn, offset >> 2);
return insn.word;
}
@@ -107,10 +89,7 @@ u32 larch_insn_gen_or(enum loongarch_gpr rd, enum loongarch_gpr rj, enum loongar
{
union loongarch_instruction insn;
- insn.reg3_format.opcode = or_op;
- insn.reg3_format.rd = rd;
- insn.reg3_format.rj = rj;
- insn.reg3_format.rk = rk;
+ emit_or(&insn, rd, rj, rk);
return insn.word;
}
@@ -124,9 +103,7 @@ u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm)
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu12iw_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu12iw(&insn, rd, imm);
return insn.word;
}
@@ -135,9 +112,7 @@ u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm)
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu32id_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu32id(&insn, rd, imm);
return insn.word;
}
@@ -146,10 +121,7 @@ u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm)
{
union loongarch_instruction insn;
- insn.reg2i12_format.opcode = lu52id_op;
- insn.reg2i12_format.rd = rd;
- insn.reg2i12_format.rj = rj;
- insn.reg2i12_format.immediate = imm;
+ emit_lu52id(&insn, rd, rj, imm);
return insn.word;
}
@@ -158,10 +130,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, unsigned l
{
union loongarch_instruction insn;
- insn.reg2i16_format.opcode = jirl_op;
- insn.reg2i16_format.rd = rd;
- insn.reg2i16_format.rj = rj;
- insn.reg2i16_format.immediate = (dest - pc) >> 2;
+ emit_jirl(&insn, rj, rd, (dest - pc) >> 2);
return insn.word;
}
--
GitLab
From e2f27392275c7ffceb4afac1567eb325722b9ae1 Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0834/1167] LoongArch: Adjust PC value when unwind next frame
in unwinder
When state->first is not set, the PC is a return address in the previous
frame. We need to adjust its value in case overflow to the next symbol.
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/kernel/unwind_prologue.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 0f8d1451ebb84..e98b00432c885 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -56,7 +56,7 @@ static bool unwind_by_prologue(struct unwind_state *state)
{
long frame_ra = -1;
unsigned long frame_size = 0;
- unsigned long size, offset, pc = state->pc;
+ unsigned long size, offset, pc;
struct pt_regs *regs;
struct stack_info *info = &state->stack_info;
union loongarch_instruction *ip, *ip_end;
@@ -78,6 +78,11 @@ static bool unwind_by_prologue(struct unwind_state *state)
return true;
}
+ /*
+ * When first is not set, the PC is a return address in the previous frame.
+ * We need to adjust its value in case overflow to the next symbol.
+ */
+ pc = state->pc - (state->first ? 0 : LOONGARCH_INSN_SIZE);
if (!kallsyms_lookup_size_offset(pc, &size, &offset))
return false;
--
GitLab
From 429a9671f235c94fc4b5d6687308714b74adc820 Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0835/1167] LoongArch: Get frame info in unwind_start() when
regs is not available
At unwind_start(), it is better to get its frame info here rather than
get them outside, even we don't have 'regs'. In this way we can simply
use unwind_{start, next_frame, done} outside.
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/kernel/process.c | 12 +++---------
arch/loongarch/kernel/unwind_guess.c | 6 ++++++
arch/loongarch/kernel/unwind_prologue.c | 16 +++++++++++++---
3 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index c583b1ef1f44c..edfd220a3737a 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -191,20 +191,14 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
unsigned long __get_wchan(struct task_struct *task)
{
- unsigned long pc;
+ unsigned long pc = 0;
struct unwind_state state;
if (!try_get_task_stack(task))
return 0;
- unwind_start(&state, task, NULL);
- state.sp = thread_saved_fp(task);
- get_stack_info(state.sp, state.task, &state.stack_info);
- state.pc = thread_saved_ra(task);
-#ifdef CONFIG_UNWINDER_PROLOGUE
- state.type = UNWINDER_PROLOGUE;
-#endif
- for (; !unwind_done(&state); unwind_next_frame(&state)) {
+ for (unwind_start(&state, task, NULL);
+ !unwind_done(&state); unwind_next_frame(&state)) {
pc = unwind_get_return_address(&state);
if (!pc)
break;
diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c
index e2d2e4f3001f4..9ef5f2a47f880 100644
--- a/arch/loongarch/kernel/unwind_guess.c
+++ b/arch/loongarch/kernel/unwind_guess.c
@@ -26,6 +26,12 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
if (regs) {
state->sp = regs->regs[3];
state->pc = regs->csr_era;
+ } else if (task && task != current) {
+ state->sp = thread_saved_fp(task);
+ state->pc = thread_saved_ra(task);
+ } else {
+ state->sp = (unsigned long)__builtin_frame_address(0);
+ state->pc = (unsigned long)__builtin_return_address(0);
}
state->task = task;
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index e98b00432c885..613545ce6a976 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -146,12 +146,22 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs)
{
memset(state, 0, sizeof(*state));
+ state->type = UNWINDER_PROLOGUE;
- if (regs && __kernel_text_address(regs->csr_era)) {
- state->pc = regs->csr_era;
+ if (regs) {
state->sp = regs->regs[3];
+ state->pc = regs->csr_era;
state->ra = regs->regs[1];
- state->type = UNWINDER_PROLOGUE;
+ if (!__kernel_text_address(state->pc))
+ state->type = UNWINDER_GUESS;
+ } else if (task && task != current) {
+ state->sp = thread_saved_fp(task);
+ state->pc = thread_saved_ra(task);
+ state->ra = 0;
+ } else {
+ state->sp = (unsigned long)__builtin_frame_address(0);
+ state->pc = (unsigned long)__builtin_return_address(0);
+ state->ra = 0;
}
state->task = task;
--
GitLab
From 5bb8d34449c4a2eb94d657b992170afafac274f9 Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0836/1167] LoongArch: Use correct sp value to get graph addr
in stack unwinders
The stack frame when function_graph enable like follows,
--------- <- function sp_on_entry
|
|
|
FAKE_RA <- sp_on_entry - sizeof(pt_regs) + PT_R1
|
--------- <- sp_on_entry - sizeof(pt_regs)
So if we want to get the &FAKE_RA we should get sp_on_entry first. In
the unwinder_prologue case, we can get the sp_on_entry as state->sp,
because we try to calculate each CFA and the ra saved address. But in
the unwinder_guess case, we cannot get it because we do not try to
calculate the CFA. Although LoongArch have not fixed frame, the $ra is
saved at CFA - 8 in most cases, we can try guess, too. As we store the
pc in state, we not need to dereference state->sp, too.
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/ftrace.h | 2 --
arch/loongarch/include/asm/unwind.h | 10 ++++++++++
arch/loongarch/kernel/unwind_guess.c | 11 ++++-------
arch/loongarch/kernel/unwind_prologue.c | 21 ++++++---------------
4 files changed, 20 insertions(+), 24 deletions(-)
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 90f9d3399b2aa..3418d32d4fc7d 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -10,8 +10,6 @@
#define FTRACE_REGS_PLT_IDX 1
#define NR_FTRACE_PLTS 2
-#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
-
#ifdef CONFIG_FUNCTION_TRACER
#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
index f2b52b9ea93d2..834ba6bd15d29 100644
--- a/arch/loongarch/include/asm/unwind.h
+++ b/arch/loongarch/include/asm/unwind.h
@@ -8,7 +8,9 @@
#define _ASM_UNWIND_H
#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
#include <asm/stacktrace.h>
enum unwinder_type {
@@ -40,4 +42,12 @@ static inline bool unwind_error(struct unwind_state *state)
return state->error;
}
+#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
+
+static inline unsigned long unwind_graph_addr(struct unwind_state *state,
+ unsigned long pc, unsigned long cfa)
+{
+ return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET));
+}
#endif /* _ASM_UNWIND_H */
diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c
index 9ef5f2a47f880..e7e637bdba17e 100644
--- a/arch/loongarch/kernel/unwind_guess.c
+++ b/arch/loongarch/kernel/unwind_guess.c
@@ -11,10 +11,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
{
if (unwind_done(state))
return 0;
- else if (state->first)
- return state->pc;
- return *(unsigned long *)(state->sp);
+ return state->pc;
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
@@ -36,7 +34,7 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
state->task = task;
state->first = true;
-
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
get_stack_info(state->sp, state->task, &state->stack_info);
if (!unwind_done(state) && !__kernel_text_address(state->pc))
@@ -60,9 +58,8 @@ bool unwind_next_frame(struct unwind_state *state)
state->sp < info->end;
state->sp += sizeof(unsigned long)) {
addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
+ state->pc = unwind_graph_addr(state, addr, state->sp + 8);
+ if (__kernel_text_address(state->pc))
return true;
}
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 613545ce6a976..463ba2391bdf4 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -21,16 +21,10 @@ static inline void unwind_state_fixup(struct unwind_state *state)
unsigned long unwind_get_return_address(struct unwind_state *state)
{
-
if (unwind_done(state))
return 0;
- else if (state->type)
- return state->pc;
- else if (state->first)
- return state->pc;
-
- return *(unsigned long *)(state->sp);
+ return state->pc;
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
@@ -43,9 +37,8 @@ static bool unwind_by_guess(struct unwind_state *state)
state->sp < info->end;
state->sp += sizeof(unsigned long)) {
addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
+ state->pc = unwind_graph_addr(state, addr, state->sp + 8);
+ if (__kernel_text_address(state->pc))
return true;
}
@@ -166,7 +159,7 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
state->task = task;
state->first = true;
-
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
get_stack_info(state->sp, state->task, &state->stack_info);
if (!unwind_done(state) && !__kernel_text_address(state->pc))
@@ -193,8 +186,7 @@ bool unwind_next_frame(struct unwind_state *state)
case UNWINDER_PROLOGUE:
if (unwind_by_prologue(state)) {
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
return true;
}
@@ -209,8 +201,7 @@ bool unwind_next_frame(struct unwind_state *state)
state->first = true;
state->ra = regs->regs[1];
state->sp = regs->regs[3];
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
+ state->pc = pc;
get_stack_info(state->sp, state->task, info);
return true;
--
GitLab
From c5ac25e0d78a6f63446b8fef4d8630ccd7a2663d Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0837/1167] LoongArch: Strip guess unwinder out from prologue
unwinder
The prolugue unwinder rely on symbol info. When PC is not in kernel text
address, it cannot find relative symbol info and it will be broken. The
guess unwinder will be used in this case. And the guess unwinder code in
prolugue unwinder is redundant. Strip it out and set the unwinder type
in unwind_state. Make guess_unwinder::unwind_next_frame() as default way
when other unwinders cannot unwind in some extreme case.
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/unwind.h | 29 +++++
arch/loongarch/kernel/Makefile | 2 +-
arch/loongarch/kernel/traps.c | 3 -
arch/loongarch/kernel/unwind.c | 32 +++++
arch/loongarch/kernel/unwind_guess.c | 52 +-------
arch/loongarch/kernel/unwind_prologue.c | 157 ++++++++++--------------
6 files changed, 129 insertions(+), 146 deletions(-)
create mode 100644 arch/loongarch/kernel/unwind.c
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
index 834ba6bd15d29..36584b95ef8b6 100644
--- a/arch/loongarch/include/asm/unwind.h
+++ b/arch/loongarch/include/asm/unwind.h
@@ -27,6 +27,8 @@ struct unwind_state {
unsigned long sp, pc, ra;
};
+bool default_next_frame(struct unwind_state *state);
+
void unwind_start(struct unwind_state *state,
struct task_struct *task, struct pt_regs *regs);
bool unwind_next_frame(struct unwind_state *state);
@@ -50,4 +52,31 @@ static inline unsigned long unwind_graph_addr(struct unwind_state *state,
return ftrace_graph_ret_addr(state->task, &state->graph_idx,
pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET));
}
+
+static __always_inline void __unwind_start(struct unwind_state *state,
+ struct task_struct *task, struct pt_regs *regs)
+{
+ memset(state, 0, sizeof(*state));
+ if (regs) {
+ state->sp = regs->regs[3];
+ state->pc = regs->csr_era;
+ state->ra = regs->regs[1];
+ } else if (task && task != current) {
+ state->sp = thread_saved_fp(task);
+ state->pc = thread_saved_ra(task);
+ state->ra = 0;
+ } else {
+ state->sp = (unsigned long)__builtin_frame_address(0);
+ state->pc = (unsigned long)__builtin_return_address(0);
+ state->ra = 0;
+ }
+ state->task = task;
+ get_stack_info(state->sp, state->task, &state->stack_info);
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+}
+
+static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
+{
+ return unwind_done(state) ? 0 : state->pc;
+}
#endif /* _ASM_UNWIND_H */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index fcaa024a685ec..c8cfbd562921d 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -8,7 +8,7 @@ extra-y := vmlinux.lds
obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \
elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
- alternative.o unaligned.o
+ alternative.o unaligned.o unwind.o
obj-$(CONFIG_ACPI) += acpi.o
obj-$(CONFIG_EFI) += efi.o
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 7ea62faeeadb5..c38a146a973b4 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -72,9 +72,6 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs,
if (!task)
task = current;
- if (user_mode(regs))
- state.type = UNWINDER_GUESS;
-
printk("%sCall Trace:", loglvl);
for (unwind_start(&state, task, pregs);
!unwind_done(&state); unwind_next_frame(&state)) {
diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c
new file mode 100644
index 0000000000000..a463d6961344c
--- /dev/null
+++ b/arch/loongarch/kernel/unwind.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2023 Loongson Technology Corporation Limited
+ */
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+
+#include <asm/unwind.h>
+
+bool default_next_frame(struct unwind_state *state)
+{
+ struct stack_info *info = &state->stack_info;
+ unsigned long addr;
+
+ if (unwind_done(state))
+ return false;
+
+ do {
+ for (state->sp += sizeof(unsigned long);
+ state->sp < info->end; state->sp += sizeof(unsigned long)) {
+ addr = *(unsigned long *)(state->sp);
+ state->pc = unwind_graph_addr(state, addr, state->sp + 8);
+ if (__kernel_text_address(state->pc))
+ return true;
+ }
+
+ state->sp = info->next_sp;
+
+ } while (!get_stack_info(state->sp, state->task, info));
+
+ return false;
+}
diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c
index e7e637bdba17e..98379b7d41475 100644
--- a/arch/loongarch/kernel/unwind_guess.c
+++ b/arch/loongarch/kernel/unwind_guess.c
@@ -2,41 +2,18 @@
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
-#include <linux/kernel.h>
-#include <linux/ftrace.h>
-
#include <asm/unwind.h>
unsigned long unwind_get_return_address(struct unwind_state *state)
{
- if (unwind_done(state))
- return 0;
-
- return state->pc;
+ return __unwind_get_return_address(state);
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
void unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs)
{
- memset(state, 0, sizeof(*state));
-
- if (regs) {
- state->sp = regs->regs[3];
- state->pc = regs->csr_era;
- } else if (task && task != current) {
- state->sp = thread_saved_fp(task);
- state->pc = thread_saved_ra(task);
- } else {
- state->sp = (unsigned long)__builtin_frame_address(0);
- state->pc = (unsigned long)__builtin_return_address(0);
- }
-
- state->task = task;
- state->first = true;
- state->pc = unwind_graph_addr(state, state->pc, state->sp);
- get_stack_info(state->sp, state->task, &state->stack_info);
-
+ __unwind_start(state, task, regs);
if (!unwind_done(state) && !__kernel_text_address(state->pc))
unwind_next_frame(state);
}
@@ -44,29 +21,6 @@ EXPORT_SYMBOL_GPL(unwind_start);
bool unwind_next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- if (unwind_done(state))
- return false;
-
- if (state->first)
- state->first = false;
-
- do {
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = unwind_graph_addr(state, addr, state->sp + 8);
- if (__kernel_text_address(state->pc))
- return true;
- }
-
- state->sp = info->next_sp;
-
- } while (!get_stack_info(state->sp, state->task, info));
-
- return false;
+ return default_next_frame(state);
}
EXPORT_SYMBOL_GPL(unwind_next_frame);
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 463ba2391bdf4..dfc352dba7465 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -19,32 +19,14 @@ static inline void unwind_state_fixup(struct unwind_state *state)
#endif
}
-unsigned long unwind_get_return_address(struct unwind_state *state)
-{
- if (unwind_done(state))
- return 0;
-
- return state->pc;
-}
-EXPORT_SYMBOL_GPL(unwind_get_return_address);
-
-static bool unwind_by_guess(struct unwind_state *state)
-{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = unwind_graph_addr(state, addr, state->sp + 8);
- if (__kernel_text_address(state->pc))
- return true;
- }
-
- return false;
-}
-
+/*
+ * LoongArch function prologue is like follows,
+ * [instructions not use stack var]
+ * addi.d sp, sp, -imm
+ * st.d xx, sp, offset <- save callee saved regs and
+ * st.d yy, sp, offset save ra if function is nest.
+ * [others instructions]
+ */
static bool unwind_by_prologue(struct unwind_state *state)
{
long frame_ra = -1;
@@ -91,6 +73,10 @@ static bool unwind_by_prologue(struct unwind_state *state)
ip++;
}
+ /*
+ * Can't find stack alloc action, PC may be in a leaf function. Only the
+ * first being true is reasonable, otherwise indicate analysis is broken.
+ */
if (!frame_size) {
if (state->first)
goto first;
@@ -108,6 +94,7 @@ static bool unwind_by_prologue(struct unwind_state *state)
ip++;
}
+ /* Can't find save $ra action, PC may be in a leaf function, too. */
if (frame_ra < 0) {
if (state->first) {
state->sp = state->sp + frame_size;
@@ -116,96 +103,48 @@ static bool unwind_by_prologue(struct unwind_state *state)
return false;
}
- if (state->first)
- state->first = false;
-
state->pc = *(unsigned long *)(state->sp + frame_ra);
state->sp = state->sp + frame_size;
goto out;
first:
- state->first = false;
- if (state->pc == state->ra)
- return false;
-
state->pc = state->ra;
out:
+ state->first = false;
unwind_state_fixup(state);
return !!__kernel_text_address(state->pc);
}
-void unwind_start(struct unwind_state *state, struct task_struct *task,
- struct pt_regs *regs)
-{
- memset(state, 0, sizeof(*state));
- state->type = UNWINDER_PROLOGUE;
-
- if (regs) {
- state->sp = regs->regs[3];
- state->pc = regs->csr_era;
- state->ra = regs->regs[1];
- if (!__kernel_text_address(state->pc))
- state->type = UNWINDER_GUESS;
- } else if (task && task != current) {
- state->sp = thread_saved_fp(task);
- state->pc = thread_saved_ra(task);
- state->ra = 0;
- } else {
- state->sp = (unsigned long)__builtin_frame_address(0);
- state->pc = (unsigned long)__builtin_return_address(0);
- state->ra = 0;
- }
-
- state->task = task;
- state->first = true;
- state->pc = unwind_graph_addr(state, state->pc, state->sp);
- get_stack_info(state->sp, state->task, &state->stack_info);
-
- if (!unwind_done(state) && !__kernel_text_address(state->pc))
- unwind_next_frame(state);
-}
-EXPORT_SYMBOL_GPL(unwind_start);
-
-bool unwind_next_frame(struct unwind_state *state)
+static bool next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- struct pt_regs *regs;
unsigned long pc;
+ struct pt_regs *regs;
+ struct stack_info *info = &state->stack_info;
if (unwind_done(state))
return false;
do {
- switch (state->type) {
- case UNWINDER_GUESS:
- state->first = false;
- if (unwind_by_guess(state))
- return true;
- break;
-
- case UNWINDER_PROLOGUE:
- if (unwind_by_prologue(state)) {
- state->pc = unwind_graph_addr(state, state->pc, state->sp);
- return true;
- }
+ if (unwind_by_prologue(state)) {
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+ return true;
+ }
- if (info->type == STACK_TYPE_IRQ &&
- info->end == state->sp) {
- regs = (struct pt_regs *)info->next_sp;
- pc = regs->csr_era;
+ if (info->type == STACK_TYPE_IRQ && info->end == state->sp) {
+ regs = (struct pt_regs *)info->next_sp;
+ pc = regs->csr_era;
- if (user_mode(regs) || !__kernel_text_address(pc))
- return false;
+ if (user_mode(regs) || !__kernel_text_address(pc))
+ return false;
- state->first = true;
- state->ra = regs->regs[1];
- state->sp = regs->regs[3];
- state->pc = pc;
- get_stack_info(state->sp, state->task, info);
+ state->first = true;
+ state->pc = pc;
+ state->ra = regs->regs[1];
+ state->sp = regs->regs[3];
+ get_stack_info(state->sp, state->task, info);
- return true;
- }
+ return true;
}
state->sp = info->next_sp;
@@ -214,4 +153,36 @@ bool unwind_next_frame(struct unwind_state *state)
return false;
}
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ return __unwind_get_return_address(state);
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs)
+{
+ __unwind_start(state, task, regs);
+ state->type = UNWINDER_PROLOGUE;
+ state->first = true;
+
+ /*
+ * The current PC is not kernel text address, we cannot find its
+ * relative symbol. Thus, prologue analysis will be broken. Luckily,
+ * we can use the default_next_frame().
+ */
+ if (!__kernel_text_address(state->pc)) {
+ state->type = UNWINDER_GUESS;
+ if (!unwind_done(state))
+ unwind_next_frame(state);
+ }
+}
+EXPORT_SYMBOL_GPL(unwind_start);
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ return state->type == UNWINDER_PROLOGUE ?
+ next_frame(state) : default_next_frame(state);
+}
EXPORT_SYMBOL_GPL(unwind_next_frame);
--
GitLab
From dc74a9e8a8c57966a563ab078ba91c8b2c0d0a72 Mon Sep 17 00:00:00 2001
From: Jinyang He <hejinyang@loongson.cn>
Date: Tue, 17 Jan 2023 11:42:16 +0800
Subject: [PATCH 0838/1167] LoongArch: Add generic ex-handler unwind in
prologue unwinder
When exception is triggered, code flow go handle_\exception in some
cases. One of stackframe in this case as follows,
high -> +-------+
| REGS | <- a pt_regs
| |
| | <- ex trigger
| REGS | <- ex pt_regs <-+
| | |
| | |
low -> +-------+ ->unwind-+
When unwinder unwinds to handler_\exception it cannot go on prologue
analysis. Because it is an asynchronous code flow, we should get the
next frame PC from regs->csr_era rather than regs->regs[1]. At init time
we copy the handlers to eentry and also copy them to NUMA-affine memory
named pcpu_handlers if NUMA is enabled. Thus, unwinder cannot unwind
normally. To solve this, we try to give some hints in handler_\exception
and fixup unwinders in unwind_next_frame().
Reported-by: Qing Zhang <zhangqing@loongson.cn>
Signed-off-by: Jinyang He <hejinyang@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
arch/loongarch/include/asm/unwind.h | 2 +-
arch/loongarch/kernel/genex.S | 3 +
arch/loongarch/kernel/unwind_prologue.c | 101 +++++++++++++++++++++---
arch/loongarch/mm/tlb.c | 2 +-
4 files changed, 93 insertions(+), 15 deletions(-)
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
index 36584b95ef8b6..b9dce87afd2e0 100644
--- a/arch/loongarch/include/asm/unwind.h
+++ b/arch/loongarch/include/asm/unwind.h
@@ -22,7 +22,7 @@ struct unwind_state {
char type; /* UNWINDER_XXX */
struct stack_info stack_info;
struct task_struct *task;
- bool first, error, is_ftrace;
+ bool first, error, reset;
int graph_idx;
unsigned long sp, pc, ra;
};
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 75e5be807a0d5..7e5c293ed89f7 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -67,14 +67,17 @@ SYM_FUNC_END(except_vec_cex)
.macro BUILD_HANDLER exception handler prep
.align 5
SYM_FUNC_START(handle_\exception)
+ 666:
BACKUP_T0T1
SAVE_ALL
build_prep_\prep
move a0, sp
la.abs t0, do_\handler
jirl ra, t0, 0
+ 668:
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_\exception)
+ SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
.endm
BUILD_HANDLER ade ade badv
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index dfc352dba7465..9095fde8e55d5 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -2,23 +2,103 @@
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
+#include <linux/cpumask.h>
#include <linux/ftrace.h>
#include <linux/kallsyms.h>
#include <asm/inst.h>
+#include <asm/loongson.h>
#include <asm/ptrace.h>
+#include <asm/setup.h>
#include <asm/unwind.h>
-static inline void unwind_state_fixup(struct unwind_state *state)
+extern const int unwind_hint_ade;
+extern const int unwind_hint_ale;
+extern const int unwind_hint_bp;
+extern const int unwind_hint_fpe;
+extern const int unwind_hint_fpu;
+extern const int unwind_hint_lsx;
+extern const int unwind_hint_lasx;
+extern const int unwind_hint_lbt;
+extern const int unwind_hint_ri;
+extern const int unwind_hint_watch;
+extern unsigned long eentry;
+#ifdef CONFIG_NUMA
+extern unsigned long pcpu_handlers[NR_CPUS];
+#endif
+
+static inline bool scan_handlers(unsigned long entry_offset)
{
-#ifdef CONFIG_DYNAMIC_FTRACE
- static unsigned long ftrace = (unsigned long)ftrace_call + 4;
+ int idx, offset;
+
+ if (entry_offset >= EXCCODE_INT_START * VECSIZE)
+ return false;
+
+ idx = entry_offset / VECSIZE;
+ offset = entry_offset % VECSIZE;
+ switch (idx) {
+ case EXCCODE_ADE:
+ return offset == unwind_hint_ade;
+ case EXCCODE_ALE:
+ return offset == unwind_hint_ale;
+ case EXCCODE_BP:
+ return offset == unwind_hint_bp;
+ case EXCCODE_FPE:
+ return offset == unwind_hint_fpe;
+ case EXCCODE_FPDIS:
+ return offset == unwind_hint_fpu;
+ case EXCCODE_LSXDIS:
+ return offset == unwind_hint_lsx;
+ case EXCCODE_LASXDIS:
+ return offset == unwind_hint_lasx;
+ case EXCCODE_BTDIS:
+ return offset == unwind_hint_lbt;
+ case EXCCODE_INE:
+ return offset == unwind_hint_ri;
+ case EXCCODE_WATCH:
+ return offset == unwind_hint_watch;
+ default:
+ return false;
+ }
+}
+
+static inline bool fix_exception(unsigned long pc)
+{
+#ifdef CONFIG_NUMA
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (!pcpu_handlers[cpu])
+ continue;
+ if (scan_handlers(pc - pcpu_handlers[cpu]))
+ return true;
+ }
+#endif
+ return scan_handlers(pc - eentry);
+}
- if (state->pc == ftrace)
- state->is_ftrace = true;
+/*
+ * As we meet ftrace_regs_entry, reset first flag like first doing
+ * tracing. Prologue analysis will stop soon because PC is at entry.
+ */
+static inline bool fix_ftrace(unsigned long pc)
+{
+#ifdef CONFIG_DYNAMIC_FTRACE
+ return pc == (unsigned long)ftrace_call + LOONGARCH_INSN_SIZE;
+#else
+ return false;
#endif
}
+static inline bool unwind_state_fixup(struct unwind_state *state)
+{
+ if (!fix_exception(state->pc) && !fix_ftrace(state->pc))
+ return false;
+
+ state->reset = true;
+ return true;
+}
+
/*
* LoongArch function prologue is like follows,
* [instructions not use stack var]
@@ -39,14 +119,10 @@ static bool unwind_by_prologue(struct unwind_state *state)
if (state->sp >= info->end || state->sp < info->begin)
return false;
- if (state->is_ftrace) {
- /*
- * As we meet ftrace_regs_entry, reset first flag like first doing
- * tracing. Prologue analysis will stop soon because PC is at entry.
- */
+ if (state->reset) {
regs = (struct pt_regs *)state->sp;
state->first = true;
- state->is_ftrace = false;
+ state->reset = false;
state->pc = regs->csr_era;
state->ra = regs->regs[1];
state->sp = regs->regs[3];
@@ -112,8 +188,7 @@ static bool unwind_by_prologue(struct unwind_state *state)
out:
state->first = false;
- unwind_state_fixup(state);
- return !!__kernel_text_address(state->pc);
+ return unwind_state_fixup(state) || __kernel_text_address(state->pc);
}
static bool next_frame(struct unwind_state *state)
diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index da3681f131c8d..8bad6b0cff59b 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -251,7 +251,7 @@ static void output_pgtable_bits_defines(void)
}
#ifdef CONFIG_NUMA
-static unsigned long pcpu_handlers[NR_CPUS];
+unsigned long pcpu_handlers[NR_CPUS];
#endif
extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
--
GitLab
From ecf7cf8efb59789e2b21d2f9ab926142579092b2 Mon Sep 17 00:00:00 2001
From: Szymon Heidrich <szymon.heidrich@gmail.com>
Date: Sat, 14 Jan 2023 19:23:26 +0100
Subject: [PATCH 0839/1167] net: usb: sr9700: Handle negative len
Packet len computed as difference of length word extracted from
skb data and four may result in a negative value. In such case
processing of the buffer should be interrupted rather than
setting sr_skb->len to an unexpectedly large value (due to cast
from signed to unsigned integer) and passing sr_skb to
usbnet_skb_return.
Fixes: e9da0b56fe27 ("sr9700: sanity check for packet length")
Signed-off-by: Szymon Heidrich <szymon.heidrich@gmail.com>
Link: https://lore.kernel.org/r/20230114182326.30479-1-szymon.heidrich@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/usb/sr9700.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 5a53e63d33a60..3164451e1010c 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -413,7 +413,7 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
/* ignore the CRC length */
len = (skb->data[1] | (skb->data[2] << 8)) - 4;
- if (len > ETH_FRAME_LEN || len > skb->len)
+ if (len > ETH_FRAME_LEN || len > skb->len || len < 0)
return 0;
/* the last packet of current skb */
--
GitLab
From 867dbe784c5010a466f00a7d1467c1c5ea569c75 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 15 Jan 2023 11:54:06 +0100
Subject: [PATCH 0840/1167] net: mdio: validate parameter addr in
mdiobus_get_phy()
The caller may pass any value as addr, what may result in an out-of-bounds
access to array mdio_map. One existing case is stmmac_init_phy() that
may pass -1 as addr. Therefore validate addr before using it.
Fixes: 7f854420fbfe ("phy: Add API for {un}registering an mdio device to a bus.")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/cdf664ea-3312-e915-73f8-021678d08887@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/phy/mdio_bus.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 1cd604cd1fa1b..16e021b477f06 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -108,7 +108,12 @@ EXPORT_SYMBOL(mdiobus_unregister_device);
struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr)
{
- struct mdio_device *mdiodev = bus->mdio_map[addr];
+ struct mdio_device *mdiodev;
+
+ if (addr < 0 || addr >= ARRAY_SIZE(bus->mdio_map))
+ return NULL;
+
+ mdiodev = bus->mdio_map[addr];
if (!mdiodev)
return NULL;
--
GitLab
From b12fece4c64857e5fab4290bf01b2e0317a88456 Mon Sep 17 00:00:00 2001
From: Pietro Borrello <borrello@diag.uniroma1.it>
Date: Mon, 16 Jan 2023 11:11:24 +0000
Subject: [PATCH 0841/1167] HID: check empty report_list in
hid_validate_values()
Add a check for empty report_list in hid_validate_values().
The missing check causes a type confusion when issuing a list_entry()
on an empty report_list.
The problem is caused by the assumption that the device must
have valid report_list. While this will be true for all normal HID
devices, a suitably malicious device can violate the assumption.
Fixes: 1b15d2e5b807 ("HID: core: fix validation of report id 0")
Signed-off-by: Pietro Borrello <borrello@diag.uniroma1.it>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index bd47628da6be0..3e1803592bd4a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -993,8 +993,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid,
* Validating on id 0 means we should examine the first
* report in the list.
*/
- report = list_entry(
- hid->report_enum[type].report_list.next,
+ report = list_first_entry_or_null(
+ &hid->report_enum[type].report_list,
struct hid_report, list);
} else {
report = hid->report_enum[type].report_id_hash[id];
--
GitLab
From c7bf714f875531f227f2ef1fdcc8f4d44e7c7d9d Mon Sep 17 00:00:00 2001
From: Pietro Borrello <borrello@diag.uniroma1.it>
Date: Mon, 16 Jan 2023 11:11:25 +0000
Subject: [PATCH 0842/1167] HID: check empty report_list in bigben_probe()
Add a check for empty report_list in bigben_probe().
The missing check causes a type confusion when issuing a list_entry()
on an empty report_list.
The problem is caused by the assumption that the device must
have valid report_list. While this will be true for all normal HID
devices, a suitably malicious device can violate the assumption.
Fixes: 256a90ed9e46 ("HID: hid-bigbenff: driver for BigBen Interactive PS3OFMINIPAD gamepad")
Signed-off-by: Pietro Borrello <borrello@diag.uniroma1.it>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-bigbenff.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c
index e8c5e3ac9fff1..e8b16665860d6 100644
--- a/drivers/hid/hid-bigbenff.c
+++ b/drivers/hid/hid-bigbenff.c
@@ -344,6 +344,11 @@ static int bigben_probe(struct hid_device *hid,
}
report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
+ if (list_empty(report_list)) {
+ hid_err(hid, "no output report found\n");
+ error = -ENODEV;
+ goto error_hw_stop;
+ }
bigben->report = list_entry(report_list->next,
struct hid_report, list);
--
GitLab
From 81aae5cbd36da836eb65025c798d15e5e28a019b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 12 Jan 2023 20:53:39 +0100
Subject: [PATCH 0843/1167] MAINTAINERS: Update the ACPICA development list
address
The previous ACPICA development list address, devel@acpica.org, started
to bounce some time ago and it is not likely to be restored, so replace
it with a new one, acpica-devel@lists.linuxfoundation.org.
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 42fc47c6edfd7..439b51c5d25f1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -383,7 +383,7 @@ ACPI COMPONENT ARCHITECTURE (ACPICA)
M: Robert Moore <robert.moore@intel.com>
M: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
L: linux-acpi@vger.kernel.org
-L: devel@acpica.org
+L: acpica-devel@lists.linuxfoundation.org
S: Supported
W: https://acpica.org/
W: https://github.com/acpica/acpica/
--
GitLab
From 8ba5fc4c154aeb3b4620f05543cce426c62ed2de Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 13 Jan 2023 12:41:26 +0100
Subject: [PATCH 0844/1167] ACPI: video: Add backlight=native DMI quirk for
Acer Aspire 4810T
The Acer Aspire 4810T predates Windows 8, so it defaults to using
acpi_video# for backlight control, but this is non functional on
this model.
Add a DMI quirk to use the native backlight interface which does
work properly.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/video_detect.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 8a541efc56756..65cec7bb6d961 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -515,6 +515,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Precision 7510"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* Acer Aspire 4810T */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 4810T"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Acer Aspire 5738z */
--
GitLab
From 1f3bd64ad921f051254591fbed04fd30b306cde6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 15 Jan 2023 18:24:08 +0100
Subject: [PATCH 0845/1167] net: stmmac: fix invalid call to mdiobus_get_phy()
In a number of cases the driver assigns a default value of -1 to
priv->plat->phy_addr. This may result in calling mdiobus_get_phy()
with addr parameter being -1. Therefore check for this scenario and
bail out before calling mdiobus_get_phy().
Fixes: 42e87024f727 ("net: stmmac: Fix case when PHY handle is not present")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/669f9671-ecd1-a41b-2727-7b73e3003985@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c6951c976f5dd..b7e5af58ab750 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1150,6 +1150,11 @@ static int stmmac_init_phy(struct net_device *dev)
int addr = priv->plat->phy_addr;
struct phy_device *phydev;
+ if (addr < 0) {
+ netdev_err(priv->dev, "no phy found\n");
+ return -ENODEV;
+ }
+
phydev = mdiobus_get_phy(priv->mii, addr);
if (!phydev) {
netdev_err(priv->dev, "no phy at addr %d\n", addr);
--
GitLab
From 431d1531466033909d2e8c754a7dc3704b70843f Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Tue, 10 Jan 2023 08:46:53 +0000
Subject: [PATCH 0846/1167] pinctrl: rockchip: fix mux route data for rk3568
IO mux selection is configured in PMU_GRF_SOC_CON4 and GRF_IOFUNC_SEL0-5
regs on RK3568. pwm0-2 is configured in PMU_GRF reg and the rest is
configured in GRF_IOFUNC regs according to TRM [1].
Update mux route data to reflect this and use proper detection pin for
UART1 IO mux M1.
This fixes HDMITX IO mux M1 selection and makes it possible to enable
HDMI CEC on my Radxa ROCK 3 Model A v1.31 board.
[1] http://opensource.rock-chips.com/images/2/26/Rockchip_RK3568_TRM_Part1_V1.3-20220930P.PDF
Fixes: c0dadc0e47a8 ("pinctrl: rockchip: add support for rk3568")
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Link: https://lore.kernel.org/r/20230110084636.1141740-1-jonas@kwiboo.se
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/pinctrl/pinctrl-rockchip.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index c3b9313e5be17..5eeac92f610a0 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -926,19 +926,19 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = {
RK_MUXROUTE_PMU(0, RK_PB5, 4, 0x0110, WRITE_MASK_VAL(3, 2, 1)), /* PWM1 IO mux M1 */
RK_MUXROUTE_PMU(0, RK_PC1, 1, 0x0110, WRITE_MASK_VAL(5, 4, 0)), /* PWM2 IO mux M0 */
RK_MUXROUTE_PMU(0, RK_PB6, 4, 0x0110, WRITE_MASK_VAL(5, 4, 1)), /* PWM2 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PA1, 4, 0x0300, WRITE_MASK_VAL(0, 0, 1)), /* CAN0 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA1, 3, 0x0300, WRITE_MASK_VAL(2, 2, 0)), /* CAN1 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PC3, 3, 0x0300, WRITE_MASK_VAL(2, 2, 1)), /* CAN1 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PB5, 3, 0x0300, WRITE_MASK_VAL(4, 4, 0)), /* CAN2 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PB2, 4, 0x0300, WRITE_MASK_VAL(4, 4, 1)), /* CAN2 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PC4, 1, 0x0300, WRITE_MASK_VAL(6, 6, 0)), /* HPDIN IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PB1, 3, 0x0300, WRITE_MASK_VAL(8, 8, 0)), /* GMAC1 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PA7, 3, 0x0300, WRITE_MASK_VAL(8, 8, 1)), /* GMAC1 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PD1, 1, 0x0300, WRITE_MASK_VAL(10, 10, 0)), /* HDMITX IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PB4, 1, 0x0300, WRITE_MASK_VAL(14, 14, 1)), /* I2C2 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA0, 1, 0x0304, WRITE_MASK_VAL(0, 0, 0)), /* I2C3 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PB6, 4, 0x0304, WRITE_MASK_VAL(0, 0, 1)), /* I2C3 IO mux M1 */
@@ -964,7 +964,7 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = {
RK_MUXROUTE_GRF(4, RK_PC3, 1, 0x0308, WRITE_MASK_VAL(12, 12, 1)), /* PWM15 IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PD2, 3, 0x0308, WRITE_MASK_VAL(14, 14, 0)), /* SDMMC2 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PA5, 5, 0x0308, WRITE_MASK_VAL(14, 14, 1)), /* SDMMC2 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD3, 3, 0x030c, WRITE_MASK_VAL(0, 0, 1)), /* SPI0 IO mux M1 */
RK_MUXROUTE_GRF(2, RK_PB5, 3, 0x030c, WRITE_MASK_VAL(2, 2, 0)), /* SPI1 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PC3, 3, 0x030c, WRITE_MASK_VAL(2, 2, 1)), /* SPI1 IO mux M1 */
@@ -973,8 +973,8 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = {
RK_MUXROUTE_GRF(4, RK_PB3, 4, 0x030c, WRITE_MASK_VAL(6, 6, 0)), /* SPI3 IO mux M0 */
RK_MUXROUTE_GRF(4, RK_PC2, 2, 0x030c, WRITE_MASK_VAL(6, 6, 1)), /* SPI3 IO mux M1 */
RK_MUXROUTE_GRF(2, RK_PB4, 2, 0x030c, WRITE_MASK_VAL(8, 8, 0)), /* UART1 IO mux M0 */
- RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */
- RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */
+ RK_MUXROUTE_GRF(3, RK_PD6, 4, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */
+ RK_MUXROUTE_GRF(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */
RK_MUXROUTE_GRF(1, RK_PD5, 2, 0x030c, WRITE_MASK_VAL(10, 10, 1)), /* UART2 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA1, 2, 0x030c, WRITE_MASK_VAL(12, 12, 0)), /* UART3 IO mux M0 */
RK_MUXROUTE_GRF(3, RK_PB7, 4, 0x030c, WRITE_MASK_VAL(12, 12, 1)), /* UART3 IO mux M1 */
@@ -1004,13 +1004,13 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = {
RK_MUXROUTE_GRF(3, RK_PD6, 5, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PA0, 4, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */
RK_MUXROUTE_GRF(3, RK_PC4, 5, 0x0314, WRITE_MASK_VAL(1, 0, 2)), /* PDM IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 1)), /* PCIE20 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PB0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 2)), /* PCIE20 IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD2, 4, 0x0314, WRITE_MASK_VAL(5, 4, 1)), /* PCIE30X1 IO mux M1 */
RK_MUXROUTE_GRF(1, RK_PA5, 4, 0x0314, WRITE_MASK_VAL(5, 4, 2)), /* PCIE30X1 IO mux M2 */
- RK_MUXROUTE_PMU(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */
+ RK_MUXROUTE_GRF(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */
RK_MUXROUTE_GRF(2, RK_PD4, 4, 0x0314, WRITE_MASK_VAL(7, 6, 1)), /* PCIE30X2 IO mux M1 */
RK_MUXROUTE_GRF(4, RK_PC2, 4, 0x0314, WRITE_MASK_VAL(7, 6, 2)), /* PCIE30X2 IO mux M2 */
};
--
GitLab
From 7ffd2266bd32d9f31a4e918443c733906cff0d19 Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Mon, 12 Dec 2022 09:51:39 +0100
Subject: [PATCH 0847/1167] ARM: dts: stm32: Fix qspi pinctrl phandle for
stm32mp15xx-dhcor-som
Chip select pinctrl phandle was missing in several stm32mp15x based boards.
Fixes: ea99a5a02ebc ("ARM: dts: stm32: Create separate pinmux for qspi cs pin in stm32mp15-pinctrl.dtsi")
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: Marek Vasut <marex@denx.de>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Reviewed-by: Marek Vasut <marex@denx.de>
Signed-off-by: Alexandre Torgue <alexandre.torgue@foss.st.com>
---
arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
index 134a798ad3f23..bb40fb46da81d 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi
@@ -247,8 +247,12 @@ &pwr_regulators {
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x200000>;
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From 21d83512bf2bd25ebed467151fd2bcd0cca7dc9a Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Mon, 12 Dec 2022 09:51:40 +0100
Subject: [PATCH 0848/1167] ARM: dts: stm32: Fix qspi pinctrl phandle for
stm32mp15xx-dhcom-som
Chip select pinctrl phandle was missing in several stm32mp15x based boards.
Fixes: ea99a5a02ebc ("ARM: dts: stm32: Create separate pinmux for qspi cs pin in stm32mp15-pinctrl.dtsi")
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: Marek Vasut <marex@denx.de>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Reviewed-by: Marek Vasut <marex@denx.de>
Signed-off-by: Alexandre Torgue <alexandre.torgue@foss.st.com>
---
arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
index 002f221f1694c..c06edd2eacb0c 100644
--- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
+++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi
@@ -428,8 +428,12 @@ &pwr_regulators {
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From 732dbcf52f74b254a7ddd4226e0b9638e1e7aeff Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Mon, 12 Dec 2022 09:51:41 +0100
Subject: [PATCH 0849/1167] ARM: dts: stm32: Fix qspi pinctrl phandle for
stm32mp157c-emstamp-argon
Chip select pinctrl phandle was missing in several stm32mp15x based boards.
Fixes: ea99a5a02ebc ("ARM: dts: stm32: Create separate pinmux for qspi cs pin in stm32mp15-pinctrl.dtsi")
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: Reinhold Mueller <reinhold.mueller@emtrion.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Alexandre Torgue <alexandre.torgue@foss.st.com>
---
arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi
index aef02e6421a36..7d11c50b9e408 100644
--- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi
@@ -391,8 +391,12 @@ &pwr_regulators {
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From 175281f80695569c7f9cf062e5d0ddc4addc109f Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Mon, 12 Dec 2022 09:51:42 +0100
Subject: [PATCH 0850/1167] ARM: dts: stm32: Fix qspi pinctrl phandle for
stm32mp151a-prtt1l
Chip select pinctrl phandle was missing in several stm32mp15x based boards.
Fixes: ea99a5a02ebc ("ARM: dts: stm32: Create separate pinmux for qspi cs pin in stm32mp15-pinctrl.dtsi")
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Cc: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Alexandre Torgue <alexandre.torgue@foss.st.com>
---
arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi
index d865ab5d866b9..dd23de85100c4 100644
--- a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi
+++ b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi
@@ -101,8 +101,12 @@ &iwdg2 {
&qspi {
pinctrl-names = "default", "sleep";
- pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>;
- pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>;
+ pinctrl-0 = <&qspi_clk_pins_a
+ &qspi_bk1_pins_a
+ &qspi_cs1_pins_a>;
+ pinctrl-1 = <&qspi_clk_sleep_pins_a
+ &qspi_bk1_sleep_pins_a
+ &qspi_cs1_sleep_pins_a>;
reg = <0x58003000 0x1000>, <0x70000000 0x4000000>;
#address-cells = <1>;
#size-cells = <0>;
--
GitLab
From cbf44580ce6b310272a73e3e794233fd064330bd Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Tue, 17 Jan 2023 15:41:40 +0100
Subject: [PATCH 0851/1167] HID: revert CHERRY_MOUSE_000C quirk
This partially reverts commit f6d910a89a2391 ("HID: usbhid: Add ALWAYS_POLL quirk
for some mice"), as it turns out to break reboot on some platforms for reason
yet to be understood.
Fixes: f6d910a89a2391 ("HID: usbhid: Add ALWAYS_POLL quirk for some mice")
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-ids.h | 1 -
drivers/hid/hid-quirks.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 82713ef3aaa64..c3735848ed5db 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -274,7 +274,6 @@
#define USB_DEVICE_ID_CH_AXIS_295 0x001c
#define USB_VENDOR_ID_CHERRY 0x046a
-#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c
#define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023
#define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 0e9702c7f7d6c..be3ad02573de8 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -54,7 +54,6 @@ static const struct hid_device_id hid_quirks[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET },
- { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS },
--
GitLab
From 9d6033e350694a67885605674244d43c9559dc36 Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <guoqing.jiang@linux.dev>
Date: Fri, 30 Dec 2022 09:09:26 +0800
Subject: [PATCH 0852/1167] block/rnbd-clt: fix wrong max ID in ida_alloc_max
We need to pass 'end - 1' to ida_alloc_max after switch from
ida_simple_get to ida_alloc_max.
Otherwise smatch warns.
drivers/block/rnbd/rnbd-clt.c:1460 init_dev() error: Calling ida_alloc_max() with a 'max' argument which is a power of 2. -1 missing?
Fixes: 24afc15dbe21 ("block/rnbd: Remove a useless mutex")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Acked-by: Jack Wang <jinpu.wang@ionos.com>
Link: https://lore.kernel.org/r/20221230010926.32243-1-guoqing.jiang@linux.dev
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/block/rnbd/rnbd-clt.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 78334da74d8bf..5eb8c7855970d 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1440,7 +1440,7 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
goto out_alloc;
}
- ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS),
+ ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1,
GFP_KERNEL);
if (ret < 0) {
pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n",
--
GitLab
From 1301c7b9f7efad2f11ef924e317c18ebd714fc9a Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Tue, 15 Nov 2022 05:00:39 -0500
Subject: [PATCH 0853/1167] usb: cdns3: remove fetched trb from cache before
dequeuing
After doorbell DMA fetches the TRB. If during dequeuing request
driver changes NORMAL TRB to LINK TRB but doesn't delete it from
controller cache then controller will handle cached TRB and packet
can be lost.
The example scenario for this issue looks like:
1. queue request - set doorbell
2. dequeue request
3. send OUT data packet from host
4. Device will accept this packet which is unexpected
5. queue new request - set doorbell
6. Device lost the expected packet.
By setting DFLUSH controller clears DRDY bit and stop DMA transfer.
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
cc: <stable@vger.kernel.org>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20221115100039.441295-1-pawell@cadence.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/cdns3/cdns3-gadget.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c
index 5adcb349718c3..ccfaebca6faa7 100644
--- a/drivers/usb/cdns3/cdns3-gadget.c
+++ b/drivers/usb/cdns3/cdns3-gadget.c
@@ -2614,6 +2614,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
u8 req_on_hw_ring = 0;
unsigned long flags;
int ret = 0;
+ int val;
if (!ep || !request || !ep->desc)
return -EINVAL;
@@ -2649,6 +2650,13 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
/* Update ring only if removed request is on pending_req_list list */
if (req_on_hw_ring && link_trb) {
+ /* Stop DMA */
+ writel(EP_CMD_DFLUSH, &priv_dev->regs->ep_cmd);
+
+ /* wait for DFLUSH cleared */
+ readl_poll_timeout_atomic(&priv_dev->regs->ep_cmd, val,
+ !(val & EP_CMD_DFLUSH), 1, 1000);
+
link_trb->buffer = cpu_to_le32(TRB_BUFFER(priv_ep->trb_pool_dma +
((priv_req->end_trb + 1) * TRB_SIZE)));
link_trb->control = cpu_to_le32((le32_to_cpu(link_trb->control) & TRB_CYCLE) |
@@ -2660,6 +2668,10 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET);
+ req = cdns3_next_request(&priv_ep->pending_req_list);
+ if (req)
+ cdns3_rearm_transfer(priv_ep, 1);
+
not_found:
spin_unlock_irqrestore(&priv_dev->lock, flags);
return ret;
--
GitLab
From d18dcfe9860e842f394e37ba01ca9440ab2178f4 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Fri, 23 Dec 2022 09:59:09 -0500
Subject: [PATCH 0854/1167] USB: gadgetfs: Fix race between mounting and
unmounting
The syzbot fuzzer and Gerald Lee have identified a use-after-free bug
in the gadgetfs driver, involving processes concurrently mounting and
unmounting the gadgetfs filesystem. In particular, gadgetfs_fill_super()
can race with gadgetfs_kill_sb(), causing the latter to deallocate
the_device while the former is using it. The output from KASAN says,
in part:
BUG: KASAN: use-after-free in instrument_atomic_read_write include/linux/instrumented.h:102 [inline]
BUG: KASAN: use-after-free in atomic_fetch_sub_release include/linux/atomic/atomic-instrumented.h:176 [inline]
BUG: KASAN: use-after-free in __refcount_sub_and_test include/linux/refcount.h:272 [inline]
BUG: KASAN: use-after-free in __refcount_dec_and_test include/linux/refcount.h:315 [inline]
BUG: KASAN: use-after-free in refcount_dec_and_test include/linux/refcount.h:333 [inline]
BUG: KASAN: use-after-free in put_dev drivers/usb/gadget/legacy/inode.c:159 [inline]
BUG: KASAN: use-after-free in gadgetfs_kill_sb+0x33/0x100 drivers/usb/gadget/legacy/inode.c:2086
Write of size 4 at addr ffff8880276d7840 by task syz-executor126/18689
CPU: 0 PID: 18689 Comm: syz-executor126 Not tainted 6.1.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
Call Trace:
<TASK>
...
atomic_fetch_sub_release include/linux/atomic/atomic-instrumented.h:176 [inline]
__refcount_sub_and_test include/linux/refcount.h:272 [inline]
__refcount_dec_and_test include/linux/refcount.h:315 [inline]
refcount_dec_and_test include/linux/refcount.h:333 [inline]
put_dev drivers/usb/gadget/legacy/inode.c:159 [inline]
gadgetfs_kill_sb+0x33/0x100 drivers/usb/gadget/legacy/inode.c:2086
deactivate_locked_super+0xa7/0xf0 fs/super.c:332
vfs_get_super fs/super.c:1190 [inline]
get_tree_single+0xd0/0x160 fs/super.c:1207
vfs_get_tree+0x88/0x270 fs/super.c:1531
vfs_fsconfig_locked fs/fsopen.c:232 [inline]
The simplest solution is to ensure that gadgetfs_fill_super() and
gadgetfs_kill_sb() are serialized by making them both acquire a new
mutex.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Reported-and-tested-by: syzbot+33d7ad66d65044b93f16@syzkaller.appspotmail.com
Reported-and-tested-by: Gerald Lee <sundaywind2004@gmail.com>
Link: https://lore.kernel.org/linux-usb/CAO3qeMVzXDP-JU6v1u5Ags6Q-bb35kg3=C6d04DjzA9ffa5x1g@mail.gmail.com/
Fixes: e5d82a7360d1 ("vfs: Convert gadgetfs to use the new mount API")
CC: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/Y6XCPXBpn3tmjdCC@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/legacy/inode.c | 28 +++++++++++++++++++++-------
1 file changed, 21 insertions(+), 7 deletions(-)
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 01c3ead7d1b42..d605bc2e7e8fd 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -229,6 +229,7 @@ static void put_ep (struct ep_data *data)
*/
static const char *CHIP;
+static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */
/*----------------------------------------------------------------------*/
@@ -2010,13 +2011,20 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
struct dev_data *dev;
+ int rc;
- if (the_device)
- return -ESRCH;
+ mutex_lock(&sb_mutex);
+
+ if (the_device) {
+ rc = -ESRCH;
+ goto Done;
+ }
CHIP = usb_get_gadget_udc_name();
- if (!CHIP)
- return -ENODEV;
+ if (!CHIP) {
+ rc = -ENODEV;
+ goto Done;
+ }
/* superblock */
sb->s_blocksize = PAGE_SIZE;
@@ -2053,13 +2061,17 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc)
* from binding to a controller.
*/
the_device = dev;
- return 0;
+ rc = 0;
+ goto Done;
-Enomem:
+ Enomem:
kfree(CHIP);
CHIP = NULL;
+ rc = -ENOMEM;
- return -ENOMEM;
+ Done:
+ mutex_unlock(&sb_mutex);
+ return rc;
}
/* "mount -t gadgetfs path /dev/gadget" ends up here */
@@ -2081,6 +2093,7 @@ static int gadgetfs_init_fs_context(struct fs_context *fc)
static void
gadgetfs_kill_sb (struct super_block *sb)
{
+ mutex_lock(&sb_mutex);
kill_litter_super (sb);
if (the_device) {
put_dev (the_device);
@@ -2088,6 +2101,7 @@ gadgetfs_kill_sb (struct super_block *sb)
}
kfree(CHIP);
CHIP = NULL;
+ mutex_unlock(&sb_mutex);
}
/*----------------------------------------------------------------------*/
--
GitLab
From dbd24ec17b85b45f4e823d1aa5607721920f2b05 Mon Sep 17 00:00:00 2001
From: Juhyung Park <qkrwngud825@gmail.com>
Date: Tue, 17 Jan 2023 17:51:54 +0900
Subject: [PATCH 0855/1167] usb-storage: apply IGNORE_UAS only for HIKSEMI
MD202 on RTL9210
The commit e00b488e813f ("usb-storage: Add Hiksemi USB3-FW to IGNORE_UAS")
blacklists UAS for all of RTL9210 enclosures.
The RTL9210 controller was advertised with UAS since its release back in
2019 and was shipped with a lot of enclosure products with different
firmware combinations.
Blacklist UAS only for HIKSEMI MD202.
This should hopefully be replaced with more robust method than just
comparing strings. But with limited information [1] provided thus far
(dmesg when the device is plugged in, which includes manufacturer and
product, but no lsusb -v to compare against), this is the best we can do
for now.
[1] https://lore.kernel.org/all/20230109115550.71688-1-qkrwngud825@gmail.com
Fixes: e00b488e813f ("usb-storage: Add Hiksemi USB3-FW to IGNORE_UAS")
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Hongling Zeng <zenghongling@kylinos.cn>
Cc: stable@vger.kernel.org
Signed-off-by: Juhyung Park <qkrwngud825@gmail.com>
Acked-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/r/20230117085154.123301-1-qkrwngud825@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/storage/uas-detect.h | 13 +++++++++++++
drivers/usb/storage/unusual_uas.h | 7 -------
2 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index 3f720faa6f97c..d73282c0ec501 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -116,6 +116,19 @@ static int uas_use_uas_driver(struct usb_interface *intf,
if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bc2)
flags |= US_FL_NO_ATA_1X;
+ /*
+ * RTL9210-based enclosure from HIKSEMI, MD202 reportedly have issues
+ * with UAS. This isn't distinguishable with just idVendor and
+ * idProduct, use manufacturer and product too.
+ *
+ * Reported-by: Hongling Zeng <zenghongling@kylinos.cn>
+ */
+ if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bda &&
+ le16_to_cpu(udev->descriptor.idProduct) == 0x9210 &&
+ (udev->manufacturer && !strcmp(udev->manufacturer, "HIKSEMI")) &&
+ (udev->product && !strcmp(udev->product, "MD202")))
+ flags |= US_FL_IGNORE_UAS;
+
usb_stor_adjust_quirks(udev, &flags);
if (flags & US_FL_IGNORE_UAS) {
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index 251778d14e2dd..c7b763d6d1023 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -83,13 +83,6 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_LUNS),
-/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */
-UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999,
- "Hiksemi",
- "External HDD",
- USB_SC_DEVICE, USB_PR_DEVICE, NULL,
- US_FL_IGNORE_UAS),
-
/* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */
UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999,
"Initio Corporation",
--
GitLab
From 8565c502e7c156d190d8e6d36e443f51b257f165 Mon Sep 17 00:00:00 2001
From: Drew Davenport <ddavenport@chromium.org>
Date: Mon, 26 Dec 2022 22:53:24 -0700
Subject: [PATCH 0856/1167] drm/i915/display: Check source height is > 0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The error message suggests that the height of the src rect must be at
least 1. Reject source with height of 0.
Cc: stable@vger.kernel.org
Signed-off-by: Drew Davenport <ddavenport@chromium.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221226225246.1.I15dff7bb5a0e485c862eae61a69096caf12ef29f@changeid
(cherry picked from commit 0fe76b198d482b41771a8d17b45fb726d13083cf)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/display/skl_universal_plane.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 76490cc59d8f1..7d07fa3123ece 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1627,7 +1627,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
u32 offset;
int ret;
- if (w > max_width || w < min_width || h > max_height) {
+ if (w > max_width || w < min_width || h > max_height || h < 1) {
drm_dbg_kms(&dev_priv->drm,
"requested Y/RGB source size %dx%d outside limits (min: %dx1 max: %dx%d)\n",
w, h, min_width, max_width, max_height);
--
GitLab
From 93915a4170e9defd56a767a18e6c4076f3d18609 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Mon, 16 Jan 2023 16:22:10 +0200
Subject: [PATCH 0857/1167] xhci-pci: set the dma max_seg_size
Allow devices to have dma operations beyond 64K, and avoid warnings such
as:
xhci_hcd 0000:00:14.0: mapping sg segment longer than device claims to support [len=98304] [max=65536]
Cc: stable@vger.kernel.org
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci-pci.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 79d679b3e0760..2c0d7038f040a 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -455,6 +455,8 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW)
pm_runtime_allow(&dev->dev);
+ dma_set_max_seg_size(&dev->dev, UINT_MAX);
+
return 0;
put_usb3_hcd:
--
GitLab
From e8fb5bc76eb86437ab87002d4a36d6da02165654 Mon Sep 17 00:00:00 2001
From: Jimmy Hu <hhhuuu@google.com>
Date: Mon, 16 Jan 2023 16:22:11 +0200
Subject: [PATCH 0858/1167] usb: xhci: Check endpoint is valid before
dereferencing it
When the host controller is not responding, all URBs queued to all
endpoints need to be killed. This can cause a kernel panic if we
dereference an invalid endpoint.
Fix this by using xhci_get_virt_ep() helper to find the endpoint and
checking if the endpoint is valid before dereferencing it.
[233311.853271] xhci-hcd xhci-hcd.1.auto: xHCI host controller not responding, assume dead
[233311.853393] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000e8
[233311.853964] pc : xhci_hc_died+0x10c/0x270
[233311.853971] lr : xhci_hc_died+0x1ac/0x270
[233311.854077] Call trace:
[233311.854085] xhci_hc_died+0x10c/0x270
[233311.854093] xhci_stop_endpoint_command_watchdog+0x100/0x1a4
[233311.854105] call_timer_fn+0x50/0x2d4
[233311.854112] expire_timers+0xac/0x2e4
[233311.854118] run_timer_softirq+0x300/0xabc
[233311.854127] __do_softirq+0x148/0x528
[233311.854135] irq_exit+0x194/0x1a8
[233311.854143] __handle_domain_irq+0x164/0x1d0
[233311.854149] gic_handle_irq.22273+0x10c/0x188
[233311.854156] el1_irq+0xfc/0x1a8
[233311.854175] lpm_cpuidle_enter+0x25c/0x418 [msm_pm]
[233311.854185] cpuidle_enter_state+0x1f0/0x764
[233311.854194] do_idle+0x594/0x6ac
[233311.854201] cpu_startup_entry+0x7c/0x80
[233311.854209] secondary_start_kernel+0x170/0x198
Fixes: 50e8725e7c42 ("xhci: Refactor command watchdog and fix split string.")
Cc: stable@vger.kernel.org
Signed-off-by: Jimmy Hu <hhhuuu@google.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Message-ID: <0fe978ed-8269-9774-1c40-f8a98c17e838@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci-ring.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index ddc30037f9cef..f5b0e1ce22af2 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1169,7 +1169,10 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
struct xhci_virt_ep *ep;
struct xhci_ring *ring;
- ep = &xhci->devs[slot_id]->eps[ep_index];
+ ep = xhci_get_virt_ep(xhci, slot_id, ep_index);
+ if (!ep)
+ return;
+
if ((ep->ep_state & EP_HAS_STREAMS) ||
(ep->ep_state & EP_GETTING_NO_STREAMS)) {
int stream_id;
--
GitLab
From a2bc47c43e70cf904b1af49f76d572326c08bca7 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Mon, 16 Jan 2023 16:22:12 +0200
Subject: [PATCH 0859/1167] xhci: Fix null pointer dereference when host dies
Make sure xhci_free_dev() and xhci_kill_endpoint_urbs() do not race
and cause null pointer dereference when host suddenly dies.
Usb core may call xhci_free_dev() which frees the xhci->devs[slot_id]
virt device at the same time that xhci_kill_endpoint_urbs() tries to
loop through all the device's endpoints, checking if there are any
cancelled urbs left to give back.
hold the xhci spinlock while freeing the virt device
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 79d7931c048a8..50b41213e8275 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3974,6 +3974,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
struct xhci_virt_device *virt_dev;
struct xhci_slot_ctx *slot_ctx;
+ unsigned long flags;
int i, ret;
/*
@@ -4000,7 +4001,11 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
virt_dev->eps[i].ep_state &= ~EP_STOP_CMD_PENDING;
virt_dev->udev = NULL;
xhci_disable_slot(xhci, udev->slot_id);
+
+ spin_lock_irqsave(&xhci->lock, flags);
xhci_free_virt_device(xhci, udev->slot_id);
+ spin_unlock_irqrestore(&xhci->lock, flags);
+
}
int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
--
GitLab
From 23a3b8d5a2365653fd9bc5a9454d1e7f4facbf85 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Mon, 16 Jan 2023 16:22:13 +0200
Subject: [PATCH 0860/1167] xhci: Add update_hub_device override for PCI xHCI
hosts
Allow PCI hosts to check and tune roothub and port settings
before the hub is up and running.
This override is needed to turn off U1 and U2 LPM for some ports
based on per port ACPI _DSM, _UPC, or possibly vendor specific mmio
values for Intel xHC hosts.
Usb core calls the host update_hub_device once it creates a hub.
Entering U1 or U2 link power save state on ports with this limitation
will cause link to fail, turning the usb device unusable in that setup.
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci-pci.c | 9 +++++++++
drivers/usb/host/xhci.c | 5 ++++-
drivers/usb/host/xhci.h | 4 ++++
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 2c0d7038f040a..b5016709b26f1 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -78,9 +78,12 @@ static const char hcd_name[] = "xhci_hcd";
static struct hc_driver __read_mostly xhci_pci_hc_driver;
static int xhci_pci_setup(struct usb_hcd *hcd);
+static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
static const struct xhci_driver_overrides xhci_pci_overrides __initconst = {
.reset = xhci_pci_setup,
+ .update_hub_device = xhci_pci_update_hub_device,
};
/* called after powerup, by probe or system-pm "wakeup" */
@@ -386,6 +389,12 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
return xhci_pci_reinit(xhci, pdev);
}
+static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags)
+{
+ return xhci_update_hub_device(hcd, hdev, tt, mem_flags);
+}
+
/*
* We need to register our own PCI probe function (instead of the USB core's
* function) in order to create a second roothub under xHCI.
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 50b41213e8275..89f92fc78bb17 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -5124,7 +5124,7 @@ static int xhci_disable_usb3_lpm_timeout(struct usb_hcd *hcd,
/* Once a hub descriptor is fetched for a device, we need to update the xHC's
* internal data structures for the device.
*/
-static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
struct usb_tt *tt, gfp_t mem_flags)
{
struct xhci_hcd *xhci = hcd_to_xhci(hcd);
@@ -5224,6 +5224,7 @@ static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
xhci_free_command(xhci, config_cmd);
return ret;
}
+EXPORT_SYMBOL_GPL(xhci_update_hub_device);
static int xhci_get_frame(struct usb_hcd *hcd)
{
@@ -5507,6 +5508,8 @@ void xhci_init_driver(struct hc_driver *drv,
drv->check_bandwidth = over->check_bandwidth;
if (over->reset_bandwidth)
drv->reset_bandwidth = over->reset_bandwidth;
+ if (over->update_hub_device)
+ drv->update_hub_device = over->update_hub_device;
}
}
EXPORT_SYMBOL_GPL(xhci_init_driver);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index c9f06c5e4e9d2..3edfacb938174 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1943,6 +1943,8 @@ struct xhci_driver_overrides {
struct usb_host_endpoint *ep);
int (*check_bandwidth)(struct usb_hcd *, struct usb_device *);
void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *);
+ int (*update_hub_device)(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
};
#define XHCI_CFC_DELAY 10
@@ -2122,6 +2124,8 @@ int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev,
struct usb_host_endpoint *ep);
int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev);
void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev);
+int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
+ struct usb_tt *tt, gfp_t mem_flags);
int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id);
int xhci_ext_cap_init(struct xhci_hcd *xhci);
--
GitLab
From 0522b9a1653048440da5f21747f21e498b9220d1 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Mon, 16 Jan 2023 16:22:14 +0200
Subject: [PATCH 0861/1167] xhci: Add a flag to disable USB3 lpm on a xhci root
port level.
One USB3 roothub port may support link power management, while another
root port on the same xHC can't due to different retimers used for
the ports.
This is the case with Intel Alder Lake, and possible future platforms
where retimers used for USB4 ports cause too long exit latecy to
enable native USB3 lpm U1 and U2 states.
Add a flag in the xhci port structure to indicate if the port is
lpm_incapable, and check it while calculating exit latency.
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-6-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci.c | 8 ++++++++
drivers/usb/host/xhci.h | 1 +
2 files changed, 9 insertions(+)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 89f92fc78bb17..2b280beb00115 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -5049,6 +5049,7 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd,
struct usb_device *udev, enum usb3_link_state state)
{
struct xhci_hcd *xhci;
+ struct xhci_port *port;
u16 hub_encoded_timeout;
int mel;
int ret;
@@ -5065,6 +5066,13 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd,
if (xhci_check_tier_policy(xhci, udev, state) < 0)
return USB3_LPM_DISABLED;
+ /* If connected to root port then check port can handle lpm */
+ if (udev->parent && !udev->parent->parent) {
+ port = xhci->usb3_rhub.ports[udev->portnum - 1];
+ if (port->lpm_incapable)
+ return USB3_LPM_DISABLED;
+ }
+
hub_encoded_timeout = xhci_calculate_lpm_timeout(hcd, udev, state);
mel = calculate_max_exit_latency(udev, state, hub_encoded_timeout);
if (mel < 0) {
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 3edfacb938174..dcee7f3207add 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1735,6 +1735,7 @@ struct xhci_port {
int hcd_portnum;
struct xhci_hub *rhub;
struct xhci_port_cap *port_cap;
+ unsigned int lpm_incapable:1;
};
struct xhci_hub {
--
GitLab
From cd702d18c882d5a4ea44bbdb38edd5d5577ef640 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Mon, 16 Jan 2023 16:22:15 +0200
Subject: [PATCH 0862/1167] usb: acpi: add helper to check port lpm capability
using acpi _DSM
Add a helper to evaluate ACPI usb device specific method (_DSM) provided
in case the USB3 port shouldn't enter U1 and U2 link states.
This _DSM was added as port specific retimer configuration may lead to
exit latencies growing beyond U1/U2 exit limits, and OS needs a way to
find which ports can't support U1/U2 link power management states.
This _DSM is also used by windows:
Link: https://docs.microsoft.com/en-us/windows-hardware/drivers/bringup/usb-device-specific-method---dsm-
Some patch issues found in testing resolved by Ron Lee
Cc: stable@vger.kernel.org
Tested-by: Ron Lee <ron.lee@intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-7-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/core/usb-acpi.c | 65 +++++++++++++++++++++++++++++++++++++
include/linux/usb.h | 3 ++
2 files changed, 68 insertions(+)
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index 6d93428432f13..533baa85083c2 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -37,6 +37,71 @@ bool usb_acpi_power_manageable(struct usb_device *hdev, int index)
}
EXPORT_SYMBOL_GPL(usb_acpi_power_manageable);
+#define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899"
+#define USB_DSM_DISABLE_U1_U2_FOR_PORT 5
+
+/**
+ * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port.
+ * @hdev: USB device belonging to the usb hub
+ * @index: zero based port index
+ *
+ * Some USB3 ports may not support USB3 link power management U1/U2 states
+ * due to different retimer setup. ACPI provides _DSM method which returns 0x01
+ * if U1 and U2 states should be disabled. Evaluate _DSM with:
+ * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899
+ * Arg1: Revision ID = 0
+ * Arg2: Function Index = 5
+ * Arg3: (empty)
+ *
+ * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0
+ */
+
+int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index)
+{
+ union acpi_object *obj;
+ acpi_handle port_handle;
+ int port1 = index + 1;
+ guid_t guid;
+ int ret;
+
+ ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid);
+ if (ret)
+ return ret;
+
+ port_handle = usb_get_hub_port_acpi_handle(hdev, port1);
+ if (!port_handle) {
+ dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1);
+ return -ENODEV;
+ }
+
+ if (!acpi_check_dsm(port_handle, &guid, 0,
+ BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) {
+ dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n",
+ port1, USB_DSM_DISABLE_U1_U2_FOR_PORT);
+ return -ENODEV;
+ }
+
+ obj = acpi_evaluate_dsm(port_handle, &guid, 0,
+ USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL);
+
+ if (!obj)
+ return -ENODEV;
+
+ if (obj->type != ACPI_TYPE_INTEGER) {
+ dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1);
+ ACPI_FREE(obj);
+ return -EINVAL;
+ }
+
+ if (obj->integer.value == 0x01)
+ ret = 1;
+
+ ACPI_FREE(obj);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable);
+
/**
* usb_acpi_set_power_state - control usb port's power via acpi power
* resource
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 7d5325d47c451..04a7e94fb7721 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -774,11 +774,14 @@ extern struct device *usb_intf_get_dma_device(struct usb_interface *intf);
extern int usb_acpi_set_power_state(struct usb_device *hdev, int index,
bool enable);
extern bool usb_acpi_power_manageable(struct usb_device *hdev, int index);
+extern int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index);
#else
static inline int usb_acpi_set_power_state(struct usb_device *hdev, int index,
bool enable) { return 0; }
static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index)
{ return true; }
+static inline int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index)
+ { return 0; }
#endif
/* USB autosuspend and autoresume */
--
GitLab
From 74622f0a81d0c2bcfc39f9192b788124e8c7f0af Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Mon, 16 Jan 2023 16:22:16 +0200
Subject: [PATCH 0863/1167] xhci: Detect lpm incapable xHC USB3 roothub ports
from ACPI tables
USB3 ports on xHC hosts may have retimers that cause too long
exit latency to work with native USB3 U1/U2 link power management states.
For now only use usb_acpi_port_lpm_incapable() to evaluate if port lpm
should be disabled while setting up the USB3 roothub.
Other ways to identify lpm incapable ports can be added here later if
ACPI _DSM does not exist.
Limit this to Intel hosts for now, this is to my knowledge only
an Intel issue.
Cc: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20230116142216.1141605-8-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/xhci-pci.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index b5016709b26f1..fb988e4ea9244 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -355,8 +355,38 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
NULL);
ACPI_FREE(obj);
}
+
+static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev)
+{
+ struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+ struct xhci_hub *rhub = &xhci->usb3_rhub;
+ int ret;
+ int i;
+
+ /* This is not the usb3 roothub we are looking for */
+ if (hcd != rhub->hcd)
+ return;
+
+ if (hdev->maxchild > rhub->num_ports) {
+ dev_err(&hdev->dev, "USB3 roothub port number mismatch\n");
+ return;
+ }
+
+ for (i = 0; i < hdev->maxchild; i++) {
+ ret = usb_acpi_port_lpm_incapable(hdev, i);
+
+ dev_dbg(&hdev->dev, "port-%d disable U1/U2 _DSM: %d\n", i + 1, ret);
+
+ if (ret >= 0) {
+ rhub->ports[i]->lpm_incapable = ret;
+ continue;
+ }
+ }
+}
+
#else
static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { }
+static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) { }
#endif /* CONFIG_ACPI */
/* called during probe() after chip reset completes */
@@ -392,6 +422,10 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
struct usb_tt *tt, gfp_t mem_flags)
{
+ /* Check if acpi claims some USB3 roothub ports are lpm incapable */
+ if (!hdev->parent)
+ xhci_find_lpm_incapable_ports(hcd, hdev);
+
return xhci_update_hub_device(hcd, hdev, tt, mem_flags);
}
--
GitLab
From f96c0384047257365371a8ac217107c0371586f1 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Thu, 15 Dec 2022 13:54:09 +0800
Subject: [PATCH 0864/1167] usb: chipidea: core: fix possible constant 0 if use
IS_ERR(ci->role_switch)
After successfully probed, ci->role_switch would only be NULL or a valid
pointer. IS_ERR(ci->role_switch) will always return 0. So no need to wrap
it with IS_ERR, otherwise the logic is wrong.
Fixes: e1b5d2bed67c ("usb: chipidea: core: handle usb role switch in a common way")
cc: <stable@vger.kernel.org>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20221215055409.3760523-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/chipidea/core.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 484b1cd234317..27c601296130e 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -1294,12 +1294,12 @@ static void ci_extcon_wakeup_int(struct ci_hdrc *ci)
cable_id = &ci->platdata->id_extcon;
cable_vbus = &ci->platdata->vbus_extcon;
- if ((!IS_ERR(cable_id->edev) || !IS_ERR(ci->role_switch))
+ if ((!IS_ERR(cable_id->edev) || ci->role_switch)
&& ci->is_otg &&
(otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS))
ci_irq(ci);
- if ((!IS_ERR(cable_vbus->edev) || !IS_ERR(ci->role_switch))
+ if ((!IS_ERR(cable_vbus->edev) || ci->role_switch)
&& ci->is_otg &&
(otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS))
ci_irq(ci);
--
GitLab
From bd449ad8cee9d4b523abbdfa73e1a2a08333f331 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Fri, 30 Dec 2022 16:17:30 +0800
Subject: [PATCH 0865/1167] usb: musb: fix error return code in
omap2430_probe()
Before calling platform_get_resource() in omap2430_probe(), the 'ret' is
re-assgined to 0, it can't return an error code, if platform_get_resource
fails. Set the error code to -EINVAL to fix this.
Fixes: ffbe2feac59b ("usb: musb: omap2430: Fix probe regression for missing resources")
Cc: stable <stable@kernel.org>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Link: https://lore.kernel.org/r/20221230081730.1655616-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/musb/omap2430.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 476f55d1fec30..44a21ec865fb2 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -411,8 +411,10 @@ static int omap2430_probe(struct platform_device *pdev)
memset(musb_res, 0, sizeof(*musb_res) * ARRAY_SIZE(musb_res));
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
+ if (!res) {
+ ret = -EINVAL;
goto err2;
+ }
musb_res[i].start = res->start;
musb_res[i].end = res->end;
--
GitLab
From fac4b8633fd682ecc8e9cff61cb3e33374a1c7e5 Mon Sep 17 00:00:00 2001
From: Jack Pham <quic_jackp@quicinc.com>
Date: Mon, 9 Jan 2023 23:12:18 -0800
Subject: [PATCH 0866/1167] usb: ucsi: Ensure connector delayed work items are
flushed
During ucsi_unregister() when destroying a connector's workqueue, there
may still be pending delayed work items that haven't been scheduled yet.
Because queue_delayed_work() uses a separate timer to schedule a work
item, the destroy_workqueue() call is not aware of any pending items.
Hence when a pending item's timer expires it would then try to queue on
a dangling workqueue pointer.
Fix this by keeping track of all work items in a list, so that prior to
destroying the workqueue any pending items can be flushed. Do this by
calling mod_delayed_work() as that will cause pending items to get
queued immediately, which then allows the ensuing destroy_workqueue() to
implicitly drain all currently queued items to completion and free
themselves.
Fixes: b9aa02ca39a4 ("usb: typec: ucsi: Add polling mechanism for partner tasks like alt mode checking")
Suggested-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Co-developed-by: Linyu Yuan <quic_linyyuan@quicinc.com>
Signed-off-by: Linyu Yuan <quic_linyyuan@quicinc.com>
Signed-off-by: Jack Pham <quic_jackp@quicinc.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20230110071218.26261-1-quic_jackp@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/typec/ucsi/ucsi.c | 24 +++++++++++++++++++++---
drivers/usb/typec/ucsi/ucsi.h | 1 +
2 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index eabe519013e78..1292241d581a6 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -187,6 +187,7 @@ EXPORT_SYMBOL_GPL(ucsi_send_command);
struct ucsi_work {
struct delayed_work work;
+ struct list_head node;
unsigned long delay;
unsigned int count;
struct ucsi_connector *con;
@@ -202,6 +203,7 @@ static void ucsi_poll_worker(struct work_struct *work)
mutex_lock(&con->lock);
if (!con->partner) {
+ list_del(&uwork->node);
mutex_unlock(&con->lock);
kfree(uwork);
return;
@@ -209,10 +211,12 @@ static void ucsi_poll_worker(struct work_struct *work)
ret = uwork->cb(con);
- if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT))
+ if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT)) {
queue_delayed_work(con->wq, &uwork->work, uwork->delay);
- else
+ } else {
+ list_del(&uwork->node);
kfree(uwork);
+ }
mutex_unlock(&con->lock);
}
@@ -236,6 +240,7 @@ static int ucsi_partner_task(struct ucsi_connector *con,
uwork->con = con;
uwork->cb = cb;
+ list_add_tail(&uwork->node, &con->partner_tasks);
queue_delayed_work(con->wq, &uwork->work, delay);
return 0;
@@ -1056,6 +1061,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index)
INIT_WORK(&con->work, ucsi_handle_connector_change);
init_completion(&con->complete);
mutex_init(&con->lock);
+ INIT_LIST_HEAD(&con->partner_tasks);
con->num = index + 1;
con->ucsi = ucsi;
@@ -1420,8 +1426,20 @@ void ucsi_unregister(struct ucsi *ucsi)
ucsi_unregister_altmodes(&ucsi->connector[i],
UCSI_RECIPIENT_CON);
ucsi_unregister_port_psy(&ucsi->connector[i]);
- if (ucsi->connector[i].wq)
+
+ if (ucsi->connector[i].wq) {
+ struct ucsi_work *uwork;
+
+ mutex_lock(&ucsi->connector[i].lock);
+ /*
+ * queue delayed items immediately so they can execute
+ * and free themselves before the wq is destroyed
+ */
+ list_for_each_entry(uwork, &ucsi->connector[i].partner_tasks, node)
+ mod_delayed_work(ucsi->connector[i].wq, &uwork->work, 0);
+ mutex_unlock(&ucsi->connector[i].lock);
destroy_workqueue(ucsi->connector[i].wq);
+ }
typec_unregister_port(ucsi->connector[i].port);
}
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index c968474ee5473..60ce9fb6e7450 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -322,6 +322,7 @@ struct ucsi_connector {
struct work_struct work;
struct completion complete;
struct workqueue_struct *wq;
+ struct list_head partner_tasks;
struct typec_port *port;
struct typec_partner *partner;
--
GitLab
From e5854355d76b8d768cea8e4fc3ce6dfdba25518a Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Tue, 10 Jan 2023 17:32:52 +0000
Subject: [PATCH 0867/1167] usb: misc: onboard_hub: Invert driver registration
order
The onboard_hub 'driver' consists of two drivers, a platform
driver and a USB driver. Currently when the onboard hub driver
is initialized it first registers the platform driver, then the
USB driver. This results in a race condition when the 'attach'
work is executed, which is scheduled when the platform device
is probed. The purpose of fhe 'attach' work is to bind elegible
USB hub devices to the onboard_hub USB driver. This fails if
the work runs before the USB driver has been registered.
Register the USB driver first, then the platform driver. This
increases the chances that the onboard_hub USB devices are probed
before their corresponding platform device, which the USB driver
tries to locate in _probe(). The driver already handles this
situation and defers probing if the onboard hub platform device
doesn't exist yet.
Cc: stable@vger.kernel.org
Fixes: 8bc063641ceb ("usb: misc: Add onboard_usb_hub driver")
Link: https://lore.kernel.org/lkml/Y6W00vQm3jfLflUJ@hovoldconsulting.com/T/#m0d64295f017942fd988f7c53425db302d61952b4
Reported-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Link: https://lore.kernel.org/r/20230110172954.v2.1.I75494ebee7027a50235ce4b1e930fa73a578fbe2@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/misc/onboard_usb_hub.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index 94e7966e199d1..db0844b30bbd1 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -433,13 +433,13 @@ static int __init onboard_hub_init(void)
{
int ret;
- ret = platform_driver_register(&onboard_hub_driver);
+ ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
if (ret)
return ret;
- ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE);
+ ret = platform_driver_register(&onboard_hub_driver);
if (ret)
- platform_driver_unregister(&onboard_hub_driver);
+ usb_deregister_device_driver(&onboard_hub_usbdev_driver);
return ret;
}
--
GitLab
From cde37881e2e14590675d0acdfbad408300d9ca95 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Tue, 10 Jan 2023 17:32:53 +0000
Subject: [PATCH 0868/1167] usb: misc: onboard_hub: Move 'attach' work to the
driver
Currently each onboard_hub platform device owns an 'attach' work,
which is scheduled when the device probes. With this deadlocks
have been reported on a Raspberry Pi 3 B+ [1], which has nested
onboard hubs.
The flow of the deadlock is something like this (with the onboard_hub
driver built as a module) [2]:
- USB root hub is instantiated
- core hub driver calls onboard_hub_create_pdevs(), which creates the
'raw' platform device for the 1st level hub
- 1st level hub is probed by the core hub driver
- core hub driver calls onboard_hub_create_pdevs(), which creates
the 'raw' platform device for the 2nd level hub
- onboard_hub platform driver is registered
- platform device for 1st level hub is probed
- schedules 'attach' work
- platform device for 2nd level hub is probed
- schedules 'attach' work
- onboard_hub USB driver is registered
- device (and parent) lock of hub is held while the device is
re-probed with the onboard_hub driver
- 'attach' work (running in another thread) calls driver_attach(), which
blocks on one of the hub device locks
- onboard_hub_destroy_pdevs() is called by the core hub driver when one
of the hubs is detached
- destroying the pdevs invokes onboard_hub_remove(), which waits for the
'attach' work to complete
- waits forever, since the 'attach' work can't acquire the device lock
Use a single work struct for the driver instead of having a work struct
per onboard hub platform driver instance. With that it isn't necessary
to cancel the work in onboard_hub_remove(), which fixes the deadlock.
The work is only cancelled when the driver is unloaded.
[1] https://lore.kernel.org/r/d04bcc45-3471-4417-b30b-5cf9880d785d@i2se.com/
[2] https://lore.kernel.org/all/Y6OrGbqaMy2iVDWB@google.com/
Cc: stable@vger.kernel.org
Fixes: 8bc063641ceb ("usb: misc: Add onboard_usb_hub driver")
Link: https://lore.kernel.org/r/d04bcc45-3471-4417-b30b-5cf9880d785d@i2se.com/
Link: https://lore.kernel.org/all/Y6OrGbqaMy2iVDWB@google.com/
Reported-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Link: https://lore.kernel.org/r/20230110172954.v2.2.I16b51f32db0c32f8a8532900bfe1c70c8572881a@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/misc/onboard_usb_hub.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c
index db0844b30bbd1..969c4c4f2ae92 100644
--- a/drivers/usb/misc/onboard_usb_hub.c
+++ b/drivers/usb/misc/onboard_usb_hub.c
@@ -27,7 +27,10 @@
#include "onboard_usb_hub.h"
+static void onboard_hub_attach_usb_driver(struct work_struct *work);
+
static struct usb_device_driver onboard_hub_usbdev_driver;
+static DECLARE_WORK(attach_usb_driver_work, onboard_hub_attach_usb_driver);
/************************** Platform driver **************************/
@@ -45,7 +48,6 @@ struct onboard_hub {
bool is_powered_on;
bool going_away;
struct list_head udev_list;
- struct work_struct attach_usb_driver_work;
struct mutex lock;
};
@@ -271,8 +273,7 @@ static int onboard_hub_probe(struct platform_device *pdev)
* This needs to be done deferred to avoid self-deadlocks on systems
* with nested onboard hubs.
*/
- INIT_WORK(&hub->attach_usb_driver_work, onboard_hub_attach_usb_driver);
- schedule_work(&hub->attach_usb_driver_work);
+ schedule_work(&attach_usb_driver_work);
return 0;
}
@@ -285,9 +286,6 @@ static int onboard_hub_remove(struct platform_device *pdev)
hub->going_away = true;
- if (&hub->attach_usb_driver_work != current_work())
- cancel_work_sync(&hub->attach_usb_driver_work);
-
mutex_lock(&hub->lock);
/* unbind the USB devices to avoid dangling references to this device */
@@ -449,6 +447,8 @@ static void __exit onboard_hub_exit(void)
{
usb_deregister_device_driver(&onboard_hub_usbdev_driver);
platform_driver_unregister(&onboard_hub_driver);
+
+ cancel_work_sync(&attach_usb_driver_work);
}
module_exit(onboard_hub_exit);
--
GitLab
From 6a19da111057f69214b97c62fb0ac59023970850 Mon Sep 17 00:00:00 2001
From: Udipto Goswami <quic_ugoswami@quicinc.com>
Date: Thu, 15 Dec 2022 10:59:05 +0530
Subject: [PATCH 0869/1167] usb: gadget: f_fs: Prevent race during
ffs_ep0_queue_wait
While performing fast composition switch, there is a possibility that the
process of ffs_ep0_write/ffs_ep0_read get into a race condition
due to ep0req being freed up from functionfs_unbind.
Consider the scenario that the ffs_ep0_write calls the ffs_ep0_queue_wait
by taking a lock &ffs->ev.waitq.lock. However, the functionfs_unbind isn't
bounded so it can go ahead and mark the ep0req to NULL, and since there
is no NULL check in ffs_ep0_queue_wait we will end up in use-after-free.
Fix this by making a serialized execution between the two functions using
a mutex_lock(ffs->mutex).
Fixes: ddf8abd25994 ("USB: f_fs: the FunctionFS driver")
Signed-off-by: Udipto Goswami <quic_ugoswami@quicinc.com>
Tested-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Link: https://lore.kernel.org/r/20221215052906.8993-2-quic_ugoswami@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/function/f_fs.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 73dc10a77cdea..bb6fe1f3a29d7 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -279,6 +279,9 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len)
struct usb_request *req = ffs->ep0req;
int ret;
+ if (!req)
+ return -EINVAL;
+
req->zero = len < le16_to_cpu(ffs->ev.setup.wLength);
spin_unlock_irq(&ffs->ev.waitq.lock);
@@ -1892,10 +1895,12 @@ static void functionfs_unbind(struct ffs_data *ffs)
ENTER();
if (!WARN_ON(!ffs->gadget)) {
+ mutex_lock(&ffs->mutex);
usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req);
ffs->ep0req = NULL;
ffs->gadget = NULL;
clear_bit(FFS_FL_BOUND, &ffs->flags);
+ mutex_unlock(&ffs->mutex);
ffs_data_put(ffs);
}
}
--
GitLab
From ce405d561b020e5a46340eb5146805a625dcacee Mon Sep 17 00:00:00 2001
From: Udipto Goswami <quic_ugoswami@quicinc.com>
Date: Thu, 15 Dec 2022 10:59:06 +0530
Subject: [PATCH 0870/1167] usb: gadget: f_fs: Ensure ep0req is dequeued before
free_request
As per the documentation, function usb_ep_free_request guarantees
the request will not be queued or no longer be re-queued (or
otherwise used). However, with the current implementation it
doesn't make sure that the request in ep0 isn't reused.
Fix this by dequeuing the ep0req on functionfs_unbind before
freeing the request to align with the definition.
Fixes: ddf8abd25994 ("USB: f_fs: the FunctionFS driver")
Signed-off-by: Udipto Goswami <quic_ugoswami@quicinc.com>
Tested-by: Krishna Kurapati <quic_kriskura@quicinc.com>
Link: https://lore.kernel.org/r/20221215052906.8993-3-quic_ugoswami@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/function/f_fs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index bb6fe1f3a29d7..523a961b910bb 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1895,6 +1895,8 @@ static void functionfs_unbind(struct ffs_data *ffs)
ENTER();
if (!WARN_ON(!ffs->gadget)) {
+ /* dequeue before freeing ep0req */
+ usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req);
mutex_lock(&ffs->mutex);
usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req);
ffs->ep0req = NULL;
--
GitLab
From 582836e3cfab4faafbdc93bbec96fce036a08ee1 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Wed, 11 Jan 2023 02:05:41 +0000
Subject: [PATCH 0871/1167] usb: typec: altmodes/displayport: Add pin
assignment helper
The code to extract a peripheral's currently supported Pin Assignments
is repeated in a couple of locations. Factor it out into a separate
function.
This will also make it easier to add fixes (we only need to update 1
location instead of 2).
Fixes: c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles")
Cc: stable@vger.kernel.org
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Benson Leung <bleung@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20230111020546.3384569-1-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/typec/altmodes/displayport.c | 22 ++++++++++++++--------
1 file changed, 14 insertions(+), 8 deletions(-)
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index de66a2949e33b..5bc7a58f7f442 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -419,6 +419,18 @@ static const char * const pin_assignments[] = {
[DP_PIN_ASSIGN_F] = "F",
};
+/*
+ * Helper function to extract a peripheral's currently supported
+ * Pin Assignments from its DisplayPort alternate mode state.
+ */
+static u8 get_current_pin_assignments(struct dp_altmode *dp)
+{
+ if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
+ return DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
+ else
+ return DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+}
+
static ssize_t
pin_assignment_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t size)
@@ -445,10 +457,7 @@ pin_assignment_store(struct device *dev, struct device_attribute *attr,
goto out_unlock;
}
- if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
- assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
- else
- assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+ assignments = get_current_pin_assignments(dp);
if (!(DP_CONF_GET_PIN_ASSIGN(conf) & assignments)) {
ret = -EINVAL;
@@ -485,10 +494,7 @@ static ssize_t pin_assignment_show(struct device *dev,
cur = get_count_order(DP_CONF_GET_PIN_ASSIGN(dp->data.conf));
- if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
- assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
- else
- assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+ assignments = get_current_pin_assignments(dp);
for (i = 0; assignments; assignments >>= 1, i++) {
if (assignments & 1) {
--
GitLab
From 9682b41e52cc9f42f5c33caf410464392adaef04 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Wed, 11 Jan 2023 02:05:42 +0000
Subject: [PATCH 0872/1167] usb: typec: altmodes/displayport: Fix pin
assignment calculation
Commit c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin
assignment for UFP receptacles") fixed the pin assignment calculation
to take into account whether the peripheral was a plug or a receptacle.
But the "pin_assignments" sysfs logic was not updated. Address this by
using the macros introduced in the aforementioned commit in the sysfs
logic too.
Fixes: c1e5c2f0cb8a ("usb: typec: altmodes/displayport: correct pin assignment for UFP receptacles")
Cc: stable@vger.kernel.org
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Benson Leung <bleung@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20230111020546.3384569-2-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/typec/altmodes/displayport.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index 5bc7a58f7f442..80d8c6c3be369 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -426,9 +426,9 @@ static const char * const pin_assignments[] = {
static u8 get_current_pin_assignments(struct dp_altmode *dp)
{
if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
- return DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo);
+ return DP_CAP_PIN_ASSIGN_DFP_D(dp->alt->vdo);
else
- return DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo);
+ return DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo);
}
static ssize_t
--
GitLab
From 85af23df903ee14bfcba60c53e4f3b640f2310f8 Mon Sep 17 00:00:00 2001
From: Prashant Malani <pmalani@chromium.org>
Date: Wed, 11 Jan 2023 02:05:43 +0000
Subject: [PATCH 0873/1167] usb: typec: altmodes/displayport: Use proper macro
for pin assignment check
While looking at the DP configuration VDO to determine the peripheral
configuration, the spec (Table 8-5: DisplayPort Configurations, VESA
DisplayPort Alt Mode Standard v2.0) lists the options as "UFP_U as a DP
Source/Sink Device".
So, use the correct macro while performing this check. Effectively it's
the same as the existing code, but the proposed macro describes the
state a little better.
No functional changes introduced.
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Prashant Malani <pmalani@chromium.org>
Reviewed-by: Benson Leung <bleung@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20230111020546.3384569-3-pmalani@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/typec/altmodes/displayport.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index 80d8c6c3be369..9a6860285fbec 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -425,7 +425,7 @@ static const char * const pin_assignments[] = {
*/
static u8 get_current_pin_assignments(struct dp_altmode *dp)
{
- if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D)
+ if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_UFP_U_AS_DFP_D)
return DP_CAP_PIN_ASSIGN_DFP_D(dp->alt->vdo);
else
return DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo);
--
GitLab
From e95765e97d9cb93258a4840440d410fa6ff7e819 Mon Sep 17 00:00:00 2001
From: Daniel Scally <dan.scally@ideasonboard.com>
Date: Fri, 16 Dec 2022 16:05:28 +0000
Subject: [PATCH 0874/1167] usb: gadget: g_webcam: Send color matching
descriptor per frame
Currently the color matching descriptor is only sent across the wire
a single time, following the descriptors for each format and frame.
According to the UVC 1.5 Specification 3.9.2.6 ("Color Matching
Descriptors"):
"Only one instance is allowed for a given format and if present,
the Color Matching descriptor shall be placed following the Video
and Still Image Frame descriptors for that format".
Add another reference to the color matching descriptor after the
yuyv frames so that it's correctly transmitted for that format
too.
Fixes: a9914127e834 ("USB gadget: Webcam device")
Cc: stable <stable@kernel.org>
Signed-off-by: Daniel Scally <dan.scally@ideasonboard.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Kieran Bingham <kieran.bingham@ideasonboard.com>
Link: https://lore.kernel.org/r/20221216160528.479094-1-dan.scally@ideasonboard.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/legacy/webcam.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c
index 53e38f87472b0..c06dd1af7a0c5 100644
--- a/drivers/usb/gadget/legacy/webcam.c
+++ b/drivers/usb/gadget/legacy/webcam.c
@@ -293,6 +293,7 @@ static const struct uvc_descriptor_header * const uvc_fs_streaming_cls[] = {
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
@@ -305,6 +306,7 @@ static const struct uvc_descriptor_header * const uvc_hs_streaming_cls[] = {
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
@@ -317,6 +319,7 @@ static const struct uvc_descriptor_header * const uvc_ss_streaming_cls[] = {
(const struct uvc_descriptor_header *) &uvc_format_yuv,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_360p,
(const struct uvc_descriptor_header *) &uvc_frame_yuv_720p,
+ (const struct uvc_descriptor_header *) &uvc_color_matching,
(const struct uvc_descriptor_header *) &uvc_format_mjpg,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p,
(const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p,
--
GitLab
From 36f78477ac2c89e9a2eed4a31404a291a3450b5d Mon Sep 17 00:00:00 2001
From: ChiYuan Huang <cy_huang@richtek.com>
Date: Mon, 9 Jan 2023 15:19:50 +0800
Subject: [PATCH 0875/1167] usb: typec: tcpm: Fix altmode re-registration
causes sysfs create fail
There's the altmode re-registeration issue after data role
swap (DR_SWAP).
Comparing to USBPD 2.0, in USBPD 3.0, it loose the limit that only DFP
can initiate the VDM command to get partner identity information.
For a USBPD 3.0 UFP device, it may already get the identity information
from its port partner before DR_SWAP. If DR_SWAP send or receive at the
mean time, 'send_discover' flag will be raised again. It causes discover
identify action restart while entering ready state. And after all
discover actions are done, the 'tcpm_register_altmodes' will be called.
If old altmode is not unregistered, this sysfs create fail can be found.
In 'DR_SWAP_CHANGE_DR' state case, only DFP will unregister altmodes.
For UFP, the original altmodes keep registered.
This patch fix the logic that after DR_SWAP, 'tcpm_unregister_altmodes'
must be called whatever the current data role is.
Reviewed-by: Macpaul Lin <macpaul.lin@mediatek.com>
Fixes: ae8a2ca8a221 ("usb: typec: Group all TCPCI/TCPM code together")
Reported-by: TommyYl Chen <tommyyl.chen@mediatek.com>
Cc: stable@vger.kernel.org
Signed-off-by: ChiYuan Huang <cy_huang@richtek.com>
Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/1673248790-15794-1-git-send-email-cy_huang@richtek.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/typec/tcpm/tcpm.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 904c7b4ce2f0c..59b366b5c6144 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4594,14 +4594,13 @@ static void run_state_machine(struct tcpm_port *port)
tcpm_set_state(port, ready_state(port), 0);
break;
case DR_SWAP_CHANGE_DR:
- if (port->data_role == TYPEC_HOST) {
- tcpm_unregister_altmodes(port);
+ tcpm_unregister_altmodes(port);
+ if (port->data_role == TYPEC_HOST)
tcpm_set_roles(port, true, port->pwr_role,
TYPEC_DEVICE);
- } else {
+ else
tcpm_set_roles(port, true, port->pwr_role,
TYPEC_HOST);
- }
tcpm_ams_finish(port);
tcpm_set_state(port, ready_state(port), 0);
break;
--
GitLab
From 7c07553807c5125c89de242d35c10c206fd8e6bb Mon Sep 17 00:00:00 2001
From: Chanh Nguyen <chanh@os.amperecomputing.com>
Date: Wed, 11 Jan 2023 13:51:05 +0700
Subject: [PATCH 0876/1167] USB: gadget: Add ID numbers to configfs-gadget
driver names
It is unable to use configfs to attach more than one gadget. When
attaching the second gadget, it always fails and the kernel message
prints out:
Error: Driver 'configfs-gadget' is already registered, aborting...
UDC core: g1: driver registration failed: -16
This commit fixes the problem by using the gadget name as a suffix
to each configfs_gadget's driver name, thus making the names
distinct.
Fixes: fc274c1e9973 ("USB: gadget: Add a new bus for gadgets")
Cc: stable <stable@kernel.org>
Signed-off-by: Chanh Nguyen <chanh@os.amperecomputing.com>
Reviewed-by: Andrzej Pietrasiewicz <andrzej.p@collabora.com>
Tested-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Frank Li <frank.li@nxp.com>
Link: https://lore.kernel.org/r/20230111065105.29205-1-chanh@os.amperecomputing.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/configfs.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 96121d1c8df4c..0853536cbf2e6 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -393,6 +393,7 @@ static void gadget_info_attr_release(struct config_item *item)
WARN_ON(!list_empty(&gi->string_list));
WARN_ON(!list_empty(&gi->available_func));
kfree(gi->composite.gadget_driver.function);
+ kfree(gi->composite.gadget_driver.driver.name);
kfree(gi);
}
@@ -1572,7 +1573,6 @@ static const struct usb_gadget_driver configfs_driver_template = {
.max_speed = USB_SPEED_SUPER_PLUS,
.driver = {
.owner = THIS_MODULE,
- .name = "configfs-gadget",
},
.match_existing_only = 1,
};
@@ -1623,13 +1623,21 @@ static struct config_group *gadgets_make(
gi->composite.gadget_driver = configfs_driver_template;
+ gi->composite.gadget_driver.driver.name = kasprintf(GFP_KERNEL,
+ "configfs-gadget.%s", name);
+ if (!gi->composite.gadget_driver.driver.name)
+ goto err;
+
gi->composite.gadget_driver.function = kstrdup(name, GFP_KERNEL);
gi->composite.name = gi->composite.gadget_driver.function;
if (!gi->composite.gadget_driver.function)
- goto err;
+ goto out_free_driver_name;
return &gi->group;
+
+out_free_driver_name:
+ kfree(gi->composite.gadget_driver.driver.name);
err:
kfree(gi);
return ERR_PTR(-ENOMEM);
--
GitLab
From c6ec929595c7443250b2a4faea988c62019d5cd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= <maze@google.com>
Date: Tue, 17 Jan 2023 05:18:39 -0800
Subject: [PATCH 0877/1167] usb: gadget: f_ncm: fix potential NULL ptr deref in
ncm_bitrate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
In Google internal bug 265639009 we've received an (as yet) unreproducible
crash report from an aarch64 GKI 5.10.149-android13 running device.
AFAICT the source code is at:
https://android.googlesource.com/kernel/common/+/refs/tags/ASB-2022-12-05_13-5.10
The call stack is:
ncm_close() -> ncm_notify() -> ncm_do_notify()
with the crash at:
ncm_do_notify+0x98/0x270
Code: 79000d0b b9000a6c f940012a f9400269 (b9405d4b)
Which I believe disassembles to (I don't know ARM assembly, but it looks sane enough to me...):
// halfword (16-bit) store presumably to event->wLength (at offset 6 of struct usb_cdc_notification)
0B 0D 00 79 strh w11, [x8, #6]
// word (32-bit) store presumably to req->Length (at offset 8 of struct usb_request)
6C 0A 00 B9 str w12, [x19, #8]
// x10 (NULL) was read here from offset 0 of valid pointer x9
// IMHO we're reading 'cdev->gadget' and getting NULL
// gadget is indeed at offset 0 of struct usb_composite_dev
2A 01 40 F9 ldr x10, [x9]
// loading req->buf pointer, which is at offset 0 of struct usb_request
69 02 40 F9 ldr x9, [x19]
// x10 is null, crash, appears to be attempt to read cdev->gadget->max_speed
4B 5D 40 B9 ldr w11, [x10, #0x5c]
which seems to line up with ncm_do_notify() case NCM_NOTIFY_SPEED code fragment:
event->wLength = cpu_to_le16(8);
req->length = NCM_STATUS_BYTECOUNT;
/* SPEED_CHANGE data is up/down speeds in bits/sec */
data = req->buf + sizeof *event;
data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget));
My analysis of registers and NULL ptr deref crash offset
(Unable to handle kernel NULL pointer dereference at virtual address 000000000000005c)
heavily suggests that the crash is due to 'cdev->gadget' being NULL when executing:
data[0] = cpu_to_le32(ncm_bitrate(cdev->gadget));
which calls:
ncm_bitrate(NULL)
which then calls:
gadget_is_superspeed(NULL)
which reads
((struct usb_gadget *)NULL)->max_speed
and hits a panic.
AFAICT, if I'm counting right, the offset of max_speed is indeed 0x5C.
(remember there's a GKI KABI reservation of 16 bytes in struct work_struct)
It's not at all clear to me how this is all supposed to work...
but returning 0 seems much better than panic-ing...
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: Carlos Llamas <cmllamas@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20230117131839.1138208-1-maze@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/gadget/function/f_ncm.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index c36bcfa0e9b46..424bb3b666dbd 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -83,7 +83,9 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f)
/* peak (theoretical) bulk transfer rate in bits-per-second */
static inline unsigned ncm_bitrate(struct usb_gadget *g)
{
- if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS)
+ if (!g)
+ return 0;
+ else if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS)
return 4250000000U;
else if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER)
return 3750000000U;
--
GitLab
From 11cefeb2058f9f2322713b2683be9301556705e2 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 12 Dec 2022 16:20:35 +0100
Subject: [PATCH 0878/1167] USB: fix misleading usb_set_intfdata() kernel doc
The struct device driver-data pointer is used for any data that a driver
may need in various callbacks while bound to the device. For
convenience, subsystems typically provide wrappers such as
usb_set_intfdata() of the generic accessor functions for use in bus
callbacks.
There is generally no longer any need for a driver to clear the pointer,
but since commit 0998d0631001 ("device-core: Ensure drvdata = NULL when
no driver is bound") the driver-data pointer is set to NULL by driver
core post unbind anyway.
For historical reasons, USB core also clears this pointer when an
explicitly claimed interface is released.
Due to a misunderstanding, a misleading kernel doc comment for
usb_set_intfdata() was recently added which claimed that the driver data
pointer must not be cleared during disconnect before "all actions [are]
completed", which is both imprecise and incorrect.
Specifically, drivers like cdc-acm which claim additional interfaces use
the driver-data pointer as a flag which is cleared when the first
interface is unbound. As long as a driver does not do something odd like
dereference the pointer in, for example, completion callbacks, this can
be done at any time during disconnect. And in any case this is no
different than for any other resource, like the driver data itself,
which may be freed by the disconnect callback.
Note that the comment actually also claimed that the interface itself
was somehow being set to NULL by driver core.
Fix the kernel doc by removing incorrect, overly specific and misleading
details and adding a comment about why some drivers do clear the
driver-data pointer.
Fixes: 27ef17849779 ("usb: add usb_set_intfdata() documentation")
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/r/20221212152035.31806-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/linux/usb.h | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 04a7e94fb7721..86d1c8e79566e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -267,16 +267,15 @@ static inline void *usb_get_intfdata(struct usb_interface *intf)
}
/**
- * usb_set_intfdata() - associate driver-specific data with the interface
- * @intf: the usb interface
- * @data: pointer to the device priv structure or %NULL
+ * usb_set_intfdata() - associate driver-specific data with an interface
+ * @intf: USB interface
+ * @data: driver data
*
- * Drivers should use this function in their probe() to associate their
- * driver-specific data with the usb interface.
+ * Drivers can use this function in their probe() callbacks to associate
+ * driver-specific data with an interface.
*
- * When disconnecting, the core will take care of setting @intf back to %NULL,
- * so no actions are needed on the driver side. The interface should not be set
- * to %NULL before all actions completed (e.g. no outsanding URB remaining).
+ * Note that there is generally no need to clear the driver-data pointer even
+ * if some drivers do so for historical or implementation-specific reasons.
*/
static inline void usb_set_intfdata(struct usb_interface *intf, void *data)
{
--
GitLab
From 7171b0e261b17de96490adf053b8bb4b00061bcf Mon Sep 17 00:00:00 2001
From: Flavio Suligoi <f.suligoi@asem.it>
Date: Mon, 19 Dec 2022 13:47:59 +0100
Subject: [PATCH 0879/1167] usb: core: hub: disable autosuspend for TI TUSB8041
The Texas Instruments TUSB8041 has an autosuspend problem at high
temperature.
If there is not USB traffic, after a couple of ms, the device enters in
autosuspend mode. In this condition the external clock stops working, to
save energy. When the USB activity turns on, ther hub exits the
autosuspend state, the clock starts running again and all works fine.
At ambient temperature all works correctly, but at high temperature,
when the USB activity turns on, the external clock doesn't restart and
the hub disappears from the USB bus.
Disabling the autosuspend mode for this hub solves the issue.
Signed-off-by: Flavio Suligoi <f.suligoi@asem.it>
Cc: stable <stable@kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20221219124759.3207032-1-f.suligoi@asem.it
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/core/hub.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 77e73fc8d6736..9eca403af2a85 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -44,6 +44,9 @@
#define USB_PRODUCT_USB5534B 0x5534
#define USB_VENDOR_CYPRESS 0x04b4
#define USB_PRODUCT_CY7C65632 0x6570
+#define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451
+#define USB_PRODUCT_TUSB8041_USB3 0x8140
+#define USB_PRODUCT_TUSB8041_USB2 0x8142
#define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01
#define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02
@@ -5854,6 +5857,16 @@ static const struct usb_device_id hub_id_table[] = {
.idVendor = USB_VENDOR_GENESYS_LOGIC,
.bInterfaceClass = USB_CLASS_HUB,
.driver_info = HUB_QUIRK_CHECK_PORT_AUTOSUSPEND},
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+ | USB_DEVICE_ID_MATCH_PRODUCT,
+ .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
+ .idProduct = USB_PRODUCT_TUSB8041_USB2,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
+ { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
+ | USB_DEVICE_ID_MATCH_PRODUCT,
+ .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS,
+ .idProduct = USB_PRODUCT_TUSB8041_USB3,
+ .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
{ .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS,
.bDeviceClass = USB_CLASS_HUB},
{ .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS,
--
GitLab
From 7746564793978fe2f43b18a302b22dca0ad3a0e8 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 17 Jan 2023 11:42:15 +0000
Subject: [PATCH 0880/1167] block: fix hctx checks for batch allocation
When there are no read queues read requests will be assigned a
default queue on allocation. However, blk_mq_get_cached_request() is not
prepared for that and will fail all attempts to grab read requests from
the cache. Worst case it doubles the number of requests allocated,
roughly half of which will be returned by blk_mq_free_plug_rqs().
It only affects batched allocations and so is io_uring specific.
For reference, QD8 t/io_uring benchmark improves by 20-35%.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/80d4511011d7d4751b4cf6375c4e38f237d935e3.1673955390.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/blk-mq.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 2c49b4151da15..9d463f7563bc5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2890,6 +2890,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
struct blk_plug *plug, struct bio **bio, unsigned int nsegs)
{
struct request *rq;
+ enum hctx_type type, hctx_type;
if (!plug)
return NULL;
@@ -2902,7 +2903,10 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q,
return NULL;
}
- if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type)
+ type = blk_mq_get_hctx_type((*bio)->bi_opf);
+ hctx_type = rq->mq_hctx->type;
+ if (type != hctx_type &&
+ !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT))
return NULL;
if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf))
return NULL;
--
GitLab
From 41e1992665a2701fa025a8b76970c43b4148446f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 17 Jan 2023 19:00:59 +0100
Subject: [PATCH 0881/1167] s390: workaround invalid gcc-11 out of bounds read
warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
GCC 11.1.0 and 11.2.0 generate a wrong warning when compiling the
kernel e.g. with allmodconfig:
arch/s390/kernel/setup.c: In function ‘setup_lowcore_dat_on’:
./include/linux/fortify-string.h:57:33: error: ‘__builtin_memcpy’ reading 128 bytes from a region of size 0 [-Werror=stringop-overread]
...
arch/s390/kernel/setup.c:526:9: note: in expansion of macro ‘memcpy’
526 | memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area,
| ^~~~~~
This could be addressed by using absolute_pointer() with the
S390_lowcore macro, but this is not a good idea since this generates
worse code for performance critical paths.
Therefore simply use a for loop to copy the array in question and get
rid of the warning.
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
---
arch/s390/kernel/setup.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 2b6091349daa2..696c9e007a369 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -508,6 +508,7 @@ static void __init setup_lowcore_dat_on(void)
{
struct lowcore *abs_lc;
unsigned long flags;
+ int i;
__ctl_clear_bit(0, 28);
S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT;
@@ -523,8 +524,8 @@ static void __init setup_lowcore_dat_on(void)
abs_lc = get_abs_lowcore(&flags);
abs_lc->restart_flags = RESTART_FLAG_CTLREGS;
abs_lc->program_new_psw = S390_lowcore.program_new_psw;
- memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area,
- sizeof(abs_lc->cregs_save_area));
+ for (i = 0; i < 16; i++)
+ abs_lc->cregs_save_area[i] = S390_lowcore.cregs_save_area[i];
put_abs_lowcore(abs_lc, flags);
}
--
GitLab
From 7d83299351fe7c812c529f5e39fe63b5312e4233 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jan 2023 17:39:32 +0100
Subject: [PATCH 0882/1167] staging: vchiq_arm: fix enum vchiq_status return
types
gcc-13 notices a type mismatch between function declaration
and definition for a few functions that have been converted
from returning vchiq specific status values to regular error
codes:
drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:662:5: error: conflicting types for 'vchiq_initialise' due to enum/integer mismatch; have 'int(struct vchiq_instance **)' [-Werror=enum-int-mismatch]
drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:1411:1: error: conflicting types for 'vchiq_use_internal' due to enum/integer mismatch; have 'int(struct vchiq_state *, struct vchiq_service *, enum USE_TYPE_E)' [-Werror=enum-int-mismatch]
drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c:1468:1: error: conflicting types for 'vchiq_release_internal' due to enum/integer mismatch; have 'int(struct vchiq_state *, struct vchiq_service *)' [-Werror=enum-int-mismatch]
Change the declarations to match the actual function definition.
Fixes: a9fbd828be7f ("staging: vchiq_arm: drop enum vchiq_status from vchiq_*_internal")
Cc: stable <stable@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20230117163957.1109872-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
.../staging/vc04_services/include/linux/raspberrypi/vchiq.h | 2 +-
drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h
index db1441c0cc662..690ab7165b2c1 100644
--- a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h
+++ b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h
@@ -86,7 +86,7 @@ struct vchiq_service_params_kernel {
struct vchiq_instance;
-extern enum vchiq_status vchiq_initialise(struct vchiq_instance **pinstance);
+extern int vchiq_initialise(struct vchiq_instance **pinstance);
extern enum vchiq_status vchiq_shutdown(struct vchiq_instance *instance);
extern enum vchiq_status vchiq_connect(struct vchiq_instance *instance);
extern enum vchiq_status vchiq_open_service(struct vchiq_instance *instance,
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
index 2851ef6b9cd0f..cd20eb18f2751 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h
@@ -100,10 +100,10 @@ vchiq_dump_platform_use_state(struct vchiq_state *state);
extern void
vchiq_dump_service_use_state(struct vchiq_state *state);
-extern enum vchiq_status
+extern int
vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service,
enum USE_TYPE_E use_type);
-extern enum vchiq_status
+extern int
vchiq_release_internal(struct vchiq_state *state,
struct vchiq_service *service);
--
GitLab
From 8026a31df6d59265553e7874cf3c2b560138a407 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 2 Jan 2023 11:16:22 -0300
Subject: [PATCH 0883/1167] tools headers UAPI: Sync linux/kvm.h with the
kernel sources
To pick the changes in:
b0305c1e0e27ad91 ("KVM: x86/xen: Add KVM_XEN_INVALID_GPA and KVM_XEN_INVALID_GFN to uapi")
That just rebuilds perf, as these patches don't add any new KVM ioctl to
be harvested for the the 'perf trace' ioctl syscall argument
beautifiers.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lore.kernel.org/lkml/Y7Loj5slB908QSXf@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/kvm.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 20522d4ba1e0d..55155e262646e 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1767,6 +1767,7 @@ struct kvm_xen_hvm_attr {
__u8 runstate_update_flag;
struct {
__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
} shared_info;
struct {
__u32 send_port;
@@ -1798,6 +1799,7 @@ struct kvm_xen_hvm_attr {
} u;
};
+
/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
@@ -1823,6 +1825,7 @@ struct kvm_xen_vcpu_attr {
__u16 pad[3];
union {
__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
__u64 pad[8];
struct {
__u64 state;
--
GitLab
From effa76856f2d7111f8c44de49f15ebdfccea8ccc Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Jan 2023 10:22:13 -0300
Subject: [PATCH 0884/1167] tools headers UAPI: Sync x86's asm/kvm.h with the
kernel sources
To pick the changes in:
8aff460f216753d8 ("KVM: x86: Add a VALID_MASK for the flags in kvm_msr_filter_range")
c1340fe3590ebbe7 ("KVM: x86: Add a VALID_MASK for the flag in kvm_msr_filter")
be83794210e7020f ("KVM: x86: Disallow the use of KVM_MSR_FILTER_DEFAULT_ALLOW in the kernel")
That just rebuilds kvm-stat.c on x86, no change in functionality.
This silences these perf build warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/kvm.h' differs from latest version at 'arch/x86/include/uapi/asm/kvm.h'
diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h
Cc: Aaron Lewis <aaronlewis@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lore.kernel.org/lkml/Y8VR5wSAkd2A0HxS@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/uapi/asm/kvm.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 649e50a8f9ddf..e48deab8901d4 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -206,6 +206,8 @@ struct kvm_msr_list {
struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_READ (1 << 0)
#define KVM_MSR_FILTER_WRITE (1 << 1)
+#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \
+ KVM_MSR_FILTER_WRITE)
__u32 flags;
__u32 nmsrs; /* number of msrs in bitmap */
__u32 base; /* MSR index the bitmap starts at */
@@ -214,8 +216,11 @@ struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_MAX_RANGES 16
struct kvm_msr_filter {
+#ifndef __KERNEL__
#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#endif
#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY)
__u32 flags;
struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
};
--
GitLab
From ac8f29aef2f1695956ff6773b33f975290437f29 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 17 Jan 2023 15:16:17 -0400
Subject: [PATCH 0885/1167] genirq/msi: Free the fwnode created by
msi_create_device_irq_domain()
msi_create_device_irq_domain() creates a firmware node for the new domain,
which is never freed. kmemleak reports:
unreferenced object 0xffff888120ba9a00 (size 96):
comm "systemd-modules", pid 221, jiffies 4294893411 (age 635.732s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 e0 19 8b 83 ff ff ff ff ................
00 00 00 00 00 00 00 00 18 9a ba 20 81 88 ff ff ........... ....
backtrace:
[<000000008cdbc98d>] __irq_domain_alloc_fwnode+0x51/0x2b0
[<00000000c57acf9d>] msi_create_device_irq_domain+0x283/0x670
[<000000009b567982>] __pci_enable_msix_range+0x49e/0xdb0
[<0000000077cc1445>] pci_alloc_irq_vectors_affinity+0x11f/0x1c0
[<00000000532e9ef5>] mlx5_irq_table_create+0x24c/0x940 [mlx5_core]
[<00000000fabd2b80>] mlx5_load+0x1fa/0x680 [mlx5_core]
[<000000006bb22ae4>] mlx5_init_one+0x485/0x670 [mlx5_core]
[<00000000eaa5e1ad>] probe_one+0x4c2/0x720 [mlx5_core]
[<00000000df8efb43>] local_pci_probe+0xd6/0x170
[<0000000085cb9924>] pci_device_probe+0x231/0x6e0
Use the proper free operation for the firmware wnode so the name is freed
during error unwind of msi_create_device_irq_domain() and also free the
node in msi_remove_device_irq_domain() if it was automatically allocated.
To avoid extra NULL pointer checks make irq_domain_free_fwnode() tolerant
of NULL.
Fixes: 27a6dea3ebaa ("genirq/msi: Provide msi_create/free_device_irq_domain()")
Reported-by: Omri Barazi <obarazi@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Kalle Valo <kvalo@kernel.org>
Tested-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/0-v2-24af6665e2da+c9-msi_leak_jgg@nvidia.com
---
kernel/irq/irqdomain.c | 2 +-
kernel/irq/msi.c | 6 +++++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8fe1da9614ee8..5c3fb6168eef2 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -114,7 +114,7 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode)
{
struct irqchip_fwid *fwid;
- if (WARN_ON(!is_fwnode_irqchip(fwnode)))
+ if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode)))
return;
fwid = container_of(fwnode, struct irqchip_fwid, fwnode);
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 955267bbc2be6..783a3e6a0b107 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -1000,7 +1000,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
fail:
msi_unlock_descs(dev);
free_fwnode:
- kfree(fwnode);
+ irq_domain_free_fwnode(fwnode);
free_bundle:
kfree(bundle);
return false;
@@ -1013,6 +1013,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
*/
void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
{
+ struct fwnode_handle *fwnode = NULL;
struct msi_domain_info *info;
struct irq_domain *domain;
@@ -1025,7 +1026,10 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid)
dev->msi.data->__domains[domid].domain = NULL;
info = domain->host_data;
+ if (irq_domain_is_msi_device(domain))
+ fwnode = domain->fwnode;
irq_domain_remove(domain);
+ irq_domain_free_fwnode(fwnode);
kfree(container_of(info, struct msi_domain_template, info));
unlock:
--
GitLab
From c410cb974f2ba562920ecb8492ee66945dcf88af Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jan 2023 14:42:32 +0100
Subject: [PATCH 0886/1167] netfilter: conntrack: handle tcp challenge acks
during connection reuse
When a connection is re-used, following can happen:
[ connection starts to close, fin sent in either direction ]
> syn # initator quickly reuses connection
< ack # peer sends a challenge ack
> rst # rst, sequence number == ack_seq of previous challenge ack
> syn # this syn is expected to pass
Problem is that the rst will fail window validation, so it gets
tagged as invalid.
If ruleset drops such packets, we get repeated syn-retransmits until
initator gives up or peer starts responding with syn/ack.
Before the commit indicated in the "Fixes" tag below this used to work:
The challenge-ack made conntrack re-init state based on the challenge
ack itself, so the following rst would pass window validation.
Add challenge-ack support: If we get ack for syn, record the ack_seq,
and then check if the rst sequence number matches the last ack number
seen in reverse direction.
Fixes: c7aab4f17021 ("netfilter: nf_conntrack_tcp: re-init for syn packets only")
Reported-by: Michal Tesar <mtesar@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_proto_tcp.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 6566310831779..3ac1af6f59fcc 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1068,6 +1068,13 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
ct->proto.tcp.last_flags |=
IP_CT_EXP_CHALLENGE_ACK;
}
+
+ /* possible challenge ack reply to syn */
+ if (old_state == TCP_CONNTRACK_SYN_SENT &&
+ index == TCP_ACK_SET &&
+ dir == IP_CT_DIR_REPLY)
+ ct->proto.tcp.last_ack = ntohl(th->ack_seq);
+
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, state,
"packet (index %d) in dir %d ignored, state %s",
@@ -1193,6 +1200,14 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
* segments we ignored. */
goto in_window;
}
+
+ /* Reset in response to a challenge-ack we let through earlier */
+ if (old_state == TCP_CONNTRACK_SYN_SENT &&
+ ct->proto.tcp.last_index == TCP_ACK_SET &&
+ ct->proto.tcp.last_dir == IP_CT_DIR_REPLY &&
+ ntohl(th->seq) == ct->proto.tcp.last_ack)
+ goto in_window;
+
break;
default:
/* Keep compilers happy. */
--
GitLab
From 2185e0fdbb2137f22a9dd9fcbf6481400d56299b Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 12 Dec 2022 05:08:28 -0800
Subject: [PATCH 0887/1167] Bluetooth: Fix a buffer overflow in mgmt_mesh_add()
Smatch Warning:
net/bluetooth/mgmt_util.c:375 mgmt_mesh_add() error: __memcpy()
'mesh_tx->param' too small (48 vs 50)
Analysis:
'mesh_tx->param' is array of size 48. This is the destination.
u8 param[sizeof(struct mgmt_cp_mesh_send) + 29]; // 19 + 29 = 48.
But in the caller 'mesh_send' we reject only when len > 50.
len > (MGMT_MESH_SEND_SIZE + 31) // 19 + 31 = 50.
Fixes: b338d91703fa ("Bluetooth: Implement support for Mesh")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Signed-off-by: Brian Gix <brian.gix@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/mgmt_util.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h
index 6a8b7e84293df..bdf978605d5a8 100644
--- a/net/bluetooth/mgmt_util.h
+++ b/net/bluetooth/mgmt_util.h
@@ -27,7 +27,7 @@ struct mgmt_mesh_tx {
struct sock *sk;
u8 handle;
u8 instance;
- u8 param[sizeof(struct mgmt_cp_mesh_send) + 29];
+ u8 param[sizeof(struct mgmt_cp_mesh_send) + 31];
};
struct mgmt_pending_cmd {
--
GitLab
From 3a4d29b6d631bb00236a98887e1039bbfc1b6ab5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 19 Dec 2022 13:32:51 -0800
Subject: [PATCH 0888/1167] Bluetooth: hci_sync: Fix use
HCI_OP_LE_READ_BUFFER_SIZE_V2
Don't try to use HCI_OP_LE_READ_BUFFER_SIZE_V2 if controller don't
support ISO channels, but in order to check if ISO channels are
supported HCI_OP_LE_READ_LOCAL_FEATURES needs to be done earlier so the
features bits can be checked on hci_le_read_buffer_size_sync.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216817
Fixes: c1631dbc00c1 ("Bluetooth: hci_sync: Fix hci_read_buffer_size_sync")
Cc: stable@vger.kernel.org # 6.1
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/hci_sync.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 9e2d7e4b850c5..b38a097344fb5 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3572,7 +3572,7 @@ static const struct hci_init_stage hci_init2[] = {
static int hci_le_read_buffer_size_sync(struct hci_dev *hdev)
{
/* Use Read LE Buffer Size V2 if supported */
- if (hdev->commands[41] & 0x20)
+ if (iso_capable(hdev) && hdev->commands[41] & 0x20)
return __hci_cmd_sync_status(hdev,
HCI_OP_LE_READ_BUFFER_SIZE_V2,
0, NULL, HCI_CMD_TIMEOUT);
@@ -3597,10 +3597,10 @@ static int hci_le_read_supported_states_sync(struct hci_dev *hdev)
/* LE Controller init stage 2 command sequence */
static const struct hci_init_stage le_init2[] = {
- /* HCI_OP_LE_READ_BUFFER_SIZE */
- HCI_INIT(hci_le_read_buffer_size_sync),
/* HCI_OP_LE_READ_LOCAL_FEATURES */
HCI_INIT(hci_le_read_local_features_sync),
+ /* HCI_OP_LE_READ_BUFFER_SIZE */
+ HCI_INIT(hci_le_read_buffer_size_sync),
/* HCI_OP_LE_READ_SUPPORTED_STATES */
HCI_INIT(hci_le_read_supported_states_sync),
{}
--
GitLab
From 3aa21311f36d8a2730c7ccef37235e951f23927b Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Wed, 4 Jan 2023 14:46:23 +0800
Subject: [PATCH 0889/1167] Bluetooth: hci_conn: Fix memory leaks
When hci_cmd_sync_queue() failed in hci_le_terminate_big() or
hci_le_big_terminate(), the memory pointed by variable d is not freed,
which will cause memory leak. Add release process to error path.
Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections")
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/hci_conn.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d3e542c2fc3e4..acf563fbdfd95 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -821,6 +821,7 @@ static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err)
static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis)
{
struct iso_list_data *d;
+ int ret;
bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis);
@@ -831,8 +832,12 @@ static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis)
d->big = big;
d->bis = bis;
- return hci_cmd_sync_queue(hdev, terminate_big_sync, d,
- terminate_big_destroy);
+ ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d,
+ terminate_big_destroy);
+ if (ret)
+ kfree(d);
+
+ return ret;
}
static int big_terminate_sync(struct hci_dev *hdev, void *data)
@@ -857,6 +862,7 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data)
static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle)
{
struct iso_list_data *d;
+ int ret;
bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle);
@@ -867,8 +873,12 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle)
d->big = big;
d->sync_handle = sync_handle;
- return hci_cmd_sync_queue(hdev, big_terminate_sync, d,
- terminate_big_destroy);
+ ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d,
+ terminate_big_destroy);
+ if (ret)
+ kfree(d);
+
+ return ret;
}
/* Cleanup BIS connection
--
GitLab
From 272970be3dabd24cbe50e393ffee8f04aec3b9a8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Thu, 29 Dec 2022 11:28:29 +0100
Subject: [PATCH 0890/1167] Bluetooth: hci_qca: Fix driver shutdown on closed
serdev
The driver shutdown callback (which sends EDL_SOC_RESET to the device
over serdev) should not be invoked when HCI device is not open (e.g. if
hci_dev_open_sync() failed), because the serdev and its TTY are not open
either. Also skip this step if device is powered off
(qca_power_shutdown()).
The shutdown callback causes use-after-free during system reboot with
Qualcomm Atheros Bluetooth:
Unable to handle kernel paging request at virtual address
0072662f67726fd7
...
CPU: 6 PID: 1 Comm: systemd-shutdow Tainted: G W
6.1.0-rt5-00325-g8a5f56bcfcca #8
Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
Call trace:
tty_driver_flush_buffer+0x4/0x30
serdev_device_write_flush+0x24/0x34
qca_serdev_shutdown+0x80/0x130 [hci_uart]
device_shutdown+0x15c/0x260
kernel_restart+0x48/0xac
KASAN report:
BUG: KASAN: use-after-free in tty_driver_flush_buffer+0x1c/0x50
Read of size 8 at addr ffff16270c2e0018 by task systemd-shutdow/1
CPU: 7 PID: 1 Comm: systemd-shutdow Not tainted
6.1.0-next-20221220-00014-gb85aaf97fb01-dirty #28
Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
Call trace:
dump_backtrace.part.0+0xdc/0xf0
show_stack+0x18/0x30
dump_stack_lvl+0x68/0x84
print_report+0x188/0x488
kasan_report+0xa4/0xf0
__asan_load8+0x80/0xac
tty_driver_flush_buffer+0x1c/0x50
ttyport_write_flush+0x34/0x44
serdev_device_write_flush+0x48/0x60
qca_serdev_shutdown+0x124/0x274
device_shutdown+0x1e8/0x350
kernel_restart+0x48/0xb0
__do_sys_reboot+0x244/0x2d0
__arm64_sys_reboot+0x54/0x70
invoke_syscall+0x60/0x190
el0_svc_common.constprop.0+0x7c/0x160
do_el0_svc+0x44/0xf0
el0_svc+0x2c/0x6c
el0t_64_sync_handler+0xbc/0x140
el0t_64_sync+0x190/0x194
Fixes: 7e7bbddd029b ("Bluetooth: hci_qca: Fix qca6390 enable failure after warm reboot")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
drivers/bluetooth/hci_qca.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 6eddc23e49d9a..bbe9cf1cae27f 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2164,10 +2164,17 @@ static void qca_serdev_shutdown(struct device *dev)
int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS);
struct serdev_device *serdev = to_serdev_device(dev);
struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
+ struct hci_uart *hu = &qcadev->serdev_hu;
+ struct hci_dev *hdev = hu->hdev;
+ struct qca_data *qca = hu->priv;
const u8 ibs_wake_cmd[] = { 0xFD };
const u8 edl_reset_soc_cmd[] = { 0x01, 0x00, 0xFC, 0x01, 0x05 };
if (qcadev->btsoc_type == QCA_QCA6390) {
+ if (test_bit(QCA_BT_OFF, &qca->flags) ||
+ !test_bit(HCI_RUNNING, &hdev->flags))
+ return;
+
serdev_device_write_flush(serdev);
ret = serdev_device_write_buf(serdev, ibs_wake_cmd,
sizeof(ibs_wake_cmd));
--
GitLab
From 1ed8b37cbaf14574c779064ef1372af62e8ba6aa Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Mon, 9 Jan 2023 09:26:51 +0800
Subject: [PATCH 0891/1167] Bluetooth: hci_sync: fix memory leak in
hci_update_adv_data()
When hci_cmd_sync_queue() failed in hci_update_adv_data(), inst_ptr is
not freed, which will cause memory leak, convert to use ERR_PTR/PTR_ERR
to pass the instance to callback so no memory needs to be allocated.
Fixes: 651cd3d65b0f ("Bluetooth: convert hci_update_adv_data to hci_sync")
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/hci_sync.c | 13 +++----------
1 file changed, 3 insertions(+), 10 deletions(-)
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index b38a097344fb5..117eedb6f7099 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -6187,20 +6187,13 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
static int _update_adv_data_sync(struct hci_dev *hdev, void *data)
{
- u8 instance = *(u8 *)data;
-
- kfree(data);
+ u8 instance = PTR_ERR(data);
return hci_update_adv_data_sync(hdev, instance);
}
int hci_update_adv_data(struct hci_dev *hdev, u8 instance)
{
- u8 *inst_ptr = kmalloc(1, GFP_KERNEL);
-
- if (!inst_ptr)
- return -ENOMEM;
-
- *inst_ptr = instance;
- return hci_cmd_sync_queue(hdev, _update_adv_data_sync, inst_ptr, NULL);
+ return hci_cmd_sync_queue(hdev, _update_adv_data_sync,
+ ERR_PTR(instance), NULL);
}
--
GitLab
From 6a5ad251b7cdb990a3705428aef408433f05614a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 10 Jan 2023 13:24:51 -0800
Subject: [PATCH 0892/1167] Bluetooth: ISO: Fix possible circular locking
dependency
This attempts to fix the following trace:
kworker/u3:1/184 is trying to acquire lock:
ffff888001888130 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}, at:
iso_connect_cfm+0x2de/0x690
but task is already holding lock:
ffff8880028d1c20 (&conn->lock){+.+.}-{2:2}, at:
iso_connect_cfm+0x265/0x690
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&conn->lock){+.+.}-{2:2}:
lock_acquire+0x176/0x3d0
_raw_spin_lock+0x2a/0x40
__iso_sock_close+0x1dd/0x4f0
iso_sock_release+0xa0/0x1b0
sock_close+0x5e/0x120
__fput+0x102/0x410
task_work_run+0xf1/0x160
exit_to_user_mode_prepare+0x170/0x180
syscall_exit_to_user_mode+0x19/0x50
do_syscall_64+0x4e/0x90
entry_SYSCALL_64_after_hwframe+0x62/0xcc
-> #0 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}:
check_prev_add+0xfc/0x1190
__lock_acquire+0x1e27/0x2750
lock_acquire+0x176/0x3d0
lock_sock_nested+0x32/0x80
iso_connect_cfm+0x2de/0x690
hci_cc_le_setup_iso_path+0x195/0x340
hci_cmd_complete_evt+0x1ae/0x500
hci_event_packet+0x38e/0x7c0
hci_rx_work+0x34c/0x980
process_one_work+0x5a5/0x9a0
worker_thread+0x89/0x6f0
kthread+0x14e/0x180
ret_from_fork+0x22/0x30
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&conn->lock);
lock(sk_lock-AF_BLUETOOTH-BTPROTO_ISO);
lock(&conn->lock);
lock(sk_lock-AF_BLUETOOTH-BTPROTO_ISO);
*** DEADLOCK ***
Fixes: ccf74f2390d6 ("Bluetooth: Add BTPROTO_ISO socket type")
Fixes: f764a6c2c1e4 ("Bluetooth: ISO: Add broadcast support")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/iso.c | 61 +++++++++++++++++++--------------------------
1 file changed, 26 insertions(+), 35 deletions(-)
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 035bb5d25f850..6157bc12b373f 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -289,15 +289,15 @@ static int iso_connect_bis(struct sock *sk)
hci_dev_unlock(hdev);
hci_dev_put(hdev);
+ err = iso_chan_add(conn, sk, NULL);
+ if (err)
+ return err;
+
lock_sock(sk);
/* Update source addr of the socket */
bacpy(&iso_pi(sk)->src, &hcon->src);
- err = iso_chan_add(conn, sk, NULL);
- if (err)
- goto release;
-
if (hcon->state == BT_CONNECTED) {
iso_sock_clear_timer(sk);
sk->sk_state = BT_CONNECTED;
@@ -306,7 +306,6 @@ static int iso_connect_bis(struct sock *sk)
iso_sock_set_timer(sk, sk->sk_sndtimeo);
}
-release:
release_sock(sk);
return err;
@@ -372,15 +371,15 @@ static int iso_connect_cis(struct sock *sk)
hci_dev_unlock(hdev);
hci_dev_put(hdev);
+ err = iso_chan_add(conn, sk, NULL);
+ if (err)
+ return err;
+
lock_sock(sk);
/* Update source addr of the socket */
bacpy(&iso_pi(sk)->src, &hcon->src);
- err = iso_chan_add(conn, sk, NULL);
- if (err)
- goto release;
-
if (hcon->state == BT_CONNECTED) {
iso_sock_clear_timer(sk);
sk->sk_state = BT_CONNECTED;
@@ -392,7 +391,6 @@ static int iso_connect_cis(struct sock *sk)
iso_sock_set_timer(sk, sk->sk_sndtimeo);
}
-release:
release_sock(sk);
return err;
@@ -1432,33 +1430,29 @@ static void iso_conn_ready(struct iso_conn *conn)
struct sock *parent;
struct sock *sk = conn->sk;
struct hci_ev_le_big_sync_estabilished *ev;
+ struct hci_conn *hcon;
BT_DBG("conn %p", conn);
if (sk) {
iso_sock_ready(conn->sk);
} else {
- iso_conn_lock(conn);
-
- if (!conn->hcon) {
- iso_conn_unlock(conn);
+ hcon = conn->hcon;
+ if (!hcon)
return;
- }
- ev = hci_recv_event_data(conn->hcon->hdev,
+ ev = hci_recv_event_data(hcon->hdev,
HCI_EVT_LE_BIG_SYNC_ESTABILISHED);
if (ev)
- parent = iso_get_sock_listen(&conn->hcon->src,
- &conn->hcon->dst,
+ parent = iso_get_sock_listen(&hcon->src,
+ &hcon->dst,
iso_match_big, ev);
else
- parent = iso_get_sock_listen(&conn->hcon->src,
+ parent = iso_get_sock_listen(&hcon->src,
BDADDR_ANY, NULL, NULL);
- if (!parent) {
- iso_conn_unlock(conn);
+ if (!parent)
return;
- }
lock_sock(parent);
@@ -1466,30 +1460,29 @@ static void iso_conn_ready(struct iso_conn *conn)
BTPROTO_ISO, GFP_ATOMIC, 0);
if (!sk) {
release_sock(parent);
- iso_conn_unlock(conn);
return;
}
iso_sock_init(sk, parent);
- bacpy(&iso_pi(sk)->src, &conn->hcon->src);
- iso_pi(sk)->src_type = conn->hcon->src_type;
+ bacpy(&iso_pi(sk)->src, &hcon->src);
+ iso_pi(sk)->src_type = hcon->src_type;
/* If hcon has no destination address (BDADDR_ANY) it means it
* was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED so we need to
* initialize using the parent socket destination address.
*/
- if (!bacmp(&conn->hcon->dst, BDADDR_ANY)) {
- bacpy(&conn->hcon->dst, &iso_pi(parent)->dst);
- conn->hcon->dst_type = iso_pi(parent)->dst_type;
- conn->hcon->sync_handle = iso_pi(parent)->sync_handle;
+ if (!bacmp(&hcon->dst, BDADDR_ANY)) {
+ bacpy(&hcon->dst, &iso_pi(parent)->dst);
+ hcon->dst_type = iso_pi(parent)->dst_type;
+ hcon->sync_handle = iso_pi(parent)->sync_handle;
}
- bacpy(&iso_pi(sk)->dst, &conn->hcon->dst);
- iso_pi(sk)->dst_type = conn->hcon->dst_type;
+ bacpy(&iso_pi(sk)->dst, &hcon->dst);
+ iso_pi(sk)->dst_type = hcon->dst_type;
- hci_conn_hold(conn->hcon);
- __iso_chan_add(conn, sk, parent);
+ hci_conn_hold(hcon);
+ iso_chan_add(conn, sk, parent);
if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags))
sk->sk_state = BT_CONNECT2;
@@ -1500,8 +1493,6 @@ static void iso_conn_ready(struct iso_conn *conn)
parent->sk_data_ready(parent);
release_sock(parent);
-
- iso_conn_unlock(conn);
}
}
--
GitLab
From e9d50f76fe1f7f6f251114919247445fb5cb3734 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 10 Jan 2023 17:04:46 -0800
Subject: [PATCH 0893/1167] Bluetooth: hci_event: Fix Invalid wait context
This fixes the following trace caused by attempting to lock
cmd_sync_work_lock while holding the rcu_read_lock:
kworker/u3:2/212 is trying to lock:
ffff888002600910 (&hdev->cmd_sync_work_lock){+.+.}-{3:3}, at:
hci_cmd_sync_queue+0xad/0x140
other info that might help us debug this:
context-{4:4}
4 locks held by kworker/u3:2/212:
#0: ffff8880028c6530 ((wq_completion)hci0#2){+.+.}-{0:0}, at:
process_one_work+0x4dc/0x9a0
#1: ffff888001aafde0 ((work_completion)(&hdev->rx_work)){+.+.}-{0:0},
at: process_one_work+0x4dc/0x9a0
#2: ffff888002600070 (&hdev->lock){+.+.}-{3:3}, at:
hci_cc_le_set_cig_params+0x64/0x4f0
#3: ffffffffa5994b00 (rcu_read_lock){....}-{1:2}, at:
hci_cc_le_set_cig_params+0x2f9/0x4f0
Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/hci_event.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0594af4e37cad..ad92a4be58517 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3848,8 +3848,11 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data,
conn->handle, conn->link);
/* Create CIS if LE is already connected */
- if (conn->link && conn->link->state == BT_CONNECTED)
+ if (conn->link && conn->link->state == BT_CONNECTED) {
+ rcu_read_unlock();
hci_le_create_cis(conn->link);
+ rcu_read_lock();
+ }
if (i == rp->num_handles)
break;
--
GitLab
From 506d9b4099a0ce8249bba16b4d0b828fdcf69d9a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 10 Jan 2023 17:18:13 -0800
Subject: [PATCH 0894/1167] Bluetooth: ISO: Fix possible circular locking
dependency
This attempts to fix the following trace:
iso-tester/52 is trying to acquire lock:
ffff8880024e0070 (&hdev->lock){+.+.}-{3:3}, at:
iso_sock_listen+0x29e/0x440
but task is already holding lock:
ffff888001978130 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}, at:
iso_sock_listen+0x8b/0x440
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}:
lock_acquire+0x176/0x3d0
lock_sock_nested+0x32/0x80
iso_connect_cfm+0x1a3/0x630
hci_cc_le_setup_iso_path+0x195/0x340
hci_cmd_complete_evt+0x1ae/0x500
hci_event_packet+0x38e/0x7c0
hci_rx_work+0x34c/0x980
process_one_work+0x5a5/0x9a0
worker_thread+0x89/0x6f0
kthread+0x14e/0x180
ret_from_fork+0x22/0x30
-> #1 (hci_cb_list_lock){+.+.}-{3:3}:
lock_acquire+0x176/0x3d0
__mutex_lock+0x13b/0xf50
hci_le_remote_feat_complete_evt+0x17e/0x320
hci_event_packet+0x38e/0x7c0
hci_rx_work+0x34c/0x980
process_one_work+0x5a5/0x9a0
worker_thread+0x89/0x6f0
kthread+0x14e/0x180
ret_from_fork+0x22/0x30
-> #0 (&hdev->lock){+.+.}-{3:3}:
check_prev_add+0xfc/0x1190
__lock_acquire+0x1e27/0x2750
lock_acquire+0x176/0x3d0
__mutex_lock+0x13b/0xf50
iso_sock_listen+0x29e/0x440
__sys_listen+0xe6/0x160
__x64_sys_listen+0x25/0x30
do_syscall_64+0x42/0x90
entry_SYSCALL_64_after_hwframe+0x62/0xcc
other info that might help us debug this:
Chain exists of:
&hdev->lock --> hci_cb_list_lock --> sk_lock-AF_BLUETOOTH-BTPROTO_ISO
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(sk_lock-AF_BLUETOOTH-BTPROTO_ISO);
lock(hci_cb_list_lock);
lock(sk_lock-AF_BLUETOOTH-BTPROTO_ISO);
lock(&hdev->lock);
*** DEADLOCK ***
1 lock held by iso-tester/52:
#0: ffff888001978130 (sk_lock-AF_BLUETOOTH-BTPROTO_ISO){+.+.}-{0:0}, at:
iso_sock_listen+0x8b/0x440
Fixes: f764a6c2c1e4 ("Bluetooth: ISO: Add broadcast support")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/iso.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 6157bc12b373f..24444b502e586 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -893,13 +893,10 @@ static int iso_listen_bis(struct sock *sk)
if (!hdev)
return -EHOSTUNREACH;
- hci_dev_lock(hdev);
-
err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst,
le_addr_type(iso_pi(sk)->dst_type),
iso_pi(sk)->bc_sid);
- hci_dev_unlock(hdev);
hci_dev_put(hdev);
return err;
--
GitLab
From 1d80d57ffcb55488f0ec0b77928d4f82d16b6a90 Mon Sep 17 00:00:00 2001
From: Ying Hsu <yinghsu@chromium.org>
Date: Wed, 11 Jan 2023 03:16:14 +0000
Subject: [PATCH 0895/1167] Bluetooth: Fix possible deadlock in
rfcomm_sk_state_change
syzbot reports a possible deadlock in rfcomm_sk_state_change [1].
While rfcomm_sock_connect acquires the sk lock and waits for
the rfcomm lock, rfcomm_sock_release could have the rfcomm
lock and hit a deadlock for acquiring the sk lock.
Here's a simplified flow:
rfcomm_sock_connect:
lock_sock(sk)
rfcomm_dlc_open:
rfcomm_lock()
rfcomm_sock_release:
rfcomm_sock_shutdown:
rfcomm_lock()
__rfcomm_dlc_close:
rfcomm_k_state_change:
lock_sock(sk)
This patch drops the sk lock before calling rfcomm_dlc_open to
avoid the possible deadlock and holds sk's reference count to
prevent use-after-free after rfcomm_dlc_open completes.
Reported-by: syzbot+d7ce59...@syzkaller.appspotmail.com
Fixes: 1804fdf6e494 ("Bluetooth: btintel: Combine setting up MSFT extension")
Link: https://syzkaller.appspot.com/bug?extid=d7ce59b06b3eb14fd218 [1]
Signed-off-by: Ying Hsu <yinghsu@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
net/bluetooth/rfcomm/sock.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 21e24da4847f0..4397e14ff560f 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -391,6 +391,7 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a
addr->sa_family != AF_BLUETOOTH)
return -EINVAL;
+ sock_hold(sk);
lock_sock(sk);
if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) {
@@ -410,14 +411,18 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a
d->sec_level = rfcomm_pi(sk)->sec_level;
d->role_switch = rfcomm_pi(sk)->role_switch;
+ /* Drop sock lock to avoid potential deadlock with the RFCOMM lock */
+ release_sock(sk);
err = rfcomm_dlc_open(d, &rfcomm_pi(sk)->src, &sa->rc_bdaddr,
sa->rc_channel);
- if (!err)
+ lock_sock(sk);
+ if (!err && !sock_flag(sk, SOCK_ZAPPED))
err = bt_sock_wait_state(sk, BT_CONNECTED,
sock_sndtimeo(sk, flags & O_NONBLOCK));
done:
release_sock(sk);
+ sock_put(sk);
return err;
}
--
GitLab
From 9ec9b2a30853ba843b70ea16f196e5fe3327be5f Mon Sep 17 00:00:00 2001
From: Caleb Connolly <caleb.connolly@linaro.org>
Date: Sun, 15 Jan 2023 17:59:24 +0000
Subject: [PATCH 0896/1167] net: ipa: disable ipa interrupt during suspend
The IPA interrupt can fire when pm_runtime is disabled due to it racing
with the PM suspend/resume code. This causes a splat in the interrupt
handler when it tries to call pm_runtime_get().
Explicitly disable the interrupt in our ->suspend callback, and
re-enable it in ->resume to avoid this. If there is an interrupt pending
it will be handled after resuming. The interrupt is a wake_irq, as a
result even when disabled if it fires it will cause the system to wake
from suspend as well as cancel any suspend transition that may be in
progress. If there is an interrupt pending, the ipa_isr_thread handler
will be called after resuming.
Fixes: 1aac309d3207 ("net: ipa: use autosuspend")
Signed-off-by: Caleb Connolly <caleb.connolly@linaro.org>
Reviewed-by: Alex Elder <elder@linaro.org>
Link: https://lore.kernel.org/r/20230115175925.465918-1-caleb.connolly@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ipa/ipa_interrupt.c | 10 ++++++++++
drivers/net/ipa/ipa_interrupt.h | 16 ++++++++++++++++
drivers/net/ipa/ipa_power.c | 17 +++++++++++++++++
3 files changed, 43 insertions(+)
diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c
index d458a35839cce..c1b3977e1ae48 100644
--- a/drivers/net/ipa/ipa_interrupt.c
+++ b/drivers/net/ipa/ipa_interrupt.c
@@ -127,6 +127,16 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id)
return IRQ_HANDLED;
}
+void ipa_interrupt_irq_disable(struct ipa *ipa)
+{
+ disable_irq(ipa->interrupt->irq);
+}
+
+void ipa_interrupt_irq_enable(struct ipa *ipa)
+{
+ enable_irq(ipa->interrupt->irq);
+}
+
/* Common function used to enable/disable TX_SUSPEND for an endpoint */
static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt,
u32 endpoint_id, bool enable)
diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h
index f31fd9965fdc6..8a1bd5b893932 100644
--- a/drivers/net/ipa/ipa_interrupt.h
+++ b/drivers/net/ipa/ipa_interrupt.h
@@ -85,6 +85,22 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt);
*/
void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt);
+/**
+ * ipa_interrupt_irq_enable() - Enable IPA interrupts
+ * @ipa: IPA pointer
+ *
+ * This enables the IPA interrupt line
+ */
+void ipa_interrupt_irq_enable(struct ipa *ipa);
+
+/**
+ * ipa_interrupt_irq_disable() - Disable IPA interrupts
+ * @ipa: IPA pointer
+ *
+ * This disables the IPA interrupt line
+ */
+void ipa_interrupt_irq_disable(struct ipa *ipa);
+
/**
* ipa_interrupt_config() - Configure the IPA interrupt framework
* @ipa: IPA pointer
diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c
index 8420f93128a26..8057be8cda801 100644
--- a/drivers/net/ipa/ipa_power.c
+++ b/drivers/net/ipa/ipa_power.c
@@ -181,6 +181,17 @@ static int ipa_suspend(struct device *dev)
__set_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+ /* Increment the disable depth to ensure that the IRQ won't
+ * be re-enabled until the matching _enable call in
+ * ipa_resume(). We do this to ensure that the interrupt
+ * handler won't run whilst PM runtime is disabled.
+ *
+ * Note that disabling the IRQ is NOT the same as disabling
+ * irq wake. If wakeup is enabled for the IPA then the IRQ
+ * will still cause the system to wake up, see irq_set_irq_wake().
+ */
+ ipa_interrupt_irq_disable(ipa);
+
return pm_runtime_force_suspend(dev);
}
@@ -193,6 +204,12 @@ static int ipa_resume(struct device *dev)
__clear_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags);
+ /* Now that PM runtime is enabled again it's safe
+ * to turn the IRQ back on and process any data
+ * that was received during suspend.
+ */
+ ipa_interrupt_irq_enable(ipa);
+
return ret;
}
--
GitLab
From 441717b6fdf2f620475b5e410f73d55154bb6f30 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Mon, 16 Jan 2023 14:20:15 +0530
Subject: [PATCH 0897/1167] MAINTAINERS: Update AMD XGBE driver maintainers
Due to other additional responsibilities Tom would no longer
be able to support AMD XGBE driver.
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20230116085015.443127-1-Shyam-sundar.S-k@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index e278cd5d0de00..e5c43cbffea78 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1104,7 +1104,6 @@ S: Supported
F: arch/arm64/boot/dts/amd/
AMD XGBE DRIVER
-M: Tom Lendacky <thomas.lendacky@amd.com>
M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com>
L: netdev@vger.kernel.org
S: Supported
--
GitLab
From 13e1df09284da53ae5abdd3364c36caf8f0f8916 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <linux@weissschuh.net>
Date: Tue, 17 Jan 2023 05:30:43 +0000
Subject: [PATCH 0898/1167] kheaders: explicitly validate existence of cpio
command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If the cpio command is not available the error emitted by
gen_kheaders.so is not clear as all output of the call to cpio is
discarded:
GNU make 4.4:
GEN kernel/kheaders_data.tar.xz
find: 'standard output': Broken pipe
find: write error
make[2]: *** [kernel/Makefile:157: kernel/kheaders_data.tar.xz] Error 127
make[1]: *** [scripts/Makefile.build:504: kernel] Error 2
GNU make < 4.4:
GEN kernel/kheaders_data.tar.xz
make[2]: *** [kernel/Makefile:157: kernel/kheaders_data.tar.xz] Error 127
make[2]: *** Waiting for unfinished jobs....
make[1]: *** [scripts/Makefile.build:504: kernel] Error 2
Add an explicit check that will trigger a clear message about the issue:
CHK kernel/kheaders_data.tar.xz
./kernel/gen_kheaders.sh: line 17: type: cpio: not found
The other commands executed by gen_kheaders.sh are part of a standard
installation, so they are not checked.
Reported-by: Amy Parker <apark0006@student.cerritos.edu>
Link: https://lore.kernel.org/lkml/CAPOgqxFva=tOuh1UitCSN38+28q3BNXKq19rEsVNPRzRqKqZ+g@mail.gmail.com/
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Nicolas Schier <n.schier@avm.de>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
kernel/gen_kheaders.sh | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 473036b43c832..81b97f0f65564 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -14,6 +14,8 @@ include/
arch/$SRCARCH/include/
"
+type cpio > /dev/null
+
# Support incremental builds by skipping archive generation
# if timestamps of files being archived are not changed.
--
GitLab
From 90e7cb78b81543998217b0eb446c067ce2191a79 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Thu, 5 Jan 2023 19:42:20 +0800
Subject: [PATCH 0899/1167] net/mlx5: fix missing mutex_unlock in
mlx5_fw_fatal_reporter_err_work()
Add missing mutex_unlock() before returning from
mlx5_fw_fatal_reporter_err_work().
Fixes: 9078e843efec ("net/mlx5: Avoid recovery in probe flows")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/health.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 96417c5feed76..879555ba847dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -677,6 +677,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
mutex_lock(&dev->intf_state_mutex);
if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
mlx5_core_err(dev, "health works are not permitted at this stage\n");
+ mutex_unlock(&dev->intf_state_mutex);
return;
}
mutex_unlock(&dev->intf_state_mutex);
--
GitLab
From 5aa56105930374928d567744595fd7ac525d0688 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Thu, 15 Dec 2022 16:44:33 +0100
Subject: [PATCH 0900/1167] net/mlx5e: Avoid false lock dependency warning on
tc_ht even more
The cited commit changed class of tc_ht internal mutex in order to avoid
false lock dependency with fs_core node and flow_table hash table
structures. However, hash table implementation internally also includes a
workqueue task with its own lockdep map which causes similar bogus lockdep
splat[0]. Fix it by also adding dedicated class for hash table workqueue
work structure of tc_ht.
[0]:
[ 1139.672465] ======================================================
[ 1139.673552] WARNING: possible circular locking dependency detected
[ 1139.674635] 6.1.0_for_upstream_debug_2022_12_12_17_02 #1 Not tainted
[ 1139.675734] ------------------------------------------------------
[ 1139.676801] modprobe/5998 is trying to acquire lock:
[ 1139.677726] ffff88811e7b93b8 (&node->lock){++++}-{3:3}, at: down_write_ref_node+0x7c/0xe0 [mlx5_core]
[ 1139.679662]
but task is already holding lock:
[ 1139.680703] ffff88813c1f96a0 (&tc_ht_lock_key){+.+.}-{3:3}, at: rhashtable_free_and_destroy+0x38/0x6f0
[ 1139.682223]
which lock already depends on the new lock.
[ 1139.683640]
the existing dependency chain (in reverse order) is:
[ 1139.684887]
-> #2 (&tc_ht_lock_key){+.+.}-{3:3}:
[ 1139.685975] __mutex_lock+0x12c/0x14b0
[ 1139.686659] rht_deferred_worker+0x35/0x1540
[ 1139.687405] process_one_work+0x7c2/0x1310
[ 1139.688134] worker_thread+0x59d/0xec0
[ 1139.688820] kthread+0x28f/0x330
[ 1139.689444] ret_from_fork+0x1f/0x30
[ 1139.690106]
-> #1 ((work_completion)(&ht->run_work)){+.+.}-{0:0}:
[ 1139.691250] __flush_work+0xe8/0x900
[ 1139.691915] __cancel_work_timer+0x2ca/0x3f0
[ 1139.692655] rhashtable_free_and_destroy+0x22/0x6f0
[ 1139.693472] del_sw_flow_table+0x22/0xb0 [mlx5_core]
[ 1139.694592] tree_put_node+0x24c/0x450 [mlx5_core]
[ 1139.695686] tree_remove_node+0x6e/0x100 [mlx5_core]
[ 1139.696803] mlx5_destroy_flow_table+0x187/0x690 [mlx5_core]
[ 1139.698017] mlx5e_tc_nic_cleanup+0x2f8/0x400 [mlx5_core]
[ 1139.699217] mlx5e_cleanup_nic_rx+0x2b/0x210 [mlx5_core]
[ 1139.700397] mlx5e_detach_netdev+0x19d/0x2b0 [mlx5_core]
[ 1139.701571] mlx5e_suspend+0xdb/0x140 [mlx5_core]
[ 1139.702665] mlx5e_remove+0x89/0x190 [mlx5_core]
[ 1139.703756] auxiliary_bus_remove+0x52/0x70
[ 1139.704492] device_release_driver_internal+0x3c1/0x600
[ 1139.705360] bus_remove_device+0x2a5/0x560
[ 1139.706080] device_del+0x492/0xb80
[ 1139.706724] mlx5_rescan_drivers_locked+0x194/0x6a0 [mlx5_core]
[ 1139.707961] mlx5_unregister_device+0x7a/0xa0 [mlx5_core]
[ 1139.709138] mlx5_uninit_one+0x5f/0x160 [mlx5_core]
[ 1139.710252] remove_one+0xd1/0x160 [mlx5_core]
[ 1139.711297] pci_device_remove+0x96/0x1c0
[ 1139.722721] device_release_driver_internal+0x3c1/0x600
[ 1139.723590] unbind_store+0x1b1/0x200
[ 1139.724259] kernfs_fop_write_iter+0x348/0x520
[ 1139.725019] vfs_write+0x7b2/0xbf0
[ 1139.725658] ksys_write+0xf3/0x1d0
[ 1139.726292] do_syscall_64+0x3d/0x90
[ 1139.726942] entry_SYSCALL_64_after_hwframe+0x46/0xb0
[ 1139.727769]
-> #0 (&node->lock){++++}-{3:3}:
[ 1139.728698] __lock_acquire+0x2cf5/0x62f0
[ 1139.729415] lock_acquire+0x1c1/0x540
[ 1139.730076] down_write+0x8e/0x1f0
[ 1139.730709] down_write_ref_node+0x7c/0xe0 [mlx5_core]
[ 1139.731841] mlx5_del_flow_rules+0x6f/0x610 [mlx5_core]
[ 1139.732982] __mlx5_eswitch_del_rule+0xdd/0x560 [mlx5_core]
[ 1139.734207] mlx5_eswitch_del_offloaded_rule+0x14/0x20 [mlx5_core]
[ 1139.735491] mlx5e_tc_rule_unoffload+0x104/0x2b0 [mlx5_core]
[ 1139.736716] mlx5e_tc_unoffload_fdb_rules+0x10c/0x1f0 [mlx5_core]
[ 1139.738007] mlx5e_tc_del_fdb_flow+0xc3c/0xfa0 [mlx5_core]
[ 1139.739213] mlx5e_tc_del_flow+0x146/0xa20 [mlx5_core]
[ 1139.740377] _mlx5e_tc_del_flow+0x38/0x60 [mlx5_core]
[ 1139.741534] rhashtable_free_and_destroy+0x3be/0x6f0
[ 1139.742351] mlx5e_tc_ht_cleanup+0x1b/0x30 [mlx5_core]
[ 1139.743512] mlx5e_cleanup_rep_tx+0x4a/0xe0 [mlx5_core]
[ 1139.744683] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core]
[ 1139.745860] mlx5e_netdev_change_profile+0xd9/0x1c0 [mlx5_core]
[ 1139.747098] mlx5e_netdev_attach_nic_profile+0x1b/0x30 [mlx5_core]
[ 1139.748372] mlx5e_vport_rep_unload+0x16a/0x1b0 [mlx5_core]
[ 1139.749590] __esw_offloads_unload_rep+0xb1/0xd0 [mlx5_core]
[ 1139.750813] mlx5_eswitch_unregister_vport_reps+0x409/0x5f0 [mlx5_core]
[ 1139.752147] mlx5e_rep_remove+0x62/0x80 [mlx5_core]
[ 1139.753293] auxiliary_bus_remove+0x52/0x70
[ 1139.754028] device_release_driver_internal+0x3c1/0x600
[ 1139.754885] driver_detach+0xc1/0x180
[ 1139.755553] bus_remove_driver+0xef/0x2e0
[ 1139.756260] auxiliary_driver_unregister+0x16/0x50
[ 1139.757059] mlx5e_rep_cleanup+0x19/0x30 [mlx5_core]
[ 1139.758207] mlx5e_cleanup+0x12/0x30 [mlx5_core]
[ 1139.759295] mlx5_cleanup+0xc/0x49 [mlx5_core]
[ 1139.760384] __x64_sys_delete_module+0x2b5/0x450
[ 1139.761166] do_syscall_64+0x3d/0x90
[ 1139.761827] entry_SYSCALL_64_after_hwframe+0x46/0xb0
[ 1139.762663]
other info that might help us debug this:
[ 1139.763925] Chain exists of:
&node->lock --> (work_completion)(&ht->run_work) --> &tc_ht_lock_key
[ 1139.765743] Possible unsafe locking scenario:
[ 1139.766688] CPU0 CPU1
[ 1139.767399] ---- ----
[ 1139.768111] lock(&tc_ht_lock_key);
[ 1139.768704] lock((work_completion)(&ht->run_work));
[ 1139.769869] lock(&tc_ht_lock_key);
[ 1139.770770] lock(&node->lock);
[ 1139.771326]
*** DEADLOCK ***
[ 1139.772345] 2 locks held by modprobe/5998:
[ 1139.772994] #0: ffff88813c1ff0e8 (&dev->mutex){....}-{3:3}, at: device_release_driver_internal+0x8d/0x600
[ 1139.774399] #1: ffff88813c1f96a0 (&tc_ht_lock_key){+.+.}-{3:3}, at: rhashtable_free_and_destroy+0x38/0x6f0
[ 1139.775822]
stack backtrace:
[ 1139.776579] CPU: 3 PID: 5998 Comm: modprobe Not tainted 6.1.0_for_upstream_debug_2022_12_12_17_02 #1
[ 1139.777935] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
[ 1139.779529] Call Trace:
[ 1139.779992] <TASK>
[ 1139.780409] dump_stack_lvl+0x57/0x7d
[ 1139.781015] check_noncircular+0x278/0x300
[ 1139.781687] ? print_circular_bug+0x460/0x460
[ 1139.782381] ? rcu_read_lock_sched_held+0x3f/0x70
[ 1139.783121] ? lock_release+0x487/0x7c0
[ 1139.783759] ? orc_find.part.0+0x1f1/0x330
[ 1139.784423] ? mark_lock.part.0+0xef/0x2fc0
[ 1139.785091] __lock_acquire+0x2cf5/0x62f0
[ 1139.785754] ? register_lock_class+0x18e0/0x18e0
[ 1139.786483] lock_acquire+0x1c1/0x540
[ 1139.787093] ? down_write_ref_node+0x7c/0xe0 [mlx5_core]
[ 1139.788195] ? lockdep_hardirqs_on_prepare+0x3f0/0x3f0
[ 1139.788978] ? register_lock_class+0x18e0/0x18e0
[ 1139.789715] down_write+0x8e/0x1f0
[ 1139.790292] ? down_write_ref_node+0x7c/0xe0 [mlx5_core]
[ 1139.791380] ? down_write_killable+0x220/0x220
[ 1139.792080] ? find_held_lock+0x2d/0x110
[ 1139.792713] down_write_ref_node+0x7c/0xe0 [mlx5_core]
[ 1139.793795] mlx5_del_flow_rules+0x6f/0x610 [mlx5_core]
[ 1139.794879] __mlx5_eswitch_del_rule+0xdd/0x560 [mlx5_core]
[ 1139.796032] ? __esw_offloads_unload_rep+0xd0/0xd0 [mlx5_core]
[ 1139.797227] ? xa_load+0x11a/0x200
[ 1139.797800] ? __xa_clear_mark+0xf0/0xf0
[ 1139.798438] mlx5_eswitch_del_offloaded_rule+0x14/0x20 [mlx5_core]
[ 1139.799660] mlx5e_tc_rule_unoffload+0x104/0x2b0 [mlx5_core]
[ 1139.800821] mlx5e_tc_unoffload_fdb_rules+0x10c/0x1f0 [mlx5_core]
[ 1139.802049] ? mlx5_eswitch_get_uplink_priv+0x25/0x80 [mlx5_core]
[ 1139.803260] mlx5e_tc_del_fdb_flow+0xc3c/0xfa0 [mlx5_core]
[ 1139.804398] ? __cancel_work_timer+0x1c2/0x3f0
[ 1139.805099] ? mlx5e_tc_unoffload_from_slow_path+0x460/0x460 [mlx5_core]
[ 1139.806387] mlx5e_tc_del_flow+0x146/0xa20 [mlx5_core]
[ 1139.807481] _mlx5e_tc_del_flow+0x38/0x60 [mlx5_core]
[ 1139.808564] rhashtable_free_and_destroy+0x3be/0x6f0
[ 1139.809336] ? mlx5e_tc_del_flow+0xa20/0xa20 [mlx5_core]
[ 1139.809336] ? mlx5e_tc_del_flow+0xa20/0xa20 [mlx5_core]
[ 1139.810455] mlx5e_tc_ht_cleanup+0x1b/0x30 [mlx5_core]
[ 1139.811552] mlx5e_cleanup_rep_tx+0x4a/0xe0 [mlx5_core]
[ 1139.812655] mlx5e_detach_netdev+0x1ca/0x2b0 [mlx5_core]
[ 1139.813768] mlx5e_netdev_change_profile+0xd9/0x1c0 [mlx5_core]
[ 1139.814952] mlx5e_netdev_attach_nic_profile+0x1b/0x30 [mlx5_core]
[ 1139.816166] mlx5e_vport_rep_unload+0x16a/0x1b0 [mlx5_core]
[ 1139.817336] __esw_offloads_unload_rep+0xb1/0xd0 [mlx5_core]
[ 1139.818507] mlx5_eswitch_unregister_vport_reps+0x409/0x5f0 [mlx5_core]
[ 1139.819788] ? mlx5_eswitch_uplink_get_proto_dev+0x30/0x30 [mlx5_core]
[ 1139.821051] ? kernfs_find_ns+0x137/0x310
[ 1139.821705] mlx5e_rep_remove+0x62/0x80 [mlx5_core]
[ 1139.822778] auxiliary_bus_remove+0x52/0x70
[ 1139.823449] device_release_driver_internal+0x3c1/0x600
[ 1139.824240] driver_detach+0xc1/0x180
[ 1139.824842] bus_remove_driver+0xef/0x2e0
[ 1139.825504] auxiliary_driver_unregister+0x16/0x50
[ 1139.826245] mlx5e_rep_cleanup+0x19/0x30 [mlx5_core]
[ 1139.827322] mlx5e_cleanup+0x12/0x30 [mlx5_core]
[ 1139.828345] mlx5_cleanup+0xc/0x49 [mlx5_core]
[ 1139.829382] __x64_sys_delete_module+0x2b5/0x450
[ 1139.830119] ? module_flags+0x300/0x300
[ 1139.830750] ? task_work_func_match+0x50/0x50
[ 1139.831440] ? task_work_cancel+0x20/0x20
[ 1139.832088] ? lockdep_hardirqs_on_prepare+0x273/0x3f0
[ 1139.832873] ? syscall_enter_from_user_mode+0x1d/0x50
[ 1139.833661] ? trace_hardirqs_on+0x2d/0x100
[ 1139.834328] do_syscall_64+0x3d/0x90
[ 1139.834922] entry_SYSCALL_64_after_hwframe+0x46/0xb0
[ 1139.835700] RIP: 0033:0x7f153e71288b
[ 1139.836302] Code: 73 01 c3 48 8b 0d 9d 75 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 6d 75 0e 00 f7 d8 64 89 01 48
[ 1139.838866] RSP: 002b:00007ffe0a3ed938 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0
[ 1139.840020] RAX: ffffffffffffffda RBX: 0000564c2cbf8220 RCX: 00007f153e71288b
[ 1139.841043] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000564c2cbf8288
[ 1139.842072] RBP: 0000564c2cbf8220 R08: 0000000000000000 R09: 0000000000000000
[ 1139.843094] R10: 00007f153e7a3ac0 R11: 0000000000000206 R12: 0000564c2cbf8288
[ 1139.844118] R13: 0000000000000000 R14: 0000564c2cbf7ae8 R15: 00007ffe0a3efcb8
Fixes: 9ba33339c043 ("net/mlx5e: Avoid false lock depenency warning on tc_ht")
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Eli Cohen <elic@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dbadaf1664879..243d5d7750beb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -166,6 +166,7 @@ struct mlx5_fs_chains *mlx5e_nic_chains(struct mlx5e_tc_table *tc)
* it's different than the ht->mutex here.
*/
static struct lock_class_key tc_ht_lock_key;
+static struct lock_class_key tc_ht_wq_key;
static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
static void free_flow_post_acts(struct mlx5e_tc_flow *flow);
@@ -5182,6 +5183,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
return err;
lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key);
+ lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
mapping_id = mlx5_query_nic_system_image_guid(dev);
@@ -5288,6 +5290,7 @@ int mlx5e_tc_ht_init(struct rhashtable *tc_ht)
return err;
lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key);
+ lockdep_init_map(&tc_ht->run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
return 0;
}
--
GitLab
From 6624bfeecf019de114f8100f1468d025d13b77a1 Mon Sep 17 00:00:00 2001
From: Adham Faris <afaris@nvidia.com>
Date: Thu, 12 Jan 2023 11:15:00 +0200
Subject: [PATCH 0901/1167] net/mlx5e: Remove redundant xsk pointer check in
mlx5e_mpwrq_validate_xsk
This validation function is relevant only for XSK cases, hence it
assumes to be called only with xsk != NULL.
Thus checking for invalid xsk pointer is redundant and misleads static
code analyzers.
This commit removes redundant xsk pointer check.
This solves the following smatch warning:
drivers/net/ethernet/mellanox/mlx5/core/en/params.c:481
mlx5e_mpwrq_validate_xsk() error: we previously assumed 'xsk' could be
null (see line 478)
Fixes: 6470d2e7e8ed ("net/mlx5e: xsk: Use KSM for unaligned XSK")
Signed-off-by: Adham Faris <afaris@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 585bdc8383ee2..4ad19c9812944 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -578,7 +578,6 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa
{
enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
- bool unaligned = xsk ? xsk->unaligned : false;
u16 max_mtu_pkts;
if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode))
@@ -591,7 +590,7 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa
* needed number of WQEs exceeds the maximum.
*/
max_mtu_pkts = min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE,
- mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, unaligned));
+ mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, xsk->unaligned));
if (params->log_rq_mtu_frames > max_mtu_pkts) {
mlx5_core_err(mdev, "Current RQ length %d is too big for XSK with given frame size %u\n",
1 << params->log_rq_mtu_frames, xsk->chunk_size);
--
GitLab
From f51471d1935ce1f504fce6c115ce3bfbc32032b0 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Tue, 27 Dec 2022 10:22:41 +0200
Subject: [PATCH 0902/1167] net/mlx5: E-switch, Fix setting of reserved fields
on MODIFY_SCHEDULING_ELEMENT
According to HW spec element_type, element_attributes and parent_element_id fields
should be reserved (0x0) when calling MODIFY_SCHEDULING_ELEMENT command.
This patch remove initialization of these fields when calling the command.
Fixes: bd77bf1cb595 ("net/mlx5: Add SRIOV VF max rate configuration support")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Eli Cohen <elic@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/esw/qos.c | 18 +++---------------
1 file changed, 3 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 4f8a24d84a86a..75015d370922e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -22,15 +22,13 @@ struct mlx5_esw_rate_group {
};
static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx,
- u32 parent_ix, u32 tsar_ix,
- u32 max_rate, u32 bw_share)
+ u32 tsar_ix, u32 max_rate, u32 bw_share)
{
u32 bitmask = 0;
if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
return -EOPNOTSUPP;
- MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
@@ -51,7 +49,7 @@ static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_g
int err;
err = esw_qos_tsar_config(dev, sched_ctx,
- esw->qos.root_tsar_ix, group->tsar_ix,
+ group->tsar_ix,
max_rate, bw_share);
if (err)
NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed");
@@ -67,23 +65,13 @@ static int esw_qos_vport_config(struct mlx5_eswitch *esw,
struct netlink_ext_ack *extack)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
- struct mlx5_esw_rate_group *group = vport->qos.group;
struct mlx5_core_dev *dev = esw->dev;
- u32 parent_tsar_ix;
- void *vport_elem;
int err;
if (!vport->qos.enabled)
return -EIO;
- parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
- MLX5_SET(scheduling_context, sched_ctx, element_type,
- SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
- vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
- element_attributes);
- MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-
- err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix,
+ err = esw_qos_tsar_config(dev, sched_ctx, vport->qos.esw_tsar_ix,
max_rate, bw_share);
if (err) {
esw_warn(esw->dev,
--
GitLab
From 4ddf77f9bc76092d268bd3af447d60d9cc62b652 Mon Sep 17 00:00:00 2001
From: Maor Dickman <maord@nvidia.com>
Date: Tue, 27 Dec 2022 10:51:38 +0200
Subject: [PATCH 0903/1167] net/mlx5e: QoS, Fix wrongfully setting
parent_element_id on MODIFY_SCHEDULING_ELEMENT
According to HW spec parent_element_id field should be reserved (0x0) when calling
MODIFY_SCHEDULING_ELEMENT command.
This patch remove the wrong initialization of reserved field, parent_element_id, on
mlx5_qos_update_node.
Fixes: 214baf22870c ("net/mlx5e: Support HTB offload")
Signed-off-by: Maor Dickman <maord@nvidia.com>
Reviewed-by: Eli Cohen <elic@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/htb.c | 4 ++--
drivers/net/ethernet/mellanox/mlx5/core/qos.c | 3 +--
drivers/net/ethernet/mellanox/mlx5/core/qos.h | 2 +-
3 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c
index 6dac76fa58a3f..09d441ecb9f6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c
@@ -637,7 +637,7 @@ mlx5e_htb_update_children(struct mlx5e_htb *htb, struct mlx5e_qos_node *node,
if (child->bw_share == old_bw_share)
continue;
- err_one = mlx5_qos_update_node(htb->mdev, child->hw_id, child->bw_share,
+ err_one = mlx5_qos_update_node(htb->mdev, child->bw_share,
child->max_average_bw, child->hw_id);
if (!err && err_one) {
err = err_one;
@@ -671,7 +671,7 @@ mlx5e_htb_node_modify(struct mlx5e_htb *htb, u16 classid, u64 rate, u64 ceil,
mlx5e_htb_convert_rate(htb, rate, node->parent, &bw_share);
mlx5e_htb_convert_ceil(htb, ceil, &max_average_bw);
- err = mlx5_qos_update_node(htb->mdev, node->parent->hw_id, bw_share,
+ err = mlx5_qos_update_node(htb->mdev, bw_share,
max_average_bw, node->hw_id);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Firmware error when modifying a node.");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
index 0777be24a3074..8bce730b5c5be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
@@ -62,13 +62,12 @@ int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id)
return mlx5_qos_create_inner_node(mdev, MLX5_QOS_DEFAULT_DWRR_UID, 0, 0, id);
}
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev,
u32 bw_share, u32 max_avg_bw, u32 id)
{
u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
u32 bitmask = 0;
- MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_avg_bw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/qos.h
index 125e4e47e6f71..624ce822b7f59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.h
@@ -23,7 +23,7 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id,
int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id,
u32 bw_share, u32 max_avg_bw, u32 *id);
int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id);
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share,
u32 max_avg_bw, u32 id);
int mlx5_qos_destroy_node(struct mlx5_core_dev *mdev, u32 id);
--
GitLab
From ffa99b534732f90077f346c62094cab3d1ccddce Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Thu, 12 Jan 2023 04:30:27 +0200
Subject: [PATCH 0904/1167] net/mlx5e: Set decap action based on attr for
sample
Currently decap action is set based on tunnel_id. That means it is
set unconditionally. But for decap, ct and sample actions, decap is
done before ct. No need to decap again in sample.
And the actions are set correctly when parsing. So set decap action
based on attr instead of tunnel_id.
Fixes: 2741f2230905 ("net/mlx5e: TC, Support sample offload action for tunneled traffic")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
index 1cbd2eb9d04f9..f2c2c752bd1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c
@@ -477,7 +477,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
struct mlx5e_sample_flow *sample_flow;
struct mlx5e_sample_attr *sample_attr;
struct mlx5_flow_attr *pre_attr;
- u32 tunnel_id = attr->tunnel_id;
struct mlx5_eswitch *esw;
u32 default_tbl_id;
u32 obj_id;
@@ -522,7 +521,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
restore_obj.sample.group_id = sample_attr->group_num;
restore_obj.sample.rate = sample_attr->rate;
restore_obj.sample.trunc_size = sample_attr->trunc_size;
- restore_obj.sample.tunnel_id = tunnel_id;
+ restore_obj.sample.tunnel_id = attr->tunnel_id;
err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id);
if (err)
goto err_obj_id;
@@ -548,7 +547,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
/* For decap action, do decap in the original flow table instead of the
* default flow table.
*/
- if (tunnel_id)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE;
--
GitLab
From 16bccbaa00b6127ed0ebfd77bd1f10341df8d498 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 9 Jan 2023 10:43:13 +0200
Subject: [PATCH 0905/1167] net/mlx5e: Remove optimization which prevented
update of ESN state
aso->use_cache variable introduced in commit 8c582ddfbb47 ("net/mlx5e: Handle
hardware IPsec limits events") was an optimization to skip recurrent calls
to mlx5e_ipsec_aso_query(). Such calls are possible when lifetime event is
generated:
-> mlx5e_ipsec_handle_event()
-> mlx5e_ipsec_aso_query() - first call
-> xfrm_state_check_expire()
-> mlx5e_xfrm_update_curlft()
-> mlx5e_ipsec_aso_query() - second call
However, such optimization not really effective as mlx5e_ipsec_aso_query()
is needed to be called for update ESN anyway, which was missed due to misplaced
use_cache assignment.
Fixes: cee137a63431 ("net/mlx5e: Handle ESN update events")
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 5 -----
.../net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 5 -----
2 files changed, 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index a92e19c4c499d..160f8883b93e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -122,11 +122,6 @@ struct mlx5e_ipsec_aso {
u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)];
dma_addr_t dma_addr;
struct mlx5_aso *aso;
- /* IPsec ASO caches data on every query call,
- * so in nested calls, we can use this boolean to save
- * recursive calls to mlx5e_ipsec_aso_query()
- */
- u8 use_cache : 1;
};
struct mlx5e_ipsec {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 8e3614218fc4f..aafbd7b244ee3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -320,7 +320,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
if (ret)
goto unlock;
- aso->use_cache = true;
if (attrs->esn_trigger &&
!MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) {
u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter);
@@ -333,7 +332,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
!MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) ||
!MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable))
xfrm_state_check_expire(sa_entry->x);
- aso->use_cache = false;
unlock:
spin_unlock(&sa_entry->x->lock);
@@ -458,9 +456,6 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
u8 ds_cnt;
lockdep_assert_held(&sa_entry->x->lock);
- if (aso->use_cache)
- return 0;
-
res = &mdev->mlx5e_res.hw_objs;
memset(aso->ctx, 0, sizeof(aso->ctx));
--
GitLab
From e4d38c454ae57e649f09a354d5a9dae063a26ee3 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 9 Jan 2023 10:34:25 +0200
Subject: [PATCH 0906/1167] net/mlx5e: Protect global IPsec ASO
ASO operations are global to whole IPsec as they share one DMA address
for all operations. As such all WQE operations need to be protected with
lock. In this case, it must be spinlock to allow mlx5e_ipsec_aso_query()
operate in atomic context.
Fixes: 1ed78fc03307 ("net/mlx5e: Update IPsec soft and hard limits")
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h | 2 ++
.../ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 7 ++++++-
2 files changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 160f8883b93e2..8bed9c3610754 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -122,6 +122,8 @@ struct mlx5e_ipsec_aso {
u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)];
dma_addr_t dma_addr;
struct mlx5_aso *aso;
+ /* Protect ASO WQ access, as it is global to whole IPsec */
+ spinlock_t lock;
};
struct mlx5e_ipsec {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index aafbd7b244ee3..2461462b7b991 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -396,6 +396,7 @@ int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec)
goto err_aso_create;
}
+ spin_lock_init(&aso->lock);
ipsec->nb.notifier_call = mlx5e_ipsec_event;
mlx5_notifier_register(mdev, &ipsec->nb);
@@ -454,10 +455,12 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
struct mlx5e_hw_objs *res;
struct mlx5_aso_wqe *wqe;
u8 ds_cnt;
+ int ret;
lockdep_assert_held(&sa_entry->x->lock);
res = &mdev->mlx5e_res.hw_objs;
+ spin_lock_bh(&aso->lock);
memset(aso->ctx, 0, sizeof(aso->ctx));
wqe = mlx5_aso_get_wqe(aso->aso);
ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
@@ -472,7 +475,9 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
mlx5e_ipsec_aso_copy(ctrl, data);
mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl);
- return mlx5_aso_poll_cq(aso->aso, false);
+ ret = mlx5_aso_poll_cq(aso->aso, false);
+ spin_unlock_bh(&aso->lock);
+ return ret;
}
void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry,
--
GitLab
From 7c83d1f4c5adae9583e7fca1e3e830d6b061522d Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Wed, 21 Dec 2022 11:14:37 +0200
Subject: [PATCH 0907/1167] net/mlx5: E-switch, Fix switchdev mode after
devlink reload
The cited commit removes eswitch mode none. So after devlink reload
in switchdev mode, eswitch mode is not changed. But actually eswitch
is disabled during devlink reload.
Fix it by setting eswitch mode to legacy when disabling eswitch
which is called by reload_down.
Fixes: f019679ea5f2 ("net/mlx5: E-switch, Remove dependency between sriov and eswitch mode")
Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 0dfd5742c6fe9..9daf55e90367b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1464,6 +1464,7 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
mlx5_lag_disable_change(esw->dev);
down_write(&esw->mode_lock);
mlx5_eswitch_disable_locked(esw);
+ esw->mode = MLX5_ESWITCH_LEGACY;
up_write(&esw->mode_lock);
mlx5_lag_enable_change(esw->dev);
}
--
GitLab
From 2c1e1b949024989e20907b84e11a731a50778416 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 30 Aug 2022 20:12:29 -0700
Subject: [PATCH 0908/1167] net: mlx5: eliminate anonymous module_init &
module_exit
Eliminate anonymous module_init() and module_exit(), which can lead to
confusion or ambiguity when reading System.map, crashes/oops/bugs,
or an initcall_debug log.
Give each of these init and exit functions unique driver-specific
names to eliminate the anonymous names.
Example 1: (System.map)
ffffffff832fc78c t init
ffffffff832fc79e t init
ffffffff832fc8f8 t init
Example 2: (initcall_debug log)
calling init+0x0/0x12 @ 1
initcall init+0x0/0x12 returned 0 after 15 usecs
calling init+0x0/0x60 @ 1
initcall init+0x0/0x60 returned 0 after 2 usecs
calling init+0x0/0x9a @ 1
initcall init+0x0/0x9a returned 0 after 74 usecs
Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Eli Cohen <eli@mellanox.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>
Cc: Leon Romanovsky <leon@kernel.org>
Cc: linux-rdma@vger.kernel.org
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index df134f6d32dc5..3d5f2a4b1fed4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2098,7 +2098,7 @@ static void mlx5_core_verify_params(void)
}
}
-static int __init init(void)
+static int __init mlx5_init(void)
{
int err;
@@ -2133,7 +2133,7 @@ static int __init init(void)
return err;
}
-static void __exit cleanup(void)
+static void __exit mlx5_cleanup(void)
{
mlx5e_cleanup();
mlx5_sf_driver_unregister();
@@ -2141,5 +2141,5 @@ static void __exit cleanup(void)
mlx5_unregister_debugfs();
}
-module_init(init);
-module_exit(cleanup);
+module_init(mlx5_init);
+module_exit(mlx5_cleanup);
--
GitLab
From e1fabbc83cb1dd4ba63932faa86c9cacb8bf791e Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Tue, 17 Jan 2023 18:00:45 +0100
Subject: [PATCH 0909/1167] efi: Remove Matthew Garrett as efivarfs maintainer
Matthew Garrett is still listed as a efivarfs co-maintainer, but the
email address bounces, and Matt is no longer involved in maintaining
this code.
So let's remove Matt as a efivarfs co-maintainer from MAINTAINERS.
Thanks for all the hard work!
Acked-by: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f86d02cb427a..08f75b87f03c2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7616,7 +7616,6 @@ S: Maintained
F: drivers/firmware/efi/test/
EFI VARIABLE FILESYSTEM
-M: Matthew Garrett <matthew.garrett@nebula.com>
M: Jeremy Kerr <jk@ozlabs.org>
M: Ard Biesheuvel <ardb@kernel.org>
L: linux-efi@vger.kernel.org
--
GitLab
From febb2c0d7c69c0396aa32d5ab425a4163473961a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= <jose.exposito89@gmail.com>
Date: Mon, 26 Dec 2022 13:34:56 +0100
Subject: [PATCH 0910/1167] HID: uclogic: Add support for XP-PEN Deco 01 V2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The XP-PEN Deco 01 V2 is a UGEE v2 device with a frame with 8 buttons.
Its pen has 2 buttons, supports tilt and pressure.
Add its ID in order to support the device.
Link: https://gitlab.freedesktop.org/libinput/libinput/-/issues/839
Tested-by: Mark Waddoups <mwaddoups@gmail.com>
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-ids.h | 1 +
drivers/hid/hid-uclogic-core.c | 2 ++
drivers/hid/hid-uclogic-params.c | 2 ++
3 files changed, 5 insertions(+)
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index c3735848ed5db..0f8c11842a3a5 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -1294,6 +1294,7 @@
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540 0x0075
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640 0x0094
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01 0x0042
+#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2 0x0905
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L 0x0935
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S 0x0909
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06 0x0078
diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c
index 7fa6fe04f1b26..cfbbc39807a69 100644
--- a/drivers/hid/hid-uclogic-core.c
+++ b/drivers/hid/hid-uclogic-core.c
@@ -525,6 +525,8 @@ static const struct hid_device_id uclogic_devices[] = {
USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c
index cd1233d7e2535..3c5eea3df3288 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -1655,6 +1655,8 @@ int uclogic_params_init(struct uclogic_params *params,
break;
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_PARBLO_A610_PRO):
+ case VID_PID(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2):
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L):
case VID_PID(USB_VENDOR_ID_UGEE,
--
GitLab
From 74cb485f68eb3dff6802ee446a602607b03f4fc9 Mon Sep 17 00:00:00 2001
From: Roderick Colenbrander <roderick@gaikai.com>
Date: Thu, 5 Jan 2023 17:59:07 -0800
Subject: [PATCH 0911/1167] HID: playstation: sanity check DualShock4
calibration data.
Some DualShock4 devices report invalid calibration data resulting
in kernel oopses due to division by zero during report handling.
The devices affected generally appear to be clone devices, which don't
implement all reports properly and don't populate proper calibration
data. The issue may have been seen on an official device with erased
calibration reports.
This patch prevents the crashes by essentially disabling calibration
when invalid values are detected.
Signed-off-by: Roderick Colenbrander <roderick.colenbrander@sony.com>
Tested-by: Alain Carlucci <alain.carlucci@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-playstation.c | 31 +++++++++++++++++++++++++++++++
1 file changed, 31 insertions(+)
diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c
index f399bf0d3c8cc..1eba50b45cb1e 100644
--- a/drivers/hid/hid-playstation.c
+++ b/drivers/hid/hid-playstation.c
@@ -1737,6 +1737,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
if (ds4->base.hdev->bus == BUS_USB) {
@@ -1830,6 +1831,21 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)
ds4->gyro_calib_data[2].sens_numer = speed_2x*DS4_GYRO_RES_PER_DEG_S;
ds4->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+ /*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->gyro_calib_data); i++) {
+ if (ds4->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds4->gyro_calib_data[i].abs_code);
+ ds4->gyro_calib_data[i].bias = 0;
+ ds4->gyro_calib_data[i].sens_numer = DS4_GYRO_RANGE;
+ ds4->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
/*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS4_ACC_RES_PER_G g.
@@ -1852,6 +1868,21 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)
ds4->accel_calib_data[2].sens_numer = 2*DS4_ACC_RES_PER_G;
ds4->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->accel_calib_data); i++) {
+ if (ds4->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds4->accel_calib_data[i].abs_code);
+ ds4->accel_calib_data[i].bias = 0;
+ ds4->accel_calib_data[i].sens_numer = DS4_ACC_RANGE;
+ ds4->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
--
GitLab
From ccf1e1626d37745d0a697db67407beec9ae9d4b8 Mon Sep 17 00:00:00 2001
From: Roderick Colenbrander <roderick@gaikai.com>
Date: Thu, 5 Jan 2023 17:59:08 -0800
Subject: [PATCH 0912/1167] HID: playstation: sanity check DualSense
calibration data.
Make sure calibration values are defined to prevent potential kernel
crashes. This fixes a hypothetical issue for virtual or clone devices
inspired by a similar fix for DS4.
Signed-off-by: Roderick Colenbrander <roderick.colenbrander@sony.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-playstation.c | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c
index 1eba50b45cb1e..27c40894acab4 100644
--- a/drivers/hid/hid-playstation.c
+++ b/drivers/hid/hid-playstation.c
@@ -944,6 +944,7 @@ ATTRIBUTE_GROUPS(ps_device);
static int dualsense_get_calibration_data(struct dualsense *ds)
{
+ struct hid_device *hdev = ds->base.hdev;
short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus;
short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus;
short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus;
@@ -954,6 +955,7 @@ static int dualsense_get_calibration_data(struct dualsense *ds)
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
buf = kzalloc(DS_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL);
@@ -1005,6 +1007,21 @@ static int dualsense_get_calibration_data(struct dualsense *ds)
ds->gyro_calib_data[2].sens_numer = speed_2x*DS_GYRO_RES_PER_DEG_S;
ds->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
+ /*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->gyro_calib_data); i++) {
+ if (ds->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds->gyro_calib_data[i].abs_code);
+ ds->gyro_calib_data[i].bias = 0;
+ ds->gyro_calib_data[i].sens_numer = DS_GYRO_RANGE;
+ ds->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
/*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS_ACC_RES_PER_G g.
@@ -1027,6 +1044,21 @@ static int dualsense_get_calibration_data(struct dualsense *ds)
ds->accel_calib_data[2].sens_numer = 2*DS_ACC_RES_PER_G;
ds->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->accel_calib_data); i++) {
+ if (ds->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds->accel_calib_data[i].abs_code);
+ ds->accel_calib_data[i].bias = 0;
+ ds->accel_calib_data[i].sens_numer = DS_ACC_RANGE;
+ ds->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
--
GitLab
From 96b3bb18f6cbe259ef4e0bed3135911b7e8d2af5 Mon Sep 17 00:00:00 2001
From: Peter Harliman Liem <pliem@maxlinear.com>
Date: Thu, 5 Jan 2023 11:05:51 +0800
Subject: [PATCH 0913/1167] dmaengine: lgm: Move DT parsing after
initialization
ldma_cfg_init() will parse DT to retrieve certain configs.
However, that is called before ldma_dma_init_vXX(), which
will make some initialization to channel configs. It will
thus incorrectly overwrite certain configs that are declared
in DT.
To fix that, we move DT parsing after initialization.
Function name is renamed to better represent what it does.
Fixes: 32d31c79a1a4 ("dmaengine: Add Intel LGM SoC DMA support.")
Signed-off-by: Peter Harliman Liem <pliem@maxlinear.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/afef6fc1ed20098b684e0d53737d69faf63c125f.1672887183.git.pliem@maxlinear.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/lgm/lgm-dma.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/dma/lgm/lgm-dma.c b/drivers/dma/lgm/lgm-dma.c
index 9b9184f964be3..1709d159af7e0 100644
--- a/drivers/dma/lgm/lgm-dma.c
+++ b/drivers/dma/lgm/lgm-dma.c
@@ -914,7 +914,7 @@ static void ldma_dev_init(struct ldma_dev *d)
}
}
-static int ldma_cfg_init(struct ldma_dev *d)
+static int ldma_parse_dt(struct ldma_dev *d)
{
struct fwnode_handle *fwnode = dev_fwnode(d->dev);
struct ldma_port *p;
@@ -1661,10 +1661,6 @@ static int intel_ldma_probe(struct platform_device *pdev)
p->ldev = d;
}
- ret = ldma_cfg_init(d);
- if (ret)
- return ret;
-
dma_dev->dev = &pdev->dev;
ch_mask = (unsigned long)d->channels_mask;
@@ -1675,6 +1671,10 @@ static int intel_ldma_probe(struct platform_device *pdev)
ldma_dma_init_v3X(j, d);
}
+ ret = ldma_parse_dt(d);
+ if (ret)
+ return ret;
+
dma_dev->device_alloc_chan_resources = ldma_alloc_chan_resources;
dma_dev->device_free_chan_resources = ldma_free_chan_resources;
dma_dev->device_terminate_all = ldma_terminate_all;
--
GitLab
From 6437a549ae178a3f5a5c03e983f291ebcdc2bbc7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jan 2023 17:44:43 +0100
Subject: [PATCH 0914/1167] drm/panfrost: fix GENERIC_ATOMIC64 dependency
On ARMv5 and earlier, a randconfig build can still run into
WARNING: unmet direct dependencies detected for IOMMU_IO_PGTABLE_LPAE
Depends on [n]: IOMMU_SUPPORT [=y] && (ARM [=y] || ARM64 || COMPILE_TEST [=y]) && !GENERIC_ATOMIC64 [=y]
Selected by [y]:
- DRM_PANFROST [=y] && HAS_IOMEM [=y] && DRM [=y] && (ARM [=y] || ARM64 || COMPILE_TEST [=y] && !GENERIC_ATOMIC64 [=y]) && MMU [=y]
Rework the dependencies to always require a working cmpxchg64.
Fixes: db594ba3fcf9 ("drm/panfrost: depend on !GENERIC_ATOMIC64 when using COMPILE_TEST")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117164456.1591901-1-arnd@kernel.org
---
drivers/gpu/drm/panfrost/Kconfig | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig
index 079600328be18..e6403a9d66ade 100644
--- a/drivers/gpu/drm/panfrost/Kconfig
+++ b/drivers/gpu/drm/panfrost/Kconfig
@@ -3,7 +3,8 @@
config DRM_PANFROST
tristate "Panfrost (DRM support for ARM Mali Midgard/Bifrost GPUs)"
depends on DRM
- depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64)
+ depends on ARM || ARM64 || COMPILE_TEST
+ depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE
depends on MMU
select DRM_SCHED
select IOMMU_SUPPORT
--
GitLab
From 6795e558e9cc6123c24e2100a2ebe88e58a792bc Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 6 Jan 2023 08:04:46 -0800
Subject: [PATCH 0915/1167] perf/x86/intel: Add Emerald Rapids
From core PMU's perspective, Emerald Rapids is the same as the Sapphire
Rapids. The only difference is the event list, which will be
supported in the perf tool later.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230106160449.3566477-1-kan.liang@linux.intel.com
---
arch/x86/events/intel/core.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index dfd2c124cdf80..bafdc2be479ac 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -6339,6 +6339,7 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_SAPPHIRERAPIDS_X:
+ case INTEL_FAM6_EMERALDRAPIDS_X:
pmem = true;
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
--
GitLab
From 5a8a05f165fb18d37526062419774d9088c2a9b9 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 6 Jan 2023 08:04:47 -0800
Subject: [PATCH 0916/1167] perf/x86/intel/cstate: Add Emerald Rapids
From the perspective of Intel cstate residency counters,
Emerald Rapids is the same as the Sapphire Rapids and Ice Lake.
Add Emerald Rapids model.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230106160449.3566477-2-kan.liang@linux.intel.com
---
arch/x86/events/intel/cstate.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 3019fb1926e35..551741e79e038 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -677,6 +677,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates),
--
GitLab
From 57054fe516d59d03a7bcf1888e82479ccc244f87 Mon Sep 17 00:00:00 2001
From: "Shawn.Shao" <shawn.shao@jaguarmicro.com>
Date: Thu, 12 Jan 2023 13:58:02 +0800
Subject: [PATCH 0917/1167] Add exception protection processing for vd in
axi_chan_handle_err function
Since there is no protection for vd, a kernel panic will be
triggered here in exceptional cases.
You can refer to the processing of axi_chan_block_xfer_complete function
The triggered kernel panic is as follows:
[ 67.848444] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000060
[ 67.848447] Mem abort info:
[ 67.848449] ESR = 0x96000004
[ 67.848451] EC = 0x25: DABT (current EL), IL = 32 bits
[ 67.848454] SET = 0, FnV = 0
[ 67.848456] EA = 0, S1PTW = 0
[ 67.848458] Data abort info:
[ 67.848460] ISV = 0, ISS = 0x00000004
[ 67.848462] CM = 0, WnR = 0
[ 67.848465] user pgtable: 4k pages, 48-bit VAs, pgdp=00000800c4c0b000
[ 67.848468] [0000000000000060] pgd=0000000000000000, p4d=0000000000000000
[ 67.848472] Internal error: Oops: 96000004 [#1] SMP
[ 67.848475] Modules linked in: dmatest
[ 67.848479] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.10.100-emu_x2rc+ #11
[ 67.848483] pstate: 62000085 (nZCv daIf -PAN -UAO +TCO BTYPE=--)
[ 67.848487] pc : axi_chan_handle_err+0xc4/0x230
[ 67.848491] lr : axi_chan_handle_err+0x30/0x230
[ 67.848493] sp : ffff0803fe55ae50
[ 67.848495] x29: ffff0803fe55ae50 x28: ffff800011212200
[ 67.848500] x27: ffff0800c42c0080 x26: ffff0800c097c080
[ 67.848504] x25: ffff800010d33880 x24: ffff80001139d850
[ 67.848508] x23: ffff0800c097c168 x22: 0000000000000000
[ 67.848512] x21: 0000000000000080 x20: 0000000000002000
[ 67.848517] x19: ffff0800c097c080 x18: 0000000000000000
[ 67.848521] x17: 0000000000000000 x16: 0000000000000000
[ 67.848525] x15: 0000000000000000 x14: 0000000000000000
[ 67.848529] x13: 0000000000000000 x12: 0000000000000040
[ 67.848533] x11: ffff0800c0400248 x10: ffff0800c040024a
[ 67.848538] x9 : ffff800010576cd4 x8 : ffff0800c0400270
[ 67.848542] x7 : 0000000000000000 x6 : ffff0800c04003e0
[ 67.848546] x5 : ffff0800c0400248 x4 : ffff0800c4294480
[ 67.848550] x3 : dead000000000100 x2 : dead000000000122
[ 67.848555] x1 : 0000000000000100 x0 : ffff0800c097c168
[ 67.848559] Call trace:
[ 67.848562] axi_chan_handle_err+0xc4/0x230
[ 67.848566] dw_axi_dma_interrupt+0xf4/0x590
[ 67.848569] __handle_irq_event_percpu+0x60/0x220
[ 67.848573] handle_irq_event+0x64/0x120
[ 67.848576] handle_fasteoi_irq+0xc4/0x220
[ 67.848580] __handle_domain_irq+0x80/0xe0
[ 67.848583] gic_handle_irq+0xc0/0x138
[ 67.848585] el1_irq+0xc8/0x180
[ 67.848588] arch_cpu_idle+0x14/0x2c
[ 67.848591] default_idle_call+0x40/0x16c
[ 67.848594] do_idle+0x1f0/0x250
[ 67.848597] cpu_startup_entry+0x2c/0x60
[ 67.848600] rest_init+0xc0/0xcc
[ 67.848603] arch_call_rest_init+0x14/0x1c
[ 67.848606] start_kernel+0x4cc/0x500
[ 67.848610] Code: eb0002ff 9a9f12d6 f2fbd5a2 f2fbd5a3 (a94602c1)
[ 67.848613] ---[ end trace 585a97036f88203a ]---
Signed-off-by: Shawn.Shao <shawn.shao@jaguarmicro.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230112055802.1764-1-shawn.shao@jaguarmicro.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index a183d93bd7e29..bf85aa0979ecb 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -1018,6 +1018,11 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
/* The bad descriptor currently is in the head of vc list */
vd = vchan_next_desc(&chan->vc);
+ if (!vd) {
+ dev_err(chan2dev(chan), "BUG: %s, IRQ with no descriptors\n",
+ axi_chan_name(chan));
+ goto out;
+ }
/* Remove the completed descriptor from issued list */
list_del(&vd->node);
@@ -1032,6 +1037,7 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status)
/* Try to restart the controller */
axi_chan_start_first_queued(chan);
+out:
spin_unlock_irqrestore(&chan->vc.lock, flags);
}
--
GitLab
From 9c7e355ccbb33d239360c876dbe49ad5ade65b47 Mon Sep 17 00:00:00 2001
From: Mohan Kumar <mkumard@nvidia.com>
Date: Mon, 2 Jan 2023 12:18:44 +0530
Subject: [PATCH 0918/1167] dmaengine: tegra210-adma: fix global intr clear
The current global interrupt clear programming register offset
was not correct. Fix the programming with right offset
Fixes: ded1f3db4cd6 ("dmaengine: tegra210-adma: prepare for supporting newer Tegra chips")
Cc: stable@vger.kernel.org
Signed-off-by: Mohan Kumar <mkumard@nvidia.com>
Link: https://lore.kernel.org/r/20230102064844.31306-1-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/tegra210-adma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index ae39b52012b2f..79da93cc77b64 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -221,7 +221,7 @@ static int tegra_adma_init(struct tegra_adma *tdma)
int ret;
/* Clear any interrupts */
- tdma_write(tdma, tdma->cdata->global_int_clear, 0x1);
+ tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1);
/* Assert soft reset */
tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1);
--
GitLab
From f3dc1b3b4750851a94212dba249703dd0e50bb20 Mon Sep 17 00:00:00 2001
From: Koba Ko <koba.ko@canonical.com>
Date: Thu, 1 Dec 2022 11:00:50 +0800
Subject: [PATCH 0919/1167] dmaengine: Fix double increment of client_count in
dma_chan_get()
The first time dma_chan_get() is called for a channel the channel
client_count is incorrectly incremented twice for public channels,
first in balance_ref_count(), and again prior to returning. This
results in an incorrect client count which will lead to the
channel resources not being freed when they should be. A simple
test of repeated module load and unload of async_tx on a Dell
Power Edge R7425 also shows this resulting in a kref underflow
warning.
[ 124.329662] async_tx: api initialized (async)
[ 129.000627] async_tx: api initialized (async)
[ 130.047839] ------------[ cut here ]------------
[ 130.052472] refcount_t: underflow; use-after-free.
[ 130.057279] WARNING: CPU: 3 PID: 19364 at lib/refcount.c:28
refcount_warn_saturate+0xba/0x110
[ 130.065811] Modules linked in: async_tx(-) rfkill intel_rapl_msr
intel_rapl_common amd64_edac edac_mce_amd ipmi_ssif kvm_amd dcdbas kvm
mgag200 drm_shmem_helper acpi_ipmi irqbypass drm_kms_helper ipmi_si
syscopyarea sysfillrect rapl pcspkr ipmi_devintf sysimgblt fb_sys_fops
k10temp i2c_piix4 ipmi_msghandler acpi_power_meter acpi_cpufreq vfat
fat drm fuse xfs libcrc32c sd_mod t10_pi sg ahci crct10dif_pclmul
libahci crc32_pclmul crc32c_intel ghash_clmulni_intel igb megaraid_sas
i40e libata i2c_algo_bit ccp sp5100_tco dca dm_mirror dm_region_hash
dm_log dm_mod [last unloaded: async_tx]
[ 130.117361] CPU: 3 PID: 19364 Comm: modprobe Kdump: loaded Not
tainted 5.14.0-185.el9.x86_64 #1
[ 130.126091] Hardware name: Dell Inc. PowerEdge R7425/02MJ3T, BIOS
1.18.0 01/17/2022
[ 130.133806] RIP: 0010:refcount_warn_saturate+0xba/0x110
[ 130.139041] Code: 01 01 e8 6d bd 55 00 0f 0b e9 72 9d 8a 00 80 3d
26 18 9c 01 00 75 85 48 c7 c7 f8 a3 03 9d c6 05 16 18 9c 01 01 e8 4a
bd 55 00 <0f> 0b e9 4f 9d 8a 00 80 3d 01 18 9c 01 00 0f 85 5e ff ff ff
48 c7
[ 130.157807] RSP: 0018:ffffbf98898afe68 EFLAGS: 00010286
[ 130.163036] RAX: 0000000000000000 RBX: ffff9da06028e598 RCX: 0000000000000000
[ 130.170172] RDX: ffff9daf9de26480 RSI: ffff9daf9de198a0 RDI: ffff9daf9de198a0
[ 130.177316] RBP: ffff9da7cddf3970 R08: 0000000000000000 R09: 00000000ffff7fff
[ 130.184459] R10: ffffbf98898afd00 R11: ffffffff9d9e8c28 R12: ffff9da7cddf1970
[ 130.191596] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[ 130.198739] FS: 00007f646435c740(0000) GS:ffff9daf9de00000(0000)
knlGS:0000000000000000
[ 130.206832] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 130.212586] CR2: 00007f6463b214f0 CR3: 00000008ab98c000 CR4: 00000000003506e0
[ 130.219729] Call Trace:
[ 130.222192] <TASK>
[ 130.224305] dma_chan_put+0x10d/0x110
[ 130.227988] dmaengine_put+0x7a/0xa0
[ 130.231575] __do_sys_delete_module.constprop.0+0x178/0x280
[ 130.237157] ? syscall_trace_enter.constprop.0+0x145/0x1d0
[ 130.242652] do_syscall_64+0x5c/0x90
[ 130.246240] ? exc_page_fault+0x62/0x150
[ 130.250178] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 130.255243] RIP: 0033:0x7f6463a3f5ab
[ 130.258830] Code: 73 01 c3 48 8b 0d 75 a8 1b 00 f7 d8 64 89 01 48
83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00
00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 45 a8 1b 00 f7 d8 64 89
01 48
[ 130.277591] RSP: 002b:00007fff22f972c8 EFLAGS: 00000206 ORIG_RAX:
00000000000000b0
[ 130.285164] RAX: ffffffffffffffda RBX: 000055b6786edd40 RCX: 00007f6463a3f5ab
[ 130.292303] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 000055b6786edda8
[ 130.299443] RBP: 000055b6786edd40 R08: 0000000000000000 R09: 0000000000000000
[ 130.306584] R10: 00007f6463b9eac0 R11: 0000000000000206 R12: 000055b6786edda8
[ 130.313731] R13: 0000000000000000 R14: 000055b6786edda8 R15: 00007fff22f995f8
[ 130.320875] </TASK>
[ 130.323081] ---[ end trace eff7156d56b5cf25 ]---
cat /sys/class/dma/dma0chan*/in_use would get the wrong result.
2
2
2
Fixes: d2f4f99db3e9 ("dmaengine: Rework dma_chan_get")
Signed-off-by: Koba Ko <koba.ko@canonical.com>
Reviewed-by: Jie Hai <haijie1@huawei.com>
Test-by: Jie Hai <haijie1@huawei.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Joel Savitz <jsavitz@redhat.com>
Link: https://lore.kernel.org/r/20221201030050.978595-1-koba.ko@canonical.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/dmaengine.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index c741b6431958c..8a6e6b60d66f3 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -451,7 +451,8 @@ static int dma_chan_get(struct dma_chan *chan)
/* The channel is already in use, update client count */
if (chan->client_count) {
__module_get(owner);
- goto out;
+ chan->client_count++;
+ return 0;
}
if (!try_module_get(owner))
@@ -470,11 +471,11 @@ static int dma_chan_get(struct dma_chan *chan)
goto err_out;
}
+ chan->client_count++;
+
if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask))
balance_ref_count(chan);
-out:
- chan->client_count++;
return 0;
err_out:
--
GitLab
From 1417f59ac0b02130ee56c0c50794b9b257be3d17 Mon Sep 17 00:00:00 2001
From: Hui Wang <hui.wang@canonical.com>
Date: Wed, 30 Nov 2022 17:08:00 +0800
Subject: [PATCH 0920/1167] dmaengine: imx-sdma: Fix a possible memory leak in
sdma_transfer_init
If the function sdma_load_context() fails, the sdma_desc will be
freed, but the allocated desc->bd is forgot to be freed.
We already met the sdma_load_context() failure case and the log as
below:
[ 450.699064] imx-sdma 30bd0000.dma-controller: Timeout waiting for CH0 ready
...
In this case, the desc->bd will not be freed without this change.
Signed-off-by: Hui Wang <hui.wang@canonical.com>
Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Link: https://lore.kernel.org/r/20221130090800.102035-1-hui.wang@canonical.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/imx-sdma.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index fbea5f62dd98b..b926abe4fa43a 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1521,10 +1521,12 @@ static struct sdma_desc *sdma_transfer_init(struct sdma_channel *sdmac,
sdma_config_ownership(sdmac, false, true, false);
if (sdma_load_context(sdmac))
- goto err_desc_out;
+ goto err_bd_out;
return desc;
+err_bd_out:
+ sdma_free_bd(desc);
err_desc_out:
kfree(desc);
err_out:
--
GitLab
From 7f2d4cdd2f32b66c452c958698fc287de4f68283 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Jan 2023 10:33:22 -0300
Subject: [PATCH 0921/1167] tools kvm headers arm64: Update KVM header from the
kernel sources
To pick the changes from:
9cb1096f8590bc59 ("KVM: arm64: Enable ring-based dirty memory tracking")
That doesn't result in any changes in tooling (built on a Libre Computer
Firefly ROC-RK3399-PC-V1.1-A running Ubuntu 22.04), only addresses this
perf build warning:
Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h'
diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lore.kernel.org/lkml/Y8fmIT5PIfGaZuwa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/arm64/include/uapi/asm/kvm.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 316917b987070..a7a857f1784d8 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -43,6 +43,7 @@
#define __KVM_HAVE_VCPU_EVENTS
#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
--
GitLab
From 8c51e8f4e9ec6b404a10c84055b8454eba9f42fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Jan 2023 09:38:16 -0300
Subject: [PATCH 0922/1167] tools headers arm64: Sync arm64's cputype.h with
the kernel sources
To get the changes in:
decb17aeb8fa2148 ("KVM: arm64: vgic: Add Apple M2 cpus to the list of broken SEIS implementations")
07e39e60bbf0ccd5 ("arm64: Add Cortex-715 CPU part definition")
8ec8490a1950efec ("arm64: Fix bit-shifting UB in the MIDR_CPU_MODEL() macro")
That addresses this perf build warning:
Warning: Kernel ABI header at 'tools/arch/arm64/include/asm/cputype.h' differs from latest version at 'arch/arm64/include/asm/cputype.h'
diff -u tools/arch/arm64/include/asm/cputype.h arch/arm64/include/asm/cputype.h
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: D Scott Phillips <scott@os.amperecomputing.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Link: http://lore.kernel.org/lkml/Y8fvEGCGn+227qW0@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/arm64/include/asm/cputype.h | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index abc418650fec0..683ca3af40848 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -41,7 +41,7 @@
(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
#define MIDR_CPU_MODEL(imp, partnum) \
- (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \
+ ((_AT(u32, imp) << MIDR_IMPLEMENTOR_SHIFT) | \
(0xf << MIDR_ARCHITECTURE_SHIFT) | \
((partnum) << MIDR_PARTNUM_SHIFT))
@@ -80,6 +80,7 @@
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
#define ARM_CPU_PART_CORTEX_A710 0xD47
+#define ARM_CPU_PART_CORTEX_A715 0xD4D
#define ARM_CPU_PART_CORTEX_X2 0xD48
#define ARM_CPU_PART_NEOVERSE_N2 0xD49
#define ARM_CPU_PART_CORTEX_A78C 0xD4B
@@ -123,6 +124,8 @@
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
@@ -142,6 +145,7 @@
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
+#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
@@ -175,6 +179,8 @@
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
--
GitLab
From d352588bbc990ba51f925f124946c42e604c502e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Jan 2023 10:12:23 -0300
Subject: [PATCH 0923/1167] perf beauty: Update copy of linux/socket.h with the
kernel sources
To pick the changes in:
b5f0de6df6dce8d6 ("net: dev: Convert sa_data to flexible array in struct sockaddr")
That don't result in any changes in the tables generated from that
header.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/perf/trace/beauty/include/linux/socket.h' differs from latest version at 'include/linux/socket.h'
diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/trace/beauty/include/linux/socket.h | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index de3701a2a2129..13c3a237b9c93 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -33,7 +33,10 @@ typedef __kernel_sa_family_t sa_family_t;
struct sockaddr {
sa_family_t sa_family; /* address family, AF_xxx */
- char sa_data[14]; /* 14 bytes of protocol address */
+ union {
+ char sa_data_min[14]; /* Minimum 14 bytes of protocol address */
+ DECLARE_FLEX_ARRAY(char, sa_data);
+ };
};
struct linger {
--
GitLab
From c905ecfbb8e5d54bbcdd2a1706b925baf1728cfe Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Jan 2023 10:27:48 -0300
Subject: [PATCH 0924/1167] tools headers: Syncronize linux/build_bug.h with
the kernel sources
To pick up the changes in:
07a368b3f55a79d3 ("bug: introduce ASSERT_STRUCT_OFFSET")
This cset only introduces a build time assert macro, that may be useful
at some point for tooling, for now it silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/linux/build_bug.h' differs from latest version at 'include/linux/build_bug.h'
diff -u tools/include/linux/build_bug.h include/linux/build_bug.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: http://lore.kernel.org/lkml/Y8f0jqQFYDAOBkHx@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/linux/build_bug.h | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index cc7070c7439ba..b4898ff085ded 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -79,4 +79,13 @@
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
#endif // static_assert
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
#endif /* _LINUX_BUILD_BUG_H */
--
GitLab
From 85c44913969bd27f15229c39383da1291800d7e9 Mon Sep 17 00:00:00 2001
From: Sohom Datta <sohomdatta1@gmail.com>
Date: Sun, 4 Dec 2022 16:28:35 +0530
Subject: [PATCH 0925/1167] perf expr: Prevent normalize() from reading into
undefined memory in the expression lexer
The current implementation does not account for a trailing backslash
followed by a null-byte.
If a null-byte is encountered following a backslash, normalize() will
continue reading (and potentially writing) into garbage memory ignoring
the EOS null-byte.
Signed-off-by: Sohom Datta <sohomdatta1+git@gmail.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20221204105836.1012885-1-sohomdatta1+git@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/expr.l | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 0168a96373309..d47de5f270a8e 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -42,8 +42,11 @@ static char *normalize(char *str, int runtime)
char *dst = str;
while (*str) {
- if (*str == '\\')
+ if (*str == '\\') {
*dst++ = *++str;
+ if (!*str)
+ break;
+ }
else if (*str == '?') {
char *paramval;
int i = 0;
--
GitLab
From 4b21b3e7ef86aff7ff961bf28b2c17ee4204da16 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Mon, 16 Jan 2023 10:31:30 +0530
Subject: [PATCH 0926/1167] perf buildid-cache: Fix the file mode with
copyfile() while adding file to build-id cache
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The test "build id cache operations" fails on powerpc as below:
Adding 5a0fd882b53084224ba47b624c55a469 ./tests/shell/../pe-file.exe: Ok
build id: 5a0fd882b53084224ba47b624c55a469
link: /tmp/perf.debug.ZTu/.build-id/5a/0fd882b53084224ba47b624c55a469
file: /tmp/perf.debug.ZTu/.build-id/5a/../../root/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf
failed: file /tmp/perf.debug.ZTu/.build-id/5a/../../root/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf does not exist
test child finished with -1
---- end ----
build id cache operations: FAILED!
The failing test is when trying to add pe-file.exe to build id cache.
'perf buildid-cache' can be used to add/remove/manage files from the
build-id cache. "-a" option is used to add a file to the build-id cache.
Simple command to do so for a PE exe file:
# ls -ltr tests/pe-file.exe
-rw-r--r--. 1 root root 75595 Jan 10 23:35 tests/pe-file.exe
The file is in home directory.
# mkdir /tmp/perf.debug.TeY1
# perf --buildid-dir /tmp/perf.debug.TeY1 buildid-cache -v -a tests/pe-file.exe
The above will create ".build-id" folder in build id directory, which is
/tmp/perf.debug.TeY1. Also adds file to this folder under build id.
Example:
# ls -ltr /tmp/perf.debug.TeY1/.build-id/5a/0fd882b53084224ba47b624c55a469/
total 76
-rw-r--r--. 1 root root 0 Jan 11 00:38 probes
-rwxr-xr-x. 1 root root 75595 Jan 11 00:38 elf
We can see in the results that file mode for original file and file in
build id directory is different. ie, build id file has executable
permission whereas original file doesn’t have.
The code path and function (build_id_cache__add to add a file to the
cache is in "util/build-id.c". In build_id_cache__add() function, it
first attempts to link the original file to destination cache folder.
If linking the file fails (which can happen if the destination and
source is on a different mount points), it will copy the file to
destination. Here copyfile() routine explicitly uses mode as "755" and
hence file in the destination will have executable permission.
Code snippet:
if (link(realname, filename) && errno != EEXIST && copyfile(name, filename))
strace logs:
172285 link("/home/<user_name>/linux/tools/perf/tests/pe-file.exe", "/tmp/perf.debug.TeY1/home/<user_name>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf") = -1 EXDEV (Invalid cross-device link)
172285 newfstatat(AT_FDCWD, "tests/pe-file.exe", {st_mode=S_IFREG|0644, st_size=75595, ...}, 0) = 0
172285 openat(AT_FDCWD, "/tmp/perf.debug.TeY1/home/<user_name>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/.elf.KbAnsl", O_RDWR|O_CREAT|O_EXCL, 0600) = 3
172285 fchmod(3, 0755) = 0
172285 openat(AT_FDCWD, "tests/pe-file.exe", O_RDONLY) = 4
172285 mmap(NULL, 75595, PROT_READ, MAP_PRIVATE, 4, 0) = 0x7fffa5cd0000
172285 pwrite64(3, "MZ\220\0\3\0\0\0\4\0\0\0\377\377\0\0\270\0\0\0\0\0\0\0@\0\0\0\0\0\0\0"..., 75595, 0) = 75595
Whereas if the link succeeds, it succeeds in the first attempt itself
and the file in the build-id dir will have same permission as original
file.
Example, above uses /tmp. Instead if we use "--buildid-dir /home/build",
linking will work here since mount points are same. Hence the
destination file will not have executable permission.
Since the testcase "tests/shell/buildid.sh" always looks for executable
file, test fails in powerpc environment when test is run from /root.
The patch adds a change in build_id_cache__add() to use copyfile_mode()
which also passes the file’s original mode as argument. This way the
destination file mode also will be same as original file.
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230116050131.17221-1-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/build-id.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a839b30c981b7..ea9c083ab1e3f 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -715,9 +715,13 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam
} else if (nsi && nsinfo__need_setns(nsi)) {
if (copyfile_ns(name, filename, nsi))
goto out_free;
- } else if (link(realname, filename) && errno != EEXIST &&
- copyfile(name, filename))
- goto out_free;
+ } else if (link(realname, filename) && errno != EEXIST) {
+ struct stat f_stat;
+
+ if (!(stat(name, &f_stat) < 0) &&
+ copyfile_mode(name, filename, f_stat.st_mode))
+ goto out_free;
+ }
}
/* Some binaries are stripped, but have .debug files with their symbol
--
GitLab
From 3d9c07c4cfc06cf7927cd00c04dffd1165d03c53 Mon Sep 17 00:00:00 2001
From: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Date: Mon, 16 Jan 2023 10:31:31 +0530
Subject: [PATCH 0927/1167] perf test build-id: Fix test check for PE file
Perf test "build id cache operations" fails for PE executable. Logs
below from powerpc system. Same is observed on x86 as well.
<<>>
Adding 5a0fd882b53084224ba47b624c55a469 ./tests/shell/../pe-file.exe: Ok
build id: 5a0fd882b53084224ba47b624c55a469
link: /tmp/perf.debug.w0V/.build-id/5a/0fd882b53084224ba47b624c55a469
file: /tmp/perf.debug.w0V/.build-id/5a/../../root/<user>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf
failed: file /tmp/perf.debug.w0V/.build-id/5a/../../root/<user>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf does not exist
test child finished with -1
---- end ----
build id cache operations: FAILED!
<<>>
The test tries to do:
<<>>
mkdir /tmp/perf.debug.TeY1
perf --buildid-dir /tmp/perf.debug.TeY1 buildid-cache -v -a ./tests/shell/../pe-file.exe
<<>>
The option "--buildid-dir" sets the build id cache directory as
/tmp/perf.debug.TeY1. The option given to buildid-cahe, ie "-a
./tests/shell/../pe-file.exe", is to add the pe-file.exe to the cache.
The testcase, sets buildid-dir and adds the file: pe-file.exe to build
id cache. To check if the command is run successfully, "check" function
looks for presence of the file in buildid cache directory. But the check
here expects the added file to be executable. Snippet below:
<<>>
if [ ! -x $file ]; then
echo "failed: file ${file} does not exist"
exit 1
fi
<<>>
The buildid test is done for sha1 binary, md5 binary and also for PE
file. The first two binaries are created at runtime by compiling with
"--build-id" option and hence the check for sha1/md5 test should use [ !
-x ]. But in case of PE file, the permission for this input file is
rw-r--r-- Hence the file added to build id cache has same permissoin
Original file:
ls tests/pe-file.exe | xargs stat --printf "%n %A \n"
tests/pe-file.exe -rw-r--r--
buildid cache file:
ls /tmp/perf.debug.w0V/.build-id/5a/../../root/<user>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf | xargs stat --printf "%n %A \n"
/tmp/perf.debug.w0V/.build-id/5a/../../root/<user>/linux/tools/perf/tests/pe-file.exe/5a0fd882b53084224ba47b624c55a469/elf -rw-r--r--
Fix the test to match with the permission of original file in case of FE
file. ie if the "tests/pe-file.exe" file is not having exec permission,
just check for existence of the buildid file using [ ! -e <file> ]
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Disha Goel <disgoel@linux.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20230116050131.17221-2-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/shell/buildid.sh | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/tools/perf/tests/shell/buildid.sh b/tools/perf/tests/shell/buildid.sh
index f05670d1e39eb..aaf851108ca35 100755
--- a/tools/perf/tests/shell/buildid.sh
+++ b/tools/perf/tests/shell/buildid.sh
@@ -77,7 +77,20 @@ check()
file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf
echo "file: ${file}"
- if [ ! -x $file ]; then
+ # Check for file permission of original file
+ # in case of pe-file.exe file
+ echo $1 | grep ".exe"
+ if [ $? -eq 0 ]; then
+ if [ -x $1 -a ! -x $file ]; then
+ echo "failed: file ${file} executable does not exist"
+ exit 1
+ fi
+
+ if [ ! -x $file -a ! -e $file ]; then
+ echo "failed: file ${file} does not exist"
+ exit 1
+ fi
+ elif [ ! -x $file ]; then
echo "failed: file ${file} does not exist"
exit 1
fi
--
GitLab
From 7b90f5a665acd46efbbfa677a3a3a18d01ad6487 Mon Sep 17 00:00:00 2001
From: Robert Hancock <robert.hancock@calian.com>
Date: Mon, 16 Jan 2023 15:41:33 -0600
Subject: [PATCH 0928/1167] net: macb: fix PTP TX timestamp failure due to
packet padding
PTP TX timestamp handling was observed to be broken with this driver
when using the raw Layer 2 PTP encapsulation. ptp4l was not receiving
the expected TX timestamp after transmitting a packet, causing it to
enter a failure state.
The problem appears to be due to the way that the driver pads packets
which are smaller than the Ethernet minimum of 60 bytes. If headroom
space was available in the SKB, this caused the driver to move the data
back to utilize it. However, this appears to cause other data references
in the SKB to become inconsistent. In particular, this caused the
ptp_one_step_sync function to later (in the TX completion path) falsely
detect the packet as a one-step SYNC packet, even when it was not, which
caused the TX timestamp to not be processed when it should be.
Using the headroom for this purpose seems like an unnecessary complexity
as this is not a hot path in the driver, and in most cases it appears
that there is sufficient tailroom to not require using the headroom
anyway. Remove this usage of headroom to prevent this inconsistency from
occurring and causing other problems.
Fixes: 653e92a9175e ("net: macb: add support for padding and fcs computation")
Signed-off-by: Robert Hancock <robert.hancock@calian.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Claudiu Beznea <claudiu.beznea@microchip.com> # on SAMA7G5
Reviewed-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/cadence/macb_main.c | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 95667b979fab4..72e42820713df 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2187,7 +2187,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) ||
skb_is_nonlinear(*skb);
int padlen = ETH_ZLEN - (*skb)->len;
- int headroom = skb_headroom(*skb);
int tailroom = skb_tailroom(*skb);
struct sk_buff *nskb;
u32 fcs;
@@ -2201,9 +2200,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
/* FCS could be appeded to tailroom. */
if (tailroom >= ETH_FCS_LEN)
goto add_fcs;
- /* FCS could be appeded by moving data to headroom. */
- else if (!cloned && headroom + tailroom >= ETH_FCS_LEN)
- padlen = 0;
/* No room for FCS, need to reallocate skb. */
else
padlen = ETH_FCS_LEN;
@@ -2212,10 +2208,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
padlen += ETH_FCS_LEN;
}
- if (!cloned && headroom + tailroom >= padlen) {
- (*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len);
- skb_set_tail_pointer(*skb, (*skb)->len);
- } else {
+ if (cloned || tailroom < padlen) {
nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
--
GitLab
From d71ebe8114b4bf622804b810f5e274069060a174 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 17 Jan 2023 11:47:07 +0800
Subject: [PATCH 0929/1167] virtio-net: correctly enable callback during
start_xmit
Commit a7766ef18b33("virtio_net: disable cb aggressively") enables
virtqueue callback via the following statement:
do {
if (use_napi)
virtqueue_disable_cb(sq->vq);
free_old_xmit_skbs(sq, false);
} while (use_napi && kick &&
unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
When NAPI is used and kick is false, the callback won't be enabled
here. And when the virtqueue is about to be full, the tx will be
disabled, but we still don't enable tx interrupt which will cause a TX
hang. This could be observed when using pktgen with burst enabled.
TO be consistent with the logic that tries to disable cb only for
NAPI, fixing this by trying to enable delayed callback only when NAPI
is enabled when the queue is about to be full.
Fixes: a7766ef18b33 ("virtio_net: disable cb aggressively")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/virtio_net.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7723b2a49d8ec..18b3de854aeb9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1877,8 +1877,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
*/
if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
netif_stop_subqueue(dev, qnum);
- if (!use_napi &&
- unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
+ if (use_napi) {
+ if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+ virtqueue_napi_schedule(&sq->napi, sq->vq);
+ } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
/* More just got used, free them then recheck. */
free_old_xmit_skbs(sq, false);
if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
--
GitLab
From 0e3b175f079247f0d40d2ab695999c309d3a7498 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 16 Jan 2023 13:37:01 -0600
Subject: [PATCH 0930/1167] gpiolib: acpi: Allow ignoring wake capability on
pins that aren't in _AEI
Using the `ignore_wake` quirk or module parameter doesn't work for any pin
that has been specified in the _CRS instead of _AEI.
Extend the `acpi_gpio_irq_is_wake` check to cover both places.
Suggested-by: Raul Rangel <rrangel@chromium.org>
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1722#note_1722335
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpiolib-acpi.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index bed0380c51360..4287555a12408 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -385,7 +385,7 @@ static bool acpi_gpio_in_ignore_list(const char *ignore_list, const char *contro
}
static bool acpi_gpio_irq_is_wake(struct device *parent,
- struct acpi_resource_gpio *agpio)
+ const struct acpi_resource_gpio *agpio)
{
unsigned int pin = agpio->pin_table[0];
@@ -778,7 +778,7 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data)
lookup->info.pin_config = agpio->pin_config;
lookup->info.debounce = agpio->debounce_timeout;
lookup->info.gpioint = gpioint;
- lookup->info.wake_capable = agpio->wake_capable == ACPI_WAKE_CAPABLE;
+ lookup->info.wake_capable = acpi_gpio_irq_is_wake(&lookup->info.adev->dev, agpio);
/*
* Polarity and triggering are only specified for GpioInt
--
GitLab
From 4cb786180dfb5258ff3111181b5e4ecb1d4a297b Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 16 Jan 2023 13:37:02 -0600
Subject: [PATCH 0931/1167] gpiolib: acpi: Add a ignore wakeup quirk for Clevo
NL5xRU
commit 1796f808e4bb ("HID: i2c-hid: acpi: Stop setting wakeup_capable")
changed the policy such that I2C touchpads may be able to wake up the
system by default if the system is configured as such.
However on Clevo NL5xRU there is a mistake in the ACPI tables that the
TP_ATTN# signal connected to GPIO 9 is configured as ActiveLow and level
triggered but connected to a pull up. As soon as the system suspends the
touchpad loses power and then the system wakes up.
To avoid this problem, introduce a quirk for this model that will prevent
the wakeup capability for being set for GPIO 9.
Fixes: 1796f808e4bb ("HID: i2c-hid: acpi: Stop setting wakeup_capable")
Reported-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1722#note_1720627
Co-developed-by: Werner Sembach <wse@tuxedocomputers.com>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpiolib-acpi.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 4287555a12408..9ef0f5641b521 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1623,6 +1623,19 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
.ignore_interrupt = "AMDI0030:00@18",
},
},
+ {
+ /*
+ * Spurious wakeups from TP_ATTN# pin
+ * Found in BIOS 1.7.8
+ * https://gitlab.freedesktop.org/drm/amd/-/issues/1722#note_1720627
+ */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
+ },
+ .driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+ .ignore_wake = "ELAN0415:00@9",
+ },
+ },
{} /* Terminating entry */
};
--
GitLab
From b9fb10d131b8c84af9bb14e2078d5c63600c7dea Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 17 Jan 2023 11:01:31 +0000
Subject: [PATCH 0932/1167] l2tp: prevent lockdep issue in
l2tp_tunnel_register()
lockdep complains with the following lock/unlock sequence:
lock_sock(sk);
write_lock_bh(&sk->sk_callback_lock);
[1] release_sock(sk);
[2] write_unlock_bh(&sk->sk_callback_lock);
We need to swap [1] and [2] to fix this issue.
Fixes: 0b2c59720e65 ("l2tp: close all race conditions in l2tp_tunnel_register()")
Reported-by: syzbot+bbd35b345c7cab0d9a08@syzkaller.appspotmail.com
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/netdev/20230114030137.672706-1-xiyou.wangcong@gmail.com/T/#m1164ff20628671b0f326a24cb106ab3239c70ce3
Cc: Cong Wang <cong.wang@bytedance.com>
Cc: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/l2tp/l2tp_core.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index b6554e32bb12a..03608d3ded4b8 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1483,10 +1483,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
lock_sock(sk);
write_lock_bh(&sk->sk_callback_lock);
ret = l2tp_validate_socket(sk, net, tunnel->encap);
- if (ret < 0) {
- release_sock(sk);
+ if (ret < 0)
goto err_inval_sock;
- }
rcu_assign_sk_user_data(sk, tunnel);
write_unlock_bh(&sk->sk_callback_lock);
@@ -1523,6 +1521,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
err_inval_sock:
write_unlock_bh(&sk->sk_callback_lock);
+ release_sock(sk);
if (tunnel->fd < 0)
sock_release(sock);
--
GitLab
From 3782c0d6edf658b71354a64d60aa7a296188fc90 Mon Sep 17 00:00:00 2001
From: Pietro Borrello <borrello@diag.uniroma1.it>
Date: Wed, 11 Jan 2023 18:12:16 +0000
Subject: [PATCH 0933/1167] HID: betop: check shape of output reports
betopff_init() only checks the total sum of the report counts for each
report field to be at least 4, but hid_betopff_play() expects 4 report
fields.
A device advertising an output report with one field and 4 report counts
would pass the check but crash the kernel with a NULL pointer dereference
in hid_betopff_play().
Fixes: 52cd7785f3cd ("HID: betop: add drivers/hid/hid-betopff.c")
Signed-off-by: Pietro Borrello <borrello@diag.uniroma1.it>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
drivers/hid/hid-betopff.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c
index 467d789f9bc2d..25ed7b9a917e4 100644
--- a/drivers/hid/hid-betopff.c
+++ b/drivers/hid/hid-betopff.c
@@ -60,7 +60,6 @@ static int betopff_init(struct hid_device *hid)
struct list_head *report_list =
&hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev;
- int field_count = 0;
int error;
int i, j;
@@ -86,19 +85,21 @@ static int betopff_init(struct hid_device *hid)
* -----------------------------------------
* Do init them with default value.
*/
+ if (report->maxfield < 4) {
+ hid_err(hid, "not enough fields in the report: %d\n",
+ report->maxfield);
+ return -ENODEV;
+ }
for (i = 0; i < report->maxfield; i++) {
+ if (report->field[i]->report_count < 1) {
+ hid_err(hid, "no values in the field\n");
+ return -ENODEV;
+ }
for (j = 0; j < report->field[i]->report_count; j++) {
report->field[i]->value[j] = 0x00;
- field_count++;
}
}
- if (field_count < 4) {
- hid_err(hid, "not enough fields in the report: %d\n",
- field_count);
- return -ENODEV;
- }
-
betopff = kzalloc(sizeof(*betopff), GFP_KERNEL);
if (!betopff)
return -ENOMEM;
--
GitLab
From 67b0b4ed259e425b7eed09da75b42c80682ca003 Mon Sep 17 00:00:00 2001
From: Sasa Dragic <sasa.dragic@gmail.com>
Date: Mon, 19 Dec 2022 18:29:27 +0100
Subject: [PATCH 0934/1167] drm/i915: re-disable RC6p on Sandy Bridge
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RC6p on Sandy Bridge got re-enabled over time, causing visual glitches
and GPU hangs.
Disabled originally in commit 1c8ecf80fdee ("drm/i915: do not enable
RC6p on Sandy Bridge").
Signed-off-by: Sasa Dragic <sasa.dragic@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221219172927.9603-2-sasa.dragic@gmail.com
Fixes: fb6db0f5bf1d ("drm/i915: Remove unsafe i915.enable_rc6")
Fixes: 13c5a577b342 ("drm/i915/gt: Select the deepest available parking mode for rc6")
Cc: stable@vger.kernel.org
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 0c8a6e9ea232c221976a0670256bd861408d9917)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/i915_pci.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index ccd1f864aa196..4fada7ebe8d82 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -423,7 +423,8 @@ static const struct intel_device_info ilk_m_info = {
.has_coherent_ggtt = true, \
.has_llc = 1, \
.has_rc6 = 1, \
- .has_rc6p = 1, \
+ /* snb does support rc6p, but enabling it causes various issues */ \
+ .has_rc6p = 0, \
.has_rps = true, \
.dma_mask_size = 40, \
.__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, \
--
GitLab
From 93eea624526fc7d070cdae463408665824075f54 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris.p.wilson@linux.intel.com>
Date: Tue, 17 Jan 2023 13:32:34 +0100
Subject: [PATCH 0935/1167] drm/i915/selftests: Unwind hugepages to drop
wakeref on error
Make sure that upon error after we have acquired the wakeref we do
release it again.
v2: add another missing "goto out_wf"(Andi).
Fixes: 027c38b4121e ("drm/i915/selftests: Grab the runtime pm in shrink_thp")
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Signed-off-by: Chris Wilson <chris.p.wilson@linux.intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117123234.26487-1-nirmoy.das@intel.com
(cherry picked from commit 14ec40a88210151296fff3e981c1a7196ad9bf55)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gem/selftests/huge_pages.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index beaf27e09e8a9..977dead10ab57 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1847,7 +1847,7 @@ static int igt_shrink_thp(void *arg)
I915_SHRINK_ACTIVE);
i915_vma_unpin(vma);
if (err)
- goto out_put;
+ goto out_wf;
/*
* Now that the pages are *unpinned* shrinking should invoke
@@ -1863,19 +1863,19 @@ static int igt_shrink_thp(void *arg)
pr_err("unexpected pages mismatch, should_swap=%s\n",
str_yes_no(should_swap));
err = -EINVAL;
- goto out_put;
+ goto out_wf;
}
if (should_swap == (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys)) {
pr_err("unexpected residual page-size bits, should_swap=%s\n",
str_yes_no(should_swap));
err = -EINVAL;
- goto out_put;
+ goto out_wf;
}
err = i915_vma_pin(vma, 0, 0, flags);
if (err)
- goto out_put;
+ goto out_wf;
while (n--) {
err = cpu_check(obj, n, 0xdeadbeaf);
--
GitLab
From a273e95721e96885971a05f1b34cb6d093904d9d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 16 Jan 2023 12:54:23 +0100
Subject: [PATCH 0936/1167] drm/i915: Allow switching away via vga-switcheroo
if uninitialized
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Always allow switching away via vga-switcheroo if the display is
uninitalized. Instead prevent switching to i915 if the device has
not been initialized.
This issue was introduced by commit 5df7bd130818 ("drm/i915: skip
display initialization when there is no display") protected, which
protects code paths from being executed on uninitialized devices.
In the case of vga-switcheroo, we want to allow a switch away from
i915's device. So run vga_switcheroo_process_delayed_switch() and
test in the switcheroo callbacks if the i915 device is available.
Fixes: 5df7bd130818 ("drm/i915: skip display initialization when there is no display")
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: "Jouni Högander" <jouni.hogander@intel.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Ramalingam C <ramalingam.c@intel.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: "José Roberto de Souza" <jose.souza@intel.com>
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Cc: intel-gfx@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v5.14+
Link: https://patchwork.freedesktop.org/patch/msgid/20230116115425.13484-2-tzimmermann@suse.de
---
drivers/gpu/drm/i915/i915_driver.c | 3 +--
drivers/gpu/drm/i915/i915_switcheroo.c | 6 +++++-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index 69103ae377792..b5700681432db 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -1073,8 +1073,7 @@ static void i915_driver_lastclose(struct drm_device *dev)
intel_fbdev_restore_mode(dev);
- if (HAS_DISPLAY(i915))
- vga_switcheroo_process_delayed_switch();
+ vga_switcheroo_process_delayed_switch();
}
static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c
index 23777d500cdf9..f45bd6b6cede4 100644
--- a/drivers/gpu/drm/i915/i915_switcheroo.c
+++ b/drivers/gpu/drm/i915/i915_switcheroo.c
@@ -19,6 +19,10 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n");
return;
}
+ if (!HAS_DISPLAY(i915)) {
+ dev_err(&pdev->dev, "Device state not initialized, aborting switch.\n");
+ return;
+ }
if (state == VGA_SWITCHEROO_ON) {
drm_info(&i915->drm, "switched on\n");
@@ -44,7 +48,7 @@ static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
* locking inversion with the driver load path. And the access here is
* completely racy anyway. So don't bother with locking for now.
*/
- return i915 && atomic_read(&i915->drm.open_count) == 0;
+ return i915 && HAS_DISPLAY(i915) && atomic_read(&i915->drm.open_count) == 0;
}
static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
--
GitLab
From d1d5101452ab04e5a3f010bdd200971d78956e5a Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 16 Jan 2023 12:54:24 +0100
Subject: [PATCH 0937/1167] drm/fb-helper: Set framebuffer for vga-switcheroo
clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Set the framebuffer info for drivers that support VGA switcheroo. Only
affects the amdgpu and nouveau drivers, which use VGA switcheroo and
generic fbdev emulation. For other drivers, this does nothing.
This fixes a potential regression in the console code. Both, amdgpu and
nouveau, invoked vga_switcheroo_client_fb_set() from their internal fbdev
code. But the call got lost when the drivers switched to the generic
emulation.
Fixes: 087451f372bf ("drm/amdgpu: use generic fb helpers instead of setting up AMD own's.")
Fixes: 4a16dd9d18a0 ("drm/nouveau/kms: switch to drm fbdev helpers")
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Karol Herbst <kherbst@redhat.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Evan Quan <evan.quan@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Cc: Likun Gao <Likun.Gao@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Stanley Yang <Stanley.Yang@amd.com>
Cc: "Tianci.Yin" <tianci.yin@amd.com>
Cc: Xiaojian Du <Xiaojian.Du@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: YiPeng Chai <YiPeng.Chai@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Bokun Zhang <Bokun.Zhang@amd.com>
Cc: Guchun Chen <guchun.chen@amd.com>
Cc: Hamza Mahfooz <hamza.mahfooz@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Solomon Chiu <solomon.chiu@amd.com>
Cc: Kai-Heng Feng <kai.heng.feng@canonical.com>
Cc: Felix Kuehling <Felix.Kuehling@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: "Marek Olšák" <marek.olsak@amd.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: "Ville Syrjälä" <ville.syrjala@linux.intel.com>
Cc: dri-devel@lists.freedesktop.org
Cc: nouveau@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v5.17+
Link: https://patchwork.freedesktop.org/patch/msgid/20230116115425.13484-3-tzimmermann@suse.de
---
drivers/gpu/drm/drm_fb_helper.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index b3a731b9170a6..0d0c26ebab906 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -30,7 +30,9 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/console.h>
+#include <linux/pci.h>
#include <linux/sysrq.h>
+#include <linux/vga_switcheroo.h>
#include <drm/drm_atomic.h>
#include <drm/drm_drv.h>
@@ -1909,6 +1911,11 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
return ret;
strcpy(fb_helper->fb->comm, "[fbcon]");
+
+ /* Set the fb info for vgaswitcheroo clients. Does nothing otherwise. */
+ if (dev_is_pci(dev->dev))
+ vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), fb_helper->info);
+
return 0;
}
--
GitLab
From 9fb0db40513e27537fde63287aea920b60557a69 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 17 Jan 2023 19:00:37 -0300
Subject: [PATCH 0938/1167] cifs: fix potential deadlock in
cache_refresh_path()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Avoid getting DFS referral from an exclusive lock in
cache_refresh_path() because the tcon IPC used for getting the
referral could be disconnected and thus causing a deadlock as shown
below:
task A task B
====== ======
cifs_demultiplex_thread() dfs_cache_find()
cifs_handle_standard() cache_refresh_path()
reconnect_dfs_server() down_write()
dfs_cache_noreq_find() get_dfs_referral()
down_read() <- deadlock smb2_get_dfs_refer()
SMB2_ioctl()
cifs_send_recv()
compound_send_recv()
wait_for_response()
where task A cannot wake up task B because it is blocked on
down_read() due to the exclusive lock held in cache_refresh_path() and
therefore not being able to make progress.
Fixes: c9f711039905 ("cifs: keep referral server sessions alive")
Reviewed-by: Aurélien Aptel <aurelien.aptel@gmail.com>
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 42 +++++++++++++++++++++++-------------------
1 file changed, 23 insertions(+), 19 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index e20f8880363fa..a6d7ae5f49a46 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -770,26 +770,27 @@ static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, const
*/
static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, const char *path)
{
- int rc;
- struct cache_entry *ce;
struct dfs_info3_param *refs = NULL;
+ struct cache_entry *ce;
int numrefs = 0;
- bool newent = false;
+ int rc;
cifs_dbg(FYI, "%s: search path: %s\n", __func__, path);
- down_write(&htable_rw_lock);
+ down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
- if (!IS_ERR(ce)) {
- if (!cache_entry_expired(ce)) {
- dump_ce(ce);
- up_write(&htable_rw_lock);
- return 0;
- }
- } else {
- newent = true;
+ if (!IS_ERR(ce) && !cache_entry_expired(ce)) {
+ up_read(&htable_rw_lock);
+ return 0;
}
+ /*
+ * Unlock shared access as we don't want to hold any locks while getting
+ * a new referral. The @ses used for performing the I/O could be
+ * reconnecting and it acquires @htable_rw_lock to look up the dfs cache
+ * in order to failover -- if necessary.
+ */
+ up_read(&htable_rw_lock);
/*
* Either the entry was not found, or it is expired.
@@ -797,19 +798,22 @@ static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, cons
*/
rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
if (rc)
- goto out_unlock;
+ goto out;
dump_refs(refs, numrefs);
- if (!newent) {
- rc = update_cache_entry_locked(ce, refs, numrefs);
- goto out_unlock;
+ down_write(&htable_rw_lock);
+ /* Re-check as another task might have it added or refreshed already */
+ ce = lookup_cache_entry(path);
+ if (!IS_ERR(ce)) {
+ if (cache_entry_expired(ce))
+ rc = update_cache_entry_locked(ce, refs, numrefs);
+ } else {
+ rc = add_cache_entry_locked(refs, numrefs);
}
- rc = add_cache_entry_locked(refs, numrefs);
-
-out_unlock:
up_write(&htable_rw_lock);
+out:
free_dfs_info_array(refs, numrefs);
return rc;
}
--
GitLab
From 48d240bf00af943db6f069a53f090e444e85f760 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 17 Jan 2023 19:00:38 -0300
Subject: [PATCH 0939/1167] cifs: avoid re-lookups in dfs_cache_find()
Simply downgrade the write lock on cache updates from
cache_refresh_path() and avoid unnecessary re-lookup in
dfs_cache_find().
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 58 ++++++++++++++++++++++++++-------------------
1 file changed, 34 insertions(+), 24 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index a6d7ae5f49a46..755a00c4cba19 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -558,7 +558,8 @@ static void remove_oldest_entry_locked(void)
}
/* Add a new DFS cache entry */
-static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs)
+static struct cache_entry *add_cache_entry_locked(struct dfs_info3_param *refs,
+ int numrefs)
{
int rc;
struct cache_entry *ce;
@@ -573,11 +574,11 @@ static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs)
rc = cache_entry_hash(refs[0].path_name, strlen(refs[0].path_name), &hash);
if (rc)
- return rc;
+ return ERR_PTR(rc);
ce = alloc_cache_entry(refs, numrefs);
if (IS_ERR(ce))
- return PTR_ERR(ce);
+ return ce;
spin_lock(&cache_ttl_lock);
if (!cache_ttl) {
@@ -594,7 +595,7 @@ static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs)
atomic_inc(&cache_count);
- return 0;
+ return ce;
}
/* Check if two DFS paths are equal. @s1 and @s2 are expected to be in @cache_cp's charset */
@@ -767,8 +768,12 @@ static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, const
*
* For interlinks, cifs_mount() and expand_dfs_referral() are supposed to
* handle them properly.
+ *
+ * On success, return entry with acquired lock for reading, otherwise error ptr.
*/
-static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, const char *path)
+static struct cache_entry *cache_refresh_path(const unsigned int xid,
+ struct cifs_ses *ses,
+ const char *path)
{
struct dfs_info3_param *refs = NULL;
struct cache_entry *ce;
@@ -780,10 +785,9 @@ static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, cons
down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
- if (!IS_ERR(ce) && !cache_entry_expired(ce)) {
- up_read(&htable_rw_lock);
- return 0;
- }
+ if (!IS_ERR(ce) && !cache_entry_expired(ce))
+ return ce;
+
/*
* Unlock shared access as we don't want to hold any locks while getting
* a new referral. The @ses used for performing the I/O could be
@@ -797,8 +801,10 @@ static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, cons
* Request a new DFS referral in order to create or update a cache entry.
*/
rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- if (rc)
+ if (rc) {
+ ce = ERR_PTR(rc);
goto out;
+ }
dump_refs(refs, numrefs);
@@ -806,16 +812,24 @@ static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, cons
/* Re-check as another task might have it added or refreshed already */
ce = lookup_cache_entry(path);
if (!IS_ERR(ce)) {
- if (cache_entry_expired(ce))
+ if (cache_entry_expired(ce)) {
rc = update_cache_entry_locked(ce, refs, numrefs);
+ if (rc)
+ ce = ERR_PTR(rc);
+ }
} else {
- rc = add_cache_entry_locked(refs, numrefs);
+ ce = add_cache_entry_locked(refs, numrefs);
}
- up_write(&htable_rw_lock);
+ if (IS_ERR(ce)) {
+ up_write(&htable_rw_lock);
+ goto out;
+ }
+
+ downgrade_write(&htable_rw_lock);
out:
free_dfs_info_array(refs, numrefs);
- return rc;
+ return ce;
}
/*
@@ -935,15 +949,8 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl
if (IS_ERR(npath))
return PTR_ERR(npath);
- rc = cache_refresh_path(xid, ses, npath);
- if (rc)
- goto out_free_path;
-
- down_read(&htable_rw_lock);
-
- ce = lookup_cache_entry(npath);
+ ce = cache_refresh_path(xid, ses, npath);
if (IS_ERR(ce)) {
- up_read(&htable_rw_lock);
rc = PTR_ERR(ce);
goto out_free_path;
}
@@ -1039,10 +1046,13 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath);
- rc = cache_refresh_path(xid, ses, npath);
- if (rc)
+ ce = cache_refresh_path(xid, ses, npath);
+ if (IS_ERR(ce)) {
+ rc = PTR_ERR(ce);
goto out_free_path;
+ }
+ up_read(&htable_rw_lock);
down_write(&htable_rw_lock);
ce = lookup_cache_entry(npath);
--
GitLab
From 11c8b3f8493cb5253da42fcd178d9b4630063f96 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 17 Jan 2023 19:00:39 -0300
Subject: [PATCH 0940/1167] cifs: don't take exclusive lock for updating target
hints
Avoid contention while updating dfs target hints. This should be
perfectly fine to update them under shared locks.
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 47 +++++++++++++++++++--------------------------
1 file changed, 20 insertions(+), 27 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 755a00c4cba19..19847f9114bac 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -269,7 +269,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v)
list_for_each_entry(t, &ce->tlist, list) {
seq_printf(m, " %s%s\n",
t->name,
- ce->tgthint == t ? " (target hint)" : "");
+ READ_ONCE(ce->tgthint) == t ? " (target hint)" : "");
}
}
}
@@ -321,7 +321,7 @@ static inline void dump_tgts(const struct cache_entry *ce)
cifs_dbg(FYI, "target list:\n");
list_for_each_entry(t, &ce->tlist, list) {
cifs_dbg(FYI, " %s%s\n", t->name,
- ce->tgthint == t ? " (target hint)" : "");
+ READ_ONCE(ce->tgthint) == t ? " (target hint)" : "");
}
}
@@ -427,7 +427,7 @@ static int cache_entry_hash(const void *data, int size, unsigned int *hash)
/* Return target hint of a DFS cache entry */
static inline char *get_tgt_name(const struct cache_entry *ce)
{
- struct cache_dfs_tgt *t = ce->tgthint;
+ struct cache_dfs_tgt *t = READ_ONCE(ce->tgthint);
return t ? t->name : ERR_PTR(-ENOENT);
}
@@ -470,6 +470,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed)
static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs,
struct cache_entry *ce, const char *tgthint)
{
+ struct cache_dfs_tgt *target;
int i;
ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL);
@@ -496,8 +497,9 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs,
ce->numtgts++;
}
- ce->tgthint = list_first_entry_or_null(&ce->tlist,
- struct cache_dfs_tgt, list);
+ target = list_first_entry_or_null(&ce->tlist, struct cache_dfs_tgt,
+ list);
+ WRITE_ONCE(ce->tgthint, target);
return 0;
}
@@ -712,14 +714,15 @@ void dfs_cache_destroy(void)
static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_info3_param *refs,
int numrefs)
{
+ struct cache_dfs_tgt *target;
+ char *th = NULL;
int rc;
- char *s, *th = NULL;
WARN_ON(!rwsem_is_locked(&htable_rw_lock));
- if (ce->tgthint) {
- s = ce->tgthint->name;
- th = kstrdup(s, GFP_ATOMIC);
+ target = READ_ONCE(ce->tgthint);
+ if (target) {
+ th = kstrdup(target->name, GFP_ATOMIC);
if (!th)
return -ENOMEM;
}
@@ -896,7 +899,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl)
}
it->it_path_consumed = t->path_consumed;
- if (ce->tgthint == t)
+ if (READ_ONCE(ce->tgthint) == t)
list_add(&it->it_list, head);
else
list_add_tail(&it->it_list, head);
@@ -1052,23 +1055,14 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
goto out_free_path;
}
- up_read(&htable_rw_lock);
- down_write(&htable_rw_lock);
-
- ce = lookup_cache_entry(npath);
- if (IS_ERR(ce)) {
- rc = PTR_ERR(ce);
- goto out_unlock;
- }
-
- t = ce->tgthint;
+ t = READ_ONCE(ce->tgthint);
if (likely(!strcasecmp(it->it_name, t->name)))
goto out_unlock;
list_for_each_entry(t, &ce->tlist, list) {
if (!strcasecmp(t->name, it->it_name)) {
- ce->tgthint = t;
+ WRITE_ONCE(ce->tgthint, t);
cifs_dbg(FYI, "%s: new target hint: %s\n", __func__,
it->it_name);
break;
@@ -1076,7 +1070,7 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
}
out_unlock:
- up_write(&htable_rw_lock);
+ up_read(&htable_rw_lock);
out_free_path:
kfree(npath);
return rc;
@@ -1106,21 +1100,20 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt
cifs_dbg(FYI, "%s: path: %s\n", __func__, path);
- if (!down_write_trylock(&htable_rw_lock))
- return;
+ down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
if (IS_ERR(ce))
goto out_unlock;
- t = ce->tgthint;
+ t = READ_ONCE(ce->tgthint);
if (unlikely(!strcasecmp(it->it_name, t->name)))
goto out_unlock;
list_for_each_entry(t, &ce->tlist, list) {
if (!strcasecmp(t->name, it->it_name)) {
- ce->tgthint = t;
+ WRITE_ONCE(ce->tgthint, t);
cifs_dbg(FYI, "%s: new target hint: %s\n", __func__,
it->it_name);
break;
@@ -1128,7 +1121,7 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt
}
out_unlock:
- up_write(&htable_rw_lock);
+ up_read(&htable_rw_lock);
}
/**
--
GitLab
From 8064f711c6a4614a848009b5a773e8d7f055a4c5 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 17 Jan 2023 19:00:40 -0300
Subject: [PATCH 0941/1167] cifs: remove duplicate code in __refresh_tcon()
The logic for creating or updating a cache entry in __refresh_tcon()
could be simply done with cache_refresh_path(), so use it instead.
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 71 +++++++++++++++++++++------------------------
1 file changed, 33 insertions(+), 38 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 19847f9114bac..58d11be9d0203 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -776,7 +776,8 @@ static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, const
*/
static struct cache_entry *cache_refresh_path(const unsigned int xid,
struct cifs_ses *ses,
- const char *path)
+ const char *path,
+ bool force_refresh)
{
struct dfs_info3_param *refs = NULL;
struct cache_entry *ce;
@@ -788,7 +789,7 @@ static struct cache_entry *cache_refresh_path(const unsigned int xid,
down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
- if (!IS_ERR(ce) && !cache_entry_expired(ce))
+ if (!IS_ERR(ce) && !force_refresh && !cache_entry_expired(ce))
return ce;
/*
@@ -800,7 +801,8 @@ static struct cache_entry *cache_refresh_path(const unsigned int xid,
up_read(&htable_rw_lock);
/*
- * Either the entry was not found, or it is expired.
+ * Either the entry was not found, or it is expired, or it is a forced
+ * refresh.
* Request a new DFS referral in order to create or update a cache entry.
*/
rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
@@ -815,7 +817,7 @@ static struct cache_entry *cache_refresh_path(const unsigned int xid,
/* Re-check as another task might have it added or refreshed already */
ce = lookup_cache_entry(path);
if (!IS_ERR(ce)) {
- if (cache_entry_expired(ce)) {
+ if (force_refresh || cache_entry_expired(ce)) {
rc = update_cache_entry_locked(ce, refs, numrefs);
if (rc)
ce = ERR_PTR(rc);
@@ -952,7 +954,7 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl
if (IS_ERR(npath))
return PTR_ERR(npath);
- ce = cache_refresh_path(xid, ses, npath);
+ ce = cache_refresh_path(xid, ses, npath, false);
if (IS_ERR(ce)) {
rc = PTR_ERR(ce);
goto out_free_path;
@@ -1049,7 +1051,7 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath);
- ce = cache_refresh_path(xid, ses, npath);
+ ce = cache_refresh_path(xid, ses, npath, false);
if (IS_ERR(ce)) {
rc = PTR_ERR(ce);
goto out_free_path;
@@ -1327,35 +1329,37 @@ static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, c
* Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new
* target shares in @refs.
*/
-static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl,
- const struct dfs_info3_param *refs, int numrefs)
+static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server,
+ struct dfs_cache_tgt_list *old_tl,
+ struct dfs_cache_tgt_list *new_tl)
{
- struct dfs_cache_tgt_iterator *it;
- int i;
-
- for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) {
- for (i = 0; i < numrefs; i++) {
- if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it),
- refs[i].node_name))
+ struct dfs_cache_tgt_iterator *oit, *nit;
+
+ for (oit = dfs_cache_get_tgt_iterator(old_tl); oit;
+ oit = dfs_cache_get_next_tgt(old_tl, oit)) {
+ for (nit = dfs_cache_get_tgt_iterator(new_tl); nit;
+ nit = dfs_cache_get_next_tgt(new_tl, nit)) {
+ if (target_share_equal(server,
+ dfs_cache_get_tgt_name(oit),
+ dfs_cache_get_tgt_name(nit)))
return;
}
}
cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
- cifs_signal_cifsd_for_reconnect(tcon->ses->server, true);
+ cifs_signal_cifsd_for_reconnect(server, true);
}
/* Refresh dfs referral of tcon and mark it for reconnect if needed */
static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_refresh)
{
- struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+ struct dfs_cache_tgt_list old_tl = DFS_CACHE_TGT_LIST_INIT(old_tl);
+ struct dfs_cache_tgt_list new_tl = DFS_CACHE_TGT_LIST_INIT(new_tl);
struct cifs_ses *ses = CIFS_DFS_ROOT_SES(tcon->ses);
struct cifs_tcon *ipc = ses->tcon_ipc;
- struct dfs_info3_param *refs = NULL;
bool needs_refresh = false;
struct cache_entry *ce;
unsigned int xid;
- int numrefs = 0;
int rc = 0;
xid = get_xid();
@@ -1364,9 +1368,8 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r
ce = lookup_cache_entry(path);
needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
if (!IS_ERR(ce)) {
- rc = get_targets(ce, &tl);
- if (rc)
- cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc);
+ rc = get_targets(ce, &old_tl);
+ cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc);
}
up_read(&htable_rw_lock);
@@ -1383,26 +1386,18 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r
}
spin_unlock(&ipc->tc_lock);
- rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- if (!rc) {
- /* Create or update a cache entry with the new referral */
- dump_refs(refs, numrefs);
-
- down_write(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- if (IS_ERR(ce))
- add_cache_entry_locked(refs, numrefs);
- else if (force_refresh || cache_entry_expired(ce))
- update_cache_entry_locked(ce, refs, numrefs);
- up_write(&htable_rw_lock);
-
- mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs);
+ ce = cache_refresh_path(xid, ses, path, true);
+ if (!IS_ERR(ce)) {
+ rc = get_targets(ce, &new_tl);
+ up_read(&htable_rw_lock);
+ cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc);
+ mark_for_reconnect_if_needed(tcon->ses->server, &old_tl, &new_tl);
}
out:
free_xid(xid);
- dfs_cache_free_tgts(&tl);
- free_dfs_info_array(refs, numrefs);
+ dfs_cache_free_tgts(&old_tl);
+ dfs_cache_free_tgts(&new_tl);
return rc;
}
--
GitLab
From 3deddb77fdd932df92f3b6a27a9cffed82c4fe1a Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Tue, 17 Jan 2023 19:00:41 -0300
Subject: [PATCH 0942/1167] cifs: handle cache lookup errors different than
-ENOENT
lookup_cache_entry() might return an error different than -ENOENT
(e.g. from ->char2uni), so handle those as well in
cache_refresh_path().
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 58d11be9d0203..308101d900061 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -644,7 +644,9 @@ static struct cache_entry *__lookup_cache_entry(const char *path, unsigned int h
*
* Use whole path components in the match. Must be called with htable_rw_lock held.
*
+ * Return cached entry if successful.
* Return ERR_PTR(-ENOENT) if the entry is not found.
+ * Return error ptr otherwise.
*/
static struct cache_entry *lookup_cache_entry(const char *path)
{
@@ -789,8 +791,13 @@ static struct cache_entry *cache_refresh_path(const unsigned int xid,
down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
- if (!IS_ERR(ce) && !force_refresh && !cache_entry_expired(ce))
+ if (!IS_ERR(ce)) {
+ if (!force_refresh && !cache_entry_expired(ce))
+ return ce;
+ } else if (PTR_ERR(ce) != -ENOENT) {
+ up_read(&htable_rw_lock);
return ce;
+ }
/*
* Unlock shared access as we don't want to hold any locks while getting
@@ -822,7 +829,7 @@ static struct cache_entry *cache_refresh_path(const unsigned int xid,
if (rc)
ce = ERR_PTR(rc);
}
- } else {
+ } else if (PTR_ERR(ce) == -ENOENT) {
ce = add_cache_entry_locked(refs, numrefs);
}
--
GitLab
From 596b53ccc36a546ab28e8897315c5b4d1d5a0200 Mon Sep 17 00:00:00 2001
From: Liu Shixin <liushixin2@huawei.com>
Date: Tue, 22 Nov 2022 10:16:12 +0800
Subject: [PATCH 0943/1167] dmaengine: xilinx_dma: call of_node_put() when
breaking out of for_each_child_of_node()
Since for_each_child_of_node() will increase the refcount of node, we need
to call of_node_put() manually when breaking out of the iteration.
Fixes: 9cd4360de609 ("dma: Add Xilinx AXI Video Direct Memory Access Engine driver support")
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Acked-by: Peter Korsgaard <peter@korsgaard.com>
Link: https://lore.kernel.org/r/20221122021612.1908866-1-liushixin2@huawei.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/xilinx/xilinx_dma.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index a8d23cdf883e5..ac09f0e5f58d8 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -3143,8 +3143,10 @@ static int xilinx_dma_probe(struct platform_device *pdev)
/* Initialize the channels */
for_each_child_of_node(node, child) {
err = xilinx_dma_child_probe(xdev, child);
- if (err < 0)
+ if (err < 0) {
+ of_node_put(child);
goto error;
+ }
}
if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) {
--
GitLab
From a7a7ee6f5a019ad72852c001abbce50d35e992f2 Mon Sep 17 00:00:00 2001
From: Akhil R <akhilrajeev@nvidia.com>
Date: Wed, 18 Jan 2023 17:28:01 +0530
Subject: [PATCH 0944/1167] dmaengine: tegra: Fix memory leak in
terminate_all()
Terminate vdesc when terminating an ongoing transfer.
This will ensure that the vdesc is present in the desc_terminated list
The descriptor will be freed later in desc_free_list().
This fixes the memory leaks which can happen when terminating an
ongoing transfer.
Fixes: ee17028009d4 ("dmaengine: tegra: Add tegra gpcdma driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
Link: https://lore.kernel.org/r/20230118115801.15210-1-akhilrajeev@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/tegra186-gpc-dma.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c
index 1d1180db6d4ec..8f67f453a4922 100644
--- a/drivers/dma/tegra186-gpc-dma.c
+++ b/drivers/dma/tegra186-gpc-dma.c
@@ -711,6 +711,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc)
return err;
}
+ vchan_terminate_vdesc(&tdc->dma_desc->vd);
tegra_dma_disable(tdc);
tdc->dma_desc = NULL;
}
--
GitLab
From ce38cb84c3e8d953f4e9beaa6ba270938242c72f Mon Sep 17 00:00:00 2001
From: Matt Atwood <matthew.s.atwood@intel.com>
Date: Wed, 23 Nov 2022 10:36:47 -0800
Subject: [PATCH 0945/1167] drm/i915/dg2: Introduce Wa_18018764978
Wa_18018764978 applies to specific steppings of DG2 (G10 C0+,
G11 and G12 A0+). Clean up style in function at the same time.
Bspec: 66622
Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221123183648.407058-1-matthew.s.atwood@intel.com
(cherry picked from commit 468a4e630c7da8cf586f85cc498d6097aed1ab4b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 3 +++
drivers/gpu/drm/i915/gt/intel_workarounds.c | 7 ++++++-
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 4a14f87e441e5..a7dc1c54785f0 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -457,6 +457,9 @@
#define GEN8_L3CNTLREG _MMIO(0x7034)
#define GEN8_ERRDETBCTRL (1 << 9)
+#define PSS_MODE2 _MMIO(0x703c)
+#define SCOREBOARD_STALL_FLUSH_CONTROL REG_BIT(5)
+
#define GEN7_SC_INSTDONE _MMIO(0x7100)
#define GEN12_SC_INSTDONE_EXTRA _MMIO(0x7104)
#define GEN12_SC_INSTDONE_EXTRA2 _MMIO(0x7108)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5be2f91801fbf..c99a3e7ef8781 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -771,9 +771,14 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
/* Wa_14014947963:dg2 */
if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) ||
- IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+ IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
+ /* Wa_18018764978:dg2 */
+ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) ||
+ IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+ wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL);
+
/* Wa_15010599737:dg2 */
wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
}
--
GitLab
From afdecb232740ae40b9384fa0ac8ed799d6546516 Mon Sep 17 00:00:00 2001
From: Matt Atwood <matthew.s.atwood@intel.com>
Date: Wed, 23 Nov 2022 10:36:48 -0800
Subject: [PATCH 0946/1167] drm/i915/dg2: Introduce Wa_18019271663
Wa_18019271663 applies to all DG2 steppings and skus.
Bspec: 66622
Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221123183648.407058-2-matthew.s.atwood@intel.com
(cherry picked from commit 900a80c5836587d95db32742f66e1f34f7b40fcb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gt/intel_gt_regs.h | 7 ++++---
drivers/gpu/drm/i915/gt/intel_workarounds.c | 3 +++
2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index a7dc1c54785f0..a5454af2a9cfd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -429,9 +429,10 @@
#define RC_OP_FLUSH_ENABLE (1 << 0)
#define HIZ_RAW_STALL_OPT_DISABLE (1 << 2)
#define CACHE_MODE_1 _MMIO(0x7004) /* IVB+ */
-#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1 << 6)
-#define GEN8_4x4_STC_OPTIMIZATION_DISABLE (1 << 6)
-#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE (1 << 1)
+#define MSAA_OPTIMIZATION_REDUC_DISABLE REG_BIT(11)
+#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE REG_BIT(6)
+#define GEN8_4x4_STC_OPTIMIZATION_DISABLE REG_BIT(6)
+#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE REG_BIT(1)
#define GEN7_GT_MODE _MMIO(0x7008)
#define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2))
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index c99a3e7ef8781..949c19339015b 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -781,6 +781,9 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
/* Wa_15010599737:dg2 */
wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+
+ /* Wa_18019271663:dg2 */
+ wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE);
}
static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
--
GitLab
From d6a49e8c4ca4d399ed65ac219585187fc8c2e2b1 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Wed, 18 Jan 2023 13:36:31 -0300
Subject: [PATCH 0947/1167] cifs: fix return of uninitialized rc in
dfs_cache_update_tgthint()
Fix this by initializing rc to 0 as cache_refresh_path() would not set
it in case of success.
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/all/202301190004.bEHvbKG6-lkp@intel.com/
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 308101d900061..e16c63997133f 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1047,10 +1047,10 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
const struct nls_table *cp, int remap, const char *path,
const struct dfs_cache_tgt_iterator *it)
{
- int rc;
- const char *npath;
- struct cache_entry *ce;
struct cache_dfs_tgt *t;
+ struct cache_entry *ce;
+ const char *npath;
+ int rc = 0;
npath = dfs_cache_canonical_path(path, cp, remap);
if (IS_ERR(npath))
--
GitLab
From e181119046a0ec16126b682163040e8e33f310c1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 16 Jan 2023 21:19:03 +0100
Subject: [PATCH 0948/1167] dt-bindings: phy: g12a-usb3-pcie-phy: fix
compatible string documentation
The compatible string in the driver doesn't have the meson prefix.
Fix this in the documentation and rename the file accordingly.
Fixes: 87a55485f2fc ("dt-bindings: phy: meson-g12a-usb3-pcie-phy: convert to yaml")
Cc: stable@vger.kernel.org
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/0a82be92-ce85-da34-9d6f-4b33034473e5@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
...a-usb3-pcie-phy.yaml => amlogic,g12a-usb3-pcie-phy.yaml} | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
rename Documentation/devicetree/bindings/phy/{amlogic,meson-g12a-usb3-pcie-phy.yaml => amlogic,g12a-usb3-pcie-phy.yaml} (82%)
diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml
similarity index 82%
rename from Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
rename to Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml
index 868b4e6fde71f..129d26e99776b 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml
@@ -2,7 +2,7 @@
# Copyright 2019 BayLibre, SAS
%YAML 1.2
---
-$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml#"
+$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Amlogic G12A USB3 + PCIE Combo PHY
@@ -13,7 +13,7 @@ maintainers:
properties:
compatible:
enum:
- - amlogic,meson-g12a-usb3-pcie-phy
+ - amlogic,g12a-usb3-pcie-phy
reg:
maxItems: 1
@@ -49,7 +49,7 @@ additionalProperties: false
examples:
- |
phy@46000 {
- compatible = "amlogic,meson-g12a-usb3-pcie-phy";
+ compatible = "amlogic,g12a-usb3-pcie-phy";
reg = <0x46000 0x2000>;
clocks = <&ref_clk>;
clock-names = "ref_clk";
--
GitLab
From c63835bf1c750c9b3aec1d5c23d811d6375fc23d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 16 Jan 2023 21:17:39 +0100
Subject: [PATCH 0949/1167] dt-bindings: phy: g12a-usb2-phy: fix compatible
string documentation
The compatible strings in the driver don't have the meson prefix.
Fix this in the documentation and rename the file accordingly.
Fixes: da86d286cce8 ("dt-bindings: phy: meson-g12a-usb2-phy: convert to yaml")
Cc: stable@vger.kernel.org
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/8d960029-e94d-224b-911f-03e5deb47ebc@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
...eson-g12a-usb2-phy.yaml => amlogic,g12a-usb2-phy.yaml} | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
rename Documentation/devicetree/bindings/phy/{amlogic,meson-g12a-usb2-phy.yaml => amlogic,g12a-usb2-phy.yaml} (85%)
diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
similarity index 85%
rename from Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
rename to Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
index f3a5fbabbbb59..bb01c6b34dabc 100644
--- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml
@@ -2,7 +2,7 @@
# Copyright 2019 BayLibre, SAS
%YAML 1.2
---
-$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb2-phy.yaml#"
+$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Amlogic G12A USB2 PHY
@@ -13,8 +13,8 @@ maintainers:
properties:
compatible:
enum:
- - amlogic,meson-g12a-usb2-phy
- - amlogic,meson-a1-usb2-phy
+ - amlogic,g12a-usb2-phy
+ - amlogic,a1-usb2-phy
reg:
maxItems: 1
@@ -68,7 +68,7 @@ additionalProperties: false
examples:
- |
phy@36000 {
- compatible = "amlogic,meson-g12a-usb2-phy";
+ compatible = "amlogic,g12a-usb2-phy";
reg = <0x36000 0x2000>;
clocks = <&xtal>;
clock-names = "xtal";
--
GitLab
From bc30c15f275484f9b9fe27c2fa0895f3022d9943 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 18 Jan 2023 11:29:58 +0100
Subject: [PATCH 0950/1167] phy: phy-can-transceiver: Skip warning if no
"max-bitrate"
According to the DT bindings, the "max-bitrate" property is optional.
However, when it is not present, a warning is printed.
Fix this by adding a missing check for -EINVAL.
Fixes: a4a86d273ff1b6f7 ("phy: phy-can-transceiver: Add support for generic CAN transceiver driver")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/88e158f97dd52ebaa7126cd9631f34764b9c0795.1674037334.git.geert+renesas@glider.be
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/phy/phy-can-transceiver.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c
index 95c6dbb52da72..ce511ad5d3690 100644
--- a/drivers/phy/phy-can-transceiver.c
+++ b/drivers/phy/phy-can-transceiver.c
@@ -99,6 +99,7 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)
struct gpio_desc *standby_gpio;
struct gpio_desc *enable_gpio;
u32 max_bitrate = 0;
+ int err;
can_transceiver_phy = devm_kzalloc(dev, sizeof(struct can_transceiver_phy), GFP_KERNEL);
if (!can_transceiver_phy)
@@ -124,8 +125,8 @@ static int can_transceiver_phy_probe(struct platform_device *pdev)
return PTR_ERR(phy);
}
- device_property_read_u32(dev, "max-bitrate", &max_bitrate);
- if (!max_bitrate)
+ err = device_property_read_u32(dev, "max-bitrate", &max_bitrate);
+ if ((err != -EINVAL) && !max_bitrate)
dev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit\n");
phy->attrs.max_link_rate = max_bitrate;
--
GitLab
From 2293a73ad4f3b6c37c06713ff1b67659d92ef43d Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Wed, 18 Jan 2023 18:06:24 +0100
Subject: [PATCH 0951/1167] drm/i915: Remove unused variable
Removed unused i915 var.
Fixes: a273e95721e9 ("drm/i915: Allow switching away via vga-switcheroo if uninitialized")
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230118170624.9326-1-nirmoy.das@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/i915_driver.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index b5700681432db..61c38fc734cfb 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -1069,8 +1069,6 @@ static int i915_driver_open(struct drm_device *dev, struct drm_file *file)
*/
static void i915_driver_lastclose(struct drm_device *dev)
{
- struct drm_i915_private *i915 = to_i915(dev);
-
intel_fbdev_restore_mode(dev);
vga_switcheroo_process_delayed_switch();
--
GitLab
From 182da6f2b81a78709c58021542fb694f8ed80774 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 12 Jan 2023 14:33:19 +0100
Subject: [PATCH 0952/1167] ACPI: PRM: Check whether EFI runtime is available
The ACPI PRM address space handler calls efi_call_virt_pointer() to
execute PRM firmware code, but doing so is only permitted when the EFI
runtime environment is available. Otherwise, such calls are guaranteed
to result in a crash, and must therefore be avoided.
Given that the EFI runtime services may become unavailable after a crash
occurring in the firmware, we need to check this each time the PRM
address space handler is invoked. If the EFI runtime services were not
available at registration time to being with, don't install the address
space handler at all.
Fixes: cefc7ca46235 ("ACPI: PRM: implement OperationRegion handler for the PlatformRtMechanism subtype")
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/prmt.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index 998101cf16e47..3d4c4620f9f95 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -236,6 +236,11 @@ static acpi_status acpi_platformrt_space_handler(u32 function,
efi_status_t status;
struct prm_context_buffer context;
+ if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+ pr_err_ratelimited("PRM: EFI runtime services no longer available\n");
+ return AE_NO_HANDLER;
+ }
+
/*
* The returned acpi_status will always be AE_OK. Error values will be
* saved in the first byte of the PRM message buffer to be used by ASL.
@@ -325,6 +330,11 @@ void __init init_prmt(void)
pr_info("PRM: found %u modules\n", mc);
+ if (!efi_enabled(EFI_RUNTIME_SERVICES)) {
+ pr_err("PRM: EFI runtime services unavailable\n");
+ return;
+ }
+
status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT,
ACPI_ADR_SPACE_PLATFORM_RT,
&acpi_platformrt_space_handler,
--
GitLab
From 30b2b2196d6e4cc24cbec633535a2404f258ce69 Mon Sep 17 00:00:00 2001
From: Enzo Matsumiya <ematsumiya@suse.de>
Date: Wed, 18 Jan 2023 14:06:57 -0300
Subject: [PATCH 0953/1167] cifs: do not include page data when checking
signature
On async reads, page data is allocated before sending. When the
response is received but it has no data to fill (e.g.
STATUS_END_OF_FILE), __calc_signature() will still include the pages in
its computation, leading to an invalid signature check.
This patch fixes this by not setting the async read smb_rqst page data
(zeroed by default) if its got_bytes is 0.
This can be reproduced/verified with xfstests generic/465.
Cc: <stable@vger.kernel.org>
Signed-off-by: Enzo Matsumiya <ematsumiya@suse.de>
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smb2pdu.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 4b71f4a92f76c..2c9ffa921e6f6 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -4163,12 +4163,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
(struct smb2_hdr *)rdata->iov[0].iov_base;
struct cifs_credits credits = { .value = 0, .instance = 0 };
struct smb_rqst rqst = { .rq_iov = &rdata->iov[1],
- .rq_nvec = 1,
- .rq_pages = rdata->pages,
- .rq_offset = rdata->page_offset,
- .rq_npages = rdata->nr_pages,
- .rq_pagesz = rdata->pagesz,
- .rq_tailsz = rdata->tailsz };
+ .rq_nvec = 1, };
+
+ if (rdata->got_bytes) {
+ rqst.rq_pages = rdata->pages;
+ rqst.rq_offset = rdata->page_offset;
+ rqst.rq_npages = rdata->nr_pages;
+ rqst.rq_pagesz = rdata->pagesz;
+ rqst.rq_tailsz = rdata->tailsz;
+ }
WARN_ONCE(rdata->server != mid->server,
"rdata server %p != mid server %p",
--
GitLab
From a1b7c8457ecc062f612a1aca174c2e1c21f9ac10 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@cjr.nz>
Date: Wed, 18 Jan 2023 13:55:01 -0300
Subject: [PATCH 0954/1167] cifs: remove unused function
Remove dfs_cache_update_tgthint() as it is not used anywhere.
Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/dfs_cache.c | 60 ---------------------------------------------
fs/cifs/dfs_cache.h | 3 ---
2 files changed, 63 deletions(-)
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index e16c63997133f..ac86bd0ebd637 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1025,66 +1025,6 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref,
return rc;
}
-/**
- * dfs_cache_update_tgthint - update target hint of a DFS cache entry
- *
- * If it doesn't find the cache entry, then it will get a DFS referral for @path
- * and create a new entry.
- *
- * In case the cache entry exists but expired, it will get a DFS referral
- * for @path and then update the respective cache entry.
- *
- * @xid: syscall id
- * @ses: smb session
- * @cp: codepage
- * @remap: type of character remapping for paths
- * @path: path to lookup in DFS referral cache
- * @it: DFS target iterator
- *
- * Return zero if the target hint was updated successfully, otherwise non-zero.
- */
-int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
- const struct nls_table *cp, int remap, const char *path,
- const struct dfs_cache_tgt_iterator *it)
-{
- struct cache_dfs_tgt *t;
- struct cache_entry *ce;
- const char *npath;
- int rc = 0;
-
- npath = dfs_cache_canonical_path(path, cp, remap);
- if (IS_ERR(npath))
- return PTR_ERR(npath);
-
- cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath);
-
- ce = cache_refresh_path(xid, ses, npath, false);
- if (IS_ERR(ce)) {
- rc = PTR_ERR(ce);
- goto out_free_path;
- }
-
- t = READ_ONCE(ce->tgthint);
-
- if (likely(!strcasecmp(it->it_name, t->name)))
- goto out_unlock;
-
- list_for_each_entry(t, &ce->tlist, list) {
- if (!strcasecmp(t->name, it->it_name)) {
- WRITE_ONCE(ce->tgthint, t);
- cifs_dbg(FYI, "%s: new target hint: %s\n", __func__,
- it->it_name);
- break;
- }
- }
-
-out_unlock:
- up_read(&htable_rw_lock);
-out_free_path:
- kfree(npath);
- return rc;
-}
-
/**
* dfs_cache_noreq_update_tgthint - update target hint of a DFS cache entry
* without sending any requests to the currently connected server.
diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h
index f7cff0be93274..be3b5a44cf827 100644
--- a/fs/cifs/dfs_cache.h
+++ b/fs/cifs/dfs_cache.h
@@ -35,9 +35,6 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl
struct dfs_cache_tgt_list *tgt_list);
int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref,
struct dfs_cache_tgt_list *tgt_list);
-int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
- const struct nls_table *cp, int remap, const char *path,
- const struct dfs_cache_tgt_iterator *it);
void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt_iterator *it);
int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it,
struct dfs_info3_param *ref);
--
GitLab
From bbbd25499100c810ceaf5193c3cfcab9f7402a33 Mon Sep 17 00:00:00 2001
From: "Alexey V. Vissarionov" <gremlin@altlinux.org>
Date: Wed, 18 Jan 2023 06:12:55 +0300
Subject: [PATCH 0955/1167] scsi: hpsa: Fix allocation size for
scsi_host_alloc()
The 'h' is a pointer to struct ctlr_info, so it's just 4 or 8 bytes, while
the structure itself is much bigger.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Fixes: edd163687ea5 ("hpsa: add driver for HP Smart Array controllers.")
Link: https://lore.kernel.org/r/20230118031255.GE15213@altlinux.org
Signed-off-by: Alexey V. Vissarionov <gremlin@altlinux.org>
Acked-by: Don Brace <don.brace@microchip.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/hpsa.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 4dbf51e2623ad..f6da34850af9d 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -5850,7 +5850,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h)
{
struct Scsi_Host *sh;
- sh = scsi_host_alloc(&hpsa_driver_template, sizeof(h));
+ sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info));
if (sh == NULL) {
dev_err(&h->pdev->dev, "scsi_host_alloc failed\n");
return -ENOMEM;
--
GitLab
From ba81043753fffbc2ad6e0c5ff2659f12ac2f46b4 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 16 Jan 2023 17:12:01 +0100
Subject: [PATCH 0956/1167] scsi: ufs: core: Fix devfreq deadlocks
There is a lock inversion and rwsem read-lock recursion in the devfreq
target callback which can lead to deadlocks.
Specifically, ufshcd_devfreq_scale() already holds a clk_scaling_lock
read lock when toggling the write booster, which involves taking the
dev_cmd mutex before taking another clk_scaling_lock read lock.
This can lead to a deadlock if another thread:
1) tries to acquire the dev_cmd and clk_scaling locks in the correct
order, or
2) takes a clk_scaling write lock before the attempt to take the
clk_scaling read lock a second time.
Fix this by dropping the clk_scaling_lock before toggling the write booster
as was done before commit 0e9d4ca43ba8 ("scsi: ufs: Protect some contexts
from unexpected clock scaling").
While the devfreq callbacks are already serialised, add a second
serialising mutex to handle the unlikely case where a callback triggered
through the devfreq sysfs interface is racing with a request to disable
clock scaling through the UFS controller 'clkscale_enable' sysfs
attribute. This could otherwise lead to the write booster being left
disabled after having disabled clock scaling.
Also take the new mutex in ufshcd_clk_scaling_allow() to make sure that any
pending write booster update has completed on return.
Note that this currently only affects Qualcomm platforms since commit
87bd05016a64 ("scsi: ufs: core: Allow host driver to disable wb toggling
during clock scaling").
The lock inversion (i.e. 1 above) was reported by lockdep as:
======================================================
WARNING: possible circular locking dependency detected
6.1.0-next-20221216 #211 Not tainted
------------------------------------------------------
kworker/u16:2/71 is trying to acquire lock:
ffff076280ba98a0 (&hba->dev_cmd.lock){+.+.}-{3:3}, at: ufshcd_query_flag+0x50/0x1c0
but task is already holding lock:
ffff076280ba9cf0 (&hba->clk_scaling_lock){++++}-{3:3}, at: ufshcd_devfreq_scale+0x2b8/0x380
which lock already depends on the new lock.
[ +0.011606]
the existing dependency chain (in reverse order) is:
-> #1 (&hba->clk_scaling_lock){++++}-{3:3}:
lock_acquire+0x68/0x90
down_read+0x58/0x80
ufshcd_exec_dev_cmd+0x70/0x2c0
ufshcd_verify_dev_init+0x68/0x170
ufshcd_probe_hba+0x398/0x1180
ufshcd_async_scan+0x30/0x320
async_run_entry_fn+0x34/0x150
process_one_work+0x288/0x6c0
worker_thread+0x74/0x450
kthread+0x118/0x120
ret_from_fork+0x10/0x20
-> #0 (&hba->dev_cmd.lock){+.+.}-{3:3}:
__lock_acquire+0x12a0/0x2240
lock_acquire.part.0+0xcc/0x220
lock_acquire+0x68/0x90
__mutex_lock+0x98/0x430
mutex_lock_nested+0x2c/0x40
ufshcd_query_flag+0x50/0x1c0
ufshcd_query_flag_retry+0x64/0x100
ufshcd_wb_toggle+0x5c/0x120
ufshcd_devfreq_scale+0x2c4/0x380
ufshcd_devfreq_target+0xf4/0x230
devfreq_set_target+0x84/0x2f0
devfreq_update_target+0xc4/0xf0
devfreq_monitor+0x38/0x1f0
process_one_work+0x288/0x6c0
worker_thread+0x74/0x450
kthread+0x118/0x120
ret_from_fork+0x10/0x20
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&hba->clk_scaling_lock);
lock(&hba->dev_cmd.lock);
lock(&hba->clk_scaling_lock);
lock(&hba->dev_cmd.lock);
*** DEADLOCK ***
Fixes: 0e9d4ca43ba8 ("scsi: ufs: Protect some contexts from unexpected clock scaling")
Cc: stable@vger.kernel.org # 5.12
Cc: Can Guo <quic_cang@quicinc.com>
Tested-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230116161201.16923-1-johan+linaro@kernel.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/ufs/core/ufshcd.c | 29 +++++++++++++++--------------
include/ufs/ufshcd.h | 2 ++
2 files changed, 17 insertions(+), 14 deletions(-)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index bda61be5f0357..3a1c4d31e010d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1234,12 +1234,14 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)
* clock scaling is in progress
*/
ufshcd_scsi_block_requests(hba);
+ mutex_lock(&hba->wb_mutex);
down_write(&hba->clk_scaling_lock);
if (!hba->clk_scaling.is_allowed ||
ufshcd_wait_for_doorbell_clr(hba, DOORBELL_CLR_TOUT_US)) {
ret = -EBUSY;
up_write(&hba->clk_scaling_lock);
+ mutex_unlock(&hba->wb_mutex);
ufshcd_scsi_unblock_requests(hba);
goto out;
}
@@ -1251,12 +1253,16 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)
return ret;
}
-static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock)
+static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool scale_up)
{
- if (writelock)
- up_write(&hba->clk_scaling_lock);
- else
- up_read(&hba->clk_scaling_lock);
+ up_write(&hba->clk_scaling_lock);
+
+ /* Enable Write Booster if we have scaled up else disable it */
+ if (ufshcd_enable_wb_if_scaling_up(hba) && !err)
+ ufshcd_wb_toggle(hba, scale_up);
+
+ mutex_unlock(&hba->wb_mutex);
+
ufshcd_scsi_unblock_requests(hba);
ufshcd_release(hba);
}
@@ -1273,7 +1279,6 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock)
static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up)
{
int ret = 0;
- bool is_writelock = true;
ret = ufshcd_clock_scaling_prepare(hba);
if (ret)
@@ -1302,15 +1307,8 @@ static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up)
}
}
- /* Enable Write Booster if we have scaled up else disable it */
- if (ufshcd_enable_wb_if_scaling_up(hba)) {
- downgrade_write(&hba->clk_scaling_lock);
- is_writelock = false;
- ufshcd_wb_toggle(hba, scale_up);
- }
-
out_unprepare:
- ufshcd_clock_scaling_unprepare(hba, is_writelock);
+ ufshcd_clock_scaling_unprepare(hba, ret, scale_up);
return ret;
}
@@ -6066,9 +6064,11 @@ static void ufshcd_force_error_recovery(struct ufs_hba *hba)
static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow)
{
+ mutex_lock(&hba->wb_mutex);
down_write(&hba->clk_scaling_lock);
hba->clk_scaling.is_allowed = allow;
up_write(&hba->clk_scaling_lock);
+ mutex_unlock(&hba->wb_mutex);
}
static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend)
@@ -9793,6 +9793,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
/* Initialize mutex for exception event control */
mutex_init(&hba->ee_ctrl_mutex);
+ mutex_init(&hba->wb_mutex);
init_rwsem(&hba->clk_scaling_lock);
ufshcd_init_clk_gating(hba);
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index 5cf81dff60aa0..727084cd79be4 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -808,6 +808,7 @@ struct ufs_hba_monitor {
* @urgent_bkops_lvl: keeps track of urgent bkops level for device
* @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for
* device is known or not.
+ * @wb_mutex: used to serialize devfreq and sysfs write booster toggling
* @clk_scaling_lock: used to serialize device commands and clock scaling
* @desc_size: descriptor sizes reported by device
* @scsi_block_reqs_cnt: reference counting for scsi block requests
@@ -951,6 +952,7 @@ struct ufs_hba {
enum bkops_status urgent_bkops_lvl;
bool is_urgent_bkops_lvl_checked;
+ struct mutex wb_mutex;
struct rw_semaphore clk_scaling_lock;
unsigned char desc_size[QUERY_DESC_IDN_MAX];
atomic_t scsi_block_reqs_cnt;
--
GitLab
From 6f1d64b13097e85abda0f91b5638000afc5f9a06 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Tue, 17 Jan 2023 13:39:36 -0600
Subject: [PATCH 0957/1167] scsi: iscsi_tcp: Fix UAF during logout when
accessing the shost ipaddress
Bug report and analysis from Ding Hui.
During iSCSI session logout, if another task accesses the shost ipaddress
attr, we can get a KASAN UAF report like this:
[ 276.942144] BUG: KASAN: use-after-free in _raw_spin_lock_bh+0x78/0xe0
[ 276.942535] Write of size 4 at addr ffff8881053b45b8 by task cat/4088
[ 276.943511] CPU: 2 PID: 4088 Comm: cat Tainted: G E 6.1.0-rc8+ #3
[ 276.943997] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020
[ 276.944470] Call Trace:
[ 276.944943] <TASK>
[ 276.945397] dump_stack_lvl+0x34/0x48
[ 276.945887] print_address_description.constprop.0+0x86/0x1e7
[ 276.946421] print_report+0x36/0x4f
[ 276.947358] kasan_report+0xad/0x130
[ 276.948234] kasan_check_range+0x35/0x1c0
[ 276.948674] _raw_spin_lock_bh+0x78/0xe0
[ 276.949989] iscsi_sw_tcp_host_get_param+0xad/0x2e0 [iscsi_tcp]
[ 276.951765] show_host_param_ISCSI_HOST_PARAM_IPADDRESS+0xe9/0x130 [scsi_transport_iscsi]
[ 276.952185] dev_attr_show+0x3f/0x80
[ 276.953005] sysfs_kf_seq_show+0x1fb/0x3e0
[ 276.953401] seq_read_iter+0x402/0x1020
[ 276.954260] vfs_read+0x532/0x7b0
[ 276.955113] ksys_read+0xed/0x1c0
[ 276.955952] do_syscall_64+0x38/0x90
[ 276.956347] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 276.956769] RIP: 0033:0x7f5d3a679222
[ 276.957161] Code: c0 e9 b2 fe ff ff 50 48 8d 3d 32 c0 0b 00 e8 a5 fe 01 00 0f 1f 44 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 48 83 ec 28 48 89 54 24
[ 276.958009] RSP: 002b:00007ffc864d16a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[ 276.958431] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f5d3a679222
[ 276.958857] RDX: 0000000000020000 RSI: 00007f5d3a4fe000 RDI: 0000000000000003
[ 276.959281] RBP: 00007f5d3a4fe000 R08: 00000000ffffffff R09: 0000000000000000
[ 276.959682] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000020000
[ 276.960126] R13: 0000000000000003 R14: 0000000000000000 R15: 0000557a26dada58
[ 276.960536] </TASK>
[ 276.961357] Allocated by task 2209:
[ 276.961756] kasan_save_stack+0x1e/0x40
[ 276.962170] kasan_set_track+0x21/0x30
[ 276.962557] __kasan_kmalloc+0x7e/0x90
[ 276.962923] __kmalloc+0x5b/0x140
[ 276.963308] iscsi_alloc_session+0x28/0x840 [scsi_transport_iscsi]
[ 276.963712] iscsi_session_setup+0xda/0xba0 [libiscsi]
[ 276.964078] iscsi_sw_tcp_session_create+0x1fd/0x330 [iscsi_tcp]
[ 276.964431] iscsi_if_create_session.isra.0+0x50/0x260 [scsi_transport_iscsi]
[ 276.964793] iscsi_if_recv_msg+0xc5a/0x2660 [scsi_transport_iscsi]
[ 276.965153] iscsi_if_rx+0x198/0x4b0 [scsi_transport_iscsi]
[ 276.965546] netlink_unicast+0x4d5/0x7b0
[ 276.965905] netlink_sendmsg+0x78d/0xc30
[ 276.966236] sock_sendmsg+0xe5/0x120
[ 276.966576] ____sys_sendmsg+0x5fe/0x860
[ 276.966923] ___sys_sendmsg+0xe0/0x170
[ 276.967300] __sys_sendmsg+0xc8/0x170
[ 276.967666] do_syscall_64+0x38/0x90
[ 276.968028] entry_SYSCALL_64_after_hwframe+0x63/0xcd
[ 276.968773] Freed by task 2209:
[ 276.969111] kasan_save_stack+0x1e/0x40
[ 276.969449] kasan_set_track+0x21/0x30
[ 276.969789] kasan_save_free_info+0x2a/0x50
[ 276.970146] __kasan_slab_free+0x106/0x190
[ 276.970470] __kmem_cache_free+0x133/0x270
[ 276.970816] device_release+0x98/0x210
[ 276.971145] kobject_cleanup+0x101/0x360
[ 276.971462] iscsi_session_teardown+0x3fb/0x530 [libiscsi]
[ 276.971775] iscsi_sw_tcp_session_destroy+0xd8/0x130 [iscsi_tcp]
[ 276.972143] iscsi_if_recv_msg+0x1bf1/0x2660 [scsi_transport_iscsi]
[ 276.972485] iscsi_if_rx+0x198/0x4b0 [scsi_transport_iscsi]
[ 276.972808] netlink_unicast+0x4d5/0x7b0
[ 276.973201] netlink_sendmsg+0x78d/0xc30
[ 276.973544] sock_sendmsg+0xe5/0x120
[ 276.973864] ____sys_sendmsg+0x5fe/0x860
[ 276.974248] ___sys_sendmsg+0xe0/0x170
[ 276.974583] __sys_sendmsg+0xc8/0x170
[ 276.974891] do_syscall_64+0x38/0x90
[ 276.975216] entry_SYSCALL_64_after_hwframe+0x63/0xcd
We can easily reproduce by two tasks:
1. while :; do iscsiadm -m node --login; iscsiadm -m node --logout; done
2. while :; do cat \
/sys/devices/platform/host*/iscsi_host/host*/ipaddress; done
iscsid | cat
--------------------------------+---------------------------------------
|- iscsi_sw_tcp_session_destroy |
|- iscsi_session_teardown |
|- device_release |
|- iscsi_session_release ||- dev_attr_show
|- kfree | |- show_host_param_
| ISCSI_HOST_PARAM_IPADDRESS
| |- iscsi_sw_tcp_host_get_param
| |- r/w tcp_sw_host->session (UAF)
|- iscsi_host_remove |
|- iscsi_host_free |
Fix the above bug by splitting the session removal into 2 parts:
1. removal from iSCSI class which includes sysfs and removal from host
tracking.
2. freeing of session.
During iscsi_tcp host and session removal we can remove the session from
sysfs then remove the host from sysfs. At this point we know userspace is
not accessing the kernel via sysfs so we can free the session and host.
Link: https://lore.kernel.org/r/20230117193937.21244-2-michael.christie@oracle.com
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Acked-by: Ding Hui <dinghui@sangfor.com.cn>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/iscsi_tcp.c | 11 +++++++++--
drivers/scsi/libiscsi.c | 38 +++++++++++++++++++++++++++++++-------
include/scsi/libiscsi.h | 2 ++
3 files changed, 42 insertions(+), 9 deletions(-)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 1d1cf641937c1..5c679a8d239bf 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -983,10 +983,17 @@ static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
if (WARN_ON_ONCE(session->leadconn))
return;
+ iscsi_session_remove(cls_session);
+ /*
+ * Our get_host_param needs to access the session, so remove the
+ * host from sysfs before freeing the session to make sure userspace
+ * is no longer accessing the callout.
+ */
+ iscsi_host_remove(shost, false);
+
iscsi_tcp_r2tpool_free(cls_session->dd_data);
- iscsi_session_teardown(cls_session);
- iscsi_host_remove(shost, false);
+ iscsi_session_free(cls_session);
iscsi_host_free(shost);
}
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index ef2fc860257e6..127f3d7f19dc6 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -3104,17 +3104,32 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
}
EXPORT_SYMBOL_GPL(iscsi_session_setup);
-/**
- * iscsi_session_teardown - destroy session, host, and cls_session
- * @cls_session: iscsi session
+/*
+ * issi_session_remove - Remove session from iSCSI class.
*/
-void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
+void iscsi_session_remove(struct iscsi_cls_session *cls_session)
{
struct iscsi_session *session = cls_session->dd_data;
- struct module *owner = cls_session->transport->owner;
struct Scsi_Host *shost = session->host;
iscsi_remove_session(cls_session);
+ /*
+ * host removal only has to wait for its children to be removed from
+ * sysfs, and iscsi_tcp needs to do iscsi_host_remove before freeing
+ * the session, so drop the session count here.
+ */
+ iscsi_host_dec_session_cnt(shost);
+}
+EXPORT_SYMBOL_GPL(iscsi_session_remove);
+
+/**
+ * iscsi_session_free - Free iscsi session and it's resources
+ * @cls_session: iscsi session
+ */
+void iscsi_session_free(struct iscsi_cls_session *cls_session)
+{
+ struct iscsi_session *session = cls_session->dd_data;
+ struct module *owner = cls_session->transport->owner;
iscsi_pool_free(&session->cmdpool);
kfree(session->password);
@@ -3132,10 +3147,19 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
kfree(session->discovery_parent_type);
iscsi_free_session(cls_session);
-
- iscsi_host_dec_session_cnt(shost);
module_put(owner);
}
+EXPORT_SYMBOL_GPL(iscsi_session_free);
+
+/**
+ * iscsi_session_teardown - destroy session and cls_session
+ * @cls_session: iscsi session
+ */
+void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
+{
+ iscsi_session_remove(cls_session);
+ iscsi_session_free(cls_session);
+}
EXPORT_SYMBOL_GPL(iscsi_session_teardown);
/**
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 695eebc6f2c89..e39fb0736ade5 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -422,6 +422,8 @@ extern int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost,
extern struct iscsi_cls_session *
iscsi_session_setup(struct iscsi_transport *, struct Scsi_Host *shost,
uint16_t, int, int, uint32_t, unsigned int);
+void iscsi_session_remove(struct iscsi_cls_session *cls_session);
+void iscsi_session_free(struct iscsi_cls_session *cls_session);
extern void iscsi_session_teardown(struct iscsi_cls_session *);
extern void iscsi_session_recovery_timedout(struct iscsi_cls_session *);
extern int iscsi_set_param(struct iscsi_cls_conn *cls_conn,
--
GitLab
From f484a794e4ee2a9ce61f52a78e810ac45f3fe3b3 Mon Sep 17 00:00:00 2001
From: Mike Christie <michael.christie@oracle.com>
Date: Tue, 17 Jan 2023 13:39:37 -0600
Subject: [PATCH 0958/1167] scsi: iscsi_tcp: Fix UAF during login when
accessing the shost ipaddress
If during iscsi_sw_tcp_session_create() iscsi_tcp_r2tpool_alloc() fails,
userspace could be accessing the host's ipaddress attr. If we then free the
session via iscsi_session_teardown() while userspace is still accessing the
session we will hit a use after free bug.
Set the tcp_sw_host->session after we have completed session creation and
can no longer fail.
Link: https://lore.kernel.org/r/20230117193937.21244-3-michael.christie@oracle.com
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: Lee Duncan <lduncan@suse.com>
Acked-by: Ding Hui <dinghui@sangfor.com.cn>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/iscsi_tcp.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 5c679a8d239bf..0454d94e8cf0d 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -849,7 +849,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
enum iscsi_host_param param, char *buf)
{
struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost);
- struct iscsi_session *session = tcp_sw_host->session;
+ struct iscsi_session *session;
struct iscsi_conn *conn;
struct iscsi_tcp_conn *tcp_conn;
struct iscsi_sw_tcp_conn *tcp_sw_conn;
@@ -859,6 +859,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
switch (param) {
case ISCSI_HOST_PARAM_IPADDRESS:
+ session = tcp_sw_host->session;
if (!session)
return -ENOTCONN;
@@ -959,11 +960,13 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max,
if (!cls_session)
goto remove_host;
session = cls_session->dd_data;
- tcp_sw_host = iscsi_host_priv(shost);
- tcp_sw_host->session = session;
if (iscsi_tcp_r2tpool_alloc(session))
goto remove_session;
+
+ /* We are now fully setup so expose the session to sysfs. */
+ tcp_sw_host = iscsi_host_priv(shost);
+ tcp_sw_host->session = session;
return cls_session;
remove_session:
--
GitLab
From 0bfe63d075789456e9589457b29d6f9c279e3252 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 18 Jan 2023 10:05:57 -0800
Subject: [PATCH 0959/1167] scsi: device_handler: alua: Remove a might_sleep()
annotation
The might_sleep() annotation in alua_rtpg_queue() is not correct since the
command completion code may call this function from atomic context.
Calling alua_rtpg_queue() from atomic context in the command completion
path is fine since request submitters must hold an sdev reference until
command execution has completed. This patch fixes the following kernel
complaint:
BUG: sleeping function called from invalid context at drivers/scsi/device_handler/scsi_dh_alua.c:992
Call Trace:
dump_stack_lvl+0xac/0x100
__might_resched+0x284/0x2c8
alua_rtpg_queue+0x3c/0x98 [scsi_dh_alua]
alua_check+0x122/0x250 [scsi_dh_alua]
alua_check_sense+0x172/0x228 [scsi_dh_alua]
scsi_check_sense+0x8a/0x2e0
scsi_decide_disposition+0x286/0x298
scsi_complete+0x6a/0x108
blk_complete_reqs+0x6e/0x88
__do_softirq+0x13e/0x6b8
__irq_exit_rcu+0x14a/0x170
irq_exit_rcu+0x22/0x50
do_ext_irq+0x10a/0x1d0
Link: https://lore.kernel.org/r/20230118180557.1212577-1-bvanassche@acm.org
Reported-by: Steffen Maier <maier@linux.ibm.com>
Reviewed-by: Martin Wilck <mwilck@suse.com>
Tested-by: Steffen Maier <maier@linux.ibm.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
drivers/scsi/device_handler/scsi_dh_alua.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 49cc18a874731..29a2865b8e2e1 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -981,6 +981,9 @@ static void alua_rtpg_work(struct work_struct *work)
*
* Returns true if and only if alua_rtpg_work() will be called asynchronously.
* That function is responsible for calling @qdata->fn().
+ *
+ * Context: may be called from atomic context (alua_check()) only if the caller
+ * holds an sdev reference.
*/
static bool alua_rtpg_queue(struct alua_port_group *pg,
struct scsi_device *sdev,
@@ -989,8 +992,6 @@ static bool alua_rtpg_queue(struct alua_port_group *pg,
int start_queue = 0;
unsigned long flags;
- might_sleep();
-
if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev))
return false;
--
GitLab
From 040625ab82ce6dca7772cb3867fe5c9eb279a344 Mon Sep 17 00:00:00 2001
From: hongao <hongao@uniontech.com>
Date: Tue, 22 Nov 2022 19:20:34 +0800
Subject: [PATCH 0960/1167] drm/amd/display: Fix set scaling doesn's work
[Why]
Setting scaling does not correctly update CRTC state. As a result
dc stream state's src (composition area) && dest (addressable area)
was not calculated as expected. This causes set scaling doesn's work.
[How]
Correctly update CRTC state when setting scaling property.
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Tested-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: hongao <hongao@uniontech.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1b7f20a9d4aeb..74f624ec55e7a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9530,8 +9530,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
goto fail;
}
- if (dm_old_con_state->abm_level !=
- dm_new_con_state->abm_level)
+ if (dm_old_con_state->abm_level != dm_new_con_state->abm_level ||
+ dm_old_con_state->scaling != dm_new_con_state->scaling)
new_crtc_state->connectors_changed = true;
}
--
GitLab
From c7bae4aaa5609c1fa9761c35dbcc5fcc92915222 Mon Sep 17 00:00:00 2001
From: jie1zhan <jesse.zhang@amd.com>
Date: Fri, 13 Jan 2023 10:39:13 +0800
Subject: [PATCH 0961/1167] drm/amdgpu: Correct the power calcultion for
Renior/Cezanne.
From smu firmware,the value of power is transferred in units of watts.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2321
Fixes: 137aac26a2ed ("drm/amdgpu/smu12: fix power reporting on renoir")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Aaron Liu <aaron.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index 85e22210963fc..5cdc07165480b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -1171,6 +1171,7 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu,
int ret = 0;
uint32_t apu_percent = 0;
uint32_t dgpu_percent = 0;
+ struct amdgpu_device *adev = smu->adev;
ret = smu_cmn_get_metrics_table(smu,
@@ -1196,7 +1197,11 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu,
*value = metrics->AverageUvdActivity / 100;
break;
case METRICS_AVERAGE_SOCKETPOWER:
- *value = (metrics->CurrentSocketPower << 8) / 1000;
+ if (((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) && (adev->pm.fw_version >= 0x40000f)) ||
+ ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0)) && (adev->pm.fw_version >= 0x373200)))
+ *value = metrics->CurrentSocketPower << 8;
+ else
+ *value = (metrics->CurrentSocketPower << 8) / 1000;
break;
case METRICS_TEMPERATURE_EDGE:
*value = (metrics->GfxTemperature / 100) *
--
GitLab
From 4463b1eea28ad733ca5cb53d89371132a57b1db3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 13 Jan 2023 17:32:45 +0100
Subject: [PATCH 0962/1167] drm/amdgpu: fix cleaning up reserved VMID on
release
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
We need to reset this or otherwise run into list corruption later on.
Fixes: e44a0fe630c5 ("drm/amdgpu: rework reserved VMID handling")
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Candice Li <candice.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index fcb711a11a5b6..3f07b1a2ce47f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -497,6 +497,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
!--id_mgr->reserved_use_count) {
/* give the reserved ID back to normal round robin */
list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
+ id_mgr->reserved = NULL;
}
vm->reserved_vmid[vmhub] = false;
mutex_unlock(&id_mgr->lock);
--
GitLab
From 79601b894849cb6f6d6122e6590f1887ac4a66b3 Mon Sep 17 00:00:00 2001
From: Joshua Ashton <joshua@froggi.es>
Date: Tue, 10 Jan 2023 20:12:21 +0000
Subject: [PATCH 0963/1167] drm/amd/display: Calculate output_color_space after
pixel encoding adjustment
Code in get_output_color_space depends on knowing the pixel encoding to
determine whether to pick between eg. COLOR_SPACE_SRGB or
COLOR_SPACE_YCBCR709 for transparent RGB -> YCbCr 4:4:4 in the driver.
v2: Fixed patch being accidentally based on a personal feature branch, oops!
Fixes: ea117312ea9f ("drm/amd/display: Reduce HDMI pixel encoding if max clock is exceeded")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 74f624ec55e7a..c994a5d8c3f57 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5311,8 +5311,6 @@ static void fill_stream_properties_from_drm_display_mode(
timing_out->aspect_ratio = get_aspect_ratio(mode_in);
- stream->output_color_space = get_output_color_space(timing_out);
-
stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
@@ -5323,6 +5321,8 @@ static void fill_stream_properties_from_drm_display_mode(
adjust_colour_depth_from_display_info(timing_out, info);
}
}
+
+ stream->output_color_space = get_output_color_space(timing_out);
}
static void fill_audio_info(struct audio_info *audio_info,
--
GitLab
From 973a9c810c785ac270a6d50d8cf862b0c1643a10 Mon Sep 17 00:00:00 2001
From: Joshua Ashton <joshua@froggi.es>
Date: Tue, 10 Jan 2023 22:50:42 +0000
Subject: [PATCH 0964/1167] drm/amd/display: Fix COLOR_SPACE_YCBCR2020_TYPE
matrix
The YCC conversion matrix for RGB -> COLOR_SPACE_YCBCR2020_TYPE is
missing the values for the fourth column of the matrix.
The fourth column of the matrix is essentially just a value that is
added given that the color is 3 components in size.
These values are needed to bias the chroma from the [-1, 1] -> [0, 1]
range.
This fixes color being very green when using Gamescope HDR on HDMI
output which prefers YCC 4:4:4.
Fixes: 40df2f809e8f ("drm/amd/display: color space ycbcr709 support")
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Joshua Ashton <joshua@froggi.es>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index 471078fc3900d..652270a0b498c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -90,8 +90,8 @@ static const struct out_csc_color_matrix_type output_csc_matrix[] = {
{ 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3,
0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} },
{ COLOR_SPACE_YCBCR2020_TYPE,
- { 0x1000, 0xF149, 0xFEB7, 0x0000, 0x0868, 0x15B2,
- 0x01E6, 0x0000, 0xFB88, 0xF478, 0x1000, 0x0000} },
+ { 0x1000, 0xF149, 0xFEB7, 0x1004, 0x0868, 0x15B2,
+ 0x01E6, 0x201, 0xFB88, 0xF478, 0x1000, 0x1004} },
{ COLOR_SPACE_YCBCR709_BLACK_TYPE,
{ 0x0000, 0x0000, 0x0000, 0x1000, 0x0000, 0x0000,
0x0000, 0x0200, 0x0000, 0x0000, 0x0000, 0x1000} },
--
GitLab
From 74ea8e78ab349514c9f4df0be1189d91267d750d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 12 Jan 2023 14:46:00 +0100
Subject: [PATCH 0965/1167] drm/amdgpu: fix amdgpu_job_free_resources v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
It can be that neither fence were initialized when we run out of UVD
streams for example.
v2: fix typo breaking compile
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2324
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9e549923622bd..c3d9d75143f4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -161,8 +161,14 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
struct dma_fence *f;
unsigned i;
- /* use sched fence if available */
- f = job->base.s_fence ? &job->base.s_fence->finished : &job->hw_fence;
+ /* Check if any fences where initialized */
+ if (job->base.s_fence && job->base.s_fence->finished.ops)
+ f = &job->base.s_fence->finished;
+ else if (job->hw_fence.ops)
+ f = &job->hw_fence;
+ else
+ f = NULL;
+
for (i = 0; i < job->num_ibs; ++i)
amdgpu_ib_free(ring->adev, &job->ibs[i], f);
}
--
GitLab
From e433adc60f7f847e734c56246b09291532f29b6d Mon Sep 17 00:00:00 2001
From: Hamza Mahfooz <hamza.mahfooz@amd.com>
Date: Tue, 17 Jan 2023 15:12:49 -0500
Subject: [PATCH 0966/1167] drm/amd/display: fix issues with driver unload
Currently, we run into a number of WARN()s when attempting to unload the
amdgpu driver (e.g. using "modprobe -r amdgpu"). These all stem from
calling drm_encoder_cleanup() too early. So, to fix this we can stop
calling drm_encoder_cleanup() from amdgpu_dm_fini() and instead have it
be called from amdgpu_dm_encoder_destroy(). Also, we don't need to free
in amdgpu_dm_encoder_destroy() since mst_encoders[] isn't explicitly
allocated by the slab allocator.
Fixes: f74367e492ba ("drm/amdgpu/display: create fake mst encoders ahead of time (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Hamza Mahfooz <hamza.mahfooz@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ----
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 1 -
2 files changed, 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c994a5d8c3f57..36483a1bf6e37 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1730,10 +1730,6 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
adev->dm.vblank_control_workqueue = NULL;
}
- for (i = 0; i < adev->dm.display_indexes_num; i++) {
- drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
- }
-
amdgpu_dm_destroy_drm_device(&adev->dm);
#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 1edf7385f8d89..d7a044e797305 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -468,7 +468,6 @@ static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs
static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
{
drm_encoder_cleanup(encoder);
- kfree(encoder);
}
static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = {
--
GitLab
From 0ddadc3a2208aedb1b27dbb76d0b4e722b5b527a Mon Sep 17 00:00:00 2001
From: Lang Yu <Lang.Yu@amd.com>
Date: Wed, 11 Jan 2023 09:52:11 +0800
Subject: [PATCH 0967/1167] drm/amdgpu: correct MEC number for gfx11 APUs
There is only one MEC on these APUs.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Aaron Liu <aaron.liu@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index a56c6e106d00d..b9b57a66e113f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1287,10 +1287,8 @@ static int gfx_v11_0_sw_init(void *handle)
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(11, 0, 0):
- case IP_VERSION(11, 0, 1):
case IP_VERSION(11, 0, 2):
case IP_VERSION(11, 0, 3):
- case IP_VERSION(11, 0, 4):
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 1;
adev->gfx.me.num_queue_per_pipe = 1;
@@ -1298,6 +1296,15 @@ static int gfx_v11_0_sw_init(void *handle)
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 4;
break;
+ case IP_VERSION(11, 0, 1):
+ case IP_VERSION(11, 0, 4):
+ adev->gfx.me.num_me = 1;
+ adev->gfx.me.num_pipe_per_me = 1;
+ adev->gfx.me.num_queue_per_pipe = 1;
+ adev->gfx.mec.num_mec = 1;
+ adev->gfx.mec.num_pipe_per_mec = 4;
+ adev->gfx.mec.num_queue_per_pipe = 4;
+ break;
default:
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 1;
--
GitLab
From dc88063b87775971be564d79dc1b05f7b8b5c135 Mon Sep 17 00:00:00 2001
From: Lang Yu <Lang.Yu@amd.com>
Date: Wed, 11 Jan 2023 09:32:15 +0800
Subject: [PATCH 0968/1167] drm/amdgpu: allow multipipe policy on ASICs with
one MEC
Always enable multipipe policy on ASICs with GC VERSION > 9.0.0
instead of MEC number > 1.
This will allow multipipe policy on ASICs with one MEC,
e.g., gfx11 APUs.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Aaron Liu <aaron.liu@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 23692e5d4d13b..3380daf42da8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -156,6 +156,9 @@ static bool amdgpu_gfx_is_compute_multipipe_capable(struct amdgpu_device *adev)
return amdgpu_compute_multipipe == 1;
}
+ if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))
+ return true;
+
/* FIXME: spreading the queues across pipes causes perf regressions
* on POLARIS11 compute workloads */
if (adev->asic_type == CHIP_POLARIS11)
--
GitLab
From e78cc6a4c7486f50c2786d91dd7d9649a87d1dcb Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 18 Jan 2023 09:19:21 -0500
Subject: [PATCH 0969/1167] drm/amd/display: disable S/G display on DCN 3.1.5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Causes flickering or white screens in some configurations.
Disable it for now until we can fix the issue.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2354
Cc: roman.li@amd.com
Cc: yifan1.zhang@amd.com
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 36483a1bf6e37..649bdd5be9512 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1504,7 +1504,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
case IP_VERSION(3, 1, 2):
case IP_VERSION(3, 1, 3):
case IP_VERSION(3, 1, 4):
- case IP_VERSION(3, 1, 5):
case IP_VERSION(3, 1, 6):
init_data.flags.gpu_vm_support = true;
break;
--
GitLab
From a52287d66dfa1cca32e6273623b63ba39d87f126 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 18 Jan 2023 09:21:22 -0500
Subject: [PATCH 0970/1167] drm/amd/display: disable S/G display on DCN 3.1.4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Causes flickering or white screens in some configurations.
Disable it for now until we can fix the issue.
Cc: roman.li@amd.com
Cc: yifan1.zhang@amd.com
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Roman Li <Roman.Li@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 649bdd5be9512..4d42033a703fa 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1503,7 +1503,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
case IP_VERSION(3, 0, 1):
case IP_VERSION(3, 1, 2):
case IP_VERSION(3, 1, 3):
- case IP_VERSION(3, 1, 4):
case IP_VERSION(3, 1, 6):
init_data.flags.gpu_vm_support = true;
break;
--
GitLab
From 339346d49ae0859fe19b860998867861d37f1a76 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 12 Jan 2023 20:41:37 -0800
Subject: [PATCH 0971/1167] net: sched: gred: prevent races when adding
offloads to stats
Naresh reports seeing a warning that gred is calling
u64_stats_update_begin() with preemption enabled.
Arnd points out it's coming from _bstats_update().
We should be holding the qdisc lock when writing
to stats, they are also updated from the datapath.
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Link: https://lore.kernel.org/all/CA+G9fYsTr9_r893+62u6UGD3dVaCE-kN9C-Apmb2m=hxjc1Cqg@mail.gmail.com/
Fixes: e49efd5288bd ("net: sched: gred: support reporting stats from offloads")
Link: https://lore.kernel.org/r/20230113044137.1383067-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/sch_gred.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index a661b062cca85..872d127c9db42 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -377,6 +377,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch)
/* Even if driver returns failure adjust the stats - in case offload
* ended but driver still wants to adjust the values.
*/
+ sch_tree_lock(sch);
for (i = 0; i < MAX_DPs; i++) {
if (!table->tab[i])
continue;
@@ -393,6 +394,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch)
sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits;
}
_bstats_update(&sch->bstats, bytes, packets);
+ sch_tree_unlock(sch);
kfree(hw_stats);
return ret;
--
GitLab
From e0be11a833e8447f51f428b213c91a9b05601815 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 17 Jan 2023 11:01:41 -0800
Subject: [PATCH 0972/1167] MAINTAINERS: add networking entries for Willem
We often have to ping Willem asking for reviews of patches
because he doesn't get included in the CC list. Add MAINTAINERS
entries for some of the areas he covers so that ./scripts/ will
know to add him.
Acked-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Link: https://lore.kernel.org/r/20230117190141.60795-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
MAINTAINERS | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index e5c43cbffea78..180c18f936b7e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15748,6 +15748,12 @@ S: Maintained
W: https://wireless.wiki.kernel.org/en/users/Drivers/p54
F: drivers/net/wireless/intersil/p54/
+PACKET SOCKETS
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: include/uapi/linux/if_packet.h
+F: net/packet/af_packet.c
+
PACKING
M: Vladimir Oltean <olteanv@gmail.com>
L: netdev@vger.kernel.org
@@ -19324,6 +19330,13 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Orphan
F: sound/soc/uniphier/
+SOCKET TIMESTAMPING
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: Documentation/networking/timestamping.rst
+F: include/uapi/linux/net_tstamp.h
+F: tools/testing/selftests/net/so_txtime.c
+
SOEKRIS NET48XX LED SUPPORT
M: Chris Boot <bootc@bootc.net>
S: Maintained
@@ -21744,6 +21757,13 @@ T: git git://linuxtv.org/media_tree.git
F: Documentation/admin-guide/media/zr364xx*
F: drivers/staging/media/deprecated/zr364xx/
+USER DATAGRAM PROTOCOL (UDP)
+M: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+S: Maintained
+F: include/linux/udp.h
+F: net/ipv4/udp.c
+F: net/ipv6/udp.c
+
USER-MODE LINUX (UML)
M: Richard Weinberger <richard@nod.at>
M: Anton Ivanov <anton.ivanov@cambridgegreys.com>
--
GitLab
From 4fb58ac3368c6058e61194ec047a5503059d90ae Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 17 Jan 2023 13:42:12 -0500
Subject: [PATCH 0973/1167] Revert "net: team: use IFF_NO_ADDRCONF flag to
prevent ipv6 addrconf"
This reverts commit 0aa64df30b382fc71d4fb1827d528e0eb3eff854.
Currently IFF_NO_ADDRCONF is used to prevent all ipv6 addrconf for the
slave ports of team, bonding and failover devices and it means no ipv6
packets can be sent out through these slave ports. However, for team
device, "nsna_ping" link_watch requires ipv6 addrconf. Otherwise, the
link will be marked failure. This patch removes the IFF_NO_ADDRCONF
flag set for team port, and we will fix the original issue in another
patch, as Jakub suggested.
Fixes: 0aa64df30b38 ("net: team: use IFF_NO_ADDRCONF flag to prevent ipv6 addrconf")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/63e09531fc47963d2e4eff376653d3db21b97058.1673980932.git.lucien.xin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/team/team.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index fcd43d62d86bc..d10606f257c43 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1044,7 +1044,6 @@ static int team_port_enter(struct team *team, struct team_port *port)
goto err_port_enter;
}
}
- port->dev->priv_flags |= IFF_NO_ADDRCONF;
return 0;
@@ -1058,7 +1057,6 @@ static void team_port_leave(struct team *team, struct team_port *port)
{
if (team->ops.port_leave)
team->ops.port_leave(team, port);
- port->dev->priv_flags &= ~IFF_NO_ADDRCONF;
dev_put(team->dev);
}
--
GitLab
From c06ba7b892a50b48522ad441a40053f483dfee9e Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Tue, 17 Jan 2023 19:25:00 +0100
Subject: [PATCH 0974/1167] nvme-apple: reset controller during shutdown
This is a functional revert of c76b8308e4c9 ("nvme-apple: fix controller
shutdown in apple_nvme_disable").
The commit broke suspend/resume since apple_nvme_reset_work() tries to
disable the controller on resume. This does not work for the apple NVMe
controller since register access only works while the co-processor
firmware is running.
Disabling the NVMe controller in the shutdown path is also required
for shutting the co-processor down. The original code was appropriate
for this hardware. Add a comment to prevent a similar breaking changes
in the future.
Fixes: c76b8308e4c9 ("nvme-apple: fix controller shutdown in apple_nvme_disable")
Reported-by: Janne Grunau <j@jannau.net>
Link: https://lore.kernel.org/all/20230110174745.GA3576@jannau.net/
Signed-off-by: Janne Grunau <j@jannau.net>
[hch: updated with a more descriptive comment from Hector Martin]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/apple.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index bf1c60edb7f9a..146c9e63ce77e 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -829,7 +829,23 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown)
apple_nvme_remove_cq(anv);
}
- nvme_disable_ctrl(&anv->ctrl, shutdown);
+ /*
+ * Always disable the NVMe controller after shutdown.
+ * We need to do this to bring it back up later anyway, and we
+ * can't do it while the firmware is not running (e.g. in the
+ * resume reset path before RTKit is initialized), so for Apple
+ * controllers it makes sense to unconditionally do it here.
+ * Additionally, this sequence of events is reliable, while
+ * others (like disabling after bringing back the firmware on
+ * resume) seem to run into trouble under some circumstances.
+ *
+ * Both U-Boot and m1n1 also use this convention (i.e. an ANS
+ * NVMe controller is handed off with firmware shut down, in an
+ * NVMe disabled state, after a clean shutdown).
+ */
+ if (shutdown)
+ nvme_disable_ctrl(&anv->ctrl, shutdown);
+ nvme_disable_ctrl(&anv->ctrl, false);
}
WRITE_ONCE(anv->ioq.enabled, false);
--
GitLab
From c0a4a1eafbd48e02829045bba3e6163c03037276 Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Tue, 17 Jan 2023 19:25:01 +0100
Subject: [PATCH 0975/1167] nvme-apple: only reset the controller when RTKit is
running
NVMe controller register access hangs indefinitely when the co-processor
is not running. A missed reset is preferable over a hanging thread since
it could be recoverable.
Signed-off-by: Janne Grunau <j@jannau.net>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/apple.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 146c9e63ce77e..b317ce6c4ec31 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1001,11 +1001,11 @@ static void apple_nvme_reset_work(struct work_struct *work)
goto out;
}
- if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
- apple_nvme_disable(anv, false);
-
/* RTKit must be shut down cleanly for the (soft)-reset to work */
if (apple_rtkit_is_running(anv->rtk)) {
+ /* reset the controller if it is enabled */
+ if (anv->ctrl.ctrl_config & NVME_CC_ENABLE)
+ apple_nvme_disable(anv, false);
dev_dbg(anv->dev, "Trying to shut down RTKit before reset.");
ret = apple_rtkit_shutdown(anv->rtk);
if (ret)
--
GitLab
From 1c5842085851f786eba24a39ecd02650ad892064 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 18 Jan 2023 08:44:16 -0800
Subject: [PATCH 0976/1167] nvme-pci: fix timeout request state check
Polling the completion can progress the request state to IDLE, either
inline with the completion, or through softirq. Either way, the state
may not be COMPLETED, so don't check for that. We only care if the state
isn't IN_FLIGHT.
This is fixing an issue where the driver aborts an IO that we just
completed. Seeing the "aborting" message instead of "polled" is very
misleading as to where the timeout problem resides.
Fixes: bf392a5dc02a9b ("nvme-pci: Remove tag from process cq")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index a2553b7d9bb8e..1ff8843bc4b36 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1362,7 +1362,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
else
nvme_poll_irqdisable(nvmeq);
- if (blk_mq_request_completed(req)) {
+ if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
--
GitLab
From cec669ff716cc83505c77b242aecf6f7baad869d Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 18 Jan 2023 20:38:48 +0530
Subject: [PATCH 0977/1167] EDAC/device: Respect any driver-supplied workqueue
polling value
The EDAC drivers may optionally pass the poll_msec value. Use that value
if available, else fall back to 1000ms.
[ bp: Touchups. ]
Fixes: e27e3dac6517 ("drivers/edac: add edac_device class")
Reported-by: Luca Weiss <luca.weiss@fairphone.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Steev Klimaszewski <steev@kali.org> # Thinkpad X13s
Tested-by: Andrew Halaney <ahalaney@redhat.com> # sa8540p-ride
Cc: <stable@vger.kernel.org> # 4.9
Link: https://lore.kernel.org/r/COZYL8MWN97H.MROQ391BGA09@otso
---
drivers/edac/edac_device.c | 15 +++++++--------
1 file changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 878deb4880cdb..0689e15107213 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -34,6 +34,9 @@
static DEFINE_MUTEX(device_ctls_mutex);
static LIST_HEAD(edac_device_list);
+/* Default workqueue processing interval on this instance, in msecs */
+#define DEFAULT_POLL_INTERVAL 1000
+
#ifdef CONFIG_EDAC_DEBUG
static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev)
{
@@ -336,7 +339,7 @@ static void edac_device_workq_function(struct work_struct *work_req)
* whole one second to save timers firing all over the period
* between integral seconds
*/
- if (edac_dev->poll_msec == 1000)
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
else
edac_queue_work(&edac_dev->work, edac_dev->delay);
@@ -366,7 +369,7 @@ static void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
* timers firing on sub-second basis, while they are happy
* to fire together on the 1 second exactly
*/
- if (edac_dev->poll_msec == 1000)
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
else
edac_queue_work(&edac_dev->work, edac_dev->delay);
@@ -400,7 +403,7 @@ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev,
edac_dev->delay = msecs_to_jiffies(msec);
/* See comment in edac_device_workq_setup() above */
- if (edac_dev->poll_msec == 1000)
+ if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL)
edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
else
edac_mod_work(&edac_dev->work, edac_dev->delay);
@@ -442,11 +445,7 @@ int edac_device_add_device(struct edac_device_ctl_info *edac_dev)
/* This instance is NOW RUNNING */
edac_dev->op_state = OP_RUNNING_POLL;
- /*
- * enable workq processing on this instance,
- * default = 1000 msec
- */
- edac_device_workq_setup(edac_dev, 1000);
+ edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL);
} else {
edac_dev->op_state = OP_RUNNING_INTERRUPT;
}
--
GitLab
From 3f4ca5fafc08881d7a57daa20449d171f2887043 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Wed, 18 Jan 2023 09:59:41 +0800
Subject: [PATCH 0978/1167] tcp: avoid the lookup process failing to get sk in
ehash table
While one cpu is working on looking up the right socket from ehash
table, another cpu is done deleting the request socket and is about
to add (or is adding) the big socket from the table. It means that
we could miss both of them, even though it has little chance.
Let me draw a call trace map of the server side.
CPU 0 CPU 1
----- -----
tcp_v4_rcv() syn_recv_sock()
inet_ehash_insert()
-> sk_nulls_del_node_init_rcu(osk)
__inet_lookup_established()
-> __sk_nulls_add_node_rcu(sk, list)
Notice that the CPU 0 is receiving the data after the final ack
during 3-way shakehands and CPU 1 is still handling the final ack.
Why could this be a real problem?
This case is happening only when the final ack and the first data
receiving by different CPUs. Then the server receiving data with
ACK flag tries to search one proper established socket from ehash
table, but apparently it fails as my map shows above. After that,
the server fetches a listener socket and then sends a RST because
it finds a ACK flag in the skb (data), which obeys RST definition
in RFC 793.
Besides, Eric pointed out there's one more race condition where it
handles tw socket hashdance. Only by adding to the tail of the list
before deleting the old one can we avoid the race if the reader has
already begun the bucket traversal and it would possibly miss the head.
Many thanks to Eric for great help from beginning to end.
Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/lkml/20230112065336.41034-1-kerneljasonxing@gmail.com/
Link: https://lore.kernel.org/r/20230118015941.1313-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/ipv4/inet_hashtables.c | 17 +++++++++++++++--
net/ipv4/inet_timewait_sock.c | 8 ++++----
2 files changed, 19 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 24a38b56fab9e..f58d73888638b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -650,8 +650,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
spin_lock(lock);
if (osk) {
WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
- ret = sk_nulls_del_node_init_rcu(osk);
- } else if (found_dup_sk) {
+ ret = sk_hashed(osk);
+ if (ret) {
+ /* Before deleting the node, we insert a new one to make
+ * sure that the look-up-sk process would not miss either
+ * of them and that at least one node would exist in ehash
+ * table all the time. Otherwise there's a tiny chance
+ * that lookup process could find nothing in ehash table.
+ */
+ __sk_nulls_add_node_tail_rcu(sk, list);
+ sk_nulls_del_node_init_rcu(osk);
+ }
+ goto unlock;
+ }
+ if (found_dup_sk) {
*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
if (*found_dup_sk)
ret = false;
@@ -660,6 +672,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
if (ret)
__sk_nulls_add_node_rcu(sk, list);
+unlock:
spin_unlock(lock);
return ret;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1d77d992e6e77..beed32fff4841 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -91,10 +91,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
}
EXPORT_SYMBOL_GPL(inet_twsk_put);
-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
- struct hlist_nulls_head *list)
+static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
+ struct hlist_nulls_head *list)
{
- hlist_nulls_add_head_rcu(&tw->tw_node, list);
+ hlist_nulls_add_tail_rcu(&tw->tw_node, list);
}
static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -147,7 +147,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_lock(lock);
- inet_twsk_add_node_rcu(tw, &ehead->chain);
+ inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
--
GitLab
From 55ba18dc62deff5910c0fa64486dea1ff20832ff Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Wed, 18 Jan 2023 15:13:00 +0800
Subject: [PATCH 0979/1167] octeontx2-pf: Fix the use of GFP_KERNEL in atomic
context on rt
The commit 4af1b64f80fb ("octeontx2-pf: Fix lmtst ID used in aura
free") uses the get/put_cpu() to protect the usage of percpu pointer
in ->aura_freeptr() callback, but it also unnecessarily disable the
preemption for the blockable memory allocation. The commit 87b93b678e95
("octeontx2-pf: Avoid use of GFP_KERNEL in atomic context") tried to
fix these sleep inside atomic warnings. But it only fix the one for
the non-rt kernel. For the rt kernel, we still get the similar warnings
like below.
BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
preempt_count: 1, expected: 0
RCU nest depth: 0, expected: 0
3 locks held by swapper/0/1:
#0: ffff800009fc5fe8 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock+0x24/0x30
#1: ffff000100c276c0 (&mbox->lock){+.+.}-{3:3}, at: otx2_init_hw_resources+0x8c/0x3a4
#2: ffffffbfef6537e0 (&cpu_rcache->lock){+.+.}-{2:2}, at: alloc_iova_fast+0x1ac/0x2ac
Preemption disabled at:
[<ffff800008b1908c>] otx2_rq_aura_pool_init+0x14c/0x284
CPU: 20 PID: 1 Comm: swapper/0 Tainted: G W 6.2.0-rc3-rt1-yocto-preempt-rt #1
Hardware name: Marvell OcteonTX CN96XX board (DT)
Call trace:
dump_backtrace.part.0+0xe8/0xf4
show_stack+0x20/0x30
dump_stack_lvl+0x9c/0xd8
dump_stack+0x18/0x34
__might_resched+0x188/0x224
rt_spin_lock+0x64/0x110
alloc_iova_fast+0x1ac/0x2ac
iommu_dma_alloc_iova+0xd4/0x110
__iommu_dma_map+0x80/0x144
iommu_dma_map_page+0xe8/0x260
dma_map_page_attrs+0xb4/0xc0
__otx2_alloc_rbuf+0x90/0x150
otx2_rq_aura_pool_init+0x1c8/0x284
otx2_init_hw_resources+0xe4/0x3a4
otx2_open+0xf0/0x610
__dev_open+0x104/0x224
__dev_change_flags+0x1e4/0x274
dev_change_flags+0x2c/0x7c
ic_open_devs+0x124/0x2f8
ip_auto_config+0x180/0x42c
do_one_initcall+0x90/0x4dc
do_basic_setup+0x10c/0x14c
kernel_init_freeable+0x10c/0x13c
kernel_init+0x2c/0x140
ret_from_fork+0x10/0x20
Of course, we can shuffle the get/put_cpu() to only wrap the invocation
of ->aura_freeptr() as what commit 87b93b678e95 does. But there are only
two ->aura_freeptr() callbacks, otx2_aura_freeptr() and
cn10k_aura_freeptr(). There is no usage of perpcu variable in the
otx2_aura_freeptr() at all, so the get/put_cpu() seems redundant to it.
We can move the get/put_cpu() into the corresponding callback which
really has the percpu variable usage and avoid the sprinkling of
get/put_cpu() in several places.
Fixes: 4af1b64f80fb ("octeontx2-pf: Fix lmtst ID used in aura free")
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Link: https://lore.kernel.org/r/20230118071300.3271125-1-haokexin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
.../net/ethernet/marvell/octeontx2/nic/otx2_common.c | 11 ++---------
.../net/ethernet/marvell/octeontx2/nic/otx2_common.h | 2 ++
2 files changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 497b777b6a34f..8a41ad8ca04f1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1012,7 +1012,6 @@ static void otx2_pool_refill_task(struct work_struct *work)
rbpool = cq->rbpool;
free_ptrs = cq->pool_ptrs;
- get_cpu();
while (cq->pool_ptrs) {
if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
/* Schedule a WQ if we fails to free atleast half of the
@@ -1032,7 +1031,6 @@ static void otx2_pool_refill_task(struct work_struct *work)
pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
cq->pool_ptrs--;
}
- put_cpu();
cq->refill_task_sched = false;
}
@@ -1387,9 +1385,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
if (err)
goto err_mem;
- get_cpu();
pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
- put_cpu();
sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
}
}
@@ -1435,21 +1431,18 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
if (err)
goto fail;
- get_cpu();
/* Allocate pointers and free them to aura/pool */
for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
pool = &pfvf->qset.pool[pool_id];
for (ptr = 0; ptr < num_ptrs; ptr++) {
err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
if (err)
- goto err_mem;
+ return -ENOMEM;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
bufptr + OTX2_HEAD_ROOM);
}
}
-err_mem:
- put_cpu();
- return err ? -ENOMEM : 0;
+ return 0;
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 5bee3c3a7ce43..3d22cc6a2804a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -736,8 +736,10 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf)
u64 ptrs[2];
ptrs[1] = buf;
+ get_cpu();
/* Free only one buffer at time during init and teardown */
__cn10k_aura_freeptr(pfvf, aura, ptrs, 2);
+ put_cpu();
}
/* Alloc pointer from pool/aura */
--
GitLab
From 899d3a3c19ac0e5da013ce34833dccb97d19b5e4 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Tue, 17 Jan 2023 18:52:35 +0100
Subject: [PATCH 0980/1167] drm/drm_vma_manager: Add drm_vma_node_allow_once()
Currently there is no easy way for a drm driver to safely check and allow
drm_vma_offset_node for a drm file just once. Allow drm drivers to call
non-refcounted version of drm_vma_node_allow() so that a driver doesn't
need to keep track of each drm_vma_node_allow() to call subsequent
drm_vma_node_revoke() to prevent memory leak.
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Suggested-by: Chris Wilson <chris.p.wilson@intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20230117175236.22317-1-nirmoy.das@intel.com
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
---
drivers/gpu/drm/drm_vma_manager.c | 76 ++++++++++++++++++++++---------
include/drm/drm_vma_manager.h | 1 +
2 files changed, 55 insertions(+), 22 deletions(-)
diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 7de37f8c68fd0..83229a031af0f 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -240,27 +240,8 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr,
}
EXPORT_SYMBOL(drm_vma_offset_remove);
-/**
- * drm_vma_node_allow - Add open-file to list of allowed users
- * @node: Node to modify
- * @tag: Tag of file to remove
- *
- * Add @tag to the list of allowed open-files for this node. If @tag is
- * already on this list, the ref-count is incremented.
- *
- * The list of allowed-users is preserved across drm_vma_offset_add() and
- * drm_vma_offset_remove() calls. You may even call it if the node is currently
- * not added to any offset-manager.
- *
- * You must remove all open-files the same number of times as you added them
- * before destroying the node. Otherwise, you will leak memory.
- *
- * This is locked against concurrent access internally.
- *
- * RETURNS:
- * 0 on success, negative error code on internal failure (out-of-mem)
- */
-int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
+static int vma_node_allow(struct drm_vma_offset_node *node,
+ struct drm_file *tag, bool ref_counted)
{
struct rb_node **iter;
struct rb_node *parent = NULL;
@@ -282,7 +263,8 @@ int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb);
if (tag == entry->vm_tag) {
- entry->vm_count++;
+ if (ref_counted)
+ entry->vm_count++;
goto unlock;
} else if (tag > entry->vm_tag) {
iter = &(*iter)->rb_right;
@@ -307,8 +289,58 @@ int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
kfree(new);
return ret;
}
+
+/**
+ * drm_vma_node_allow - Add open-file to list of allowed users
+ * @node: Node to modify
+ * @tag: Tag of file to remove
+ *
+ * Add @tag to the list of allowed open-files for this node. If @tag is
+ * already on this list, the ref-count is incremented.
+ *
+ * The list of allowed-users is preserved across drm_vma_offset_add() and
+ * drm_vma_offset_remove() calls. You may even call it if the node is currently
+ * not added to any offset-manager.
+ *
+ * You must remove all open-files the same number of times as you added them
+ * before destroying the node. Otherwise, you will leak memory.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on internal failure (out-of-mem)
+ */
+int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag)
+{
+ return vma_node_allow(node, tag, true);
+}
EXPORT_SYMBOL(drm_vma_node_allow);
+/**
+ * drm_vma_node_allow_once - Add open-file to list of allowed users
+ * @node: Node to modify
+ * @tag: Tag of file to remove
+ *
+ * Add @tag to the list of allowed open-files for this node.
+ *
+ * The list of allowed-users is preserved across drm_vma_offset_add() and
+ * drm_vma_offset_remove() calls. You may even call it if the node is currently
+ * not added to any offset-manager.
+ *
+ * This is not ref-counted unlike drm_vma_node_allow() hence drm_vma_node_revoke()
+ * should only be called once after this.
+ *
+ * This is locked against concurrent access internally.
+ *
+ * RETURNS:
+ * 0 on success, negative error code on internal failure (out-of-mem)
+ */
+int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag)
+{
+ return vma_node_allow(node, tag, false);
+}
+EXPORT_SYMBOL(drm_vma_node_allow_once);
+
/**
* drm_vma_node_revoke - Remove open-file from list of allowed users
* @node: Node to modify
diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h
index 4f8c35206f7cd..6c2a2f21dbf00 100644
--- a/include/drm/drm_vma_manager.h
+++ b/include/drm/drm_vma_manager.h
@@ -74,6 +74,7 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr,
struct drm_vma_offset_node *node);
int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag);
+int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag);
void drm_vma_node_revoke(struct drm_vma_offset_node *node,
struct drm_file *tag);
bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node,
--
GitLab
From 0220e4fe178c3390eb0291cdb34912d66972db8a Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@intel.com>
Date: Tue, 17 Jan 2023 18:52:36 +0100
Subject: [PATCH 0981/1167] drm/i915: Fix a memory leak with reused mmap_offset
drm_vma_node_allow() and drm_vma_node_revoke() should be called in
balanced pairs. We call drm_vma_node_allow() once per-file everytime a
user calls mmap_offset, but only call drm_vma_node_revoke once per-file
on each mmap_offset. As the mmap_offset is reused by the client, the
per-file vm_count may remain non-zero and the rbtree leaked.
Call drm_vma_node_allow_once() instead to prevent that memory leak.
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
Fixes: 786555987207 ("drm/i915/gem: Store mmap_offsets in an rbtree rather than a plain list")
Reported-by: Chuansheng Liu <chuansheng.liu@intel.com>
Reported-by: Mirsad Todorovac <mirsad.todorovac@alu.unizg.hr>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20230117175236.22317-2-nirmoy.das@intel.com
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
---
drivers/gpu/drm/i915/gem/i915_gem_mman.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 0ad44f3868ded..c7c252d4d366d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -697,7 +697,7 @@ mmap_offset_attach(struct drm_i915_gem_object *obj,
GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo);
out:
if (file)
- drm_vma_node_allow(&mmo->vma_node, file);
+ drm_vma_node_allow_once(&mmo->vma_node, file);
return mmo;
err:
--
GitLab
From 7d80dbd708c18c683dd34f79b600a05307707ce8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Jan 2023 10:01:41 +0100
Subject: [PATCH 0982/1167] usb: dwc3: fix extcon dependency
The dwc3 core support now links against the extcon subsystem,
so it cannot be built-in when extcon is a loadable module:
arm-linux-gnueabi-ld: drivers/usb/dwc3/core.o: in function `dwc3_get_extcon':
core.c:(.text+0x572): undefined reference to `extcon_get_edev_by_phandle'
arm-linux-gnueabi-ld: core.c:(.text+0x596): undefined reference to `extcon_get_extcon_dev'
arm-linux-gnueabi-ld: core.c:(.text+0x5ea): undefined reference to `extcon_find_edev_by_node'
There was already a Kconfig dependency in the dual-role support,
but this is now needed for the entire dwc3 driver.
It is still possible to build dwc3 without extcon, but this
prevents it from being set to built-in when extcon is a loadable
module.
Fixes: d182c2e1bc92 ("usb: dwc3: Don't switch OTG -> peripheral if extcon is present")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20230118090147.2126563-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/dwc3/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index b2f72b0e75c6b..be954a9abbe05 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -3,6 +3,7 @@
config USB_DWC3
tristate "DesignWare USB3 DRD Core Support"
depends on (USB || USB_GADGET) && HAS_DMA
+ depends on (EXTCON || EXTCON=n)
select USB_XHCI_PLATFORM if USB_XHCI_HCD
select USB_ROLE_SWITCH if USB_DWC3_DUAL_ROLE
help
@@ -44,7 +45,6 @@ config USB_DWC3_GADGET
config USB_DWC3_DUAL_ROLE
bool "Dual Role mode"
depends on ((USB=y || USB=USB_DWC3) && (USB_GADGET=y || USB_GADGET=USB_DWC3))
- depends on (EXTCON=y || EXTCON=USB_DWC3)
help
This is the default mode of working of DWC3 controller where
both host and gadget features are enabled.
--
GitLab
From 95e5fda3b5f9ed8239b145da3fa01e641cf5d53c Mon Sep 17 00:00:00 2001
From: Eric Pilmore <epilmore@gigaio.com>
Date: Wed, 18 Jan 2023 19:39:08 -0800
Subject: [PATCH 0983/1167] ptdma: pt_core_execute_cmd() should use spinlock
The interrupt handler (pt_core_irq_handler()) of the ptdma
driver can be called from interrupt context. The code flow
in this function can lead down to pt_core_execute_cmd() which
will attempt to grab a mutex, which is not appropriate in
interrupt context and ultimately leads to a kernel panic.
The fix here changes this mutex to a spinlock, which has
been verified to resolve the issue.
Fixes: fa5d823b16a9 ("dmaengine: ptdma: Initial driver for the AMD PTDMA")
Signed-off-by: Eric Pilmore <epilmore@gigaio.com>
Link: https://lore.kernel.org/r/20230119033907.35071-1-epilmore@gigaio.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
drivers/dma/ptdma/ptdma-dev.c | 7 ++++---
drivers/dma/ptdma/ptdma.h | 2 +-
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/drivers/dma/ptdma/ptdma-dev.c b/drivers/dma/ptdma/ptdma-dev.c
index 377da23012ac2..a2bf13ff18b6d 100644
--- a/drivers/dma/ptdma/ptdma-dev.c
+++ b/drivers/dma/ptdma/ptdma-dev.c
@@ -71,12 +71,13 @@ static int pt_core_execute_cmd(struct ptdma_desc *desc, struct pt_cmd_queue *cmd
bool soc = FIELD_GET(DWORD0_SOC, desc->dw0);
u8 *q_desc = (u8 *)&cmd_q->qbase[cmd_q->qidx];
u32 tail;
+ unsigned long flags;
if (soc) {
desc->dw0 |= FIELD_PREP(DWORD0_IOC, desc->dw0);
desc->dw0 &= ~DWORD0_SOC;
}
- mutex_lock(&cmd_q->q_mutex);
+ spin_lock_irqsave(&cmd_q->q_lock, flags);
/* Copy 32-byte command descriptor to hw queue. */
memcpy(q_desc, desc, 32);
@@ -91,7 +92,7 @@ static int pt_core_execute_cmd(struct ptdma_desc *desc, struct pt_cmd_queue *cmd
/* Turn the queue back on using our cached control register */
pt_start_queue(cmd_q);
- mutex_unlock(&cmd_q->q_mutex);
+ spin_unlock_irqrestore(&cmd_q->q_lock, flags);
return 0;
}
@@ -199,7 +200,7 @@ int pt_core_init(struct pt_device *pt)
cmd_q->pt = pt;
cmd_q->dma_pool = dma_pool;
- mutex_init(&cmd_q->q_mutex);
+ spin_lock_init(&cmd_q->q_lock);
/* Page alignment satisfies our needs for N <= 128 */
cmd_q->qsize = Q_SIZE(Q_DESC_SIZE);
diff --git a/drivers/dma/ptdma/ptdma.h b/drivers/dma/ptdma/ptdma.h
index d093c43b7d134..21b4bf895200b 100644
--- a/drivers/dma/ptdma/ptdma.h
+++ b/drivers/dma/ptdma/ptdma.h
@@ -196,7 +196,7 @@ struct pt_cmd_queue {
struct ptdma_desc *qbase;
/* Aligned queue start address (per requirement) */
- struct mutex q_mutex ____cacheline_aligned;
+ spinlock_t q_lock ____cacheline_aligned;
unsigned int qidx;
unsigned int qsize;
--
GitLab
From 39af728649b05e88a2b40e714feeee6451c3f18e Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Wed, 23 Nov 2022 10:25:42 +0800
Subject: [PATCH 0984/1167] device property: fix of node refcount leak in
fwnode_graph_get_next_endpoint()
The 'parent' returned by fwnode_graph_get_port_parent()
with refcount incremented when 'prev' is not NULL, it
needs be put when finish using it.
Because the parent is const, introduce a new variable to
store the returned fwnode, then put it before returning
from fwnode_graph_get_next_endpoint().
Fixes: b5b41ab6b0c1 ("device property: Check fwnode->secondary in fwnode_graph_get_next_endpoint()")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-and-tested-by: Daniel Scally <djrscally@gmail.com>
Link: https://lore.kernel.org/r/20221123022542.2999510-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/property.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/drivers/base/property.c b/drivers/base/property.c
index bbb3e499ff4a5..083a95791d3b3 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -997,26 +997,32 @@ struct fwnode_handle *
fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
struct fwnode_handle *prev)
{
+ struct fwnode_handle *ep, *port_parent = NULL;
const struct fwnode_handle *parent;
- struct fwnode_handle *ep;
/*
* If this function is in a loop and the previous iteration returned
* an endpoint from fwnode->secondary, then we need to use the secondary
* as parent rather than @fwnode.
*/
- if (prev)
- parent = fwnode_graph_get_port_parent(prev);
- else
+ if (prev) {
+ port_parent = fwnode_graph_get_port_parent(prev);
+ parent = port_parent;
+ } else {
parent = fwnode;
+ }
if (IS_ERR_OR_NULL(parent))
return NULL;
ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev);
if (ep)
- return ep;
+ goto out_put_port_parent;
+
+ ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL);
- return fwnode_graph_get_next_endpoint(parent->secondary, NULL);
+out_put_port_parent:
+ fwnode_handle_put(port_parent);
+ return ep;
}
EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
--
GitLab
From b8caf69a6946e18ffebad49847e258f5b6d52ac2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 21 Dec 2022 17:40:22 +0100
Subject: [PATCH 0985/1167] tty: serial: qcom-geni-serial: fix
slab-out-of-bounds on RX FIFO buffer
Driver's probe allocates memory for RX FIFO (port->rx_fifo) based on
default RX FIFO depth, e.g. 16. Later during serial startup the
qcom_geni_serial_port_setup() updates the RX FIFO depth
(port->rx_fifo_depth) to match real device capabilities, e.g. to 32.
The RX UART handle code will read "port->rx_fifo_depth" number of words
into "port->rx_fifo" buffer, thus exceeding the bounds. This can be
observed in certain configurations with Qualcomm Bluetooth HCI UART
device and KASAN:
Bluetooth: hci0: QCA Product ID :0x00000010
Bluetooth: hci0: QCA SOC Version :0x400a0200
Bluetooth: hci0: QCA ROM Version :0x00000200
Bluetooth: hci0: QCA Patch Version:0x00000d2b
Bluetooth: hci0: QCA controller version 0x02000200
Bluetooth: hci0: QCA Downloading qca/htbtfw20.tlv
bluetooth hci0: Direct firmware load for qca/htbtfw20.tlv failed with error -2
Bluetooth: hci0: QCA Failed to request file: qca/htbtfw20.tlv (-2)
Bluetooth: hci0: QCA Failed to download patch (-2)
==================================================================
BUG: KASAN: slab-out-of-bounds in handle_rx_uart+0xa8/0x18c
Write of size 4 at addr ffff279347d578c0 by task swapper/0/0
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.1.0-rt5-00350-gb2450b7e00be-dirty #26
Hardware name: Qualcomm Technologies, Inc. Robotics RB5 (DT)
Call trace:
dump_backtrace.part.0+0xe0/0xf0
show_stack+0x18/0x40
dump_stack_lvl+0x8c/0xb8
print_report+0x188/0x488
kasan_report+0xb4/0x100
__asan_store4+0x80/0xa4
handle_rx_uart+0xa8/0x18c
qcom_geni_serial_handle_rx+0x84/0x9c
qcom_geni_serial_isr+0x24c/0x760
__handle_irq_event_percpu+0x108/0x500
handle_irq_event+0x6c/0x110
handle_fasteoi_irq+0x138/0x2cc
generic_handle_domain_irq+0x48/0x64
If the RX FIFO depth changes after probe, be sure to resize the buffer.
Fixes: f9d690b6ece7 ("tty: serial: qcom_geni_serial: Allocate port->rx_fifo buffer in probe")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20221221164022.1087814-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/qcom_geni_serial.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index b487823f0e617..49b9ffeae6760 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -864,9 +864,10 @@ static irqreturn_t qcom_geni_serial_isr(int isr, void *dev)
return IRQ_HANDLED;
}
-static void get_tx_fifo_size(struct qcom_geni_serial_port *port)
+static int setup_fifos(struct qcom_geni_serial_port *port)
{
struct uart_port *uport;
+ u32 old_rx_fifo_depth = port->rx_fifo_depth;
uport = &port->uport;
port->tx_fifo_depth = geni_se_get_tx_fifo_depth(&port->se);
@@ -874,6 +875,16 @@ static void get_tx_fifo_size(struct qcom_geni_serial_port *port)
port->rx_fifo_depth = geni_se_get_rx_fifo_depth(&port->se);
uport->fifosize =
(port->tx_fifo_depth * port->tx_fifo_width) / BITS_PER_BYTE;
+
+ if (port->rx_fifo && (old_rx_fifo_depth != port->rx_fifo_depth) && port->rx_fifo_depth) {
+ port->rx_fifo = devm_krealloc(uport->dev, port->rx_fifo,
+ port->rx_fifo_depth * sizeof(u32),
+ GFP_KERNEL);
+ if (!port->rx_fifo)
+ return -ENOMEM;
+ }
+
+ return 0;
}
@@ -888,6 +899,7 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport)
u32 rxstale = DEFAULT_BITS_PER_CHAR * STALE_TIMEOUT;
u32 proto;
u32 pin_swap;
+ int ret;
proto = geni_se_read_proto(&port->se);
if (proto != GENI_SE_UART) {
@@ -897,7 +909,9 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport)
qcom_geni_serial_stop_rx(uport);
- get_tx_fifo_size(port);
+ ret = setup_fifos(port);
+ if (ret)
+ return ret;
writel(rxstale, uport->membase + SE_UART_RX_STALE_CNT);
--
GitLab
From e8914b52e5b024e4af3d810a935fe0805eee8a36 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Tue, 3 Jan 2023 11:34:35 +0200
Subject: [PATCH 0986/1167] serial: pch_uart: Pass correct sg to dma_unmap_sg()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
A local variable sg is used to store scatterlist pointer in
pch_dma_tx_complete(). The for loop doing Tx byte accounting before
dma_unmap_sg() alters sg in its increment statement. Therefore, the
pointer passed into dma_unmap_sg() won't match to the one given to
dma_map_sg().
To fix the problem, use priv->sg_tx_p directly in dma_unmap_sg()
instead of the local variable.
Fixes: da3564ee027e ("pch_uart: add multi-scatter processing")
Cc: stable@vger.kernel.org
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20230103093435.4396-1-ilpo.jarvinen@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/pch_uart.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 3d54a43768cd2..9576ba8bbc40e 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -749,7 +749,7 @@ static void pch_dma_tx_complete(void *arg)
uart_xmit_advance(port, sg_dma_len(sg));
async_tx_ack(priv->desc_tx);
- dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE);
+ dma_unmap_sg(port->dev, priv->sg_tx_p, priv->orig_nent, DMA_TO_DEVICE);
priv->tx_dma_use = 0;
priv->nent = 0;
priv->orig_nent = 0;
--
GitLab
From 4f39aca2360c82dccd2f5179d77e94aab665bea6 Mon Sep 17 00:00:00 2001
From: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Date: Sun, 8 Jan 2023 19:17:35 +0100
Subject: [PATCH 0987/1167] serial: amba-pl011: fix high priority character
transmission in rs486 mode
In RS485 mode the transmission of a high priority character fails since it
is written to the data register before the transmitter is enabled. Fix this
in pl011_tx_chars() by enabling RS485 transmission before writing the
character.
Fixes: 8d479237727c ("serial: amba-pl011: add RS485 support")
Cc: stable@vger.kernel.org
Signed-off-by: Lino Sanfilippo <l.sanfilippo@kunbus.com>
Link: https://lore.kernel.org/r/20230108181735.10937-1-LinoSanfilippo@gmx.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/amba-pl011.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index d75c39f4622b7..d8c2f3455eeba 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1466,6 +1466,10 @@ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq)
struct circ_buf *xmit = &uap->port.state->xmit;
int count = uap->fifosize >> 1;
+ if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
+ !uap->rs485_tx_started)
+ pl011_rs485_tx_start(uap);
+
if (uap->port.x_char) {
if (!pl011_tx_char(uap, uap->port.x_char, from_irq))
return true;
@@ -1477,10 +1481,6 @@ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq)
return false;
}
- if ((uap->port.rs485.flags & SER_RS485_ENABLED) &&
- !uap->rs485_tx_started)
- pl011_rs485_tx_start(uap);
-
/* If we are using DMA mode, try to send some characters. */
if (pl011_dma_tx_irq(uap))
return true;
--
GitLab
From f24771b62a83239f0dce816bddf0f6807f436235 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Thu, 12 Jan 2023 19:04:17 +0100
Subject: [PATCH 0988/1167] serial: stm32: Merge hard IRQ and threaded IRQ
handling into single IRQ handler
Requesting an interrupt with IRQF_ONESHOT will run the primary handler
in the hard-IRQ context even in the force-threaded mode. The
force-threaded mode is used by PREEMPT_RT in order to avoid acquiring
sleeping locks (spinlock_t) in hard-IRQ context. This combination
makes it impossible and leads to "sleeping while atomic" warnings.
Use one interrupt handler for both handlers (primary and secondary)
and drop the IRQF_ONESHOT flag which is not needed.
Fixes: e359b4411c283 ("serial: stm32: fix threaded interrupt handling")
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Valentin Caron <valentin.caron@foss.st.com> # V3
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230112180417.25595-1-marex@denx.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/stm32-usart.c | 31 ++++---------------------------
1 file changed, 4 insertions(+), 27 deletions(-)
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index a1490033aa164..1e24bee2b0ef7 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -797,23 +797,9 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr)
spin_unlock(&port->lock);
}
- if (stm32_usart_rx_dma_enabled(port))
- return IRQ_WAKE_THREAD;
- else
- return IRQ_HANDLED;
-}
-
-static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr)
-{
- struct uart_port *port = ptr;
- struct tty_port *tport = &port->state->port;
- struct stm32_port *stm32_port = to_stm32_port(port);
- unsigned int size;
- unsigned long flags;
-
/* Receiver timeout irq for DMA RX */
- if (!stm32_port->throttled) {
- spin_lock_irqsave(&port->lock, flags);
+ if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) {
+ spin_lock(&port->lock);
size = stm32_usart_receive_chars(port, false);
uart_unlock_and_check_sysrq_irqrestore(port, flags);
if (size)
@@ -1015,10 +1001,8 @@ static int stm32_usart_startup(struct uart_port *port)
u32 val;
int ret;
- ret = request_threaded_irq(port->irq, stm32_usart_interrupt,
- stm32_usart_threaded_interrupt,
- IRQF_ONESHOT | IRQF_NO_SUSPEND,
- name, port);
+ ret = request_irq(port->irq, stm32_usart_interrupt,
+ IRQF_NO_SUSPEND, name, port);
if (ret)
return ret;
@@ -1601,13 +1585,6 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port,
struct dma_slave_config config;
int ret;
- /*
- * Using DMA and threaded handler for the console could lead to
- * deadlocks.
- */
- if (uart_console(port))
- return -ENODEV;
-
stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L,
&stm32port->rx_dma_buf,
GFP_KERNEL);
--
GitLab
From 5abbeebd8296c2301023b8dc4b5a6c0d5229b4f5 Mon Sep 17 00:00:00 2001
From: Gaosheng Cui <cuigaosheng1@huawei.com>
Date: Fri, 2 Dec 2022 14:06:33 +0800
Subject: [PATCH 0989/1167] tty: fix possible null-ptr-defer in
spk_ttyio_release
Run the following tests on the qemu platform:
syzkaller:~# modprobe speakup_audptr
input: Speakup as /devices/virtual/input/input4
initialized device: /dev/synth, node (MAJOR 10, MINOR 125)
speakup 3.1.6: initialized
synth name on entry is: (null)
synth probe
spk_ttyio_initialise_ldisc failed because tty_kopen_exclusive returned
failed (errno -16), then remove the module, we will get a null-ptr-defer
problem, as follow:
syzkaller:~# modprobe -r speakup_audptr
releasing synth audptr
BUG: kernel NULL pointer dereference, address: 0000000000000080
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 0 P4D 0
Oops: 0002 [#1] PREEMPT SMP PTI
CPU: 2 PID: 204 Comm: modprobe Not tainted 6.1.0-rc6-dirty #1
RIP: 0010:mutex_lock+0x14/0x30
Call Trace:
<TASK>
spk_ttyio_release+0x19/0x70 [speakup]
synth_release.part.6+0xac/0xc0 [speakup]
synth_remove+0x56/0x60 [speakup]
__x64_sys_delete_module+0x156/0x250
? fpregs_assert_state_consistent+0x1d/0x50
do_syscall_64+0x37/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
</TASK>
Modules linked in: speakup_audptr(-) speakup
Dumping ftrace buffer:
in_synth->dev was not initialized during modprobe, so we add check
for in_synth->dev to fix this bug.
Fixes: 4f2a81f3a882 ("speakup: Reference synth from tty and tty from synth")
Cc: stable <stable@kernel.org>
Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Link: https://lore.kernel.org/r/20221202060633.217364-1-cuigaosheng1@huawei.com
Reviewed-by: Samuel Thibault <samuel.thibault@ens-lyon.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/accessibility/speakup/spk_ttyio.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c
index 08cf8a17754bb..07373b3debd1e 100644
--- a/drivers/accessibility/speakup/spk_ttyio.c
+++ b/drivers/accessibility/speakup/spk_ttyio.c
@@ -354,6 +354,9 @@ void spk_ttyio_release(struct spk_synth *in_synth)
{
struct tty_struct *tty = in_synth->dev;
+ if (tty == NULL)
+ return;
+
tty_lock(tty);
if (tty->ops->close)
--
GitLab
From 5bfdd3c654bd879bff50c2e85e42f85ae698b42f Mon Sep 17 00:00:00 2001
From: Tobias Schramm <t.schramm@manjaro.org>
Date: Mon, 9 Jan 2023 08:29:40 +0100
Subject: [PATCH 0990/1167] serial: atmel: fix incorrect baudrate setup
Commit ba47f97a18f2 ("serial: core: remove baud_rates when serial console
setup") changed uart_set_options to select the correct baudrate
configuration based on the absolute error between requested baudrate and
available standard baudrate settings.
Prior to that commit the baudrate was selected based on which predefined
standard baudrate did not exceed the requested baudrate.
This change of selection logic was never reflected in the atmel serial
driver. Thus the comment left in the atmel serial driver is no longer
accurate.
Additionally the manual rounding up described in that comment and applied
via (quot - 1) requests an incorrect baudrate. Since uart_set_options uses
tty_termios_encode_baud_rate to determine the appropriate baudrate flags
this can cause baudrate selection to fail entirely because
tty_termios_encode_baud_rate will only select a baudrate if relative error
between requested and selected baudrate does not exceed +/-2%.
Fix that by requesting actual, exact baudrate used by the serial.
Fixes: ba47f97a18f2 ("serial: core: remove baud_rates when serial console setup")
Cc: stable <stable@kernel.org>
Signed-off-by: Tobias Schramm <t.schramm@manjaro.org>
Acked-by: Richard Genoud <richard.genoud@gmail.com>
Link: https://lore.kernel.org/r/20230109072940.202936-1-t.schramm@manjaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/atmel_serial.c | 8 +-------
1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index f1c06e12efa0b..9cd7479b03c08 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2657,13 +2657,7 @@ static void __init atmel_console_get_options(struct uart_port *port, int *baud,
else if (mr == ATMEL_US_PAR_ODD)
*parity = 'o';
- /*
- * The serial core only rounds down when matching this to a
- * supported baud rate. Make sure we don't end up slightly
- * lower than one of those, as it would make us fall through
- * to a much lower baud rate than we really want.
- */
- *baud = port->uartclk / (16 * (quot - 1));
+ *baud = port->uartclk / (16 * quot);
}
static int __init atmel_console_setup(struct console *co, char *options)
--
GitLab
From 5342ab0af45064cbdc773645b93ab70c24ee161f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 15 Dec 2022 17:54:24 +0100
Subject: [PATCH 0991/1167] tty: serial: qcom_geni: avoid duplicate struct
member init
When -Woverride-init is enabled in a build, gcc points out that
qcom_geni_serial_pm_ops contains conflicting initializers:
drivers/tty/serial/qcom_geni_serial.c:1586:20: error: initialized field overwritten [-Werror=override-init]
1586 | .restore = qcom_geni_serial_sys_hib_resume,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/tty/serial/qcom_geni_serial.c:1586:20: note: (near initialization for 'qcom_geni_serial_pm_ops.restore')
drivers/tty/serial/qcom_geni_serial.c:1587:17: error: initialized field overwritten [-Werror=override-init]
1587 | .thaw = qcom_geni_serial_sys_hib_resume,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Open-code the initializers with the version that was already used,
and use the pm_sleep_ptr() method to deal with unused ones,
in place of the __maybe_unused annotation.
Fixes: 35781d8356a2 ("tty: serial: qcom-geni-serial: Add support for Hibernation feature")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20221215165453.1864836-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/qcom_geni_serial.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 49b9ffeae6760..57f04f8bf5043 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1530,7 +1530,7 @@ static int qcom_geni_serial_remove(struct platform_device *pdev)
return 0;
}
-static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev)
+static int qcom_geni_serial_sys_suspend(struct device *dev)
{
struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
struct uart_port *uport = &port->uport;
@@ -1547,7 +1547,7 @@ static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev)
return uart_suspend_port(private_data->drv, uport);
}
-static int __maybe_unused qcom_geni_serial_sys_resume(struct device *dev)
+static int qcom_geni_serial_sys_resume(struct device *dev)
{
int ret;
struct qcom_geni_serial_port *port = dev_get_drvdata(dev);
@@ -1595,10 +1595,12 @@ static int qcom_geni_serial_sys_hib_resume(struct device *dev)
}
static const struct dev_pm_ops qcom_geni_serial_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(qcom_geni_serial_sys_suspend,
- qcom_geni_serial_sys_resume)
- .restore = qcom_geni_serial_sys_hib_resume,
- .thaw = qcom_geni_serial_sys_hib_resume,
+ .suspend = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .resume = pm_sleep_ptr(qcom_geni_serial_sys_resume),
+ .freeze = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .poweroff = pm_sleep_ptr(qcom_geni_serial_sys_suspend),
+ .restore = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume),
+ .thaw = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume),
};
static const struct of_device_id qcom_geni_serial_match_table[] = {
--
GitLab
From 423d5081d0451faa59a707e57373801da5b40141 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 19 Jan 2023 09:01:27 -0700
Subject: [PATCH 0992/1167] io_uring/msg_ring: move double lock/unlock helpers
higher up
In preparation for needing them somewhere else, move them and get rid of
the unused 'issue_flags' for the unlock side.
No functional changes in this patch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/msg_ring.c | 47 ++++++++++++++++++++++-----------------------
1 file changed, 23 insertions(+), 24 deletions(-)
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 2d3cd945a531b..321f5eafef992 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -25,6 +25,28 @@ struct io_msg {
u32 flags;
};
+static void io_double_unlock_ctx(struct io_ring_ctx *octx)
+{
+ mutex_unlock(&octx->uring_lock);
+}
+
+static int io_double_lock_ctx(struct io_ring_ctx *octx,
+ unsigned int issue_flags)
+{
+ /*
+ * To ensure proper ordering between the two ctxs, we can only
+ * attempt a trylock on the target. If that fails and we already have
+ * the source ctx lock, punt to io-wq.
+ */
+ if (!(issue_flags & IO_URING_F_UNLOCKED)) {
+ if (!mutex_trylock(&octx->uring_lock))
+ return -EAGAIN;
+ return 0;
+ }
+ mutex_lock(&octx->uring_lock);
+ return 0;
+}
+
void io_msg_ring_cleanup(struct io_kiocb *req)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
@@ -77,29 +99,6 @@ static int io_msg_ring_data(struct io_kiocb *req)
return -EOVERFLOW;
}
-static void io_double_unlock_ctx(struct io_ring_ctx *octx,
- unsigned int issue_flags)
-{
- mutex_unlock(&octx->uring_lock);
-}
-
-static int io_double_lock_ctx(struct io_ring_ctx *octx,
- unsigned int issue_flags)
-{
- /*
- * To ensure proper ordering between the two ctxs, we can only
- * attempt a trylock on the target. If that fails and we already have
- * the source ctx lock, punt to io-wq.
- */
- if (!(issue_flags & IO_URING_F_UNLOCKED)) {
- if (!mutex_trylock(&octx->uring_lock))
- return -EAGAIN;
- return 0;
- }
- mutex_lock(&octx->uring_lock);
- return 0;
-}
-
static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
@@ -148,7 +147,7 @@ static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flag
if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
ret = -EOVERFLOW;
out_unlock:
- io_double_unlock_ctx(target_ctx, issue_flags);
+ io_double_unlock_ctx(target_ctx);
return ret;
}
--
GitLab
From 2efb6edd52dc50273f5e68ad863dd1b1fb2f2d1c Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Tue, 3 Jan 2023 14:37:54 +0000
Subject: [PATCH 0993/1167] comedi: adv_pci1760: Fix PWM instruction handling
(Actually, this is fixing the "Read the Current Status" command sent to
the device's outgoing mailbox, but it is only currently used for the PWM
instructions.)
The PCI-1760 is operated mostly by sending commands to a set of Outgoing
Mailbox registers, waiting for the command to complete, and reading the
result from the Incoming Mailbox registers. One of these commands is
the "Read the Current Status" command. The number of this command is
0x07 (see the User's Manual for the PCI-1760 at
<https://advdownload.advantech.com/productfile/Downloadfile2/1-11P6653/PCI-1760.pdf>.
The `PCI1760_CMD_GET_STATUS` macro defined in the driver should expand
to this command number 0x07, but unfortunately it currently expands to
0x03. (Command number 0x03 is not defined in the User's Manual.)
Correct the definition of the `PCI1760_CMD_GET_STATUS` macro to fix it.
This is used by all the PWM subdevice related instructions handled by
`pci1760_pwm_insn_config()` which are probably all broken. The effect
of sending the undefined command number 0x03 is not known.
Fixes: 14b93bb6bbf0 ("staging: comedi: adv_pci_dio: separate out PCI-1760 support")
Cc: <stable@vger.kernel.org> # v4.5+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20230103143754.17564-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/comedi/drivers/adv_pci1760.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/comedi/drivers/adv_pci1760.c b/drivers/comedi/drivers/adv_pci1760.c
index fcfc2e299110e..27f3890f471df 100644
--- a/drivers/comedi/drivers/adv_pci1760.c
+++ b/drivers/comedi/drivers/adv_pci1760.c
@@ -58,7 +58,7 @@
#define PCI1760_CMD_CLR_IMB2 0x00 /* Clears IMB2 */
#define PCI1760_CMD_SET_DO 0x01 /* Set output state */
#define PCI1760_CMD_GET_DO 0x02 /* Read output status */
-#define PCI1760_CMD_GET_STATUS 0x03 /* Read current status */
+#define PCI1760_CMD_GET_STATUS 0x07 /* Read current status */
#define PCI1760_CMD_GET_FW_VER 0x0e /* Read firmware version */
#define PCI1760_CMD_GET_HW_VER 0x0f /* Read hardware version */
#define PCI1760_CMD_SET_PWM_HI(x) (0x10 + (x) * 2) /* Set "hi" period */
--
GitLab
From 25d5648802f12ae486076ceca5d7ddf1fef792b2 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Mon, 5 Dec 2022 16:04:34 +0800
Subject: [PATCH 0994/1167] w1: fix deadloop in __w1_remove_master_device()
I got a deadloop report while doing device(ds2482) add/remove test:
[ 162.241881] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1.
[ 163.272251] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1.
[ 164.296157] w1_master_driver w1_bus_master1: Waiting for w1_bus_master1 to become free: refcnt=1.
...
__w1_remove_master_device() can't return, because the dev->refcnt is not zero.
w1_add_master_device() |
w1_alloc_dev() |
atomic_set(&dev->refcnt, 2) |
kthread_run() |
|__w1_remove_master_device()
| kthread_stop()
// KTHREAD_SHOULD_STOP is set, |
// threadfn(w1_process) won't be |
// called. |
kthread() |
| // refcnt will never be 0, it's deadloop.
| while (atomic_read(&dev->refcnt)) {...}
After calling w1_add_master_device(), w1_process() is not really
invoked, before w1_process() starting, if kthread_stop() is called
in __w1_remove_master_device(), w1_process() will never be called,
the refcnt can not be decreased, then it causes deadloop in remove
function because of non-zero refcnt.
We need to make sure w1_process() is really started, so move the
set refcnt into w1_process() to fix this problem.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Link: https://lore.kernel.org/r/20221205080434.3149205-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/w1/w1.c | 2 ++
drivers/w1/w1_int.c | 5 ++---
2 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index f2ae2e563dc54..8b35fae4cd619 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -1166,6 +1166,8 @@ int w1_process(void *data)
/* remainder if it woke up early */
unsigned long jremain = 0;
+ atomic_inc(&dev->refcnt);
+
for (;;) {
if (!jremain && dev->search_count) {
diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c
index b3e1792d9c49f..3a71c5eb2f837 100644
--- a/drivers/w1/w1_int.c
+++ b/drivers/w1/w1_int.c
@@ -51,10 +51,9 @@ static struct w1_master *w1_alloc_dev(u32 id, int slave_count, int slave_ttl,
dev->search_count = w1_search_count;
dev->enable_pullup = w1_enable_pullup;
- /* 1 for w1_process to decrement
- * 1 for __w1_remove_master_device to decrement
+ /* For __w1_remove_master_device to decrement
*/
- atomic_set(&dev->refcnt, 2);
+ atomic_set(&dev->refcnt, 1);
INIT_LIST_HEAD(&dev->slist);
INIT_LIST_HEAD(&dev->async_list);
--
GitLab
From 36225a7c72e9e3e1ce4001b6ce72849f5c9a2d3b Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Mon, 5 Dec 2022 18:15:58 +0800
Subject: [PATCH 0995/1167] w1: fix WARNING after calling w1_process()
I got the following WARNING message while removing driver(ds2482):
------------[ cut here ]------------
do not call blocking ops when !TASK_RUNNING; state=1 set at [<000000002d50bfb6>] w1_process+0x9e/0x1d0 [wire]
WARNING: CPU: 0 PID: 262 at kernel/sched/core.c:9817 __might_sleep+0x98/0xa0
CPU: 0 PID: 262 Comm: w1_bus_master1 Tainted: G N 6.1.0-rc3+ #307
RIP: 0010:__might_sleep+0x98/0xa0
Call Trace:
exit_signals+0x6c/0x550
do_exit+0x2b4/0x17e0
kthread_exit+0x52/0x60
kthread+0x16d/0x1e0
ret_from_fork+0x1f/0x30
The state of task is set to TASK_INTERRUPTIBLE in loop in w1_process(),
set it to TASK_RUNNING when it breaks out of the loop to avoid the
warning.
Fixes: 3c52e4e62789 ("W1: w1_process, block or sleep")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Link: https://lore.kernel.org/r/20221205101558.3599162-1-yangyingliang@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/w1/w1.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index 8b35fae4cd619..4a2ddf730a3ac 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -1195,8 +1195,10 @@ int w1_process(void *data)
*/
mutex_unlock(&dev->list_mutex);
- if (kthread_should_stop())
+ if (kthread_should_stop()) {
+ __set_current_state(TASK_RUNNING);
break;
+ }
/* Only sleep when the search is active. */
if (dev->search_count) {
--
GitLab
From 9be182da0a7526f1b9a3777a336f83baa2e64d23 Mon Sep 17 00:00:00 2001
From: Chen Zhongjin <chenzhongjin@huawei.com>
Date: Fri, 25 Nov 2022 14:35:41 +0800
Subject: [PATCH 0996/1167] driver core: Fix test_async_probe_init saves device
in wrong array
In test_async_probe_init, second set of asynchronous devices are saved
in sync_dev[sync_id], which should be async_dev[async_id].
This makes these devices not unregistered when exit.
> modprobe test_async_driver_probe && \
> modprobe -r test_async_driver_probe && \
> modprobe test_async_driver_probe
...
> sysfs: cannot create duplicate filename '/devices/platform/test_async_driver.4'
> kobject_add_internal failed for test_async_driver.4 with -EEXIST,
don't try to register things with the same name in the same directory.
Fixes: 57ea974fb871 ("driver core: Rewrite test_async_driver_probe to cover serialization and NUMA affinity")
Signed-off-by: Chen Zhongjin <chenzhongjin@huawei.com>
Link: https://lore.kernel.org/r/20221125063541.241328-1-chenzhongjin@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/base/test/test_async_driver_probe.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c
index 4d1976ca50727..929410d0dd6fe 100644
--- a/drivers/base/test/test_async_driver_probe.c
+++ b/drivers/base/test/test_async_driver_probe.c
@@ -145,7 +145,7 @@ static int __init test_async_probe_init(void)
calltime = ktime_get();
for_each_online_cpu(cpu) {
nid = cpu_to_node(cpu);
- pdev = &sync_dev[sync_id];
+ pdev = &async_dev[async_id];
*pdev = test_platform_device_register_node("test_async_driver",
async_id,
--
GitLab
From 8c29f016540532582721cec1dbf6d144873433ba Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Wed, 18 Jan 2023 11:49:43 +0530
Subject: [PATCH 0997/1167] x86/sev: Add SEV-SNP guest feature negotiation
support
The hypervisor can enable various new features (SEV_FEATURES[1:63]) and start a
SNP guest. Some of these features need guest side implementation. If any of
these features are enabled without it, the behavior of the SNP guest will be
undefined. It may fail booting in a non-obvious way making it difficult to
debug.
Instead of allowing the guest to continue and have it fail randomly later,
detect this early and fail gracefully.
The SEV_STATUS MSR indicates features which the hypervisor has enabled. While
booting, SNP guests should ascertain that all the enabled features have guest
side implementation. In case a feature is not implemented in the guest, the
guest terminates booting with GHCB protocol Non-Automatic Exit(NAE) termination
request event, see "SEV-ES Guest-Hypervisor Communication Block Standardization"
document (currently at https://developer.amd.com/wp-content/resources/56421.pdf),
section "Termination Request".
Populate SW_EXITINFO2 with mask of unsupported features that the hypervisor can
easily report to the user.
More details in the AMD64 APM Vol 2, Section "SEV_STATUS MSR".
[ bp:
- Massage.
- Move snp_check_features() call to C code.
Note: the CC:stable@ aspect here is to be able to protect older, stable
kernels when running on newer hypervisors. Or not "running" but fail
reliably and in a well-defined manner instead of randomly. ]
Fixes: cbd3d4f7c4e5 ("x86/sev: Check SEV-SNP features support")
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20230118061943.534309-1-nikunj@amd.com
---
Documentation/x86/amd-memory-encryption.rst | 36 +++++++++++
arch/x86/boot/compressed/ident_map_64.c | 6 ++
arch/x86/boot/compressed/misc.h | 2 +
arch/x86/boot/compressed/sev.c | 70 +++++++++++++++++++++
arch/x86/include/asm/msr-index.h | 20 ++++++
arch/x86/include/uapi/asm/svm.h | 6 ++
6 files changed, 140 insertions(+)
diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst
index a1940ebe7be50..934310ce72582 100644
--- a/Documentation/x86/amd-memory-encryption.rst
+++ b/Documentation/x86/amd-memory-encryption.rst
@@ -95,3 +95,39 @@ by supplying mem_encrypt=on on the kernel command line. However, if BIOS does
not enable SME, then Linux will not be able to activate memory encryption, even
if configured to do so by default or the mem_encrypt=on command line parameter
is specified.
+
+Secure Nested Paging (SNP)
+==========================
+
+SEV-SNP introduces new features (SEV_FEATURES[1:63]) which can be enabled
+by the hypervisor for security enhancements. Some of these features need
+guest side implementation to function correctly. The below table lists the
+expected guest behavior with various possible scenarios of guest/hypervisor
+SNP feature support.
+
++-----------------+---------------+---------------+------------------+
+| Feature Enabled | Guest needs | Guest has | Guest boot |
+| by the HV | implementation| implementation| behaviour |
++=================+===============+===============+==================+
+| No | No | No | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| No | Yes | No | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| No | Yes | Yes | Boot |
+| | | | |
++-----------------+---------------+---------------+------------------+
+| Yes | No | No | Boot with |
+| | | | feature enabled |
++-----------------+---------------+---------------+------------------+
+| Yes | Yes | No | Graceful boot |
+| | | | failure |
++-----------------+---------------+---------------+------------------+
+| Yes | Yes | Yes | Boot with |
+| | | | feature enabled |
++-----------------+---------------+---------------+------------------+
+
+More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR
+
+[1] https://www.amd.com/system/files/TechDocs/40332.pdf
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index d4a314cc50d6e..321a5011042d4 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode)
/* Load the new page-table. */
write_cr3(top_level_pgt);
+
+ /*
+ * Now that the required page table mappings are established and a
+ * GHCB can be used, check for SNP guest/HV feature compatibility.
+ */
+ snp_check_features();
}
static pte_t *split_large_pmd(struct x86_mapping_info *info,
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 62208ec04ca4b..20118fb7c53bb 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -126,6 +126,7 @@ static inline void console_init(void)
#ifdef CONFIG_AMD_MEM_ENCRYPT
void sev_enable(struct boot_params *bp);
+void snp_check_features(void);
void sev_es_shutdown_ghcb(void);
extern bool sev_es_check_ghcb_fault(unsigned long address);
void snp_set_page_private(unsigned long paddr);
@@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp)
if (bp)
bp->cc_blob_address = 0;
}
+static inline void snp_check_features(void) { }
static inline void sev_es_shutdown_ghcb(void) { }
static inline bool sev_es_check_ghcb_fault(unsigned long address)
{
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index c93930d5ccbd0..d63ad8f99f83a 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void)
error("Can't unmap GHCB page");
}
+static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set,
+ unsigned int reason, u64 exit_info_2)
+{
+ u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason);
+
+ vc_ghcb_invalidate(ghcb);
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST);
+ ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
+ ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+ VMGEXIT();
+
+ while (true)
+ asm volatile("hlt\n" : : : "memory");
+}
+
bool sev_es_check_ghcb_fault(unsigned long address)
{
/* Check whether the fault was on the GHCB page */
@@ -270,6 +287,59 @@ static void enforce_vmpl0(void)
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
}
+/*
+ * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
+ * guest side implementation for proper functioning of the guest. If any
+ * of these features are enabled in the hypervisor but are lacking guest
+ * side implementation, the behavior of the guest will be undefined. The
+ * guest could fail in non-obvious way making it difficult to debug.
+ *
+ * As the behavior of reserved feature bits is unknown to be on the
+ * safe side add them to the required features mask.
+ */
+#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \
+ MSR_AMD64_SNP_REFLECT_VC | \
+ MSR_AMD64_SNP_RESTRICTED_INJ | \
+ MSR_AMD64_SNP_ALT_INJ | \
+ MSR_AMD64_SNP_DEBUG_SWAP | \
+ MSR_AMD64_SNP_VMPL_SSS | \
+ MSR_AMD64_SNP_SECURE_TSC | \
+ MSR_AMD64_SNP_VMGEXIT_PARAM | \
+ MSR_AMD64_SNP_VMSA_REG_PROTECTION | \
+ MSR_AMD64_SNP_RESERVED_BIT13 | \
+ MSR_AMD64_SNP_RESERVED_BIT15 | \
+ MSR_AMD64_SNP_RESERVED_MASK)
+
+/*
+ * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented
+ * by the guest kernel. As and when a new feature is implemented in the
+ * guest kernel, a corresponding bit should be added to the mask.
+ */
+#define SNP_FEATURES_PRESENT (0)
+
+void snp_check_features(void)
+{
+ u64 unsupported;
+
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ return;
+
+ /*
+ * Terminate the boot if hypervisor has enabled any feature lacking
+ * guest side implementation. Pass on the unsupported features mask through
+ * EXIT_INFO_2 of the GHCB protocol so that those features can be reported
+ * as part of the guest boot failure.
+ */
+ unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+ if (unsupported) {
+ if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb()))
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+ sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN,
+ GHCB_SNP_UNSUPPORTED, unsupported);
+ }
+}
+
void sev_enable(struct boot_params *bp)
{
unsigned int eax, ebx, ecx, edx;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 37ff47552bcb7..d3fe82c5d6b66 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -566,6 +566,26 @@
#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
#define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
+/* SNP feature bits enabled by the hypervisor */
+#define MSR_AMD64_SNP_VTOM BIT_ULL(3)
+#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4)
+#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5)
+#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6)
+#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8)
+#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9)
+#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10)
+#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12)
+#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14)
+#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16)
+#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17)
+
+/* SNP feature bits reserved for future use. */
+#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13)
+#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15)
+#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18)
+
#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f
/* AMD Collaborative Processor Performance Control MSRs */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index f69c168391aa5..80e1df482337d 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -116,6 +116,12 @@
#define SVM_VMGEXIT_AP_CREATE 1
#define SVM_VMGEXIT_AP_DESTROY 2
#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd
+#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe
+#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \
+ /* SW_EXITINFO1[3:0] */ \
+ (((((u64)reason_set) & 0xf)) | \
+ /* SW_EXITINFO1[11:4] */ \
+ ((((u64)reason_code) & 0xff) << 4))
#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff
/* Exit code reserved for hypervisor/software use */
--
GitLab
From 8ccc99362b60c6f27bb46f36fdaaccf4ef0303de Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 18 Jan 2023 13:24:12 +0100
Subject: [PATCH 0998/1167] net/ulp: use consistent error code when blocking
ULP
The referenced commit changed the error code returned by the kernel
when preventing a non-established socket from attaching the ktls
ULP. Before to such a commit, the user-space got ENOTCONN instead
of EINVAL.
The existing self-tests depend on such error code, and the change
caused a failure:
RUN global.non_established ...
tls.c:1673:non_established:Expected errno (22) == ENOTCONN (107)
non_established: Test failed at step #3
FAIL global.non_established
In the unlikely event existing applications do the same, address
the issue by restoring the prior error code in the above scenario.
Note that the only other ULP performing similar checks at init
time - smc_ulp_ops - also fails with ENOTCONN when trying to attach
the ULP to a non-established socket.
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Fixes: 2c02d41d71f9 ("net/ulp: prevent ULP without clone op from entering the LISTEN status")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://lore.kernel.org/r/7bb199e7a93317fb6f8bf8b9b2dc71c18f337cde.1674042685.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/tcp_ulp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 05b6077b9f2c3..2aa442128630e 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -139,7 +139,7 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
if (sk->sk_socket)
clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
- err = -EINVAL;
+ err = -ENOTCONN;
if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
goto out_err;
--
GitLab
From 903848249a781d76d59561d51676c95b3a4d7162 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 18 Jan 2023 10:18:47 -0500
Subject: [PATCH 0999/1167] selftests/net: toeplitz: fix race on tpacket_v3
block close
Avoid race between process wakeup and tpacket_v3 block timeout.
The test waits for cfg_timeout_msec for packets to arrive. Packets
arrive in tpacket_v3 rings, which pass packets ("frames") to the
process in batches ("blocks"). The sk waits for req3.tp_retire_blk_tov
msec to release a block.
Set the block timeout lower than the process waiting time, else
the process may find that no block has been released by the time it
scans the socket list. Convert to a ring of more than one, smaller,
blocks with shorter timeouts. Blocks must be page aligned, so >= 64KB.
Fixes: 5ebfb4cc3048 ("selftests/net: toeplitz test")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20230118151847.4124260-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
tools/testing/selftests/net/toeplitz.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c
index 90026a27eac0c..9ba03164d73a6 100644
--- a/tools/testing/selftests/net/toeplitz.c
+++ b/tools/testing/selftests/net/toeplitz.c
@@ -215,7 +215,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame)
}
/* A single TPACKET_V3 block can hold multiple frames */
-static void recv_block(struct ring_state *ring)
+static bool recv_block(struct ring_state *ring)
{
struct tpacket_block_desc *block;
char *frame;
@@ -223,7 +223,7 @@ static void recv_block(struct ring_state *ring)
block = (void *)(ring->mmap + ring->idx * ring_block_sz);
if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
- return;
+ return false;
frame = (char *)block;
frame += block->hdr.bh1.offset_to_first_pkt;
@@ -235,6 +235,8 @@ static void recv_block(struct ring_state *ring)
block->hdr.bh1.block_status = TP_STATUS_KERNEL;
ring->idx = (ring->idx + 1) % ring_block_nr;
+
+ return true;
}
/* simple test: sleep once unconditionally and then process all rings */
@@ -245,7 +247,7 @@ static void process_rings(void)
usleep(1000 * cfg_timeout_msec);
for (i = 0; i < num_cpus; i++)
- recv_block(&rings[i]);
+ do {} while (recv_block(&rings[i]));
fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
frames_received - frames_nohash - frames_error,
@@ -257,12 +259,12 @@ static char *setup_ring(int fd)
struct tpacket_req3 req3 = {0};
void *ring;
- req3.tp_retire_blk_tov = cfg_timeout_msec;
+ req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
req3.tp_frame_size = 2048;
req3.tp_frame_nr = 1 << 10;
- req3.tp_block_nr = 2;
+ req3.tp_block_nr = 16;
req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
req3.tp_block_size /= req3.tp_block_nr;
--
GitLab
From 6c977c5c2e4c5d8ad1b604724cc344e38f96fe9b Mon Sep 17 00:00:00 2001
From: Rakesh Sankaranarayanan <rakesh.sankaranarayanan@microchip.com>
Date: Wed, 18 Jan 2023 23:17:35 +0530
Subject: [PATCH 1000/1167] net: dsa: microchip: ksz9477: port map correction
in ALU table entry register
ALU table entry 2 register in KSZ9477 have bit positions reserved for
forwarding port map. This field is referred in ksz9477_fdb_del() for
clearing forward port map and alu table.
But current fdb_del refer ALU table entry 3 register for accessing forward
port map. Update ksz9477_fdb_del() to get forward port map from correct
alu table entry register.
With this bug, issue can be observed while deleting static MAC entries.
Delete any specific MAC entry using "bridge fdb del" command. This should
clear all the specified MAC entries. But it is observed that entries with
self static alone are retained.
Tested on LAN9370 EVB since ksz9477_fdb_del() is used common across
LAN937x and KSZ series.
Fixes: b987e98e50ab ("dsa: add DSA switch driver for Microchip KSZ9477")
Signed-off-by: Rakesh Sankaranarayanan <rakesh.sankaranarayanan@microchip.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://lore.kernel.org/r/20230118174735.702377-1-rakesh.sankaranarayanan@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/dsa/microchip/ksz9477.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 47b54ecf2c6f6..6178a96e389f2 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -540,10 +540,10 @@ int ksz9477_fdb_del(struct ksz_device *dev, int port,
ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]);
/* clear forwarding port */
- alu_table[2] &= ~BIT(port);
+ alu_table[1] &= ~BIT(port);
/* if there is no port to forward, clear table */
- if ((alu_table[2] & ALU_V_PORT_MAP) == 0) {
+ if ((alu_table[1] & ALU_V_PORT_MAP) == 0) {
alu_table[0] = 0;
alu_table[1] = 0;
alu_table[2] = 0;
--
GitLab
From e12d7a46f65ae4b7d58a5e0c1cbfa825cf8d830d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 19 Jan 2023 09:04:40 -0700
Subject: [PATCH 1001/1167] io_uring/msg_ring: fix missing lock on overflow for
IOPOLL
If the target ring is configured with IOPOLL, then we always need to hold
the target ring uring_lock before posting CQEs. We could just grab it
unconditionally, but since we don't expect many target rings to be of this
type, make grabbing the uring_lock conditional on the ring type.
Link: https://lore.kernel.org/io-uring/Y8krlYa52%2F0YGqkg@ip-172-31-85-199.ec2.internal/
Reported-by: Xingyuan Mo <hdthky0@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/msg_ring.c | 39 ++++++++++++++++++++++++++++++---------
1 file changed, 30 insertions(+), 9 deletions(-)
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 321f5eafef992..a333781565d31 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -65,20 +65,33 @@ static void io_msg_tw_complete(struct callback_head *head)
struct io_ring_ctx *target_ctx = req->file->private_data;
int ret = 0;
- if (current->flags & PF_EXITING)
+ if (current->flags & PF_EXITING) {
ret = -EOWNERDEAD;
- else if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
- ret = -EOVERFLOW;
+ } else {
+ /*
+ * If the target ring is using IOPOLL mode, then we need to be
+ * holding the uring_lock for posting completions. Other ring
+ * types rely on the regular completion locking, which is
+ * handled while posting.
+ */
+ if (target_ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_lock(&target_ctx->uring_lock);
+ if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = -EOVERFLOW;
+ if (target_ctx->flags & IORING_SETUP_IOPOLL)
+ mutex_unlock(&target_ctx->uring_lock);
+ }
if (ret < 0)
req_set_fail(req);
io_req_queue_tw_complete(req, ret);
}
-static int io_msg_ring_data(struct io_kiocb *req)
+static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *target_ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
+ int ret;
if (msg->src_fd || msg->dst_fd || msg->flags)
return -EINVAL;
@@ -93,10 +106,18 @@ static int io_msg_ring_data(struct io_kiocb *req)
return IOU_ISSUE_SKIP_COMPLETE;
}
- if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
- return 0;
-
- return -EOVERFLOW;
+ ret = -EOVERFLOW;
+ if (target_ctx->flags & IORING_SETUP_IOPOLL) {
+ if (unlikely(io_double_lock_ctx(target_ctx, issue_flags)))
+ return -EAGAIN;
+ if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = 0;
+ io_double_unlock_ctx(target_ctx);
+ } else {
+ if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0))
+ ret = 0;
+ }
+ return ret;
}
static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags)
@@ -223,7 +244,7 @@ int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags)
switch (msg->cmd) {
case IORING_MSG_DATA:
- ret = io_msg_ring_data(req);
+ ret = io_msg_ring_data(req, issue_flags);
break;
case IORING_MSG_SEND_FD:
ret = io_msg_send_fd(req, issue_flags);
--
GitLab
From 6c54b7bc8a31ce0f7cc7f8deef05067df414f1d8 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 18 Jan 2023 14:08:24 +0530
Subject: [PATCH 1002/1167] thermal: core: call put_device() only after
device_register() fails
put_device() shouldn't be called before a prior call to
device_register(). __thermal_cooling_device_register() doesn't follow
that properly and needs fixing. Also
thermal_cooling_device_destroy_sysfs() is getting called unnecessarily
on few error paths.
Fix all this by placing the calls at the right place.
Based on initial work done by Caleb Connolly.
Fixes: 4748f9687caa ("thermal: core: fix some possible name leaks in error paths")
Fixes: c408b3d1d9bb ("thermal: Validate new state in cur_state_store()")
Reported-by: Caleb Connolly <caleb.connolly@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Tested-by: Frank Rowand <frowand.list@gmail.com>
Reviewed-by: Yang Yingliang <yangyingliang@huawei.com>
Tested-by: Caleb Connolly <caleb.connolly@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/thermal/thermal_core.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index f17ab2316dbd0..77bd47d976a21 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -909,15 +909,20 @@ __thermal_cooling_device_register(struct device_node *np,
cdev->devdata = devdata;
ret = cdev->ops->get_max_state(cdev, &cdev->max_state);
- if (ret)
- goto out_kfree_type;
+ if (ret) {
+ kfree(cdev->type);
+ goto out_ida_remove;
+ }
thermal_cooling_device_setup_sysfs(cdev);
+
ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
if (ret) {
+ kfree(cdev->type);
thermal_cooling_device_destroy_sysfs(cdev);
- goto out_kfree_type;
+ goto out_ida_remove;
}
+
ret = device_register(&cdev->device);
if (ret)
goto out_kfree_type;
@@ -943,6 +948,8 @@ __thermal_cooling_device_register(struct device_node *np,
thermal_cooling_device_destroy_sysfs(cdev);
kfree(cdev->type);
put_device(&cdev->device);
+
+ /* thermal_release() takes care of the rest */
cdev = NULL;
out_ida_remove:
ida_free(&thermal_cdev_ida, id);
--
GitLab
From fe0ba8c23f9a35b0307eb662f16dd3a75fcdae41 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 17 Jan 2023 16:57:23 +0100
Subject: [PATCH 1003/1167] acpi: Fix suspend with Xen PV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Commit f1e525009493 ("x86/boot: Skip realmode init code when running as
Xen PV guest") missed one code path accessing real_mode_header, leading
to dereferencing NULL when suspending the system under Xen:
[ 348.284004] PM: suspend entry (deep)
[ 348.289532] Filesystems sync: 0.005 seconds
[ 348.291545] Freezing user space processes ... (elapsed 0.000 seconds) done.
[ 348.292457] OOM killer disabled.
[ 348.292462] Freezing remaining freezable tasks ... (elapsed 0.104 seconds) done.
[ 348.396612] printk: Suspending console(s) (use no_console_suspend to debug)
[ 348.749228] PM: suspend devices took 0.352 seconds
[ 348.769713] ACPI: EC: interrupt blocked
[ 348.816077] BUG: kernel NULL pointer dereference, address: 000000000000001c
[ 348.816080] #PF: supervisor read access in kernel mode
[ 348.816081] #PF: error_code(0x0000) - not-present page
[ 348.816083] PGD 0 P4D 0
[ 348.816086] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 348.816089] CPU: 0 PID: 6764 Comm: systemd-sleep Not tainted 6.1.3-1.fc32.qubes.x86_64 #1
[ 348.816092] Hardware name: Star Labs StarBook/StarBook, BIOS 8.01 07/03/2022
[ 348.816093] RIP: e030:acpi_get_wakeup_address+0xc/0x20
Fix that by adding an optional acpi callback allowing to skip setting
the wakeup address, as in the Xen PV case this will be handled by the
hypervisor anyway.
Fixes: f1e525009493 ("x86/boot: Skip realmode init code when running as Xen PV guest")
Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/all/20230117155724.22940-1-jgross%40suse.com
---
arch/x86/include/asm/acpi.h | 8 ++++++++
drivers/acpi/sleep.c | 6 +++++-
2 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 65064d9f7fa6e..8eb74cf386dbe 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -14,6 +14,7 @@
#include <asm/mmu.h>
#include <asm/mpspec.h>
#include <asm/x86_init.h>
+#include <asm/cpufeature.h>
#ifdef CONFIG_ACPI_APEI
# include <asm/pgtable_types.h>
@@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void);
/* Physical address to resume after wakeup */
unsigned long acpi_get_wakeup_address(void);
+static inline bool acpi_skip_set_wakeup_address(void)
+{
+ return cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+
+#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
+
/*
* Check if the CPU can handle C2 and deeper
*/
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 0b557c0d405ef..4ca6672512722 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -60,13 +60,17 @@ static struct notifier_block tts_notifier = {
.priority = 0,
};
+#ifndef acpi_skip_set_wakeup_address
+#define acpi_skip_set_wakeup_address() false
+#endif
+
static int acpi_sleep_prepare(u32 acpi_state)
{
#ifdef CONFIG_ACPI_SLEEP
unsigned long acpi_wakeup_address;
/* do we have a wakeup address for S2 and S3? */
- if (acpi_state == ACPI_STATE_S3) {
+ if (acpi_state == ACPI_STATE_S3 && !acpi_skip_set_wakeup_address()) {
acpi_wakeup_address = acpi_get_wakeup_address();
if (!acpi_wakeup_address)
return -EFAULT;
--
GitLab
From d374a16539b14dde0b8a3e69fb9169a7454a806c Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@vrull.eu>
Date: Thu, 5 Jan 2023 20:26:10 +0100
Subject: [PATCH 1004/1167] RISC-V: fix compile error from deduplicated
__ALTERNATIVE_CFG_2
On the non-assembler-side wrapping alternative-macros inside other macros
to prevent duplication of code works, as the end result will just be a
string that gets fed to the asm instruction.
In real assembler code, wrapping .macro blocks inside other .macro blocks
brings more restrictions on usage it seems and the optimization done by
commit 2ba8c7dc71c0 ("riscv: Don't duplicate __ALTERNATIVE_CFG in __ALTERNATIVE_CFG_2")
results in a compile error like:
../arch/riscv/lib/strcmp.S: Assembler messages:
../arch/riscv/lib/strcmp.S:15: Error: too many positional arguments
../arch/riscv/lib/strcmp.S:15: Error: backward ref to unknown label "886:"
../arch/riscv/lib/strcmp.S:15: Error: backward ref to unknown label "887:"
../arch/riscv/lib/strcmp.S:15: Error: backward ref to unknown label "886:"
../arch/riscv/lib/strcmp.S:15: Error: backward ref to unknown label "887:"
../arch/riscv/lib/strcmp.S:15: Error: backward ref to unknown label "886:"
../arch/riscv/lib/strcmp.S:15: Error: attempt to move .org backwards
Wrapping the variables containing assembler code in quotes solves this issue,
compilation and the code in question still works and objdump also shows sane
decompiled results of the affected code.
Fixes: 2ba8c7dc71c0 ("riscv: Don't duplicate __ALTERNATIVE_CFG in __ALTERNATIVE_CFG_2")
Signed-off-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Reviewed-by: Palmer Dabbelt <palmer@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/20230105192610.1940841-1-heiko@sntech.de
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/include/asm/alternative-macros.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h
index 7226e2462584b..2c0f4c887289a 100644
--- a/arch/riscv/include/asm/alternative-macros.h
+++ b/arch/riscv/include/asm/alternative-macros.h
@@ -46,7 +46,7 @@
.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \
new_c_2, vendor_id_2, errata_id_2, enable_2
- ALTERNATIVE_CFG \old_c, \new_c_1, \vendor_id_1, \errata_id_1, \enable_1
+ ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1
ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2
.endm
--
GitLab
From 6d0cc1b1f22adb254408a42043d3939bed65545d Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Fri, 6 Jan 2023 12:53:45 +0000
Subject: [PATCH 1005/1167] MAINTAINERS: add an IRC entry for RISC-V
I remember being told "Just ping me on IRC" about patches, but googling
at the time was not helpful. #riscv on libera is not linux specific,
but a bunch of contributors etc do hang out there.
Add a link to the maintainers entry to help others find it in the future!
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20230106125344.1685266-1-conor@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f61eb221415bd..0f9f685ce39c6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17948,6 +17948,7 @@ M: Albert Ou <aou@eecs.berkeley.edu>
L: linux-riscv@lists.infradead.org
S: Supported
Q: https://patchwork.kernel.org/project/linux-riscv/list/
+C: irc://irc.libera.chat/riscv
P: Documentation/riscv/patch-acceptance.rst
T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git
F: arch/riscv/
--
GitLab
From 5b89c6f9b2df2b7cf6da8e0b2b87c8995b378cad Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 7 Jan 2023 01:12:13 +0900
Subject: [PATCH 1006/1167] riscv: fix -Wundef warning for
CONFIG_RISCV_BOOT_SPINWAIT
Since commit 80b6093b55e3 ("kbuild: add -Wundef to KBUILD_CPPFLAGS
for W=1 builds"), building with W=1 detects misuse of #if.
$ make W=1 ARCH=riscv CROSS_COMPILE=riscv64-linux-gnu- arch/riscv/kernel/
[snip]
AS arch/riscv/kernel/head.o
arch/riscv/kernel/head.S:329:5: warning: "CONFIG_RISCV_BOOT_SPINWAIT" is not defined, evaluates to 0 [-Wundef]
329 | #if CONFIG_RISCV_BOOT_SPINWAIT
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
CONFIG_RISCV_BOOT_SPINWAIT is a bool option. #ifdef should be used.
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Fixes: 2ffc48fc7071 ("RISC-V: Move spinwait booting method to its own config")
Link: https://lore.kernel.org/r/20230106161213.2374093-1-masahiroy@kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/kernel/head.S | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index b865046e4dbbc..4bf6c449d78b6 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -326,7 +326,7 @@ clear_bss_done:
call soc_early_init
tail start_kernel
-#if CONFIG_RISCV_BOOT_SPINWAIT
+#ifdef CONFIG_RISCV_BOOT_SPINWAIT
.Lsecondary_start:
/* Set trap vector to spin forever to help debug */
la a3, .Lsecondary_park
--
GitLab
From 0a4eecf96c640886226f1ca7fdbb11bb20bc55b9 Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Tue, 17 Jan 2023 17:50:17 +0000
Subject: [PATCH 1007/1167] dt-bindings: i2c: renesas,rzv2m: Fix SoC specific
string
The preferred form for Renesas' compatible strings is:
"<vendor>,<family>-<module>"
Somehow the compatible string for the r9a09g011 I2C IP was upstreamed
as renesas,i2c-r9a09g011 instead of renesas,r9a09g011-i2c, which
is really confusing, especially considering the generic fallback
is renesas,rzv2m-i2c.
The first user of renesas,i2c-r9a09g011 in the kernel is not yet in
a kernel release, it will be in v6.1, therefore it can still be
fixed in v6.1.
Even if we don't fix it before v6.2, I don't think there is any
harm in making such a change.
s/renesas,i2c-r9a09g011/renesas,r9a09g011-i2c/g for consistency.
Fixes: ba7a4d15e2c4 ("dt-bindings: i2c: Document RZ/V2M I2C controller")
Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml
index c46378efc1239..92e899905ef88 100644
--- a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml
+++ b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml
@@ -16,7 +16,7 @@ properties:
compatible:
items:
- enum:
- - renesas,i2c-r9a09g011 # RZ/V2M
+ - renesas,r9a09g011-i2c # RZ/V2M
- const: renesas,rzv2m-i2c
reg:
@@ -66,7 +66,7 @@ examples:
#include <dt-bindings/interrupt-controller/arm-gic.h>
i2c0: i2c@a4030000 {
- compatible = "renesas,i2c-r9a09g011", "renesas,rzv2m-i2c";
+ compatible = "renesas,r9a09g011-i2c", "renesas,rzv2m-i2c";
reg = <0xa4030000 0x80>;
interrupts = <GIC_SPI 232 IRQ_TYPE_EDGE_RISING>,
<GIC_SPI 236 IRQ_TYPE_EDGE_RISING>;
--
GitLab
From 07ea567d84cdf0add274d66db7c02b55b818d517 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:48 +0530
Subject: [PATCH 1008/1167] octeontx2-af: recover CPT engine when it gets fault
When CPT engine has uncorrectable errors, it will get halted and
must be disabled and re-enabled. This patch adds code for the same.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 110 +++++++++++++-----
1 file changed, 80 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 38bbae5d9ae05..1ed16ce515bb1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -37,34 +37,60 @@
(_rsp)->free_sts_##etype = free_sts; \
})
-static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr)
+static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr)
{
struct rvu_block *block = ptr;
struct rvu *rvu = block->rvu;
int blkaddr = block->addr;
- u64 reg0, reg1, reg2;
-
- reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0));
- reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1));
- if (!is_rvu_otx2(rvu)) {
- reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2));
- dev_err_ratelimited(rvu->dev,
- "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx",
- reg0, reg1, reg2);
- } else {
- dev_err_ratelimited(rvu->dev,
- "Received CPTAF FLT irq : 0x%llx, 0x%llx",
- reg0, reg1);
+ u64 reg, val;
+ int i, eng;
+ u8 grp;
+
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(vec));
+ dev_err_ratelimited(rvu->dev, "Received CPTAF FLT%d irq : 0x%llx", vec, reg);
+
+ i = -1;
+ while ((i = find_next_bit((unsigned long *)®, 64, i + 1)) < 64) {
+ switch (vec) {
+ case 0:
+ eng = i;
+ break;
+ case 1:
+ eng = i + 64;
+ break;
+ case 2:
+ eng = i + 128;
+ break;
+ }
+ grp = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng)) & 0xFF;
+ /* Disable and enable the engine which triggers fault */
+ rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), 0x0);
+ val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng));
+ rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val & ~1ULL);
+
+ rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), grp);
+ rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val | 1ULL);
}
-
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0);
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1);
- if (!is_rvu_otx2(rvu))
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(vec), reg);
return IRQ_HANDLED;
}
+static irqreturn_t rvu_cpt_af_flt0_intr_handler(int irq, void *ptr)
+{
+ return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT0, ptr);
+}
+
+static irqreturn_t rvu_cpt_af_flt1_intr_handler(int irq, void *ptr)
+{
+ return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT1, ptr);
+}
+
+static irqreturn_t rvu_cpt_af_flt2_intr_handler(int irq, void *ptr)
+{
+ return cpt_af_flt_intr_handler(CPT_10K_AF_INT_VEC_FLT2, ptr);
+}
+
static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr)
{
struct rvu_block *block = ptr;
@@ -119,8 +145,10 @@ static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off)
int i;
/* Disable all CPT AF interrupts */
- for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++)
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(0), ~0ULL);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(1), ~0ULL);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(2), 0xFFFF);
+
rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1);
@@ -151,7 +179,7 @@ static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr)
/* Disable all CPT AF interrupts */
for (i = 0; i < CPT_AF_INT_VEC_RVU; i++)
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), ~0ULL);
rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1);
@@ -172,16 +200,31 @@ static int cpt_10k_register_interrupts(struct rvu_block *block, int off)
{
struct rvu *rvu = block->rvu;
int blkaddr = block->addr;
+ irq_handler_t flt_fn;
int i, ret;
for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) {
sprintf(&rvu->irq_name[(off + i) * NAME_SIZE], "CPTAF FLT%d", i);
+
+ switch (i) {
+ case CPT_10K_AF_INT_VEC_FLT0:
+ flt_fn = rvu_cpt_af_flt0_intr_handler;
+ break;
+ case CPT_10K_AF_INT_VEC_FLT1:
+ flt_fn = rvu_cpt_af_flt1_intr_handler;
+ break;
+ case CPT_10K_AF_INT_VEC_FLT2:
+ flt_fn = rvu_cpt_af_flt2_intr_handler;
+ break;
+ }
ret = rvu_cpt_do_register_interrupt(block, off + i,
- rvu_cpt_af_flt_intr_handler,
- &rvu->irq_name[(off + i) * NAME_SIZE]);
+ flt_fn, &rvu->irq_name[(off + i) * NAME_SIZE]);
if (ret)
goto err;
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1);
+ if (i == CPT_10K_AF_INT_VEC_FLT2)
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0xFFFF);
+ else
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL);
}
ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU,
@@ -208,8 +251,8 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr)
{
struct rvu_hwinfo *hw = rvu->hw;
struct rvu_block *block;
+ irq_handler_t flt_fn;
int i, offs, ret = 0;
- char irq_name[16];
if (!is_block_implemented(rvu->hw, blkaddr))
return 0;
@@ -226,13 +269,20 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr)
return cpt_10k_register_interrupts(block, offs);
for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) {
- snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i);
+ sprintf(&rvu->irq_name[(offs + i) * NAME_SIZE], "CPTAF FLT%d", i);
+ switch (i) {
+ case CPT_AF_INT_VEC_FLT0:
+ flt_fn = rvu_cpt_af_flt0_intr_handler;
+ break;
+ case CPT_AF_INT_VEC_FLT1:
+ flt_fn = rvu_cpt_af_flt1_intr_handler;
+ break;
+ }
ret = rvu_cpt_do_register_interrupt(block, offs + i,
- rvu_cpt_af_flt_intr_handler,
- irq_name);
+ flt_fn, &rvu->irq_name[(offs + i) * NAME_SIZE]);
if (ret)
goto err;
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL);
}
ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU,
--
GitLab
From f58cf765e8f5f4860ea094aa12c156d9195a4c28 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:49 +0530
Subject: [PATCH 1009/1167] octeontx2-af: add mbox for CPT LF reset
On OcteonTX2 SoC, the admin function (AF) is the only one with all
priviliges to configure HW and alloc resources, PFs and it's VFs
have to request AF via mailbox for all their needs.
This patch adds a new mailbox for CPT VFs to request for CPT LF
reset.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../net/ethernet/marvell/octeontx2/af/mbox.h | 8 +++++
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 33 +++++++++++++++++++
2 files changed, 41 insertions(+)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index d2584ebb7a70c..b121e3d9f5619 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -195,6 +195,7 @@ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \
M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \
msg_rsp) \
M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \
+M(CPT_LF_RESET, 0xA08, cpt_lf_reset, cpt_lf_rst_req, msg_rsp) \
/* SDP mbox IDs (range 0x1000 - 0x11FF) */ \
M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \
M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \
@@ -1692,6 +1693,13 @@ struct cpt_inst_lmtst_req {
u64 rsvd;
};
+/* Mailbox message format to request for CPT LF reset */
+struct cpt_lf_rst_req {
+ struct mbox_msghdr hdr;
+ u32 slot;
+ u32 rsvd;
+};
+
struct sdp_node_info {
/* Node to which this PF belons to */
u8 node_id;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 1ed16ce515bb1..1cd34914cb86b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -851,6 +851,39 @@ int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req,
return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc);
}
+int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req,
+ struct msg_rsp *rsp)
+{
+ u16 pcifunc = req->hdr.pcifunc;
+ struct rvu_block *block;
+ int cptlf, blkaddr, ret;
+ u16 actual_slot;
+ u64 ctl, ctl2;
+
+ blkaddr = rvu_get_blkaddr_from_slot(rvu, BLKTYPE_CPT, pcifunc,
+ req->slot, &actual_slot);
+ if (blkaddr < 0)
+ return CPT_AF_ERR_LF_INVALID;
+
+ block = &rvu->hw->block[blkaddr];
+
+ cptlf = rvu_get_lf(rvu, block, pcifunc, actual_slot);
+ if (cptlf < 0)
+ return CPT_AF_ERR_LF_INVALID;
+ ctl = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf));
+ ctl2 = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf));
+
+ ret = rvu_lf_reset(rvu, block, cptlf);
+ if (ret)
+ dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n",
+ block->addr, cptlf);
+
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), ctl);
+ rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), ctl2);
+
+ return 0;
+}
+
static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
{
struct cpt_rxc_time_cfg_req req;
--
GitLab
From 1286c50ae9e0f5025b165c8f2321b3ce3b558002 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:50 +0530
Subject: [PATCH 1010/1167] octeontx2-af: modify FLR sequence for CPT
On OcteonTX2 platform CPT instruction enqueue is only
possible via LMTST operations.
The existing FLR sequence mentioned in HRM requires
a dummy LMTST to CPT but LMTST can't be submitted from
AF driver. So, HW team provided a new sequence to avoid
dummy LMTST. This patch adds code for the same.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../net/ethernet/marvell/octeontx2/af/rvu.h | 12 +++
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 86 +++++++++----------
.../ethernet/marvell/octeontx2/af/rvu_reg.h | 2 +
3 files changed, 53 insertions(+), 47 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7f0a64731c675..20c75d7c962ef 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -459,6 +459,7 @@ struct rvu {
struct rvu_pfvf *pf;
struct rvu_pfvf *hwvf;
struct mutex rsrc_lock; /* Serialize resource alloc/free */
+ struct mutex alias_lock; /* Serialize bar2 alias access */
int vfs; /* Number of VFs attached to RVU */
int nix_blkaddr[MAX_NIX_BLKS];
@@ -546,6 +547,17 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
return readq(rvu->pfreg_base + offset);
}
+static inline void rvu_bar2_sel_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
+{
+ /* HW requires read back of RVU_AF_BAR2_SEL register to make sure completion of
+ * write operation.
+ */
+ rvu_write64(rvu, block, offset, val);
+ rvu_read64(rvu, block, offset);
+ /* Barrier to ensure read completes before accessing LF registers */
+ mb();
+}
+
/* Silicon revisions */
static inline bool is_rvu_pre_96xx_C0(struct rvu *rvu)
{
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 1cd34914cb86b..e8973294c4f88 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -930,68 +930,63 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n");
}
-#define INPROG_INFLIGHT(reg) ((reg) & 0x1FF)
-#define INPROG_GRB_PARTIAL(reg) ((reg) & BIT_ULL(31))
-#define INPROG_GRB(reg) (((reg) >> 32) & 0xFF)
-#define INPROG_GWB(reg) (((reg) >> 40) & 0xFF)
+#define INFLIGHT GENMASK_ULL(8, 0)
+#define GRB_CNT GENMASK_ULL(39, 32)
+#define GWB_CNT GENMASK_ULL(47, 40)
+#define XQ_XOR GENMASK_ULL(63, 63)
+#define DQPTR GENMASK_ULL(19, 0)
+#define NQPTR GENMASK_ULL(51, 32)
static void cpt_lf_disable_iqueue(struct rvu *rvu, int blkaddr, int slot)
{
- int i = 0, hard_lp_ctr = 100000;
- u64 inprog, grp_ptr;
- u16 nq_ptr, dq_ptr;
+ int timeout = 1000000;
+ u64 inprog, inst_ptr;
+ u64 qsize, pending;
+ int i = 0;
/* Disable instructions enqueuing */
rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_CTL), 0x0);
- /* Disable executions in the LF's queue */
inprog = rvu_read64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- inprog &= ~BIT_ULL(16);
+ inprog |= BIT_ULL(16);
rvu_write64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), inprog);
- /* Wait for CPT queue to become execution-quiescent */
+ qsize = rvu_read64(rvu, blkaddr,
+ CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_SIZE)) & 0x7FFF;
do {
- inprog = rvu_read64(rvu, blkaddr,
- CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- if (INPROG_GRB_PARTIAL(inprog)) {
- i = 0;
- hard_lp_ctr--;
- } else {
- i++;
- }
-
- grp_ptr = rvu_read64(rvu, blkaddr,
- CPT_AF_BAR2_ALIASX(slot,
- CPT_LF_Q_GRP_PTR));
- nq_ptr = (grp_ptr >> 32) & 0x7FFF;
- dq_ptr = grp_ptr & 0x7FFF;
-
- } while (hard_lp_ctr && (i < 10) && (nq_ptr != dq_ptr));
+ inst_ptr = rvu_read64(rvu, blkaddr,
+ CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_INST_PTR));
+ pending = (FIELD_GET(XQ_XOR, inst_ptr) * qsize * 40) +
+ FIELD_GET(NQPTR, inst_ptr) -
+ FIELD_GET(DQPTR, inst_ptr);
+ udelay(1);
+ timeout--;
+ } while ((pending != 0) && (timeout != 0));
- if (hard_lp_ctr == 0)
- dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n");
+ if (timeout == 0)
+ dev_warn(rvu->dev, "TIMEOUT: CPT poll on pending instructions\n");
- i = 0;
- hard_lp_ctr = 100000;
+ timeout = 1000000;
+ /* Wait for CPT queue to become execution-quiescent */
do {
inprog = rvu_read64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- if ((INPROG_INFLIGHT(inprog) == 0) &&
- (INPROG_GWB(inprog) < 40) &&
- ((INPROG_GRB(inprog) == 0) ||
- (INPROG_GRB((inprog)) == 40))) {
+ if ((FIELD_GET(INFLIGHT, inprog) == 0) &&
+ (FIELD_GET(GRB_CNT, inprog) == 0)) {
i++;
} else {
i = 0;
- hard_lp_ctr--;
+ timeout--;
}
- } while (hard_lp_ctr && (i < 10));
+ } while ((timeout != 0) && (i < 10));
- if (hard_lp_ctr == 0)
- dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n");
+ if (timeout == 0)
+ dev_warn(rvu->dev, "TIMEOUT: CPT poll on inflight count\n");
+ /* Wait for 2 us to flush all queue writes to memory */
+ udelay(2);
}
int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot)
@@ -1001,18 +996,15 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s
if (is_cpt_pf(rvu, pcifunc) || is_cpt_vf(rvu, pcifunc))
cpt_rxc_teardown(rvu, blkaddr);
+ mutex_lock(&rvu->alias_lock);
/* Enable BAR2 ALIAS for this pcifunc. */
reg = BIT_ULL(16) | pcifunc;
- rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
+ rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
cpt_lf_disable_iqueue(rvu, blkaddr, slot);
- /* Set group drop to help clear out hardware */
- reg = rvu_read64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- reg |= BIT_ULL(17);
- rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), reg);
-
- rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
+ rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
+ mutex_unlock(&rvu->alias_lock);
return 0;
}
@@ -1147,7 +1139,7 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc)
/* Enable BAR2 ALIAS for this pcifunc. */
reg = BIT_ULL(16) | pcifunc;
- rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
+ rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
for (i = 0; i < max_ctx_entries; i++) {
cam_data = rvu_read64(rvu, blkaddr, CPT_AF_CTX_CAM_DATA(i));
@@ -1160,7 +1152,7 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc)
reg);
}
}
- rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
+ rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
unlock:
mutex_unlock(&rvu->rsrc_lock);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 0e0d536645ac7..5437bd20c7192 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -545,6 +545,8 @@
#define CPT_LF_CTL 0x10
#define CPT_LF_INPROG 0x40
+#define CPT_LF_Q_SIZE 0x100
+#define CPT_LF_Q_INST_PTR 0x110
#define CPT_LF_Q_GRP_PTR 0x120
#define CPT_LF_CTX_FLUSH 0x510
--
GitLab
From 9adb04ff62f51265002c2c83e718bcf459e06e48 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:51 +0530
Subject: [PATCH 1011/1167] octeontx2-af: optimize cpt pf identification
Optimize CPT PF identification in mbox handling for faster
mbox response by doing it at AF driver probe instead of
every mbox message.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 8 ++++++++
drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 2 ++
drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 13 ++++++++++---
3 files changed, 20 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 3f5e09b77d4bd..8683ce57ed3fb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1164,8 +1164,16 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
goto nix_err;
}
+ err = rvu_cpt_init(rvu);
+ if (err) {
+ dev_err(rvu->dev, "%s: Failed to initialize cpt\n", __func__);
+ goto mcs_err;
+ }
+
return 0;
+mcs_err:
+ rvu_mcs_exit(rvu);
nix_err:
rvu_nix_freemem(rvu);
npa_err:
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 20c75d7c962ef..2f480c73ef553 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -511,6 +511,7 @@ struct rvu {
struct ptp *ptp;
int mcs_blk_cnt;
+ int cpt_pf_num;
#ifdef CONFIG_DEBUG_FS
struct rvu_debugfs rvu_dbg;
@@ -877,6 +878,7 @@ void rvu_cpt_unregister_interrupts(struct rvu *rvu);
int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf,
int slot);
int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc);
+int rvu_cpt_init(struct rvu *rvu);
/* CN10K RVU */
int rvu_set_channels_base(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index e8973294c4f88..f970cb9b0bff3 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -340,7 +340,7 @@ static int get_cpt_pf_num(struct rvu *rvu)
static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
{
- int cpt_pf_num = get_cpt_pf_num(rvu);
+ int cpt_pf_num = rvu->cpt_pf_num;
if (rvu_get_pf(pcifunc) != cpt_pf_num)
return false;
@@ -352,7 +352,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
{
- int cpt_pf_num = get_cpt_pf_num(rvu);
+ int cpt_pf_num = rvu->cpt_pf_num;
if (rvu_get_pf(pcifunc) != cpt_pf_num)
return false;
@@ -1015,7 +1015,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s
static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr,
int nix_blkaddr)
{
- int cpt_pf_num = get_cpt_pf_num(rvu);
+ int cpt_pf_num = rvu->cpt_pf_num;
struct cpt_inst_lmtst_req *req;
dma_addr_t res_daddr;
int timeout = 3000;
@@ -1159,3 +1159,10 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc)
return 0;
}
+
+int rvu_cpt_init(struct rvu *rvu)
+{
+ /* Retrieve CPT PF number */
+ rvu->cpt_pf_num = get_cpt_pf_num(rvu);
+ return 0;
+}
--
GitLab
From d5b2e0a299f36c6ccdda4830525ca20550243536 Mon Sep 17 00:00:00 2001
From: Nithin Dabilpuram <ndabilpuram@marvell.com>
Date: Wed, 18 Jan 2023 17:33:52 +0530
Subject: [PATCH 1012/1167] octeontx2-af: restore rxc conf after teardown
sequence
CN10K CPT coprocessor includes a component named RXC which
is responsible for reassembly of inner IP packets. RXC has
the feature to evict oldest entries based on age/threshold.
The age/threshold is being set to minimum values to evict
all entries at the time of teardown.
This patch adds code to restore timeout and threshold config
after teardown sequence is complete as it is global config.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 22 +++++++++++++++----
1 file changed, 18 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index f970cb9b0bff3..302ff549284e5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -812,10 +812,21 @@ int rvu_mbox_handler_cpt_sts(struct rvu *rvu, struct cpt_sts_req *req,
#define RXC_ZOMBIE_COUNT GENMASK_ULL(60, 48)
static void cpt_rxc_time_cfg(struct rvu *rvu, struct cpt_rxc_time_cfg_req *req,
- int blkaddr)
+ int blkaddr, struct cpt_rxc_time_cfg_req *save)
{
u64 dfrg_reg;
+ if (save) {
+ /* Save older config */
+ dfrg_reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_DFRG);
+ save->zombie_thres = FIELD_GET(RXC_ZOMBIE_THRES, dfrg_reg);
+ save->zombie_limit = FIELD_GET(RXC_ZOMBIE_LIMIT, dfrg_reg);
+ save->active_thres = FIELD_GET(RXC_ACTIVE_THRES, dfrg_reg);
+ save->active_limit = FIELD_GET(RXC_ACTIVE_LIMIT, dfrg_reg);
+
+ save->step = rvu_read64(rvu, blkaddr, CPT_AF_RXC_TIME_CFG);
+ }
+
dfrg_reg = FIELD_PREP(RXC_ZOMBIE_THRES, req->zombie_thres);
dfrg_reg |= FIELD_PREP(RXC_ZOMBIE_LIMIT, req->zombie_limit);
dfrg_reg |= FIELD_PREP(RXC_ACTIVE_THRES, req->active_thres);
@@ -840,7 +851,7 @@ int rvu_mbox_handler_cpt_rxc_time_cfg(struct rvu *rvu,
!is_cpt_vf(rvu, req->hdr.pcifunc))
return CPT_AF_ERR_ACCESS_DENIED;
- cpt_rxc_time_cfg(rvu, req, blkaddr);
+ cpt_rxc_time_cfg(rvu, req, blkaddr, NULL);
return 0;
}
@@ -886,7 +897,7 @@ int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req,
static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
{
- struct cpt_rxc_time_cfg_req req;
+ struct cpt_rxc_time_cfg_req req, prev;
int timeout = 2000;
u64 reg;
@@ -902,7 +913,7 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
req.active_thres = 1;
req.active_limit = 1;
- cpt_rxc_time_cfg(rvu, &req, blkaddr);
+ cpt_rxc_time_cfg(rvu, &req, blkaddr, &prev);
do {
reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS);
@@ -928,6 +939,9 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
if (timeout == 0)
dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n");
+
+ /* Restore config */
+ cpt_rxc_time_cfg(rvu, &prev, blkaddr, NULL);
}
#define INFLIGHT GENMASK_ULL(8, 0)
--
GitLab
From c0688ec002a451d04a51d43b849765c5ce6cb36f Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:53 +0530
Subject: [PATCH 1013/1167] octeontx2-af: update cpt lf alloc mailbox
The CN10K CPT coprocessor contains a context processor
to accelerate updates to the IPsec security association
contexts. The context processor contains a context cache.
This patch updates CPT LF ALLOC mailbox to config ctx_ilen
requested by VFs. CPT_LF_ALLOC:ctx_ilen is the size of
initial context fetch.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/marvell/octeontx2/af/mbox.h | 2 ++
drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 10 +++++++---
2 files changed, 9 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index b121e3d9f5619..e2ae9c317ce27 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1610,6 +1610,8 @@ struct cpt_lf_alloc_req_msg {
u16 sso_pf_func;
u16 eng_grpmsk;
int blkaddr;
+ u8 ctx_ilen_valid : 1;
+ u8 ctx_ilen : 7;
};
#define CPT_INLINE_INBOUND 0
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 302ff549284e5..d7ca7e953683b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -17,7 +17,7 @@
#define PCI_DEVID_OTX2_CPT10K_PF 0xA0F2
/* Length of initial context fetch in 128 byte words */
-#define CPT_CTX_ILEN 2ULL
+#define CPT_CTX_ILEN 1ULL
#define cpt_get_eng_sts(e_min, e_max, rsp, etype) \
({ \
@@ -421,8 +421,12 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu,
/* Set CPT LF group and priority */
val = (u64)req->eng_grpmsk << 48 | 1;
- if (!is_rvu_otx2(rvu))
- val |= (CPT_CTX_ILEN << 17);
+ if (!is_rvu_otx2(rvu)) {
+ if (req->ctx_ilen_valid)
+ val |= (req->ctx_ilen << 17);
+ else
+ val |= (CPT_CTX_ILEN << 17);
+ }
rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val);
--
GitLab
From 8299ffe3dc3dc9ac2bd60e3a8332008f03156aca Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Wed, 18 Jan 2023 17:33:54 +0530
Subject: [PATCH 1014/1167] octeontx2-af: add mbox to return CPT_AF_FLT_INT
info
CPT HW would trigger the CPT AF FLT interrupt when CPT engines
hits some uncorrectable errors and AF is the one which receives
the interrupt and recovers the engines.
This patch adds a mailbox for CPT VFs to request for CPT faulted
and recovered engines info.
Signed-off-by: Srujana Challa <schalla@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
.../net/ethernet/marvell/octeontx2/af/mbox.h | 17 +++++++++
.../net/ethernet/marvell/octeontx2/af/rvu.h | 4 +++
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 35 +++++++++++++++++++
3 files changed, 56 insertions(+)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index e2ae9c317ce27..84761c7f6717d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -196,6 +196,8 @@ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \
msg_rsp) \
M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \
M(CPT_LF_RESET, 0xA08, cpt_lf_reset, cpt_lf_rst_req, msg_rsp) \
+M(CPT_FLT_ENG_INFO, 0xA09, cpt_flt_eng_info, cpt_flt_eng_info_req, \
+ cpt_flt_eng_info_rsp) \
/* SDP mbox IDs (range 0x1000 - 0x11FF) */ \
M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \
M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \
@@ -1702,6 +1704,21 @@ struct cpt_lf_rst_req {
u32 rsvd;
};
+/* Mailbox message format to request for CPT faulted engines */
+struct cpt_flt_eng_info_req {
+ struct mbox_msghdr hdr;
+ int blkaddr;
+ bool reset;
+ u32 rsvd;
+};
+
+struct cpt_flt_eng_info_rsp {
+ struct mbox_msghdr hdr;
+ u64 flt_eng_map[CPT_10K_AF_INT_VEC_RVU];
+ u64 rcvrd_eng_map[CPT_10K_AF_INT_VEC_RVU];
+ u64 rsvd;
+};
+
struct sdp_node_info {
/* Node to which this PF belons to */
u8 node_id;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 2f480c73ef553..5eea2b6cf6bdb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -108,6 +108,8 @@ struct rvu_block {
u64 lfreset_reg;
unsigned char name[NAME_SIZE];
struct rvu *rvu;
+ u64 cpt_flt_eng_map[3];
+ u64 cpt_rcvrd_eng_map[3];
};
struct nix_mcast {
@@ -526,6 +528,8 @@ struct rvu {
struct list_head mcs_intrq_head;
/* mcs interrupt queue lock */
spinlock_t mcs_intrq_lock;
+ /* CPT interrupt lock */
+ spinlock_t cpt_intr_lock;
};
static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index d7ca7e953683b..f047185f38e0f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -70,6 +70,14 @@ static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr)
rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), grp);
rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val | 1ULL);
+
+ spin_lock(&rvu->cpt_intr_lock);
+ block->cpt_flt_eng_map[vec] |= BIT_ULL(i);
+ val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(eng));
+ val = val & 0x3;
+ if (val == 0x1 || val == 0x2)
+ block->cpt_rcvrd_eng_map[vec] |= BIT_ULL(i);
+ spin_unlock(&rvu->cpt_intr_lock);
}
rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(vec), reg);
@@ -899,6 +907,31 @@ int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req,
return 0;
}
+int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_req *req,
+ struct cpt_flt_eng_info_rsp *rsp)
+{
+ struct rvu_block *block;
+ unsigned long flags;
+ int blkaddr, vec;
+
+ blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
+ if (blkaddr < 0)
+ return blkaddr;
+
+ block = &rvu->hw->block[blkaddr];
+ for (vec = 0; vec < CPT_10K_AF_INT_VEC_RVU; vec++) {
+ spin_lock_irqsave(&rvu->cpt_intr_lock, flags);
+ rsp->flt_eng_map[vec] = block->cpt_flt_eng_map[vec];
+ rsp->rcvrd_eng_map[vec] = block->cpt_rcvrd_eng_map[vec];
+ if (req->reset) {
+ block->cpt_flt_eng_map[vec] = 0x0;
+ block->cpt_rcvrd_eng_map[vec] = 0x0;
+ }
+ spin_unlock_irqrestore(&rvu->cpt_intr_lock, flags);
+ }
+ return 0;
+}
+
static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
{
struct cpt_rxc_time_cfg_req req, prev;
@@ -1182,5 +1215,7 @@ int rvu_cpt_init(struct rvu *rvu)
{
/* Retrieve CPT PF number */
rvu->cpt_pf_num = get_cpt_pf_num(rvu);
+ spin_lock_init(&rvu->cpt_intr_lock);
+
return 0;
}
--
GitLab
From e49560f02716839a74a7907200a589c1f990261b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 12 Jan 2023 22:37:56 -0800
Subject: [PATCH 1015/1167] i2c: axxia: use 'struct' for kernel-doc notation
Add "struct" to prevent this kernel-doc warning:
drivers/i2c/busses/i2c-axxia.c:135: warning: cannot understand function prototype: 'struct axxia_i2c_dev '
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-axxia.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c
index bdf3b50de8adb..c1c74ce084071 100644
--- a/drivers/i2c/busses/i2c-axxia.c
+++ b/drivers/i2c/busses/i2c-axxia.c
@@ -118,7 +118,7 @@
#define SDA_HOLD_TIME 0x90
/**
- * axxia_i2c_dev - I2C device context
+ * struct axxia_i2c_dev - I2C device context
* @base: pointer to register struct
* @msg: pointer to current message
* @msg_r: pointer to current read message (sequence transfer)
--
GitLab
From 0582d984793d30442da88fe458674502bad1ad29 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 12 Jan 2023 22:38:05 -0800
Subject: [PATCH 1016/1167] i2c: rk3x: fix a bunch of kernel-doc warnings
Fix multiple W=1 kernel-doc warnings in i2c-rk3x.c:
drivers/i2c/busses/i2c-rk3x.c:83: warning: missing initial short description on line:
* struct i2c_spec_values:
drivers/i2c/busses/i2c-rk3x.c:139: warning: missing initial short description on line:
* struct rk3x_i2c_calced_timings:
drivers/i2c/busses/i2c-rk3x.c:162: warning: missing initial short description on line:
* struct rk3x_i2c_soc_data:
drivers/i2c/busses/i2c-rk3x.c:242: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Generate a START condition, which triggers a REG_INT_START interrupt.
drivers/i2c/busses/i2c-rk3x.c:261: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
drivers/i2c/busses/i2c-rk3x.c:304: warning: expecting prototype for Setup a read according to i2c(). Prototype was for rk3x_i2c_prepare_read() instead
drivers/i2c/busses/i2c-rk3x.c:335: warning: expecting prototype for Fill the transmit buffer with data from i2c(). Prototype was for rk3x_i2c_fill_transmit_buf() instead
drivers/i2c/busses/i2c-rk3x.c:535: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Get timing values of I2C specification
drivers/i2c/busses/i2c-rk3x.c:552: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Calculate divider values for desired SCL frequency
drivers/i2c/busses/i2c-rk3x.c:713: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Calculate timing values for desired SCL frequency
drivers/i2c/busses/i2c-rk3x.c:963: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
* Setup I2C registers for an I2C operation specified by msgs, num.
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
---
drivers/i2c/busses/i2c-rk3x.c | 44 +++++++++++++++++------------------
1 file changed, 22 insertions(+), 22 deletions(-)
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index d1658ed76562b..b31cf4f18f854 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -80,7 +80,7 @@ enum {
#define DEFAULT_SCL_RATE (100 * 1000) /* Hz */
/**
- * struct i2c_spec_values:
+ * struct i2c_spec_values - I2C specification values for various modes
* @min_hold_start_ns: min hold time (repeated) START condition
* @min_low_ns: min LOW period of the SCL clock
* @min_high_ns: min HIGH period of the SCL cloc
@@ -136,7 +136,7 @@ static const struct i2c_spec_values fast_mode_plus_spec = {
};
/**
- * struct rk3x_i2c_calced_timings:
+ * struct rk3x_i2c_calced_timings - calculated V1 timings
* @div_low: Divider output for low
* @div_high: Divider output for high
* @tuning: Used to adjust setup/hold data time,
@@ -159,7 +159,7 @@ enum rk3x_i2c_state {
};
/**
- * struct rk3x_i2c_soc_data:
+ * struct rk3x_i2c_soc_data - SOC-specific data
* @grf_offset: offset inside the grf regmap for setting the i2c type
* @calc_timings: Callback function for i2c timing information calculated
*/
@@ -239,7 +239,8 @@ static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c)
}
/**
- * Generate a START condition, which triggers a REG_INT_START interrupt.
+ * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt.
+ * @i2c: target controller data
*/
static void rk3x_i2c_start(struct rk3x_i2c *i2c)
{
@@ -258,8 +259,8 @@ static void rk3x_i2c_start(struct rk3x_i2c *i2c)
}
/**
- * Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
- *
+ * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
+ * @i2c: target controller data
* @error: Error code to return in rk3x_i2c_xfer
*/
static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error)
@@ -298,7 +299,8 @@ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error)
}
/**
- * Setup a read according to i2c->msg
+ * rk3x_i2c_prepare_read - Setup a read according to i2c->msg
+ * @i2c: target controller data
*/
static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c)
{
@@ -329,7 +331,8 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c)
}
/**
- * Fill the transmit buffer with data from i2c->msg
+ * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg
+ * @i2c: target controller data
*/
static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c)
{
@@ -532,11 +535,10 @@ static irqreturn_t rk3x_i2c_irq(int irqno, void *dev_id)
}
/**
- * Get timing values of I2C specification
- *
+ * rk3x_i2c_get_spec - Get timing values of I2C specification
* @speed: Desired SCL frequency
*
- * Returns: Matched i2c spec values.
+ * Return: Matched i2c_spec_values.
*/
static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed)
{
@@ -549,13 +551,12 @@ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed)
}
/**
- * Calculate divider values for desired SCL frequency
- *
+ * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency
* @clk_rate: I2C input clock rate
* @t: Known I2C timing information
* @t_calc: Caculated rk3x private timings that would be written into regs
*
- * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case
+ * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case
* a best-effort divider value is returned in divs. If the target rate is
* too high, we silently use the highest possible rate.
*/
@@ -710,13 +711,12 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate,
}
/**
- * Calculate timing values for desired SCL frequency
- *
+ * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency
* @clk_rate: I2C input clock rate
* @t: Known I2C timing information
* @t_calc: Caculated rk3x private timings that would be written into regs
*
- * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case
+ * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case
* a best-effort divider value is returned in divs. If the target rate is
* too high, we silently use the highest possible rate.
* The following formulas are v1's method to calculate timings.
@@ -960,14 +960,14 @@ static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long
}
/**
- * Setup I2C registers for an I2C operation specified by msgs, num.
- *
- * Must be called with i2c->lock held.
- *
+ * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num.
+ * @i2c: target controller data
* @msgs: I2C msgs to process
* @num: Number of msgs
*
- * returns: Number of I2C msgs processed or negative in case of error
+ * Must be called with i2c->lock held.
+ *
+ * Return: Number of I2C msgs processed or negative in case of error
*/
static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num)
{
--
GitLab
From fdfc76a116b5e9d3e98e6c96fe83b42d011d21d4 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Wed, 18 Jan 2023 10:56:38 -0600
Subject: [PATCH 1017/1167] net: stmmac: enable all safety features by default
In the original implementation of dwmac5
commit 8bf993a5877e ("net: stmmac: Add support for DWMAC5 and implement Safety Features")
all safety features were enabled by default.
Later it seems some implementations didn't have support for all the
features, so in
commit 5ac712dcdfef ("net: stmmac: enable platform specific safety features")
the safety_feat_cfg structure was added to the callback and defined for
some platforms to selectively enable these safety features.
The problem is that only certain platforms were given that software
support. If the automotive safety package bit is set in the hardware
features register the safety feature callback is called for the platform,
and for platforms that didn't get a safety_feat_cfg defined this results
in the following NULL pointer dereference:
[ 7.933303] Call trace:
[ 7.935812] dwmac5_safety_feat_config+0x20/0x170 [stmmac]
[ 7.941455] __stmmac_open+0x16c/0x474 [stmmac]
[ 7.946117] stmmac_open+0x38/0x70 [stmmac]
[ 7.950414] __dev_open+0x100/0x1dc
[ 7.954006] __dev_change_flags+0x18c/0x204
[ 7.958297] dev_change_flags+0x24/0x6c
[ 7.962237] do_setlink+0x2b8/0xfa4
[ 7.965827] __rtnl_newlink+0x4ec/0x840
[ 7.969766] rtnl_newlink+0x50/0x80
[ 7.973353] rtnetlink_rcv_msg+0x12c/0x374
[ 7.977557] netlink_rcv_skb+0x5c/0x130
[ 7.981500] rtnetlink_rcv+0x18/0x2c
[ 7.985172] netlink_unicast+0x2e8/0x340
[ 7.989197] netlink_sendmsg+0x1a8/0x420
[ 7.993222] ____sys_sendmsg+0x218/0x280
[ 7.997249] ___sys_sendmsg+0xac/0x100
[ 8.001103] __sys_sendmsg+0x84/0xe0
[ 8.004776] __arm64_sys_sendmsg+0x24/0x30
[ 8.008983] invoke_syscall+0x48/0x114
[ 8.012840] el0_svc_common.constprop.0+0xcc/0xec
[ 8.017665] do_el0_svc+0x38/0xb0
[ 8.021071] el0_svc+0x2c/0x84
[ 8.024212] el0t_64_sync_handler+0xf4/0x120
[ 8.028598] el0t_64_sync+0x190/0x194
Go back to the original behavior, if the automotive safety package
is found to be supported in hardware enable all the features unless
safety_feat_cfg is passed in saying this particular platform only
supports a subset of the features.
Fixes: 5ac712dcdfef ("net: stmmac: enable platform specific safety features")
Reported-by: Ning Cai <ncai@quicinc.com>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/dwmac5.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 9c2d40f853ed0..413f660172199 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -186,11 +186,25 @@ static void dwmac5_handle_dma_err(struct net_device *ndev,
int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp,
struct stmmac_safety_feature_cfg *safety_feat_cfg)
{
+ struct stmmac_safety_feature_cfg all_safety_feats = {
+ .tsoee = 1,
+ .mrxpee = 1,
+ .mestee = 1,
+ .mrxee = 1,
+ .mtxee = 1,
+ .epsi = 1,
+ .edpp = 1,
+ .prtyen = 1,
+ .tmouten = 1,
+ };
u32 value;
if (!asp)
return -EINVAL;
+ if (!safety_feat_cfg)
+ safety_feat_cfg = &all_safety_feats;
+
/* 1. Enable Safety Features */
value = readl(ioaddr + MTL_ECC_CONTROL);
value |= MEEAO; /* MTL ECC Error Addr Status Override */
--
GitLab
From d2c865553adb7ad9abf3894cbb209cf1bc95484a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jan 2023 17:41:14 +0100
Subject: [PATCH 1018/1167] firmware: zynqmp: fix declarations for gcc-13
gcc-13.0.1 reports a type mismatch for two functions:
drivers/firmware/xilinx/zynqmp.c:1228:5: error: conflicting types for 'zynqmp_pm_set_rpu_mode' due to enum/integer mismatch; have 'int(u32, enum rpu_oper_mode)' {aka 'int(unsigned int, enum rpu_oper_mode)'} [-Werror=enum-int-mismatch]
1228 | int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
| ^~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/firmware/xilinx/zynqmp.c:25:
include/linux/firmware/xlnx-zynqmp.h:552:5: note: previous declaration of 'zynqmp_pm_set_rpu_mode' with type 'int(u32, u32)' {aka 'int(unsigned int, unsigned int)'}
552 | int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1);
| ^~~~~~~~~~~~~~~~~~~~~~
drivers/firmware/xilinx/zynqmp.c:1246:5: error: conflicting types for 'zynqmp_pm_set_tcm_config' due to enum/integer mismatch; have 'int(u32, enum rpu_tcm_comb)' {aka 'int(unsigned int, enum rpu_tcm_comb)'} [-Werror=enum-int-mismatch]
1246 | int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
| ^~~~~~~~~~~~~~~~~~~~~~~~
include/linux/firmware/xlnx-zynqmp.h:553:5: note: previous declaration of 'zynqmp_pm_set_tcm_config' with type 'int(u32, u32)' {aka 'int(unsigned int, unsigned int)'}
553 | int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1);
| ^~~~~~~~~~~~~~~~~~~~~~~~
Change the declaration in the header to match the function definition.
Acked-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
include/linux/firmware/xlnx-zynqmp.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index b986e267d149b..b09f443d3ab9d 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -545,8 +545,8 @@ int zynqmp_pm_request_wake(const u32 node,
const u64 address,
const enum zynqmp_pm_request_ack ack);
int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode);
-int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1);
-int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1);
+int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode);
+int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode);
int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value);
int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
u32 value);
@@ -845,12 +845,12 @@ static inline int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mo
return -ENODEV;
}
-static inline int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1)
+static inline int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode)
{
return -ENODEV;
}
-static inline int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1)
+static inline int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode)
{
return -ENODEV;
}
--
GitLab
From 2cbafffbf69addd7509072f4be5917f81d238cf6 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 20 Jan 2023 11:16:59 +0100
Subject: [PATCH 1019/1167] Revert "serial: stm32: Merge hard IRQ and threaded
IRQ handling into single IRQ handler"
This reverts commit f24771b62a83239f0dce816bddf0f6807f436235 as it is
reported to break the build.
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/r/202301200130.ttBiTzfO-lkp@intel.com
Fixes: f24771b62a83 ("serial: stm32: Merge hard IRQ and threaded IRQ handling into single IRQ handler")
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Valentin Caron <valentin.caron@foss.st.com> # V3
Cc: Marek Vasut <marex@denx.de>
Cc: Johan Hovold <johan@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/stm32-usart.c | 31 +++++++++++++++++++++++++++----
1 file changed, 27 insertions(+), 4 deletions(-)
diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c
index 1e24bee2b0ef7..a1490033aa164 100644
--- a/drivers/tty/serial/stm32-usart.c
+++ b/drivers/tty/serial/stm32-usart.c
@@ -797,9 +797,23 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr)
spin_unlock(&port->lock);
}
+ if (stm32_usart_rx_dma_enabled(port))
+ return IRQ_WAKE_THREAD;
+ else
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr)
+{
+ struct uart_port *port = ptr;
+ struct tty_port *tport = &port->state->port;
+ struct stm32_port *stm32_port = to_stm32_port(port);
+ unsigned int size;
+ unsigned long flags;
+
/* Receiver timeout irq for DMA RX */
- if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) {
- spin_lock(&port->lock);
+ if (!stm32_port->throttled) {
+ spin_lock_irqsave(&port->lock, flags);
size = stm32_usart_receive_chars(port, false);
uart_unlock_and_check_sysrq_irqrestore(port, flags);
if (size)
@@ -1001,8 +1015,10 @@ static int stm32_usart_startup(struct uart_port *port)
u32 val;
int ret;
- ret = request_irq(port->irq, stm32_usart_interrupt,
- IRQF_NO_SUSPEND, name, port);
+ ret = request_threaded_irq(port->irq, stm32_usart_interrupt,
+ stm32_usart_threaded_interrupt,
+ IRQF_ONESHOT | IRQF_NO_SUSPEND,
+ name, port);
if (ret)
return ret;
@@ -1585,6 +1601,13 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port,
struct dma_slave_config config;
int ret;
+ /*
+ * Using DMA and threaded handler for the console could lead to
+ * deadlocks.
+ */
+ if (uart_console(port))
+ return -ENODEV;
+
stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L,
&stm32port->rx_dma_buf,
GFP_KERNEL);
--
GitLab
From a43866856125c3c432e2fbb6cc63cee1539ec4a7 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Tue, 13 Dec 2022 00:02:46 +0200
Subject: [PATCH 1020/1167] mei: bus: fix unlink on bus in error path
Unconditional call to mei_cl_unlink in mei_cl_bus_dev_release leads
to call of the mei_cl_unlink without corresponding mei_cl_link.
This leads to miscalculation of open_handle_count (decrease without
increase).
Call unlink in mei_cldev_enable fail path and remove blanket unlink
from mei_cl_bus_dev_release.
Fixes: 34f1166afd67 ("mei: bus: need to unlink client before freeing")
Cc: <stable@vger.kernel.org>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Reviewed-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20221212220247.286019-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/mei/bus.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 4a08b624910a0..a81b890c7ee64 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -702,13 +702,15 @@ void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size)
if (cl->state == MEI_FILE_UNINITIALIZED) {
ret = mei_cl_link(cl);
if (ret)
- goto out;
+ goto notlinked;
/* update pointers */
cl->cldev = cldev;
}
ret = mei_cl_dma_alloc_and_map(cl, NULL, buffer_id, size);
-out:
+ if (ret)
+ mei_cl_unlink(cl);
+notlinked:
mutex_unlock(&bus->device_lock);
if (ret)
return ERR_PTR(ret);
@@ -758,7 +760,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev)
if (cl->state == MEI_FILE_UNINITIALIZED) {
ret = mei_cl_link(cl);
if (ret)
- goto out;
+ goto notlinked;
/* update pointers */
cl->cldev = cldev;
}
@@ -785,6 +787,9 @@ int mei_cldev_enable(struct mei_cl_device *cldev)
}
out:
+ if (ret)
+ mei_cl_unlink(cl);
+notlinked:
mutex_unlock(&bus->device_lock);
return ret;
@@ -1277,7 +1282,6 @@ static void mei_cl_bus_dev_release(struct device *dev)
mei_cl_flush_queues(cldev->cl, NULL);
mei_me_cl_put(cldev->me_cl);
mei_dev_bus_put(cldev->bus);
- mei_cl_unlink(cldev->cl);
kfree(cldev->cl);
kfree(cldev);
}
--
GitLab
From 0c4d68261717f89fa8c4f98a6967c3832fcb3ad0 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Tue, 13 Dec 2022 00:02:47 +0200
Subject: [PATCH 1021/1167] mei: me: add meteor lake point M DID
Add Meteor Lake Point M device id.
Cc: <stable@vger.kernel.org>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20221212220247.286019-2-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/mei/hw-me-regs.h | 2 ++
drivers/misc/mei/pci-me.c | 2 ++
2 files changed, 4 insertions(+)
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 99966cd3e7d89..bdc65d50b945f 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -111,6 +111,8 @@
#define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */
+#define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */
+
/*
* MEI HW Section
*/
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 704cd0caa172c..5bf0d50d55a00 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -118,6 +118,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
{MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)},
+
/* required last entry */
{0, }
};
--
GitLab
From 5023adc364df004bd8e57afe89a4bd8019485c3d Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Tue, 29 Nov 2022 12:45:16 +0300
Subject: [PATCH 1022/1167] misc: fastrpc: fix error code in fastrpc_req_mmap()
The "err" variable shadows an earlier global variable so this code
returns success instead of a negative error code.
Fixes: 532ad70c6d44 ("misc: fastrpc: Add mmap request assigning for static PD pool")
Signed-off-by: Dan Carpenter <error27@gmail.com>
Link: https://lore.kernel.org/r/Y4XUrMETCl1O6t0A@kili
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/fastrpc.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index c9902a1dcf5d3..876f0f146b16e 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -1894,7 +1894,6 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
/* Add memory to static PD pool, protection thru hypervisor */
if (req.flags != ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) {
struct qcom_scm_vmperm perm;
- int err = 0;
perm.vmid = QCOM_SCM_VMID_HLOS;
perm.perm = QCOM_SCM_PERM_RWX;
--
GitLab
From 9446fa1683a7e3937d9970248ced427c1983a1c5 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 24 Nov 2022 17:49:39 +0000
Subject: [PATCH 1023/1167] misc: fastrpc: Fix use-after-free and race in
fastrpc_map_find
Currently, there is a race window between the point when the mutex is
unlocked in fastrpc_map_lookup and the reference count increasing
(fastrpc_map_get) in fastrpc_map_find, which can also lead to
use-after-free.
So lets merge fastrpc_map_find into fastrpc_map_lookup which allows us
to both protect the maps list by also taking the &fl->lock spinlock and
the reference count, since the spinlock will be released only after.
Add take_ref argument to make this suitable for all callers.
Fixes: 8f6c1d8c4f0c ("misc: fastrpc: Add fdlist implementation")
Cc: stable <stable@kernel.org>
Co-developed-by: Ola Jeppsson <ola@snap.com>
Signed-off-by: Ola Jeppsson <ola@snap.com>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20221124174941.418450-2-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/fastrpc.c | 41 +++++++++++++++++++++--------------------
1 file changed, 21 insertions(+), 20 deletions(-)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 876f0f146b16e..dedc067fbec81 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -351,30 +351,31 @@ static void fastrpc_map_get(struct fastrpc_map *map)
static int fastrpc_map_lookup(struct fastrpc_user *fl, int fd,
- struct fastrpc_map **ppmap)
+ struct fastrpc_map **ppmap, bool take_ref)
{
+ struct fastrpc_session_ctx *sess = fl->sctx;
struct fastrpc_map *map = NULL;
+ int ret = -ENOENT;
- mutex_lock(&fl->mutex);
+ spin_lock(&fl->lock);
list_for_each_entry(map, &fl->maps, node) {
- if (map->fd == fd) {
- *ppmap = map;
- mutex_unlock(&fl->mutex);
- return 0;
- }
- }
- mutex_unlock(&fl->mutex);
-
- return -ENOENT;
-}
+ if (map->fd != fd)
+ continue;
-static int fastrpc_map_find(struct fastrpc_user *fl, int fd,
- struct fastrpc_map **ppmap)
-{
- int ret = fastrpc_map_lookup(fl, fd, ppmap);
+ if (take_ref) {
+ ret = fastrpc_map_get(map);
+ if (ret) {
+ dev_dbg(sess->dev, "%s: Failed to get map fd=%d ret=%d\n",
+ __func__, fd, ret);
+ break;
+ }
+ }
- if (!ret)
- fastrpc_map_get(*ppmap);
+ *ppmap = map;
+ ret = 0;
+ break;
+ }
+ spin_unlock(&fl->lock);
return ret;
}
@@ -746,7 +747,7 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd,
struct fastrpc_map *map = NULL;
int err = 0;
- if (!fastrpc_map_find(fl, fd, ppmap))
+ if (!fastrpc_map_lookup(fl, fd, ppmap, true))
return 0;
map = kzalloc(sizeof(*map), GFP_KERNEL);
@@ -1070,7 +1071,7 @@ static int fastrpc_put_args(struct fastrpc_invoke_ctx *ctx,
for (i = 0; i < FASTRPC_MAX_FDLIST; i++) {
if (!fdlist[i])
break;
- if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap))
+ if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap, false))
fastrpc_map_put(mmap);
}
--
GitLab
From 5bb96c8f9268e2fdb0e5321cbc358ee5941efc15 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@linaro.org>
Date: Thu, 24 Nov 2022 17:49:40 +0000
Subject: [PATCH 1024/1167] misc: fastrpc: Don't remove map on creater_process
and device_release
Do not remove the map from the list on error path in
fastrpc_init_create_process, instead call fastrpc_map_put, to avoid
use-after-free. Do not remove it on fastrpc_device_release either,
call fastrpc_map_put instead.
The fastrpc_free_map is the only proper place to remove the map.
This is called only after the reference count is 0.
Fixes: b49f6d83e290 ("misc: fastrpc: Fix a possible double free")
Cc: stable <stable@kernel.org>
Co-developed-by: Ola Jeppsson <ola@snap.com>
Signed-off-by: Ola Jeppsson <ola@snap.com>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20221124174941.418450-3-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/fastrpc.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index dedc067fbec81..9f8d52b59ed2d 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -334,6 +334,13 @@ static void fastrpc_free_map(struct kref *ref)
dma_buf_put(map->buf);
}
+ if (map->fl) {
+ spin_lock(&map->fl->lock);
+ list_del(&map->node);
+ spin_unlock(&map->fl->lock);
+ map->fl = NULL;
+ }
+
kfree(map);
}
@@ -1434,12 +1441,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl,
fl->init_mem = NULL;
fastrpc_buf_free(imem);
err_alloc:
- if (map) {
- spin_lock(&fl->lock);
- list_del(&map->node);
- spin_unlock(&fl->lock);
- fastrpc_map_put(map);
- }
+ fastrpc_map_put(map);
err:
kfree(args);
@@ -1515,10 +1517,8 @@ static int fastrpc_device_release(struct inode *inode, struct file *file)
fastrpc_context_put(ctx);
}
- list_for_each_entry_safe(map, m, &fl->maps, node) {
- list_del(&map->node);
+ list_for_each_entry_safe(map, m, &fl->maps, node)
fastrpc_map_put(map);
- }
list_for_each_entry_safe(buf, b, &fl->mmaps, node) {
list_del(&buf->node);
--
GitLab
From 96b328d119eca7563c1edcc4e1039a62e6370ecb Mon Sep 17 00:00:00 2001
From: Ola Jeppsson <ola@snap.com>
Date: Thu, 24 Nov 2022 17:49:41 +0000
Subject: [PATCH 1025/1167] misc: fastrpc: Fix use-after-free race condition
for maps
It is possible that in between calling fastrpc_map_get() until
map->fl->lock is taken in fastrpc_free_map(), another thread can call
fastrpc_map_lookup() and get a reference to a map that is about to be
deleted.
Rewrite fastrpc_map_get() to only increase the reference count of a map
if it's non-zero. Propagate this to callers so they can know if a map is
about to be deleted.
Fixes this warning:
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 5 PID: 10100 at lib/refcount.c:25 refcount_warn_saturate
...
Call trace:
refcount_warn_saturate
[fastrpc_map_get inlined]
[fastrpc_map_lookup inlined]
fastrpc_map_create
fastrpc_internal_invoke
fastrpc_device_ioctl
__arm64_sys_ioctl
invoke_syscall
Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method")
Cc: stable <stable@kernel.org>
Signed-off-by: Ola Jeppsson <ola@snap.com>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20221124174941.418450-4-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/fastrpc.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 9f8d52b59ed2d..a2a1258531d08 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -350,10 +350,12 @@ static void fastrpc_map_put(struct fastrpc_map *map)
kref_put(&map->refcount, fastrpc_free_map);
}
-static void fastrpc_map_get(struct fastrpc_map *map)
+static int fastrpc_map_get(struct fastrpc_map *map)
{
- if (map)
- kref_get(&map->refcount);
+ if (!map)
+ return -ENOENT;
+
+ return kref_get_unless_zero(&map->refcount) ? 0 : -ENOENT;
}
--
GitLab
From a769b05eeed7accc4019a1ed9799dd72067f1ce8 Mon Sep 17 00:00:00 2001
From: Khazhismel Kumykov <khazhy@chromium.org>
Date: Tue, 17 Jan 2023 17:02:12 -0800
Subject: [PATCH 1026/1167] gsmi: fix null-deref in gsmi_get_variable
We can get EFI variables without fetching the attribute, so we must
allow for that in gsmi.
commit 859748255b43 ("efi: pstore: Omit efivars caching EFI varstore
access layer") added a new get_variable call with attr=NULL, which
triggers panic in gsmi.
Fixes: 74c5b31c6618 ("driver: Google EFI SMI")
Cc: stable <stable@kernel.org>
Signed-off-by: Khazhismel Kumykov <khazhy@google.com>
Link: https://lore.kernel.org/r/20230118010212.1268474-1-khazhy@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/firmware/google/gsmi.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c
index 4e2575dfeb908..871bedf533a80 100644
--- a/drivers/firmware/google/gsmi.c
+++ b/drivers/firmware/google/gsmi.c
@@ -361,9 +361,10 @@ static efi_status_t gsmi_get_variable(efi_char16_t *name,
memcpy(data, gsmi_dev.data_buf->start, *data_size);
/* All variables are have the following attributes */
- *attr = EFI_VARIABLE_NON_VOLATILE |
- EFI_VARIABLE_BOOTSERVICE_ACCESS |
- EFI_VARIABLE_RUNTIME_ACCESS;
+ if (attr)
+ *attr = EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS;
}
spin_unlock_irqrestore(&gsmi_dev.lock, flags);
--
GitLab
From aaca766c77fcf5aabda846d3372a1d40b0d4735d Mon Sep 17 00:00:00 2001
From: Elliot Berman <quic_eberman@quicinc.com>
Date: Thu, 12 Jan 2023 10:23:12 -0800
Subject: [PATCH 1027/1167] misc: fastrpc: Pass bitfield into
qcom_scm_assign_mem
The srcvm parameter of qcom_scm_assign_mem is a pointer to a bitfield of
VMIDs. The bitfield is updated with which VMIDs have permissions
after the qcom_scm_assign_mem call. This makes it simpler for clients to
make qcom_scm_assign_mem calls later, they always pass in same srcvm
bitfield and do not need to closely track whether memory was originally
shared.
When restoring permissions to HLOS, fastrpc is incorrectly using the
first VMID directly -- neither the BIT nor the other possible VMIDs the
memory was already assigned to. We already have a field intended for
this purpose: "perms" in the struct fastrpc_channel_ctx, but it was
never used. Start using the perms field.
Cc: Abel Vesa <abel.vesa@linaro.org>
Cc: Vamsi Krishna Gattupalli <quic_vgattupa@quicinc.com>
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Fixes: e90d91190619 ("misc: fastrpc: Add support to secure memory map")
Fixes: 0871561055e6 ("misc: fastrpc: Add support for audiopd")
Fixes: 532ad70c6d44 ("misc: fastrpc: Add mmap request assigning for static PD pool")
Tested-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Elliot Berman <quic_eberman@quicinc.com>
drivers/misc/fastrpc.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
Link: https://lore.kernel.org/r/20230112182313.521467-1-quic_eberman@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/fastrpc.c | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index a2a1258531d08..5310606113fe5 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -321,7 +321,7 @@ static void fastrpc_free_map(struct kref *ref)
perm.vmid = QCOM_SCM_VMID_HLOS;
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(map->phys, map->size,
- &(map->fl->cctx->vmperms[0].vmid), &perm, 1);
+ &map->fl->cctx->perms, &perm, 1);
if (err) {
dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
map->phys, map->size, err);
@@ -798,10 +798,8 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd,
* If subsystem VMIDs are defined in DTSI, then do
* hyp_assign from HLOS to those VM(s)
*/
- unsigned int perms = BIT(QCOM_SCM_VMID_HLOS);
-
map->attr = attr;
- err = qcom_scm_assign_mem(map->phys, (u64)map->size, &perms,
+ err = qcom_scm_assign_mem(map->phys, (u64)map->size, &fl->cctx->perms,
fl->cctx->vmperms, fl->cctx->vmcount);
if (err) {
dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
@@ -1268,10 +1266,9 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
/* Map if we have any heap VMIDs associated with this ADSP Static Process. */
if (fl->cctx->vmcount) {
- unsigned int perms = BIT(QCOM_SCM_VMID_HLOS);
-
err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
- (u64)fl->cctx->remote_heap->size, &perms,
+ (u64)fl->cctx->remote_heap->size,
+ &fl->cctx->perms,
fl->cctx->vmperms, fl->cctx->vmcount);
if (err) {
dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d",
@@ -1319,7 +1316,7 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl,
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys,
(u64)fl->cctx->remote_heap->size,
- &(fl->cctx->vmperms[0].vmid), &perm, 1);
+ &fl->cctx->perms, &perm, 1);
if (err)
dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
fl->cctx->remote_heap->phys, fl->cctx->remote_heap->size, err);
@@ -1901,7 +1898,7 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
perm.vmid = QCOM_SCM_VMID_HLOS;
perm.perm = QCOM_SCM_PERM_RWX;
err = qcom_scm_assign_mem(buf->phys, buf->size,
- &(fl->cctx->vmperms[0].vmid), &perm, 1);
+ &fl->cctx->perms, &perm, 1);
if (err) {
dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
buf->phys, buf->size, err);
--
GitLab
From 3daed6345d5880464f46adab871d208e1baa2f3a Mon Sep 17 00:00:00 2001
From: Vishnu Dasa <vdasa@vmware.com>
Date: Tue, 29 Nov 2022 23:05:11 -0800
Subject: [PATCH 1028/1167] VMCI: Use threaded irqs instead of tasklets
The vmci_dispatch_dgs() tasklet function calls vmci_read_data()
which uses wait_event() resulting in invalid sleep in an atomic
context (and therefore potentially in a deadlock).
Use threaded irqs to fix this issue and completely remove usage
of tasklets.
[ 20.264639] BUG: sleeping function called from invalid context at drivers/misc/vmw_vmci/vmci_guest.c:145
[ 20.264643] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 762, name: vmtoolsd
[ 20.264645] preempt_count: 101, expected: 0
[ 20.264646] RCU nest depth: 0, expected: 0
[ 20.264647] 1 lock held by vmtoolsd/762:
[ 20.264648] #0: ffff0000874ae440 (sk_lock-AF_VSOCK){+.+.}-{0:0}, at: vsock_connect+0x60/0x330 [vsock]
[ 20.264658] Preemption disabled at:
[ 20.264659] [<ffff80000151d7d8>] vmci_send_datagram+0x44/0xa0 [vmw_vmci]
[ 20.264665] CPU: 0 PID: 762 Comm: vmtoolsd Not tainted 5.19.0-0.rc8.20220727git39c3c396f813.60.fc37.aarch64 #1
[ 20.264667] Hardware name: VMware, Inc. VBSA/VBSA, BIOS VEFI 12/31/2020
[ 20.264668] Call trace:
[ 20.264669] dump_backtrace+0xc4/0x130
[ 20.264672] show_stack+0x24/0x80
[ 20.264673] dump_stack_lvl+0x88/0xb4
[ 20.264676] dump_stack+0x18/0x34
[ 20.264677] __might_resched+0x1a0/0x280
[ 20.264679] __might_sleep+0x58/0x90
[ 20.264681] vmci_read_data+0x74/0x120 [vmw_vmci]
[ 20.264683] vmci_dispatch_dgs+0x64/0x204 [vmw_vmci]
[ 20.264686] tasklet_action_common.constprop.0+0x13c/0x150
[ 20.264688] tasklet_action+0x40/0x50
[ 20.264689] __do_softirq+0x23c/0x6b4
[ 20.264690] __irq_exit_rcu+0x104/0x214
[ 20.264691] irq_exit_rcu+0x1c/0x50
[ 20.264693] el1_interrupt+0x38/0x6c
[ 20.264695] el1h_64_irq_handler+0x18/0x24
[ 20.264696] el1h_64_irq+0x68/0x6c
[ 20.264697] preempt_count_sub+0xa4/0xe0
[ 20.264698] _raw_spin_unlock_irqrestore+0x64/0xb0
[ 20.264701] vmci_send_datagram+0x7c/0xa0 [vmw_vmci]
[ 20.264703] vmci_datagram_dispatch+0x84/0x100 [vmw_vmci]
[ 20.264706] vmci_datagram_send+0x2c/0x40 [vmw_vmci]
[ 20.264709] vmci_transport_send_control_pkt+0xb8/0x120 [vmw_vsock_vmci_transport]
[ 20.264711] vmci_transport_connect+0x40/0x7c [vmw_vsock_vmci_transport]
[ 20.264713] vsock_connect+0x278/0x330 [vsock]
[ 20.264715] __sys_connect_file+0x8c/0xc0
[ 20.264718] __sys_connect+0x84/0xb4
[ 20.264720] __arm64_sys_connect+0x2c/0x3c
[ 20.264721] invoke_syscall+0x78/0x100
[ 20.264723] el0_svc_common.constprop.0+0x68/0x124
[ 20.264724] do_el0_svc+0x38/0x4c
[ 20.264725] el0_svc+0x60/0x180
[ 20.264726] el0t_64_sync_handler+0x11c/0x150
[ 20.264728] el0t_64_sync+0x190/0x194
Signed-off-by: Vishnu Dasa <vdasa@vmware.com>
Suggested-by: Zack Rusin <zackr@vmware.com>
Reported-by: Nadav Amit <namit@vmware.com>
Reported-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Fixes: 463713eb6164 ("VMCI: dma dg: add support for DMA datagrams receive")
Cc: <stable@vger.kernel.org> # v5.18+
Cc: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Bryan Tan <bryantan@vmware.com>
Reviewed-by: Bryan Tan <bryantan@vmware.com>
Reviewed-by: Zack Rusin <zackr@vmware.com>
Link: https://lore.kernel.org/r/20221130070511.46558-1-vdasa@vmware.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/misc/vmw_vmci/vmci_guest.c | 49 ++++++++++++------------------
1 file changed, 19 insertions(+), 30 deletions(-)
diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c
index aa7b05de97dd5..4f8d962bb5b2a 100644
--- a/drivers/misc/vmw_vmci/vmci_guest.c
+++ b/drivers/misc/vmw_vmci/vmci_guest.c
@@ -56,8 +56,6 @@ struct vmci_guest_device {
bool exclusive_vectors;
- struct tasklet_struct datagram_tasklet;
- struct tasklet_struct bm_tasklet;
struct wait_queue_head inout_wq;
void *data_buffer;
@@ -304,9 +302,8 @@ static int vmci_check_host_caps(struct pci_dev *pdev)
* This function assumes that it has exclusive access to the data
* in register(s) for the duration of the call.
*/
-static void vmci_dispatch_dgs(unsigned long data)
+static void vmci_dispatch_dgs(struct vmci_guest_device *vmci_dev)
{
- struct vmci_guest_device *vmci_dev = (struct vmci_guest_device *)data;
u8 *dg_in_buffer = vmci_dev->data_buffer;
struct vmci_datagram *dg;
size_t dg_in_buffer_size = VMCI_MAX_DG_SIZE;
@@ -465,10 +462,8 @@ static void vmci_dispatch_dgs(unsigned long data)
* Scans the notification bitmap for raised flags, clears them
* and handles the notifications.
*/
-static void vmci_process_bitmap(unsigned long data)
+static void vmci_process_bitmap(struct vmci_guest_device *dev)
{
- struct vmci_guest_device *dev = (struct vmci_guest_device *)data;
-
if (!dev->notification_bitmap) {
dev_dbg(dev->dev, "No bitmap present in %s\n", __func__);
return;
@@ -486,13 +481,13 @@ static irqreturn_t vmci_interrupt(int irq, void *_dev)
struct vmci_guest_device *dev = _dev;
/*
- * If we are using MSI-X with exclusive vectors then we simply schedule
- * the datagram tasklet, since we know the interrupt was meant for us.
+ * If we are using MSI-X with exclusive vectors then we simply call
+ * vmci_dispatch_dgs(), since we know the interrupt was meant for us.
* Otherwise we must read the ICR to determine what to do.
*/
if (dev->exclusive_vectors) {
- tasklet_schedule(&dev->datagram_tasklet);
+ vmci_dispatch_dgs(dev);
} else {
unsigned int icr;
@@ -502,12 +497,12 @@ static irqreturn_t vmci_interrupt(int irq, void *_dev)
return IRQ_NONE;
if (icr & VMCI_ICR_DATAGRAM) {
- tasklet_schedule(&dev->datagram_tasklet);
+ vmci_dispatch_dgs(dev);
icr &= ~VMCI_ICR_DATAGRAM;
}
if (icr & VMCI_ICR_NOTIFICATION) {
- tasklet_schedule(&dev->bm_tasklet);
+ vmci_process_bitmap(dev);
icr &= ~VMCI_ICR_NOTIFICATION;
}
@@ -536,7 +531,7 @@ static irqreturn_t vmci_interrupt_bm(int irq, void *_dev)
struct vmci_guest_device *dev = _dev;
/* For MSI-X we can just assume it was meant for us. */
- tasklet_schedule(&dev->bm_tasklet);
+ vmci_process_bitmap(dev);
return IRQ_HANDLED;
}
@@ -638,10 +633,6 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
vmci_dev->iobase = iobase;
vmci_dev->mmio_base = mmio_base;
- tasklet_init(&vmci_dev->datagram_tasklet,
- vmci_dispatch_dgs, (unsigned long)vmci_dev);
- tasklet_init(&vmci_dev->bm_tasklet,
- vmci_process_bitmap, (unsigned long)vmci_dev);
init_waitqueue_head(&vmci_dev->inout_wq);
if (mmio_base != NULL) {
@@ -808,8 +799,9 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
* Request IRQ for legacy or MSI interrupts, or for first
* MSI-X vector.
*/
- error = request_irq(pci_irq_vector(pdev, 0), vmci_interrupt,
- IRQF_SHARED, KBUILD_MODNAME, vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 0), NULL,
+ vmci_interrupt, IRQF_SHARED,
+ KBUILD_MODNAME, vmci_dev);
if (error) {
dev_err(&pdev->dev, "Irq %u in use: %d\n",
pci_irq_vector(pdev, 0), error);
@@ -823,9 +815,9 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
* between the vectors.
*/
if (vmci_dev->exclusive_vectors) {
- error = request_irq(pci_irq_vector(pdev, 1),
- vmci_interrupt_bm, 0, KBUILD_MODNAME,
- vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 1), NULL,
+ vmci_interrupt_bm, 0,
+ KBUILD_MODNAME, vmci_dev);
if (error) {
dev_err(&pdev->dev,
"Failed to allocate irq %u: %d\n",
@@ -833,9 +825,11 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
goto err_free_irq;
}
if (caps_in_use & VMCI_CAPS_DMA_DATAGRAM) {
- error = request_irq(pci_irq_vector(pdev, 2),
- vmci_interrupt_dma_datagram,
- 0, KBUILD_MODNAME, vmci_dev);
+ error = request_threaded_irq(pci_irq_vector(pdev, 2),
+ NULL,
+ vmci_interrupt_dma_datagram,
+ 0, KBUILD_MODNAME,
+ vmci_dev);
if (error) {
dev_err(&pdev->dev,
"Failed to allocate irq %u: %d\n",
@@ -871,8 +865,6 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
err_free_irq:
free_irq(pci_irq_vector(pdev, 0), vmci_dev);
- tasklet_kill(&vmci_dev->datagram_tasklet);
- tasklet_kill(&vmci_dev->bm_tasklet);
err_disable_msi:
pci_free_irq_vectors(pdev);
@@ -943,9 +935,6 @@ static void vmci_guest_remove_device(struct pci_dev *pdev)
free_irq(pci_irq_vector(pdev, 0), vmci_dev);
pci_free_irq_vectors(pdev);
- tasklet_kill(&vmci_dev->datagram_tasklet);
- tasklet_kill(&vmci_dev->bm_tasklet);
-
if (vmci_dev->notification_bitmap) {
/*
* The device reset above cleared the bitmap state of the
--
GitLab
From 14ee78d5932afeb710c8305196a676a715bfdea8 Mon Sep 17 00:00:00 2001
From: Matthew Howell <matthew.howell@sealevel.com>
Date: Thu, 19 Jan 2023 14:40:29 -0500
Subject: [PATCH 1029/1167] serial: exar: Add support for Sealevel 7xxxC serial
cards
Add support for Sealevel 7xxxC serial cards.
This patch:
* Adds IDs to recognize 7xxxC cards from Sealevel Systems.
* Updates exar_pci_probe() to set nr_ports to last two bytes of primary
dev ID for these cards.
Signed-off-by: Matthew Howell <matthew.howell@sealevel.com>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2301191440010.22558@tstest-VirtualBox
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/tty/serial/8250/8250_exar.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c
index 314a05e009df9..64770c62bbec5 100644
--- a/drivers/tty/serial/8250/8250_exar.c
+++ b/drivers/tty/serial/8250/8250_exar.c
@@ -43,6 +43,12 @@
#define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358
#define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358
+#define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001
+#define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002
+#define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004
+#define PCI_DEVICE_ID_SEALEVEL_780xC 0x1008
+#define PCI_DEVICE_ID_SEALEVEL_716xC 0x1010
+
#define UART_EXAR_INT0 0x80
#define UART_EXAR_8XMODE 0x88 /* 8X sampling rate select */
#define UART_EXAR_SLEEP 0x8b /* Sleep mode */
@@ -638,6 +644,8 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent)
nr_ports = BIT(((pcidev->device & 0x38) >> 3) - 1);
else if (board->num_ports)
nr_ports = board->num_ports;
+ else if (pcidev->vendor == PCI_VENDOR_ID_SEALEVEL)
+ nr_ports = pcidev->device & 0xff;
else
nr_ports = pcidev->device & 0x0f;
@@ -864,6 +872,12 @@ static const struct pci_device_id exar_pci_tbl[] = {
EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4),
EXAR_DEVICE(COMMTECH, 2324PCI335, pbn_fastcom335_4),
EXAR_DEVICE(COMMTECH, 2328PCI335, pbn_fastcom335_8),
+
+ EXAR_DEVICE(SEALEVEL, 710xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 720xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 740xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 780xC, pbn_exar_XR17V35x),
+ EXAR_DEVICE(SEALEVEL, 716xC, pbn_exar_XR17V35x),
{ 0, }
};
MODULE_DEVICE_TABLE(pci, exar_pci_tbl);
--
GitLab
From d3e599c090fc6977331150c5f0a69ab8ce87da21 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 18 Jan 2023 12:35:01 -0800
Subject: [PATCH 1030/1167] bnxt: Do not read past the end of test names
Test names were being concatenated based on a offset beyond the end of
the first name, which tripped the buffer overflow detection logic:
detected buffer overflow in strnlen
[...]
Call Trace:
bnxt_ethtool_init.cold+0x18/0x18
Refactor struct hwrm_selftest_qlist_output to use an actual array,
and adjust the concatenation to use snprintf() rather than a series of
strncat() calls.
Reported-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Link: https://lore.kernel.org/lkml/Y8F%2F1w1AZTvLglFX@x1-carbon/
Tested-by: Niklas Cassel <Niklas.Cassel@wdc.com>
Fixes: eb51365846bc ("bnxt_en: Add basic ethtool -t selftest support.")
Cc: Michael Chan <michael.chan@broadcom.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 13 ++++---------
drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 9 +--------
2 files changed, 5 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index cbf17fcfb7ab4..ec573127b7076 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -3969,7 +3969,7 @@ void bnxt_ethtool_init(struct bnxt *bp)
test_info->timeout = HWRM_CMD_TIMEOUT;
for (i = 0; i < bp->num_tests; i++) {
char *str = test_info->string[i];
- char *fw_str = resp->test0_name + i * 32;
+ char *fw_str = resp->test_name[i];
if (i == BNXT_MACLPBK_TEST_IDX) {
strcpy(str, "Mac loopback test (offline)");
@@ -3980,14 +3980,9 @@ void bnxt_ethtool_init(struct bnxt *bp)
} else if (i == BNXT_IRQ_TEST_IDX) {
strcpy(str, "Interrupt_test (offline)");
} else {
- strscpy(str, fw_str, ETH_GSTRING_LEN);
- strncat(str, " test", ETH_GSTRING_LEN - strlen(str));
- if (test_info->offline_mask & (1 << i))
- strncat(str, " (offline)",
- ETH_GSTRING_LEN - strlen(str));
- else
- strncat(str, " (online)",
- ETH_GSTRING_LEN - strlen(str));
+ snprintf(str, ETH_GSTRING_LEN, "%s test (%s)",
+ fw_str, test_info->offline_mask & (1 << i) ?
+ "offline" : "online");
}
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 2686a714a59f7..a5408879e077e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -10249,14 +10249,7 @@ struct hwrm_selftest_qlist_output {
u8 unused_0;
__le16 test_timeout;
u8 unused_1[2];
- char test0_name[32];
- char test1_name[32];
- char test2_name[32];
- char test3_name[32];
- char test4_name[32];
- char test5_name[32];
- char test6_name[32];
- char test7_name[32];
+ char test_name[8][32];
u8 eyescope_target_BER_support;
#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED 0x0UL
#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED 0x1UL
--
GitLab
From 300b655db1b5152d6101bcb6801d50899b20c2d6 Mon Sep 17 00:00:00 2001
From: David Morley <morleyd@google.com>
Date: Thu, 19 Jan 2023 19:00:28 +0000
Subject: [PATCH 1031/1167] tcp: fix rate_app_limited to default to 1
The initial default value of 0 for tp->rate_app_limited was incorrect,
since a flow is indeed application-limited until it first sends
data. Fixing the default to be 1 is generally correct but also
specifically will help user-space applications avoid using the initial
tcpi_delivery_rate value of 0 that persists until the connection has
some non-zero bandwidth sample.
Fixes: eb8329e0a04d ("tcp: export data delivery rate")
Suggested-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David Morley <morleyd@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Tested-by: David Morley <morleyd@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/tcp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c567d5e8053e0..33f559f491c8c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -435,6 +435,7 @@ void tcp_init_sock(struct sock *sk)
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
/* See draft-stevens-tcpca-spec-01 for discussion of the
* initialization of these values.
@@ -3178,6 +3179,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->plb_rehash = 0;
/* There's a bubble in the pipe until at least the first ACK. */
tp->app_limited = ~0U;
+ tp->rate_app_limited = 1;
tp->rack.mstamp = 0;
tp->rack.advanced = 0;
tp->rack.reo_wnd_steps = 1;
--
GitLab
From 5d3d01ae15d2f37ed0325c99ab47ef0ae5d05f3c Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Fri, 20 Jan 2023 13:27:14 +0100
Subject: [PATCH 1032/1167] usb: host: ehci-fsl: Fix module alias
Commit ca07e1c1e4a6 ("drivers:usb:fsl:Make fsl ehci drv an independent
driver module") changed DRV_NAME which was used for MODULE_ALIAS as well.
Starting from this the module alias didn't match the platform device
name created in fsl-mph-dr-of.c
Change DRV_NAME to match the driver name for host mode in fsl-mph-dr-of.
This is needed for module autoloading on ls1021a.
Fixes: ca07e1c1e4a6 ("drivers:usb:fsl:Make fsl ehci drv an independent driver module")
Cc: stable <stable@kernel.org>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/20230120122714.3848784-1-alexander.stein@ew.tq-group.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/host/ehci-fsl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index 9cea785934e59..38d06e5abfbb3 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -29,7 +29,7 @@
#include "ehci-fsl.h"
#define DRIVER_DESC "Freescale EHCI Host controller driver"
-#define DRV_NAME "ehci-fsl"
+#define DRV_NAME "fsl-ehci"
static struct hc_driver __read_mostly fsl_ehci_hc_driver;
--
GitLab
From 14ff7460bb58662d86aa50298943cc7d25532e28 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 20 Jan 2023 14:53:30 +0100
Subject: [PATCH 1033/1167] USB: misc: iowarrior: fix up header size for
USB_DEVICE_ID_CODEMERCS_IOW100
The USB_DEVICE_ID_CODEMERCS_IOW100 header size was incorrect, it should
be 12, not 13.
Cc: stable <stable@kernel.org>
Fixes: 17a82716587e ("USB: iowarrior: fix up report size handling for some devices")
Reported-by: Christoph Jung <jung@codemercs.com>
Link: https://lore.kernel.org/r/20230120135330.3842518-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/usb/misc/iowarrior.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index f9427a67789cf..1e3df27bab58f 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -814,7 +814,7 @@ static int iowarrior_probe(struct usb_interface *interface,
break;
case USB_DEVICE_ID_CODEMERCS_IOW100:
- dev->report_size = 13;
+ dev->report_size = 12;
break;
}
}
--
GitLab
From 4bb3d82a1820c1b609ede8eb2332f3cb038c5840 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 20 Jan 2023 14:14:47 +0100
Subject: [PATCH 1034/1167] regulator: dt-bindings: samsung,s2mps14: add lost
samsung,ext-control-gpios
The samsung,ext-control-gpios property was lost during conversion to DT
schema:
exynos3250-artik5-eval.dtb: pmic@66: regulators:LDO11: Unevaluated properties are not allowed ('samsung,ext-control-gpios' was unexpected)
Fixes: ea98b9eba05c ("regulator: dt-bindings: samsung,s2m: convert to dtschema")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20230120131447.289702-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
.../bindings/regulator/samsung,s2mps14.yaml | 21 +++++++++++++++++--
1 file changed, 19 insertions(+), 2 deletions(-)
diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml
index 01f9d4e236e94..a7feb497eb89b 100644
--- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml
+++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml
@@ -19,8 +19,8 @@ description: |
additional information and example.
patternProperties:
- # 25 LDOs
- "^LDO([1-9]|[1][0-9]|2[0-5])$":
+ # 25 LDOs, without LDO10-12
+ "^LDO([1-9]|1[3-9]|2[0-5])$":
type: object
$ref: regulator.yaml#
unevaluatedProperties: false
@@ -30,6 +30,23 @@ patternProperties:
required:
- regulator-name
+ "^LDO(1[0-2])$":
+ type: object
+ $ref: regulator.yaml#
+ unevaluatedProperties: false
+ description:
+ Properties for single LDO regulator.
+
+ properties:
+ samsung,ext-control-gpios:
+ maxItems: 1
+ description:
+ LDO10, LDO11 and LDO12 can be configured to external control over
+ GPIO.
+
+ required:
+ - regulator-name
+
# 5 bucks
"^BUCK[1-5]$":
type: object
--
GitLab
From 51cdc8bc120ef6e42f6fb758341f5d91bc955952 Mon Sep 17 00:00:00 2001
From: Yi Liu <yi.l.liu@intel.com>
Date: Fri, 20 Jan 2023 07:05:28 -0800
Subject: [PATCH 1035/1167] kvm/vfio: Fix potential deadlock on vfio group_lock
Currently it is possible that the final put of a KVM reference comes from
vfio during its device close operation. This occurs while the vfio group
lock is held; however, if the vfio device is still in the kvm device list,
then the following call chain could result in a deadlock:
VFIO holds group->group_lock/group_rwsem
-> kvm_put_kvm
-> kvm_destroy_vm
-> kvm_destroy_devices
-> kvm_vfio_destroy
-> kvm_vfio_file_set_kvm
-> vfio_file_set_kvm
-> try to hold group->group_lock/group_rwsem
The key function is the kvm_destroy_devices() which triggers destroy cb
of kvm_device_ops. It calls back to vfio and try to hold group_lock. So
if this path doesn't call back to vfio, this dead lock would be fixed.
Actually, there is a way for it. KVM provides another point to free the
kvm-vfio device which is the point when the device file descriptor is
closed. This can be achieved by providing the release cb instead of the
destroy cb. Also rename kvm_vfio_destroy() to be kvm_vfio_release().
/*
* Destroy is responsible for freeing dev.
*
* Destroy may be called before or after destructors are called
* on emulated I/O regions, depending on whether a reference is
* held by a vcpu or other kvm component that gets destroyed
* after the emulated I/O.
*/
void (*destroy)(struct kvm_device *dev);
/*
* Release is an alternative method to free the device. It is
* called when the device file descriptor is closed. Once
* release is called, the destroy method will not be called
* anymore as the device is removed from the device list of
* the VM. kvm->lock is held.
*/
void (*release)(struct kvm_device *dev);
Fixes: 421cfe6596f6 ("vfio: remove VFIO_GROUP_NOTIFY_SET_KVM")
Reported-by: Alex Williamson <alex.williamson@redhat.com>
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Link: https://lore.kernel.org/r/20230114000351.115444-1-mjrosato@linux.ibm.com
Link: https://lore.kernel.org/r/20230120150528.471752-1-yi.l.liu@intel.com
[aw: update comment as well, s/destroy/release/]
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
virt/kvm/vfio.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 495ceabffe88b..9584eb57e0eda 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -336,7 +336,7 @@ static int kvm_vfio_has_attr(struct kvm_device *dev,
return -ENXIO;
}
-static void kvm_vfio_destroy(struct kvm_device *dev)
+static void kvm_vfio_release(struct kvm_device *dev)
{
struct kvm_vfio *kv = dev->private;
struct kvm_vfio_group *kvg, *tmp;
@@ -355,7 +355,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
kvm_vfio_update_coherency(dev);
kfree(kv);
- kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
+ kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */
}
static int kvm_vfio_create(struct kvm_device *dev, u32 type);
@@ -363,7 +363,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type);
static struct kvm_device_ops kvm_vfio_ops = {
.name = "kvm-vfio",
.create = kvm_vfio_create,
- .destroy = kvm_vfio_destroy,
+ .release = kvm_vfio_release,
.set_attr = kvm_vfio_set_attr,
.has_attr = kvm_vfio_has_attr,
};
--
GitLab
From 45a919bbb21c642e0c34dac483d1e003560159dc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 20 Jan 2023 08:38:16 -0800
Subject: [PATCH 1036/1167] Revert "Merge branch 'octeontx2-af-CPT'"
This reverts commit b4fbf0b27fa9dd2594b3371532341bd4636a00f9, reversing
changes made to 6c977c5c2e4c5d8ad1b604724cc344e38f96fe9b.
This seems like net-next material.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
.../net/ethernet/marvell/octeontx2/af/mbox.h | 27 --
.../net/ethernet/marvell/octeontx2/af/rvu.c | 8 -
.../net/ethernet/marvell/octeontx2/af/rvu.h | 18 -
.../ethernet/marvell/octeontx2/af/rvu_cpt.c | 309 +++++-------------
.../ethernet/marvell/octeontx2/af/rvu_reg.h | 2 -
5 files changed, 87 insertions(+), 277 deletions(-)
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index 84761c7f6717d..d2584ebb7a70c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -195,9 +195,6 @@ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \
M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \
msg_rsp) \
M(CPT_CTX_CACHE_SYNC, 0xA07, cpt_ctx_cache_sync, msg_req, msg_rsp) \
-M(CPT_LF_RESET, 0xA08, cpt_lf_reset, cpt_lf_rst_req, msg_rsp) \
-M(CPT_FLT_ENG_INFO, 0xA09, cpt_flt_eng_info, cpt_flt_eng_info_req, \
- cpt_flt_eng_info_rsp) \
/* SDP mbox IDs (range 0x1000 - 0x11FF) */ \
M(SET_SDP_CHAN_INFO, 0x1000, set_sdp_chan_info, sdp_chan_info_msg, msg_rsp) \
M(GET_SDP_CHAN_INFO, 0x1001, get_sdp_chan_info, msg_req, sdp_get_chan_info_msg) \
@@ -1612,8 +1609,6 @@ struct cpt_lf_alloc_req_msg {
u16 sso_pf_func;
u16 eng_grpmsk;
int blkaddr;
- u8 ctx_ilen_valid : 1;
- u8 ctx_ilen : 7;
};
#define CPT_INLINE_INBOUND 0
@@ -1697,28 +1692,6 @@ struct cpt_inst_lmtst_req {
u64 rsvd;
};
-/* Mailbox message format to request for CPT LF reset */
-struct cpt_lf_rst_req {
- struct mbox_msghdr hdr;
- u32 slot;
- u32 rsvd;
-};
-
-/* Mailbox message format to request for CPT faulted engines */
-struct cpt_flt_eng_info_req {
- struct mbox_msghdr hdr;
- int blkaddr;
- bool reset;
- u32 rsvd;
-};
-
-struct cpt_flt_eng_info_rsp {
- struct mbox_msghdr hdr;
- u64 flt_eng_map[CPT_10K_AF_INT_VEC_RVU];
- u64 rcvrd_eng_map[CPT_10K_AF_INT_VEC_RVU];
- u64 rsvd;
-};
-
struct sdp_node_info {
/* Node to which this PF belons to */
u8 node_id;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 8683ce57ed3fb..3f5e09b77d4bd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -1164,16 +1164,8 @@ static int rvu_setup_hw_resources(struct rvu *rvu)
goto nix_err;
}
- err = rvu_cpt_init(rvu);
- if (err) {
- dev_err(rvu->dev, "%s: Failed to initialize cpt\n", __func__);
- goto mcs_err;
- }
-
return 0;
-mcs_err:
- rvu_mcs_exit(rvu);
nix_err:
rvu_nix_freemem(rvu);
npa_err:
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 5eea2b6cf6bdb..7f0a64731c675 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -108,8 +108,6 @@ struct rvu_block {
u64 lfreset_reg;
unsigned char name[NAME_SIZE];
struct rvu *rvu;
- u64 cpt_flt_eng_map[3];
- u64 cpt_rcvrd_eng_map[3];
};
struct nix_mcast {
@@ -461,7 +459,6 @@ struct rvu {
struct rvu_pfvf *pf;
struct rvu_pfvf *hwvf;
struct mutex rsrc_lock; /* Serialize resource alloc/free */
- struct mutex alias_lock; /* Serialize bar2 alias access */
int vfs; /* Number of VFs attached to RVU */
int nix_blkaddr[MAX_NIX_BLKS];
@@ -513,7 +510,6 @@ struct rvu {
struct ptp *ptp;
int mcs_blk_cnt;
- int cpt_pf_num;
#ifdef CONFIG_DEBUG_FS
struct rvu_debugfs rvu_dbg;
@@ -528,8 +524,6 @@ struct rvu {
struct list_head mcs_intrq_head;
/* mcs interrupt queue lock */
spinlock_t mcs_intrq_lock;
- /* CPT interrupt lock */
- spinlock_t cpt_intr_lock;
};
static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
@@ -552,17 +546,6 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
return readq(rvu->pfreg_base + offset);
}
-static inline void rvu_bar2_sel_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
-{
- /* HW requires read back of RVU_AF_BAR2_SEL register to make sure completion of
- * write operation.
- */
- rvu_write64(rvu, block, offset, val);
- rvu_read64(rvu, block, offset);
- /* Barrier to ensure read completes before accessing LF registers */
- mb();
-}
-
/* Silicon revisions */
static inline bool is_rvu_pre_96xx_C0(struct rvu *rvu)
{
@@ -882,7 +865,6 @@ void rvu_cpt_unregister_interrupts(struct rvu *rvu);
int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf,
int slot);
int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc);
-int rvu_cpt_init(struct rvu *rvu);
/* CN10K RVU */
int rvu_set_channels_base(struct rvu *rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index f047185f38e0f..38bbae5d9ae05 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -17,7 +17,7 @@
#define PCI_DEVID_OTX2_CPT10K_PF 0xA0F2
/* Length of initial context fetch in 128 byte words */
-#define CPT_CTX_ILEN 1ULL
+#define CPT_CTX_ILEN 2ULL
#define cpt_get_eng_sts(e_min, e_max, rsp, etype) \
({ \
@@ -37,66 +37,32 @@
(_rsp)->free_sts_##etype = free_sts; \
})
-static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr)
+static irqreturn_t rvu_cpt_af_flt_intr_handler(int irq, void *ptr)
{
struct rvu_block *block = ptr;
struct rvu *rvu = block->rvu;
int blkaddr = block->addr;
- u64 reg, val;
- int i, eng;
- u8 grp;
-
- reg = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(vec));
- dev_err_ratelimited(rvu->dev, "Received CPTAF FLT%d irq : 0x%llx", vec, reg);
-
- i = -1;
- while ((i = find_next_bit((unsigned long *)®, 64, i + 1)) < 64) {
- switch (vec) {
- case 0:
- eng = i;
- break;
- case 1:
- eng = i + 64;
- break;
- case 2:
- eng = i + 128;
- break;
- }
- grp = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng)) & 0xFF;
- /* Disable and enable the engine which triggers fault */
- rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), 0x0);
- val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng));
- rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val & ~1ULL);
-
- rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL2(eng), grp);
- rvu_write64(rvu, blkaddr, CPT_AF_EXEX_CTL(eng), val | 1ULL);
-
- spin_lock(&rvu->cpt_intr_lock);
- block->cpt_flt_eng_map[vec] |= BIT_ULL(i);
- val = rvu_read64(rvu, blkaddr, CPT_AF_EXEX_STS(eng));
- val = val & 0x3;
- if (val == 0x1 || val == 0x2)
- block->cpt_rcvrd_eng_map[vec] |= BIT_ULL(i);
- spin_unlock(&rvu->cpt_intr_lock);
- }
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(vec), reg);
-
- return IRQ_HANDLED;
-}
+ u64 reg0, reg1, reg2;
-static irqreturn_t rvu_cpt_af_flt0_intr_handler(int irq, void *ptr)
-{
- return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT0, ptr);
-}
+ reg0 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(0));
+ reg1 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(1));
+ if (!is_rvu_otx2(rvu)) {
+ reg2 = rvu_read64(rvu, blkaddr, CPT_AF_FLTX_INT(2));
+ dev_err_ratelimited(rvu->dev,
+ "Received CPTAF FLT irq : 0x%llx, 0x%llx, 0x%llx",
+ reg0, reg1, reg2);
+ } else {
+ dev_err_ratelimited(rvu->dev,
+ "Received CPTAF FLT irq : 0x%llx, 0x%llx",
+ reg0, reg1);
+ }
-static irqreturn_t rvu_cpt_af_flt1_intr_handler(int irq, void *ptr)
-{
- return cpt_af_flt_intr_handler(CPT_AF_INT_VEC_FLT1, ptr);
-}
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(0), reg0);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(1), reg1);
+ if (!is_rvu_otx2(rvu))
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT(2), reg2);
-static irqreturn_t rvu_cpt_af_flt2_intr_handler(int irq, void *ptr)
-{
- return cpt_af_flt_intr_handler(CPT_10K_AF_INT_VEC_FLT2, ptr);
+ return IRQ_HANDLED;
}
static irqreturn_t rvu_cpt_af_rvu_intr_handler(int irq, void *ptr)
@@ -153,10 +119,8 @@ static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off)
int i;
/* Disable all CPT AF interrupts */
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(0), ~0ULL);
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(1), ~0ULL);
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(2), 0xFFFF);
-
+ for (i = 0; i < CPT_10K_AF_INT_VEC_RVU; i++)
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1);
@@ -187,7 +151,7 @@ static void cpt_unregister_interrupts(struct rvu *rvu, int blkaddr)
/* Disable all CPT AF interrupts */
for (i = 0; i < CPT_AF_INT_VEC_RVU; i++)
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), ~0ULL);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i), 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1);
rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1);
@@ -208,31 +172,16 @@ static int cpt_10k_register_interrupts(struct rvu_block *block, int off)
{
struct rvu *rvu = block->rvu;
int blkaddr = block->addr;
- irq_handler_t flt_fn;
int i, ret;
for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) {
sprintf(&rvu->irq_name[(off + i) * NAME_SIZE], "CPTAF FLT%d", i);
-
- switch (i) {
- case CPT_10K_AF_INT_VEC_FLT0:
- flt_fn = rvu_cpt_af_flt0_intr_handler;
- break;
- case CPT_10K_AF_INT_VEC_FLT1:
- flt_fn = rvu_cpt_af_flt1_intr_handler;
- break;
- case CPT_10K_AF_INT_VEC_FLT2:
- flt_fn = rvu_cpt_af_flt2_intr_handler;
- break;
- }
ret = rvu_cpt_do_register_interrupt(block, off + i,
- flt_fn, &rvu->irq_name[(off + i) * NAME_SIZE]);
+ rvu_cpt_af_flt_intr_handler,
+ &rvu->irq_name[(off + i) * NAME_SIZE]);
if (ret)
goto err;
- if (i == CPT_10K_AF_INT_VEC_FLT2)
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0xFFFF);
- else
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1);
}
ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU,
@@ -259,8 +208,8 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr)
{
struct rvu_hwinfo *hw = rvu->hw;
struct rvu_block *block;
- irq_handler_t flt_fn;
int i, offs, ret = 0;
+ char irq_name[16];
if (!is_block_implemented(rvu->hw, blkaddr))
return 0;
@@ -277,20 +226,13 @@ static int cpt_register_interrupts(struct rvu *rvu, int blkaddr)
return cpt_10k_register_interrupts(block, offs);
for (i = CPT_AF_INT_VEC_FLT0; i < CPT_AF_INT_VEC_RVU; i++) {
- sprintf(&rvu->irq_name[(offs + i) * NAME_SIZE], "CPTAF FLT%d", i);
- switch (i) {
- case CPT_AF_INT_VEC_FLT0:
- flt_fn = rvu_cpt_af_flt0_intr_handler;
- break;
- case CPT_AF_INT_VEC_FLT1:
- flt_fn = rvu_cpt_af_flt1_intr_handler;
- break;
- }
+ snprintf(irq_name, sizeof(irq_name), "CPTAF FLT%d", i);
ret = rvu_cpt_do_register_interrupt(block, offs + i,
- flt_fn, &rvu->irq_name[(offs + i) * NAME_SIZE]);
+ rvu_cpt_af_flt_intr_handler,
+ irq_name);
if (ret)
goto err;
- rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL);
+ rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0x1);
}
ret = rvu_cpt_do_register_interrupt(block, offs + CPT_AF_INT_VEC_RVU,
@@ -348,7 +290,7 @@ static int get_cpt_pf_num(struct rvu *rvu)
static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
{
- int cpt_pf_num = rvu->cpt_pf_num;
+ int cpt_pf_num = get_cpt_pf_num(rvu);
if (rvu_get_pf(pcifunc) != cpt_pf_num)
return false;
@@ -360,7 +302,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
{
- int cpt_pf_num = rvu->cpt_pf_num;
+ int cpt_pf_num = get_cpt_pf_num(rvu);
if (rvu_get_pf(pcifunc) != cpt_pf_num)
return false;
@@ -429,12 +371,8 @@ int rvu_mbox_handler_cpt_lf_alloc(struct rvu *rvu,
/* Set CPT LF group and priority */
val = (u64)req->eng_grpmsk << 48 | 1;
- if (!is_rvu_otx2(rvu)) {
- if (req->ctx_ilen_valid)
- val |= (req->ctx_ilen << 17);
- else
- val |= (CPT_CTX_ILEN << 17);
- }
+ if (!is_rvu_otx2(rvu))
+ val |= (CPT_CTX_ILEN << 17);
rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val);
@@ -824,21 +762,10 @@ int rvu_mbox_handler_cpt_sts(struct rvu *rvu, struct cpt_sts_req *req,
#define RXC_ZOMBIE_COUNT GENMASK_ULL(60, 48)
static void cpt_rxc_time_cfg(struct rvu *rvu, struct cpt_rxc_time_cfg_req *req,
- int blkaddr, struct cpt_rxc_time_cfg_req *save)
+ int blkaddr)
{
u64 dfrg_reg;
- if (save) {
- /* Save older config */
- dfrg_reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_DFRG);
- save->zombie_thres = FIELD_GET(RXC_ZOMBIE_THRES, dfrg_reg);
- save->zombie_limit = FIELD_GET(RXC_ZOMBIE_LIMIT, dfrg_reg);
- save->active_thres = FIELD_GET(RXC_ACTIVE_THRES, dfrg_reg);
- save->active_limit = FIELD_GET(RXC_ACTIVE_LIMIT, dfrg_reg);
-
- save->step = rvu_read64(rvu, blkaddr, CPT_AF_RXC_TIME_CFG);
- }
-
dfrg_reg = FIELD_PREP(RXC_ZOMBIE_THRES, req->zombie_thres);
dfrg_reg |= FIELD_PREP(RXC_ZOMBIE_LIMIT, req->zombie_limit);
dfrg_reg |= FIELD_PREP(RXC_ACTIVE_THRES, req->active_thres);
@@ -863,7 +790,7 @@ int rvu_mbox_handler_cpt_rxc_time_cfg(struct rvu *rvu,
!is_cpt_vf(rvu, req->hdr.pcifunc))
return CPT_AF_ERR_ACCESS_DENIED;
- cpt_rxc_time_cfg(rvu, req, blkaddr, NULL);
+ cpt_rxc_time_cfg(rvu, req, blkaddr);
return 0;
}
@@ -874,67 +801,9 @@ int rvu_mbox_handler_cpt_ctx_cache_sync(struct rvu *rvu, struct msg_req *req,
return rvu_cpt_ctx_flush(rvu, req->hdr.pcifunc);
}
-int rvu_mbox_handler_cpt_lf_reset(struct rvu *rvu, struct cpt_lf_rst_req *req,
- struct msg_rsp *rsp)
-{
- u16 pcifunc = req->hdr.pcifunc;
- struct rvu_block *block;
- int cptlf, blkaddr, ret;
- u16 actual_slot;
- u64 ctl, ctl2;
-
- blkaddr = rvu_get_blkaddr_from_slot(rvu, BLKTYPE_CPT, pcifunc,
- req->slot, &actual_slot);
- if (blkaddr < 0)
- return CPT_AF_ERR_LF_INVALID;
-
- block = &rvu->hw->block[blkaddr];
-
- cptlf = rvu_get_lf(rvu, block, pcifunc, actual_slot);
- if (cptlf < 0)
- return CPT_AF_ERR_LF_INVALID;
- ctl = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf));
- ctl2 = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf));
-
- ret = rvu_lf_reset(rvu, block, cptlf);
- if (ret)
- dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n",
- block->addr, cptlf);
-
- rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), ctl);
- rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), ctl2);
-
- return 0;
-}
-
-int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_req *req,
- struct cpt_flt_eng_info_rsp *rsp)
-{
- struct rvu_block *block;
- unsigned long flags;
- int blkaddr, vec;
-
- blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
- if (blkaddr < 0)
- return blkaddr;
-
- block = &rvu->hw->block[blkaddr];
- for (vec = 0; vec < CPT_10K_AF_INT_VEC_RVU; vec++) {
- spin_lock_irqsave(&rvu->cpt_intr_lock, flags);
- rsp->flt_eng_map[vec] = block->cpt_flt_eng_map[vec];
- rsp->rcvrd_eng_map[vec] = block->cpt_rcvrd_eng_map[vec];
- if (req->reset) {
- block->cpt_flt_eng_map[vec] = 0x0;
- block->cpt_rcvrd_eng_map[vec] = 0x0;
- }
- spin_unlock_irqrestore(&rvu->cpt_intr_lock, flags);
- }
- return 0;
-}
-
static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
{
- struct cpt_rxc_time_cfg_req req, prev;
+ struct cpt_rxc_time_cfg_req req;
int timeout = 2000;
u64 reg;
@@ -950,7 +819,7 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
req.active_thres = 1;
req.active_limit = 1;
- cpt_rxc_time_cfg(rvu, &req, blkaddr, &prev);
+ cpt_rxc_time_cfg(rvu, &req, blkaddr);
do {
reg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS);
@@ -976,68 +845,70 @@ static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
if (timeout == 0)
dev_warn(rvu->dev, "Poll for RXC zombie count hits hard loop counter\n");
-
- /* Restore config */
- cpt_rxc_time_cfg(rvu, &prev, blkaddr, NULL);
}
-#define INFLIGHT GENMASK_ULL(8, 0)
-#define GRB_CNT GENMASK_ULL(39, 32)
-#define GWB_CNT GENMASK_ULL(47, 40)
-#define XQ_XOR GENMASK_ULL(63, 63)
-#define DQPTR GENMASK_ULL(19, 0)
-#define NQPTR GENMASK_ULL(51, 32)
+#define INPROG_INFLIGHT(reg) ((reg) & 0x1FF)
+#define INPROG_GRB_PARTIAL(reg) ((reg) & BIT_ULL(31))
+#define INPROG_GRB(reg) (((reg) >> 32) & 0xFF)
+#define INPROG_GWB(reg) (((reg) >> 40) & 0xFF)
static void cpt_lf_disable_iqueue(struct rvu *rvu, int blkaddr, int slot)
{
- int timeout = 1000000;
- u64 inprog, inst_ptr;
- u64 qsize, pending;
- int i = 0;
+ int i = 0, hard_lp_ctr = 100000;
+ u64 inprog, grp_ptr;
+ u16 nq_ptr, dq_ptr;
/* Disable instructions enqueuing */
rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_CTL), 0x0);
+ /* Disable executions in the LF's queue */
inprog = rvu_read64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- inprog |= BIT_ULL(16);
+ inprog &= ~BIT_ULL(16);
rvu_write64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), inprog);
- qsize = rvu_read64(rvu, blkaddr,
- CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_SIZE)) & 0x7FFF;
+ /* Wait for CPT queue to become execution-quiescent */
do {
- inst_ptr = rvu_read64(rvu, blkaddr,
- CPT_AF_BAR2_ALIASX(slot, CPT_LF_Q_INST_PTR));
- pending = (FIELD_GET(XQ_XOR, inst_ptr) * qsize * 40) +
- FIELD_GET(NQPTR, inst_ptr) -
- FIELD_GET(DQPTR, inst_ptr);
- udelay(1);
- timeout--;
- } while ((pending != 0) && (timeout != 0));
+ inprog = rvu_read64(rvu, blkaddr,
+ CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
+ if (INPROG_GRB_PARTIAL(inprog)) {
+ i = 0;
+ hard_lp_ctr--;
+ } else {
+ i++;
+ }
- if (timeout == 0)
- dev_warn(rvu->dev, "TIMEOUT: CPT poll on pending instructions\n");
+ grp_ptr = rvu_read64(rvu, blkaddr,
+ CPT_AF_BAR2_ALIASX(slot,
+ CPT_LF_Q_GRP_PTR));
+ nq_ptr = (grp_ptr >> 32) & 0x7FFF;
+ dq_ptr = grp_ptr & 0x7FFF;
- timeout = 1000000;
- /* Wait for CPT queue to become execution-quiescent */
+ } while (hard_lp_ctr && (i < 10) && (nq_ptr != dq_ptr));
+
+ if (hard_lp_ctr == 0)
+ dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n");
+
+ i = 0;
+ hard_lp_ctr = 100000;
do {
inprog = rvu_read64(rvu, blkaddr,
CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
- if ((FIELD_GET(INFLIGHT, inprog) == 0) &&
- (FIELD_GET(GRB_CNT, inprog) == 0)) {
+ if ((INPROG_INFLIGHT(inprog) == 0) &&
+ (INPROG_GWB(inprog) < 40) &&
+ ((INPROG_GRB(inprog) == 0) ||
+ (INPROG_GRB((inprog)) == 40))) {
i++;
} else {
i = 0;
- timeout--;
+ hard_lp_ctr--;
}
- } while ((timeout != 0) && (i < 10));
+ } while (hard_lp_ctr && (i < 10));
- if (timeout == 0)
- dev_warn(rvu->dev, "TIMEOUT: CPT poll on inflight count\n");
- /* Wait for 2 us to flush all queue writes to memory */
- udelay(2);
+ if (hard_lp_ctr == 0)
+ dev_warn(rvu->dev, "CPT FLR hits hard loop counter\n");
}
int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int slot)
@@ -1047,15 +918,18 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s
if (is_cpt_pf(rvu, pcifunc) || is_cpt_vf(rvu, pcifunc))
cpt_rxc_teardown(rvu, blkaddr);
- mutex_lock(&rvu->alias_lock);
/* Enable BAR2 ALIAS for this pcifunc. */
reg = BIT_ULL(16) | pcifunc;
- rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
+ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
cpt_lf_disable_iqueue(rvu, blkaddr, slot);
- rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
- mutex_unlock(&rvu->alias_lock);
+ /* Set group drop to help clear out hardware */
+ reg = rvu_read64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG));
+ reg |= BIT_ULL(17);
+ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_ALIASX(slot, CPT_LF_INPROG), reg);
+
+ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
return 0;
}
@@ -1066,7 +940,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf, int s
static int cpt_inline_inb_lf_cmd_send(struct rvu *rvu, int blkaddr,
int nix_blkaddr)
{
- int cpt_pf_num = rvu->cpt_pf_num;
+ int cpt_pf_num = get_cpt_pf_num(rvu);
struct cpt_inst_lmtst_req *req;
dma_addr_t res_daddr;
int timeout = 3000;
@@ -1190,7 +1064,7 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc)
/* Enable BAR2 ALIAS for this pcifunc. */
reg = BIT_ULL(16) | pcifunc;
- rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
+ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, reg);
for (i = 0; i < max_ctx_entries; i++) {
cam_data = rvu_read64(rvu, blkaddr, CPT_AF_CTX_CAM_DATA(i));
@@ -1203,19 +1077,10 @@ int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc)
reg);
}
}
- rvu_bar2_sel_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
+ rvu_write64(rvu, blkaddr, CPT_AF_BAR2_SEL, 0);
unlock:
mutex_unlock(&rvu->rsrc_lock);
return 0;
}
-
-int rvu_cpt_init(struct rvu *rvu)
-{
- /* Retrieve CPT PF number */
- rvu->cpt_pf_num = get_cpt_pf_num(rvu);
- spin_lock_init(&rvu->cpt_intr_lock);
-
- return 0;
-}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index 5437bd20c7192..0e0d536645ac7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -545,8 +545,6 @@
#define CPT_LF_CTL 0x10
#define CPT_LF_INPROG 0x40
-#define CPT_LF_Q_SIZE 0x100
-#define CPT_LF_Q_INST_PTR 0x110
#define CPT_LF_Q_GRP_PTR 0x120
#define CPT_LF_CTX_FLUSH 0x510
--
GitLab
From 56d8e3180c065c9b78ed77afcd0cf99677a4e22f Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 20 Jan 2023 16:38:05 +0000
Subject: [PATCH 1037/1167] io_uring/msg_ring: fix flagging remote execution
There is a couple of problems with queueing a tw in io_msg_ring_data()
for remote execution. First, once we queue it the target ring can
go away and so setting IORING_SQ_TASKRUN there is not safe. Secondly,
the userspace might not expect IORING_SQ_TASKRUN.
Extract a helper and uniformly use TWA_SIGNAL without TWA_SIGNAL_NO_IPI
tricks for now, just as it was done in the original patch.
Cc: stable@vger.kernel.org
Fixes: 6d043ee1164ca ("io_uring: do msg_ring in target task via tw")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/msg_ring.c | 40 +++++++++++++++++++++++-----------------
1 file changed, 23 insertions(+), 17 deletions(-)
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index a333781565d31..bb868447dcdfd 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -58,6 +58,25 @@ void io_msg_ring_cleanup(struct io_kiocb *req)
msg->src_file = NULL;
}
+static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx)
+{
+ if (!target_ctx->task_complete)
+ return false;
+ return current != target_ctx->submitter_task;
+}
+
+static int io_msg_exec_remote(struct io_kiocb *req, task_work_func_t func)
+{
+ struct io_ring_ctx *ctx = req->file->private_data;
+ struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
+
+ init_task_work(&msg->tw, func);
+ if (task_work_add(ctx->submitter_task, &msg->tw, TWA_SIGNAL))
+ return -EOWNERDEAD;
+
+ return IOU_ISSUE_SKIP_COMPLETE;
+}
+
static void io_msg_tw_complete(struct callback_head *head)
{
struct io_msg *msg = container_of(head, struct io_msg, tw);
@@ -96,15 +115,8 @@ static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags)
if (msg->src_fd || msg->dst_fd || msg->flags)
return -EINVAL;
- if (target_ctx->task_complete && current != target_ctx->submitter_task) {
- init_task_work(&msg->tw, io_msg_tw_complete);
- if (task_work_add(target_ctx->submitter_task, &msg->tw,
- TWA_SIGNAL_NO_IPI))
- return -EOWNERDEAD;
-
- atomic_or(IORING_SQ_TASKRUN, &target_ctx->rings->sq_flags);
- return IOU_ISSUE_SKIP_COMPLETE;
- }
+ if (io_msg_need_remote(target_ctx))
+ return io_msg_exec_remote(req, io_msg_tw_complete);
ret = -EOVERFLOW;
if (target_ctx->flags & IORING_SETUP_IOPOLL) {
@@ -202,14 +214,8 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
req->flags |= REQ_F_NEED_CLEANUP;
}
- if (target_ctx->task_complete && current != target_ctx->submitter_task) {
- init_task_work(&msg->tw, io_msg_tw_fd_complete);
- if (task_work_add(target_ctx->submitter_task, &msg->tw,
- TWA_SIGNAL))
- return -EOWNERDEAD;
-
- return IOU_ISSUE_SKIP_COMPLETE;
- }
+ if (io_msg_need_remote(target_ctx))
+ return io_msg_exec_remote(req, io_msg_tw_fd_complete);
return io_msg_install_complete(req, issue_flags);
}
--
GitLab
From 8579538c89e33ce78be2feb41e07489c8cbf8f31 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 20 Jan 2023 16:38:06 +0000
Subject: [PATCH 1038/1167] io_uring/msg_ring: fix remote queue to disabled
ring
IORING_SETUP_R_DISABLED rings don't have the submitter task set, so
it's not always safe to use ->submitter_task. Disallow posting msg_ring
messaged to disabled rings. Also add task NULL check for loosy sync
around testing for IORING_SETUP_R_DISABLED.
Cc: stable@vger.kernel.org
Fixes: 6d043ee1164ca ("io_uring: do msg_ring in target task via tw")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 4 ++--
io_uring/msg_ring.c | 8 ++++++++
2 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 2ac1cd8d23ea6..0a4efada9b3c3 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3674,7 +3674,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
if (ctx->flags & IORING_SETUP_SINGLE_ISSUER
&& !(ctx->flags & IORING_SETUP_R_DISABLED))
- ctx->submitter_task = get_task_struct(current);
+ WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
file = io_uring_get_file(ctx);
if (IS_ERR(file)) {
@@ -3868,7 +3868,7 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx)
return -EBADFD;
if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task)
- ctx->submitter_task = get_task_struct(current);
+ WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
if (ctx->restrictions.registered)
ctx->restricted = 1;
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index bb868447dcdfd..15602a136821b 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -69,6 +69,10 @@ static int io_msg_exec_remote(struct io_kiocb *req, task_work_func_t func)
{
struct io_ring_ctx *ctx = req->file->private_data;
struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg);
+ struct task_struct *task = READ_ONCE(ctx->submitter_task);
+
+ if (unlikely(!task))
+ return -EOWNERDEAD;
init_task_work(&msg->tw, func);
if (task_work_add(ctx->submitter_task, &msg->tw, TWA_SIGNAL))
@@ -114,6 +118,8 @@ static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags)
if (msg->src_fd || msg->dst_fd || msg->flags)
return -EINVAL;
+ if (target_ctx->flags & IORING_SETUP_R_DISABLED)
+ return -EBADFD;
if (io_msg_need_remote(target_ctx))
return io_msg_exec_remote(req, io_msg_tw_complete);
@@ -206,6 +212,8 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags)
if (target_ctx == ctx)
return -EINVAL;
+ if (target_ctx->flags & IORING_SETUP_R_DISABLED)
+ return -EBADFD;
if (!src_file) {
src_file = io_msg_grab_file(req, issue_flags);
if (!src_file)
--
GitLab
From 4411a608f7c8df000cb1a9f7881982dd8e10839a Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Thu, 15 Dec 2022 23:50:48 +0100
Subject: [PATCH 1039/1167] iavf: fix temporary deadlock and failure to set MAC
address
We are seeing an issue where setting the MAC address on iavf fails with
EAGAIN after the 2.5s timeout expires in iavf_set_mac().
There is the following deadlock scenario:
iavf_set_mac(), holding rtnl_lock, waits on:
iavf_watchdog_task (within iavf_wq) to send a message to the PF,
and
iavf_adminq_task (within iavf_wq) to receive a response from the PF.
In this adapter state (>=__IAVF_DOWN), these tasks do not need to take
rtnl_lock, but iavf_wq is a global single-threaded workqueue, so they
may get stuck waiting for another adapter's iavf_watchdog_task to run
iavf_init_config_adapter(), which does take rtnl_lock.
The deadlock resolves itself by the timeout in iavf_set_mac(),
which results in EAGAIN returned to userspace.
Let's break the deadlock loop by changing iavf_wq into a per-adapter
workqueue, so that one adapter's tasks are not blocked by another's.
Fixes: 35a2443d0910 ("iavf: Add waiting for response from PF in set mac")
Co-developed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/iavf/iavf.h | 2 +-
.../net/ethernet/intel/iavf/iavf_ethtool.c | 10 +--
drivers/net/ethernet/intel/iavf/iavf_main.c | 86 +++++++++----------
.../net/ethernet/intel/iavf/iavf_virtchnl.c | 2 +-
4 files changed, 49 insertions(+), 51 deletions(-)
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 0d1bab4ac1b07..2a9f1eeeb7015 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -249,6 +249,7 @@ struct iavf_cloud_filter {
/* board specific private data structure */
struct iavf_adapter {
+ struct workqueue_struct *wq;
struct work_struct reset_task;
struct work_struct adminq_task;
struct delayed_work client_task;
@@ -459,7 +460,6 @@ struct iavf_device {
/* needed by iavf_ethtool.c */
extern char iavf_driver_name[];
-extern struct workqueue_struct *iavf_wq;
static inline const char *iavf_state_str(enum iavf_state_t state)
{
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index d79ead5e8d0ca..6f171d1d85b75 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -532,7 +532,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags)
if (changed_flags & IAVF_FLAG_LEGACY_RX) {
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
}
@@ -672,7 +672,7 @@ static int iavf_set_ringparam(struct net_device *netdev,
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
return 0;
@@ -1433,7 +1433,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
spin_unlock_bh(&adapter->fdir_fltr_lock);
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
ret:
if (err && fltr)
@@ -1474,7 +1474,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
spin_unlock_bh(&adapter->fdir_fltr_lock);
if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST)
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
return err;
}
@@ -1658,7 +1658,7 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter,
spin_unlock_bh(&adapter->adv_rss_lock);
if (!err)
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
mutex_unlock(&adapter->crit_lock);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index adc02adef83a2..0aa32c164ecf4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -49,7 +49,6 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver")
MODULE_LICENSE("GPL v2");
static const struct net_device_ops iavf_netdev_ops;
-struct workqueue_struct *iavf_wq;
int iavf_status_to_errno(enum iavf_status status)
{
@@ -277,7 +276,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter)
if (!(adapter->flags &
(IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
}
@@ -291,7 +290,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter)
void iavf_schedule_request_stats(struct iavf_adapter *adapter)
{
adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
@@ -411,7 +410,7 @@ static irqreturn_t iavf_msix_aq(int irq, void *data)
if (adapter->state != __IAVF_REMOVE)
/* schedule work on the private workqueue */
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
return IRQ_HANDLED;
}
@@ -1034,7 +1033,7 @@ int iavf_replace_primary_mac(struct iavf_adapter *adapter,
/* schedule the watchdog task to immediately process the request */
if (f) {
- queue_work(iavf_wq, &adapter->watchdog_task.work);
+ queue_work(adapter->wq, &adapter->watchdog_task.work);
return 0;
}
return -ENOMEM;
@@ -1257,7 +1256,7 @@ static void iavf_up_complete(struct iavf_adapter *adapter)
adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES;
if (CLIENT_ENABLED(adapter))
adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
@@ -1414,7 +1413,7 @@ void iavf_down(struct iavf_adapter *adapter)
adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES;
}
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
/**
@@ -2248,7 +2247,7 @@ iavf_set_vlan_offload_features(struct iavf_adapter *adapter,
if (aq_required) {
adapter->aq_required |= aq_required;
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
}
}
@@ -2700,7 +2699,7 @@ static void iavf_watchdog_task(struct work_struct *work)
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
mutex_unlock(&adapter->crit_lock);
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
return;
}
@@ -2708,31 +2707,31 @@ static void iavf_watchdog_task(struct work_struct *work)
case __IAVF_STARTUP:
iavf_startup(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(30));
return;
case __IAVF_INIT_VERSION_CHECK:
iavf_init_version_check(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(30));
return;
case __IAVF_INIT_GET_RESOURCES:
iavf_init_get_resources(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_EXTENDED_CAPS:
iavf_init_process_extended_caps(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_CONFIG_ADAPTER:
iavf_init_config_adapter(adapter);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(1));
return;
case __IAVF_INIT_FAILED:
@@ -2751,14 +2750,14 @@ static void iavf_watchdog_task(struct work_struct *work)
adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED;
iavf_shutdown_adminq(hw);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task, (5 * HZ));
return;
}
/* Try again from failed step*/
iavf_change_state(adapter, adapter->last_state);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ);
return;
case __IAVF_COMM_FAILED:
if (test_bit(__IAVF_IN_REMOVE_TASK,
@@ -2789,13 +2788,14 @@ static void iavf_watchdog_task(struct work_struct *work)
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task,
msecs_to_jiffies(10));
return;
case __IAVF_RESETTING:
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ HZ * 2);
return;
case __IAVF_DOWN:
case __IAVF_DOWN_PENDING:
@@ -2834,9 +2834,9 @@ static void iavf_watchdog_task(struct work_struct *work)
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
mutex_unlock(&adapter->crit_lock);
- queue_delayed_work(iavf_wq,
+ queue_delayed_work(adapter->wq,
&adapter->watchdog_task, HZ * 2);
return;
}
@@ -2845,12 +2845,13 @@ static void iavf_watchdog_task(struct work_struct *work)
mutex_unlock(&adapter->crit_lock);
restart_watchdog:
if (adapter->state >= __IAVF_DOWN)
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
if (adapter->aq_required)
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(20));
else
- queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ HZ * 2);
}
/**
@@ -2952,7 +2953,7 @@ static void iavf_reset_task(struct work_struct *work)
*/
if (!mutex_trylock(&adapter->crit_lock)) {
if (adapter->state != __IAVF_REMOVE)
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
goto reset_finish;
}
@@ -3116,7 +3117,7 @@ static void iavf_reset_task(struct work_struct *work)
bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID);
bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID);
- mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2);
/* We were running when the reset started, so we need to restore some
* state here.
@@ -3208,7 +3209,7 @@ static void iavf_adminq_task(struct work_struct *work)
if (adapter->state == __IAVF_REMOVE)
return;
- queue_work(iavf_wq, &adapter->adminq_task);
+ queue_work(adapter->wq, &adapter->adminq_task);
goto out;
}
@@ -4349,7 +4350,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu)
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
return 0;
@@ -4898,6 +4899,13 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
hw = &adapter->hw;
hw->back = adapter;
+ adapter->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+ iavf_driver_name);
+ if (!adapter->wq) {
+ err = -ENOMEM;
+ goto err_alloc_wq;
+ }
+
adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1;
iavf_change_state(adapter, __IAVF_STARTUP);
@@ -4942,7 +4950,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
INIT_WORK(&adapter->adminq_task, iavf_adminq_task);
INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task);
INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task);
- queue_delayed_work(iavf_wq, &adapter->watchdog_task,
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
/* Setup the wait queue for indicating transition to down status */
@@ -4954,6 +4962,8 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
return 0;
err_ioremap:
+ destroy_workqueue(adapter->wq);
+err_alloc_wq:
free_netdev(netdev);
err_alloc_etherdev:
pci_disable_pcie_error_reporting(pdev);
@@ -5023,7 +5033,7 @@ static int __maybe_unused iavf_resume(struct device *dev_d)
return err;
}
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
netif_device_attach(adapter->netdev);
@@ -5170,6 +5180,8 @@ static void iavf_remove(struct pci_dev *pdev)
}
spin_unlock_bh(&adapter->adv_rss_lock);
+ destroy_workqueue(adapter->wq);
+
free_netdev(netdev);
pci_disable_pcie_error_reporting(pdev);
@@ -5196,24 +5208,11 @@ static struct pci_driver iavf_driver = {
**/
static int __init iavf_init_module(void)
{
- int ret;
-
pr_info("iavf: %s\n", iavf_driver_string);
pr_info("%s\n", iavf_copyright);
- iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1,
- iavf_driver_name);
- if (!iavf_wq) {
- pr_err("%s: Failed to create workqueue\n", iavf_driver_name);
- return -ENOMEM;
- }
-
- ret = pci_register_driver(&iavf_driver);
- if (ret)
- destroy_workqueue(iavf_wq);
-
- return ret;
+ return pci_register_driver(&iavf_driver);
}
module_init(iavf_init_module);
@@ -5227,7 +5226,6 @@ module_init(iavf_init_module);
static void __exit iavf_exit_module(void)
{
pci_unregister_driver(&iavf_driver);
- destroy_workqueue(iavf_wq);
}
module_exit(iavf_exit_module);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 24a701fd140e9..0752fd67c96e5 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1952,7 +1952,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) {
adapter->flags |= IAVF_FLAG_RESET_PENDING;
dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
- queue_work(iavf_wq, &adapter->reset_task);
+ queue_work(adapter->wq, &adapter->reset_task);
}
break;
default:
--
GitLab
From 7598f4b40bd60e4a4280de645eb2893eea80b59d Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Tue, 3 Jan 2023 17:42:27 +0100
Subject: [PATCH 1040/1167] iavf: Move netdev_update_features() into watchdog
task
Remove netdev_update_features() from iavf_adminq_task(), as it can cause
deadlocks due to needing rtnl_lock. Instead use the
IAVF_FLAG_SETUP_NETDEV_FEATURES flag to indicate that netdev features need
to be updated in the watchdog task. iavf_set_vlan_offload_features()
and iavf_set_queue_vlan_tag_loc() can be called directly from
iavf_virtchnl_completion().
Suggested-by: Phani Burra <phani.r.burra@intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Tested-by: Marek Szlosek <marek.szlosek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/iavf/iavf_main.c | 27 +++++++------------
.../net/ethernet/intel/iavf/iavf_virtchnl.c | 8 ++++++
2 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 0aa32c164ecf4..de7112ae84169 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2692,6 +2692,15 @@ static void iavf_watchdog_task(struct work_struct *work)
goto restart_watchdog;
}
+ if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) &&
+ adapter->netdev_registered &&
+ !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) &&
+ rtnl_trylock()) {
+ netdev_update_features(adapter->netdev);
+ rtnl_unlock();
+ adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
+ }
+
if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)
iavf_change_state(adapter, __IAVF_COMM_FAILED);
@@ -3233,24 +3242,6 @@ static void iavf_adminq_task(struct work_struct *work)
} while (pending);
mutex_unlock(&adapter->crit_lock);
- if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES)) {
- if (adapter->netdev_registered ||
- !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) {
- struct net_device *netdev = adapter->netdev;
-
- rtnl_lock();
- netdev_update_features(netdev);
- rtnl_unlock();
- /* Request VLAN offload settings */
- if (VLAN_V2_ALLOWED(adapter))
- iavf_set_vlan_offload_features
- (adapter, 0, netdev->features);
-
- iavf_set_queue_vlan_tag_loc(adapter);
- }
-
- adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES;
- }
if ((adapter->flags &
(IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) ||
adapter->state == __IAVF_RESETTING)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 0752fd67c96e5..365ca0c710c4a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -2226,6 +2226,14 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
iavf_process_config(adapter);
adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES;
+
+ /* Request VLAN offload settings */
+ if (VLAN_V2_ALLOWED(adapter))
+ iavf_set_vlan_offload_features(adapter, 0,
+ netdev->features);
+
+ iavf_set_queue_vlan_tag_loc(adapter);
+
was_mac_changed = !ether_addr_equal(netdev->dev_addr,
adapter->hw.mac.addr);
--
GitLab
From e2b53ea5a7c1fb484277ad12cd075f502cf03b04 Mon Sep 17 00:00:00 2001
From: Stefan Assmann <sassmann@kpanic.de>
Date: Tue, 10 Jan 2023 09:00:18 +0100
Subject: [PATCH 1041/1167] iavf: schedule watchdog immediately when changing
primary MAC
iavf_replace_primary_mac() utilizes queue_work() to schedule the
watchdog task but that only ensures that the watchdog task is queued
to run. To make sure the watchdog is executed asap use
mod_delayed_work().
Without this patch it may take up to 2s until the watchdog task gets
executed, which may cause long delays when setting the MAC address.
Fixes: a3e839d539e0 ("iavf: Add usage of new virtchnl format to set default MAC")
Signed-off-by: Stefan Assmann <sassmann@kpanic.de>
Reviewed-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
drivers/net/ethernet/intel/iavf/iavf_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index de7112ae84169..4b09785d2147a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1033,7 +1033,7 @@ int iavf_replace_primary_mac(struct iavf_adapter *adapter,
/* schedule the watchdog task to immediately process the request */
if (f) {
- queue_work(adapter->wq, &adapter->watchdog_task.work);
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
return 0;
}
return -ENOMEM;
--
GitLab
From 977c6ba624f24ae20cf0faee871257a39348d4a9 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 18 Jan 2023 20:38:50 +0530
Subject: [PATCH 1042/1167] EDAC/qcom: Do not pass llcc_driv_data as
edac_device_ctl_info's pvt_info
The memory for llcc_driv_data is allocated by the LLCC driver. But when
it is passed as the private driver info to the EDAC core, it will get freed
during the qcom_edac driver release. So when the qcom_edac driver gets probed
again, it will try to use the freed data leading to the use-after-free bug.
Hence, do not pass llcc_driv_data as pvt_info but rather reference it
using the platform_data pointer in the qcom_edac driver.
Fixes: 27450653f1db ("drivers: edac: Add EDAC driver support for QCOM SoCs")
Reported-by: Steev Klimaszewski <steev@kali.org>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Steev Klimaszewski <steev@kali.org> # Thinkpad X13s
Tested-by: Andrew Halaney <ahalaney@redhat.com> # sa8540p-ride
Cc: <stable@vger.kernel.org> # 4.20
Link: https://lore.kernel.org/r/20230118150904.26913-4-manivannan.sadhasivam@linaro.org
---
drivers/edac/qcom_edac.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
index 97a27e42dd610..c45519f59dc11 100644
--- a/drivers/edac/qcom_edac.c
+++ b/drivers/edac/qcom_edac.c
@@ -252,7 +252,7 @@ dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type)
static int
dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank)
{
- struct llcc_drv_data *drv = edev_ctl->pvt_info;
+ struct llcc_drv_data *drv = edev_ctl->dev->platform_data;
int ret;
ret = dump_syn_reg_values(drv, bank, err_type);
@@ -289,7 +289,7 @@ static irqreturn_t
llcc_ecc_irq_handler(int irq, void *edev_ctl)
{
struct edac_device_ctl_info *edac_dev_ctl = edev_ctl;
- struct llcc_drv_data *drv = edac_dev_ctl->pvt_info;
+ struct llcc_drv_data *drv = edac_dev_ctl->dev->platform_data;
irqreturn_t irq_rc = IRQ_NONE;
u32 drp_error, trp_error, i;
int ret;
@@ -358,7 +358,6 @@ static int qcom_llcc_edac_probe(struct platform_device *pdev)
edev_ctl->dev_name = dev_name(dev);
edev_ctl->ctl_name = "llcc";
edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE;
- edev_ctl->pvt_info = llcc_driv_data;
rc = edac_device_add_device(edev_ctl);
if (rc)
--
GitLab
From 0d0d4680db22eda1eea785c47bbf66a9b33a8b16 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Thu, 29 Dec 2022 18:33:25 +0900
Subject: [PATCH 1043/1167] ksmbd: add max connections parameter
Add max connections parameter to limit number of maximum simultaneous
connections.
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Cc: stable@vger.kernel.org
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/ksmbd_netlink.h | 3 ++-
fs/ksmbd/server.h | 1 +
fs/ksmbd/transport_ipc.c | 3 +++
fs/ksmbd/transport_tcp.c | 17 ++++++++++++++++-
4 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h
index b6bd8311e6b4d..fb8b2d566efb6 100644
--- a/fs/ksmbd/ksmbd_netlink.h
+++ b/fs/ksmbd/ksmbd_netlink.h
@@ -106,7 +106,8 @@ struct ksmbd_startup_request {
__u32 sub_auth[3]; /* Subauth value for Security ID */
__u32 smb2_max_credits; /* MAX credits */
__u32 smbd_max_io_size; /* smbd read write size */
- __u32 reserved[127]; /* Reserved room */
+ __u32 max_connections; /* Number of maximum simultaneous connections */
+ __u32 reserved[126]; /* Reserved room */
__u32 ifc_list_sz; /* interfaces list size */
__s8 ____payload[];
};
diff --git a/fs/ksmbd/server.h b/fs/ksmbd/server.h
index ac9d932f8c8aa..db72781817603 100644
--- a/fs/ksmbd/server.h
+++ b/fs/ksmbd/server.h
@@ -41,6 +41,7 @@ struct ksmbd_server_config {
unsigned int share_fake_fscaps;
struct smb_sid domain_sid;
unsigned int auth_mechs;
+ unsigned int max_connections;
char *conf[SERVER_CONF_WORK_GROUP + 1];
};
diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c
index c9aca21637d5b..40c721f9227e4 100644
--- a/fs/ksmbd/transport_ipc.c
+++ b/fs/ksmbd/transport_ipc.c
@@ -308,6 +308,9 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req)
if (req->smbd_max_io_size)
init_smbd_max_io_size(req->smbd_max_io_size);
+ if (req->max_connections)
+ server_conf.max_connections = req->max_connections;
+
ret = ksmbd_set_netbios_name(req->netbios_name);
ret |= ksmbd_set_server_string(req->server_string);
ret |= ksmbd_set_work_group(req->work_group);
diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c
index 4c6bd0b699791..603893fd87f57 100644
--- a/fs/ksmbd/transport_tcp.c
+++ b/fs/ksmbd/transport_tcp.c
@@ -15,6 +15,8 @@
#define IFACE_STATE_DOWN BIT(0)
#define IFACE_STATE_CONFIGURED BIT(1)
+static atomic_t active_num_conn;
+
struct interface {
struct task_struct *ksmbd_kthread;
struct socket *ksmbd_socket;
@@ -185,8 +187,10 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk)
struct tcp_transport *t;
t = alloc_transport(client_sk);
- if (!t)
+ if (!t) {
+ sock_release(client_sk);
return -ENOMEM;
+ }
csin = KSMBD_TCP_PEER_SOCKADDR(KSMBD_TRANS(t)->conn);
if (kernel_getpeername(client_sk, csin) < 0) {
@@ -239,6 +243,15 @@ static int ksmbd_kthread_fn(void *p)
continue;
}
+ if (server_conf.max_connections &&
+ atomic_inc_return(&active_num_conn) >= server_conf.max_connections) {
+ pr_info_ratelimited("Limit the maximum number of connections(%u)\n",
+ atomic_read(&active_num_conn));
+ atomic_dec(&active_num_conn);
+ sock_release(client_sk);
+ continue;
+ }
+
ksmbd_debug(CONN, "connect success: accepted new connection\n");
client_sk->sk->sk_rcvtimeo = KSMBD_TCP_RECV_TIMEOUT;
client_sk->sk->sk_sndtimeo = KSMBD_TCP_SEND_TIMEOUT;
@@ -368,6 +381,8 @@ static int ksmbd_tcp_writev(struct ksmbd_transport *t, struct kvec *iov,
static void ksmbd_tcp_disconnect(struct ksmbd_transport *t)
{
free_transport(TCP_TRANS(t));
+ if (server_conf.max_connections)
+ atomic_dec(&active_num_conn);
}
static void tcp_destroy_socket(struct socket *ksmbd_socket)
--
GitLab
From 5fde3c21cf33830eda7bfd006dc7f4bf07ec9fe6 Mon Sep 17 00:00:00 2001
From: Marios Makassikis <mmakassikis@freebox.fr>
Date: Wed, 11 Jan 2023 17:39:02 +0100
Subject: [PATCH 1044/1167] ksmbd: do not sign response to session request for
guest login
If ksmbd.mountd is configured to assign unknown users to the guest account
("map to guest = bad user" in the config), ksmbd signs the response.
This is wrong according to MS-SMB2 3.3.5.5.3:
12. If the SMB2_SESSION_FLAG_IS_GUEST bit is not set in the SessionFlags
field, and Session.IsAnonymous is FALSE, the server MUST sign the
final session setup response before sending it to the client, as
follows:
[...]
This fixes libsmb2 based applications failing to establish a session
("Wrong signature in received").
Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Cc: stable@vger.kernel.org
Signed-off-by: Marios Makassikis <mmakassikis@freebox.fr>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/smb2pdu.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 38fbda52e06fe..d681f91947d92 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -8663,6 +8663,7 @@ int smb3_decrypt_req(struct ksmbd_work *work)
bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work)
{
struct ksmbd_conn *conn = work->conn;
+ struct ksmbd_session *sess = work->sess;
struct smb2_hdr *rsp = smb2_get_msg(work->response_buf);
if (conn->dialect < SMB30_PROT_ID)
@@ -8672,6 +8673,7 @@ bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work)
rsp = ksmbd_resp_buf_next(work);
if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE &&
+ sess->user && !user_guest(sess->user) &&
rsp->Status == STATUS_SUCCESS)
return true;
return false;
--
GitLab
From 8caa03f10bf92cb8657408a6ece6a8a73f96ce13 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 20 Jan 2023 15:08:21 -0700
Subject: [PATCH 1045/1167] io_uring/poll: don't reissue in case of poll race
on multishot request
A previous commit fixed a poll race that can occur, but it's only
applicable for multishot requests. For a multishot request, we can safely
ignore a spurious wakeup, as we never leave the waitqueue to begin with.
A blunt reissue of a multishot armed request can cause us to leak a
buffer, if they are ring provided. While this seems like a bug in itself,
it's not really defined behavior to reissue a multishot request directly.
It's less efficient to do so as well, and not required to rearm anything
like it is for singleshot poll requests.
Cc: stable@vger.kernel.org
Fixes: 6e5aedb9324a ("io_uring/poll: attempt request issue after racy poll wakeup")
Reported-and-tested-by: Olivier Langlois <olivier@trillion01.com>
Link: https://github.com/axboe/liburing/issues/778
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/poll.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/io_uring/poll.c b/io_uring/poll.c
index 32e5fc8365e6a..2ac1366adbd77 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -283,8 +283,12 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked)
* to the waitqueue, so if we get nothing back, we
* should be safe and attempt a reissue.
*/
- if (unlikely(!req->cqe.res))
+ if (unlikely(!req->cqe.res)) {
+ /* Multishot armed need not reissue */
+ if (!(req->apoll_events & EPOLLONESHOT))
+ continue;
return IOU_POLL_REISSUE;
+ }
}
if (req->apoll_events & EPOLLONESHOT)
return IOU_POLL_DONE;
--
GitLab
From f0950402e8c76e7dcb08563f1b4e8000fbc62455 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Jan 2023 11:01:50 +0000
Subject: [PATCH 1046/1167] netlink: prevent potential spectre v1 gadgets
Most netlink attributes are parsed and validated from
__nla_validate_parse() or validate_nla()
u16 type = nla_type(nla);
if (type == 0 || type > maxtype) {
/* error or continue */
}
@type is then used as an array index and can be used
as a Spectre v1 gadget.
array_index_nospec() can be used to prevent leaking
content of kernel memory to malicious users.
This should take care of vast majority of netlink uses,
but an audit is needed to take care of others where
validation is not yet centralized in core netlink functions.
Fixes: bfa83a9e03cf ("[NETLINK]: Type-safe netlink messages/attributes interface")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230119110150.2678537-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
lib/nlattr.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 9055e8b4d144e..489e15bde5c1d 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -10,6 +10,7 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/jiffies.h>
+#include <linux/nospec.h>
#include <linux/skbuff.h>
#include <linux/string.h>
#include <linux/types.h>
@@ -381,6 +382,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
if (type <= 0 || type > maxtype)
return 0;
+ type = array_index_nospec(type, maxtype + 1);
pt = &policy[type];
BUG_ON(pt->type > NLA_TYPE_MAX);
@@ -596,6 +598,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
}
continue;
}
+ type = array_index_nospec(type, maxtype + 1);
if (policy) {
int err = validate_nla(nla, maxtype, policy,
validate, extack, depth);
--
GitLab
From 20e3028c39a5bf882e91e717da96d14f1acec40e Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Thu, 19 Jan 2023 12:59:10 -0800
Subject: [PATCH 1047/1167] net: mana: Fix IRQ name - add PCI and queue number
The PCI and queue number info is missing in IRQ names.
Add PCI and queue number to IRQ names, to allow CPU affinity
tuning scripts to work.
Cc: stable@vger.kernel.org
Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Link: https://lore.kernel.org/r/1674161950-19708-1-git-send-email-haiyangz@microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/microsoft/mana/gdma_main.c | 9 ++++++++-
include/net/mana/gdma.h | 3 +++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index e708c2d049839..b144f2237748e 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1259,13 +1259,20 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
gic->handler = NULL;
gic->arg = NULL;
+ if (!i)
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s",
+ pci_name(pdev));
+ else
+ snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s",
+ i - 1, pci_name(pdev));
+
irq = pci_irq_vector(pdev, i);
if (irq < 0) {
err = irq;
goto free_mask;
}
- err = request_irq(irq, mana_gd_intr, 0, "mana_intr", gic);
+ err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
if (err)
goto free_mask;
irq_set_affinity_and_hint(irq, req_mask);
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index b3ba04615caa3..56189e4252da3 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -336,9 +336,12 @@ struct gdma_queue_spec {
};
};
+#define MANA_IRQ_NAME_SZ 32
+
struct gdma_irq_context {
void (*handler)(void *arg);
void *arg;
+ char name[MANA_IRQ_NAME_SZ];
};
struct gdma_context {
--
GitLab
From fd941bd64f0776e4c51d8934f8e666cfbe14406a Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Fri, 20 Jan 2023 09:19:59 +0900
Subject: [PATCH 1048/1167] net: ethernet: renesas: rswitch: Fix ethernet-ports
handling
If one of ports in the ethernet-ports was disabled, this driver
failed to probe all ports. So, fix it.
Fixes: 3590918b5d07 ("net: ethernet: renesas: Add support for "Ethernet Switch"")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20230120001959.1059850-1-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/renesas/rswitch.c | 22 +++++++++++++---------
drivers/net/ethernet/renesas/rswitch.h | 12 ++++++++++++
2 files changed, 25 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 6441892636dba..2370c7797a0aa 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1074,8 +1074,11 @@ static struct device_node *rswitch_get_port_node(struct rswitch_device *rdev)
port = NULL;
goto out;
}
- if (index == rdev->etha->index)
+ if (index == rdev->etha->index) {
+ if (!of_device_is_available(port))
+ port = NULL;
break;
+ }
}
out:
@@ -1106,7 +1109,7 @@ static int rswitch_etha_get_params(struct rswitch_device *rdev)
port = rswitch_get_port_node(rdev);
if (!port)
- return -ENODEV;
+ return 0; /* ignored */
err = of_get_phy_mode(port, &rdev->etha->phy_interface);
of_node_put(port);
@@ -1324,13 +1327,13 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv)
{
int i, err;
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = rswitch_ether_port_init_one(priv->rdev[i]);
if (err)
goto err_init_one;
}
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = rswitch_serdes_init(priv->rdev[i]);
if (err)
goto err_serdes;
@@ -1339,12 +1342,12 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv)
return 0;
err_serdes:
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
rswitch_serdes_deinit(priv->rdev[i]);
i = RSWITCH_NUM_PORTS;
err_init_one:
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
rswitch_ether_port_deinit_one(priv->rdev[i]);
return err;
@@ -1608,6 +1611,7 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index)
netif_napi_add(ndev, &rdev->napi, rswitch_poll);
port = rswitch_get_port_node(rdev);
+ rdev->disabled = !port;
err = of_get_ethdev_address(port, ndev);
of_node_put(port);
if (err) {
@@ -1707,16 +1711,16 @@ static int rswitch_init(struct rswitch_private *priv)
if (err)
goto err_ether_port_init_all;
- for (i = 0; i < RSWITCH_NUM_PORTS; i++) {
+ rswitch_for_each_enabled_port(priv, i) {
err = register_netdev(priv->rdev[i]->ndev);
if (err) {
- for (i--; i >= 0; i--)
+ rswitch_for_each_enabled_port_continue_reverse(priv, i)
unregister_netdev(priv->rdev[i]->ndev);
goto err_register_netdev;
}
}
- for (i = 0; i < RSWITCH_NUM_PORTS; i++)
+ rswitch_for_each_enabled_port(priv, i)
netdev_info(priv->rdev[i]->ndev, "MAC address %pM\n",
priv->rdev[i]->ndev->dev_addr);
diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h
index edbdd1b98d3d9..49efb0f31c77a 100644
--- a/drivers/net/ethernet/renesas/rswitch.h
+++ b/drivers/net/ethernet/renesas/rswitch.h
@@ -13,6 +13,17 @@
#define RSWITCH_MAX_NUM_QUEUES 128
#define RSWITCH_NUM_PORTS 3
+#define rswitch_for_each_enabled_port(priv, i) \
+ for (i = 0; i < RSWITCH_NUM_PORTS; i++) \
+ if (priv->rdev[i]->disabled) \
+ continue; \
+ else
+
+#define rswitch_for_each_enabled_port_continue_reverse(priv, i) \
+ for (i--; i >= 0; i--) \
+ if (priv->rdev[i]->disabled) \
+ continue; \
+ else
#define TX_RING_SIZE 1024
#define RX_RING_SIZE 1024
@@ -938,6 +949,7 @@ struct rswitch_device {
struct rswitch_gwca_queue *tx_queue;
struct rswitch_gwca_queue *rx_queue;
u8 ts_tag;
+ bool disabled;
int port;
struct rswitch_etha *etha;
--
GitLab
From 71ab9c3e2253619136c31c89dbb2c69305cc89b1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 19 Jan 2023 19:55:45 +0100
Subject: [PATCH 1049/1167] net: fix UaF in netns ops registration error path
If net_assign_generic() fails, the current error path in ops_init() tries
to clear the gen pointer slot. Anyway, in such error path, the gen pointer
itself has not been modified yet, and the existing and accessed one is
smaller than the accessed index, causing an out-of-bounds error:
BUG: KASAN: slab-out-of-bounds in ops_init+0x2de/0x320
Write of size 8 at addr ffff888109124978 by task modprobe/1018
CPU: 2 PID: 1018 Comm: modprobe Not tainted 6.2.0-rc2.mptcp_ae5ac65fbed5+ #1641
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.1-2.fc37 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x6a/0x9f
print_address_description.constprop.0+0x86/0x2b5
print_report+0x11b/0x1fb
kasan_report+0x87/0xc0
ops_init+0x2de/0x320
register_pernet_operations+0x2e4/0x750
register_pernet_subsys+0x24/0x40
tcf_register_action+0x9f/0x560
do_one_initcall+0xf9/0x570
do_init_module+0x190/0x650
load_module+0x1fa5/0x23c0
__do_sys_finit_module+0x10d/0x1b0
do_syscall_64+0x58/0x80
entry_SYSCALL_64_after_hwframe+0x72/0xdc
RIP: 0033:0x7f42518f778d
Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48
89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff
ff 73 01 c3 48 8b 0d cb 56 2c 00 f7 d8 64 89 01 48
RSP: 002b:00007fff96869688 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
RAX: ffffffffffffffda RBX: 00005568ef7f7c90 RCX: 00007f42518f778d
RDX: 0000000000000000 RSI: 00005568ef41d796 RDI: 0000000000000003
RBP: 00005568ef41d796 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000
R13: 00005568ef7f7d30 R14: 0000000000040000 R15: 0000000000000000
</TASK>
This change addresses the issue by skipping the gen pointer
de-reference in the mentioned error-path.
Found by code inspection and verified with explicit error injection
on a kasan-enabled kernel.
Fixes: d266935ac43d ("net: fix UAF issue in nfqnl_nf_hook_drop() when ops_init() failed")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/cec4e0f3bb2c77ac03a6154a8508d3930beb5f0f.1674154348.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/core/net_namespace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 5581d22cc1912..078a0a420c8a7 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -137,12 +137,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
return 0;
if (ops->id && ops->size) {
-cleanup:
ng = rcu_dereference_protected(net->gen,
lockdep_is_held(&pernet_ops_rwsem));
ng->ptr[*ops->id] = NULL;
}
+cleanup:
kfree(data);
out:
--
GitLab
From c3b37c2d77a2c735857c55492ee81e88e855497d Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 19 Jan 2023 17:09:02 +0000
Subject: [PATCH 1050/1167] KVM: arm64: Pass the actual page address to
mte_clear_page_tags()
Commit d77e59a8fccd ("arm64: mte: Lock a page for MTE tag
initialisation") added a call to mte_clear_page_tags() in case a
prior mte_copy_tags_from_user() failed in order to avoid stale tags in
the guest page (it should have really been a separate commit).
Unfortunately, the argument passed to this function was the address of
the struct page rather than the actual page address. Fix this function
call.
Fixes: d77e59a8fccd ("arm64: mte: Lock a page for MTE tag initialisation")
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230119170902.1574756-1-catalin.marinas@arm.com
---
arch/arm64/kvm/guest.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 5626ddb540ce3..cf4c495a43213 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -1079,7 +1079,7 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
/* uaccess failed, don't leave stale tags */
if (num_tags != MTE_GRANULES_PER_PAGE)
- mte_clear_page_tags(page);
+ mte_clear_page_tags(maddr);
set_page_mte_tagged(page);
kvm_release_pfn_dirty(pfn);
--
GitLab
From ef3691683d7bfd0a2acf48812e4ffe894f10bfa8 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 19 Jan 2023 11:07:59 +0000
Subject: [PATCH 1051/1167] KVM: arm64: GICv4.1: Fix race with doorbell on VPE
activation/deactivation
To save the vgic LPI pending state with GICv4.1, the VPEs must all be
unmapped from the ITSs so that the sGIC caches can be flushed.
The opposite is done once the state is saved.
This is all done by using the activate/deactivate irqdomain callbacks
directly from the vgic code. Crutially, this is done without holding
the irqdesc lock for the interrupts that represent the VPE. And these
callbacks are changing the state of the irqdesc. What could possibly
go wrong?
If a doorbell fires while we are messing with the irqdesc state,
it will acquire the lock and change the interrupt state concurrently.
Since we don't hole the lock, curruption occurs in on the interrupt
state. Oh well.
While acquiring the lock would fix this (and this was Shanker's
initial approach), this is still a layering violation we could do
without. A better approach is actually to free the VPE interrupt,
do what we have to do, and re-request it.
It is more work, but this usually happens only once in the lifetime
of the VM and we don't really care about this sort of overhead.
Fixes: f66b7b151e00 ("KVM: arm64: GICv4.1: Try to save VLPI state in save_pending_tables")
Reported-by: Shanker Donthineni <sdonthineni@nvidia.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230118022348.4137094-1-sdonthineni@nvidia.com
---
arch/arm64/kvm/vgic/vgic-v3.c | 25 +++++++++++--------------
arch/arm64/kvm/vgic/vgic-v4.c | 8 ++++++--
arch/arm64/kvm/vgic/vgic.h | 1 +
3 files changed, 18 insertions(+), 16 deletions(-)
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 2074521d4a8ce..2624963cb95b3 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -350,26 +350,23 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
* The deactivation of the doorbell interrupt will trigger the
* unmapping of the associated vPE.
*/
-static void unmap_all_vpes(struct vgic_dist *dist)
+static void unmap_all_vpes(struct kvm *kvm)
{
- struct irq_desc *desc;
+ struct vgic_dist *dist = &kvm->arch.vgic;
int i;
- for (i = 0; i < dist->its_vm.nr_vpes; i++) {
- desc = irq_to_desc(dist->its_vm.vpes[i]->irq);
- irq_domain_deactivate_irq(irq_desc_get_irq_data(desc));
- }
+ for (i = 0; i < dist->its_vm.nr_vpes; i++)
+ free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i));
}
-static void map_all_vpes(struct vgic_dist *dist)
+static void map_all_vpes(struct kvm *kvm)
{
- struct irq_desc *desc;
+ struct vgic_dist *dist = &kvm->arch.vgic;
int i;
- for (i = 0; i < dist->its_vm.nr_vpes; i++) {
- desc = irq_to_desc(dist->its_vm.vpes[i]->irq);
- irq_domain_activate_irq(irq_desc_get_irq_data(desc), false);
- }
+ for (i = 0; i < dist->its_vm.nr_vpes; i++)
+ WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i),
+ dist->its_vm.vpes[i]->irq));
}
/**
@@ -394,7 +391,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
* and enabling of the doorbells have already been done.
*/
if (kvm_vgic_global_state.has_gicv4_1) {
- unmap_all_vpes(dist);
+ unmap_all_vpes(kvm);
vlpi_avail = true;
}
@@ -444,7 +441,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
out:
if (vlpi_avail)
- map_all_vpes(dist);
+ map_all_vpes(kvm);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index ad06ba6c9b009..a413718be92b8 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -222,6 +222,11 @@ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val)
*val = !!(*ptr & mask);
}
+int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq)
+{
+ return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu);
+}
+
/**
* vgic_v4_init - Initialize the GICv4 data structures
* @kvm: Pointer to the VM being initialized
@@ -283,8 +288,7 @@ int vgic_v4_init(struct kvm *kvm)
irq_flags &= ~IRQ_NOAUTOEN;
irq_set_status_flags(irq, irq_flags);
- ret = request_irq(irq, vgic_v4_doorbell_handler,
- 0, "vcpu", vcpu);
+ ret = vgic_v4_request_vpe_irq(vcpu, irq);
if (ret) {
kvm_err("failed to allocate vcpu IRQ%d\n", irq);
/*
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 0c8da72953f06..23e280fa0a16f 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -331,5 +331,6 @@ int vgic_v4_init(struct kvm *kvm);
void vgic_v4_teardown(struct kvm *kvm);
void vgic_v4_configure_vsgis(struct kvm *kvm);
void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
+int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);
#endif
--
GitLab
From 739790605705ddcf18f21782b9c99ad7d53a8c11 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Fri, 20 Jan 2023 11:03:20 +0100
Subject: [PATCH 1052/1167] prlimit: do_prlimit needs to have a speculation
check
do_prlimit() adds the user-controlled resource value to a pointer that
will subsequently be dereferenced. In order to help prevent this
codepath from being used as a spectre "gadget" a barrier needs to be
added after checking the range.
Reported-by: Jordy Zomer <jordyzomer@google.com>
Tested-by: Jordy Zomer <jordyzomer@google.com>
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
kernel/sys.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/sys.c b/kernel/sys.c
index 5fd54bf0e8867..88b31f096fb2d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1442,6 +1442,8 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource,
if (resource >= RLIM_NLIMITS)
return -EINVAL;
+ resource = array_index_nospec(resource, RLIM_NLIMITS);
+
if (new_rlim) {
if (new_rlim->rlim_cur > new_rlim->rlim_max)
return -EINVAL;
--
GitLab
From f3bbac32475b27f49be201f896d98d4009de1562 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 17 Jan 2023 20:27:23 -0800
Subject: [PATCH 1053/1167] ext4: deal with legacy signed xattr name hash
values
We potentially have old hashes of the xattr names generated on systems
with signed 'char' types. Now that everybody uses '-funsigned-char',
those hashes will no longer match.
This only happens if you use xattrs names that have the high bit set,
which probably doesn't happen in practice, but the xfstest generic/454
shows it.
Instead of adding a new "signed xattr hash filesystem" bit and having to
deal with all the possible combinations, just calculate the hash both
ways if the first one fails, and always generate new hashes with the
proper unsigned char version.
Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/oe-lkp/202212291509.704a11c9-oliver.sang@intel.com
Link: https://lore.kernel.org/all/CAHk-=whUNjwqZXa-MH9KMmc_CpQpoFKFjAB9ZKHuu=TbsouT4A@mail.gmail.com/
Exposed-by: 3bc753c06dd0 ("kbuild: treat char as always unsigned")
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Andreas Dilger <adilger@dilger.ca>
Cc: Theodore Ts'o <tytso@mit.edu>,
Cc: Jason Donenfeld <Jason@zx2c4.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
fs/ext4/xattr.c | 41 +++++++++++++++++++++++++++++++++++++++--
1 file changed, 39 insertions(+), 2 deletions(-)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 7decaaf27e82b..69a1b8c6a2eca 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -81,6 +81,8 @@ ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
struct mb_cache_entry **);
static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
size_t value_count);
+static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value,
+ size_t value_count);
static void ext4_xattr_rehash(struct ext4_xattr_header *);
static const struct xattr_handler * const ext4_xattr_handler_map[] = {
@@ -470,8 +472,21 @@ ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
tmp_data = cpu_to_le32(hash);
e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len,
&tmp_data, 1);
- if (e_hash != entry->e_hash)
- return -EFSCORRUPTED;
+ /* All good? */
+ if (e_hash == entry->e_hash)
+ return 0;
+
+ /*
+ * Not good. Maybe the entry hash was calculated
+ * using the buggy signed char version?
+ */
+ e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len,
+ &tmp_data, 1);
+ if (e_hash == entry->e_hash)
+ return 0;
+
+ /* Still no match - bad */
+ return -EFSCORRUPTED;
}
return 0;
}
@@ -3091,6 +3106,28 @@ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
return cpu_to_le32(hash);
}
+/*
+ * ext4_xattr_hash_entry_signed()
+ *
+ * Compute the hash of an extended attribute incorrectly.
+ */
+static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count)
+{
+ __u32 hash = 0;
+
+ while (name_len--) {
+ hash = (hash << NAME_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
+ (signed char)*name++;
+ }
+ while (value_count--) {
+ hash = (hash << VALUE_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+ le32_to_cpu(*value++);
+ }
+ return cpu_to_le32(hash);
+}
+
#undef NAME_HASH_SHIFT
#undef VALUE_HASH_SHIFT
--
GitLab
From 2241ab53cbb5cdb08a6b2d4688feb13971058f65 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 21 Jan 2023 16:27:01 -0800
Subject: [PATCH 1054/1167] Linux 6.2-rc5
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index 33a4e312b66de..c1ead4cd2342a 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
--
GitLab
From 95ecbd0f162fc06ef4c4045a66f653f47b62a2d3 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 19 Jan 2023 20:14:42 +0100
Subject: [PATCH 1055/1167] Revert "gfs2: stop using generic_writepages in
gfs2_ail1_start_one"
Commit b2b0a5e97855 switched from generic_writepages() to
filemap_fdatawrite_wbc() in gfs2_ail1_start_one() on the path to
replacing ->writepage() with ->writepages() and eventually eliminating
the former. Function gfs2_ail1_start_one() is called from
gfs2_log_flush(), our main function for flushing the filesystem log.
Unfortunately, at least as implemented today, ->writepage() and
->writepages() are entirely different operations for journaled data
inodes: while the former creates and submits transactions covering the
data to be written, the latter flushes dirty buffers out to disk.
With gfs2_ail1_start_one() now calling ->writepages(), we end up
creating filesystem transactions while we are in the course of a log
flush, which immediately deadlocks on the sdp->sd_log_flush_lock
semaphore.
Work around that by going back to how things used to work before commit
b2b0a5e97855 for now; figuring out a superior solution will take time we
don't have available right now. However ...
Since the removal of generic_writepages() is imminent, open-code it
here. We're already inside a blk_start_plug() ... blk_finish_plug()
section here, so skip that part of the original generic_writepages().
This reverts commit b2b0a5e978552e348f85ad9c7568b630a5ede659.
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
fs/gfs2/log.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 723639376ae2a..61323deb80bc7 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -80,6 +80,15 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
brelse(bd->bd_bh);
}
+static int __gfs2_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
+{
+ struct address_space *mapping = data;
+ int ret = mapping->a_ops->writepage(page, wbc);
+ mapping_set_error(mapping, ret);
+ return ret;
+}
+
/**
* gfs2_ail1_start_one - Start I/O on a transaction
* @sdp: The superblock
@@ -131,7 +140,7 @@ __acquires(&sdp->sd_ail_lock)
if (!mapping)
continue;
spin_unlock(&sdp->sd_ail_lock);
- ret = filemap_fdatawrite_wbc(mapping, wbc);
+ ret = write_cache_pages(mapping, wbc, __gfs2_writepage, mapping);
if (need_resched()) {
blk_finish_plug(plug);
cond_resched();
--
GitLab
From 50aa870ba2f7735f556e52d15f61cd0f359c4c0b Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sun, 22 Jan 2023 04:04:50 -0500
Subject: [PATCH 1056/1167] selftests: kvm: move declaration at the beginning
of main()
Placing a declaration of evt_reset is pedantically invalid
according to the C standard. While GCC does not really care
and only warns with -Wpedantic, clang ignores the declaration
altogether with an error:
x86_64/xen_shinfo_test.c:965:2: error: expected expression
struct kvm_xen_hvm_attr evt_reset = {
^
x86_64/xen_shinfo_test.c:969:38: error: use of undeclared identifier evt_reset
vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
^
Reported-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Reported-by: Sean Christopherson <seanjc@google.com>
Fixes: a79b53aaaab5 ("KVM: x86: fix deadlock for KVM_XEN_EVTCHN_RESET", 2022-12-28)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index dae510c263b45..13c75dc18c10b 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -434,6 +434,7 @@ static void *juggle_shinfo_state(void *arg)
int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
+ struct kvm_xen_hvm_attr evt_reset;
struct kvm_vm *vm;
pthread_t thread;
bool verbose;
@@ -962,10 +963,8 @@ int main(int argc, char *argv[])
}
done:
- struct kvm_xen_hvm_attr evt_reset = {
- .type = KVM_XEN_ATTR_TYPE_EVTCHN,
- .u.evtchn.flags = KVM_XEN_EVTCHN_RESET,
- };
+ evt_reset.type = KVM_XEN_ATTR_TYPE_EVTCHN;
+ evt_reset.u.evtchn.flags = KVM_XEN_EVTCHN_RESET;
vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
alarm(0);
--
GitLab
From a44b331614e6f7e63902ed7dff7adc8c85edd8bc Mon Sep 17 00:00:00 2001
From: Hendrik Borghorst <hborghor@amazon.de>
Date: Mon, 14 Nov 2022 16:48:23 +0000
Subject: [PATCH 1057/1167] KVM: x86/vmx: Do not skip segment attributes if
unusable bit is set
When serializing and deserializing kvm_sregs, attributes of the segment
descriptors are stored by user space. For unusable segments,
vmx_segment_access_rights skips all attributes and sets them to 0.
This means we zero out the DPL (Descriptor Privilege Level) for unusable
entries.
Unusable segments are - contrary to their name - usable in 64bit mode and
are used by guests to for example create a linear map through the
NULL selector.
VMENTER checks if SS.DPL is correct depending on the CS segment type.
For types 9 (Execute Only) and 11 (Execute Read), CS.DPL must be equal to
SS.DPL [1].
We have seen real world guests setting CS to a usable segment with DPL=3
and SS to an unusable segment with DPL=3. Once we go through an sregs
get/set cycle, SS.DPL turns to 0. This causes the virtual machine to crash
reproducibly.
This commit changes the attribute logic to always preserve attributes for
unusable segments. According to [2] SS.DPL is always saved on VM exits,
regardless of the unusable bit so user space applications should have saved
the information on serialization correctly.
[3] specifies that besides SS.DPL the rest of the attributes of the
descriptors are undefined after VM entry if unusable bit is set. So, there
should be no harm in setting them all to the previous state.
[1] Intel SDM Vol 3C 26.3.1.2 Checks on Guest Segment Registers
[2] Intel SDM Vol 3C 27.3.2 Saving Segment Registers and Descriptor-Table
Registers
[3] Intel SDM Vol 3C 26.3.2.2 Loading Guest Segment Registers and
Descriptor-Table Registers
Cc: Alexander Graf <graf@amazon.de>
Cc: stable@vger.kernel.org
Signed-off-by: Hendrik Borghorst <hborghor@amazon.de>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Alexander Graf <graf@amazon.com>
Message-Id: <20221114164823.69555-1-hborghor@amazon.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/vmx/vmx.c | 21 +++++++++------------
1 file changed, 9 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index fc9008dbed334..7eec0226d56a2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3440,18 +3440,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
u32 ar;
- if (var->unusable || !var->present)
- ar = 1 << 16;
- else {
- ar = var->type & 15;
- ar |= (var->s & 1) << 4;
- ar |= (var->dpl & 3) << 5;
- ar |= (var->present & 1) << 7;
- ar |= (var->avl & 1) << 12;
- ar |= (var->l & 1) << 13;
- ar |= (var->db & 1) << 14;
- ar |= (var->g & 1) << 15;
- }
+ ar = var->type & 15;
+ ar |= (var->s & 1) << 4;
+ ar |= (var->dpl & 3) << 5;
+ ar |= (var->present & 1) << 7;
+ ar |= (var->avl & 1) << 12;
+ ar |= (var->l & 1) << 13;
+ ar |= (var->db & 1) << 14;
+ ar |= (var->g & 1) << 15;
+ ar |= (var->unusable || !var->present) << 16;
return ar;
}
--
GitLab
From c2c46b10d52624376322b01654095a84611c7e09 Mon Sep 17 00:00:00 2001
From: Vipin Sharma <vipinsh@google.com>
Date: Wed, 11 Jan 2023 10:34:08 -0800
Subject: [PATCH 1058/1167] KVM: selftests: Make reclaim_period_ms input always
be positive
reclaim_period_ms used to be positive only but the commit 0001725d0f9b
("KVM: selftests: Add atoi_positive() and atoi_non_negative() for input
validation") incorrectly changed it to non-negative validation.
Change validation to allow only positive input.
Fixes: 0001725d0f9b ("KVM: selftests: Add atoi_positive() and atoi_non_negative() for input validation")
Signed-off-by: Vipin Sharma <vipinsh@google.com>
Reported-by: Ben Gardon <bgardon@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20230111183408.104491-1-vipinsh@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index ea0978f22db86..251794f837193 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -241,7 +241,7 @@ int main(int argc, char **argv)
while ((opt = getopt(argc, argv, "hp:t:r")) != -1) {
switch (opt) {
case 'p':
- reclaim_period_ms = atoi_non_negative("Reclaim period", optarg);
+ reclaim_period_ms = atoi_positive("Reclaim period", optarg);
break;
case 't':
token = atoi_paranoid(optarg);
--
GitLab
From 27b5de622ea3fe0ad5a31a0ebd9f7a0a276932d1 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 20 Jan 2023 09:58:27 -0700
Subject: [PATCH 1059/1167] x86/build: Move '-mindirect-branch-cs-prefix' out
of GCC-only block
LLVM 16 will have support for this flag so move it out of the GCC-only
block to allow LLVM builds to take advantage of it.
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://github.com/ClangBuiltLinux/linux/issues/1665
Link: https://github.com/llvm/llvm-project/commit/6f867f9102838ebe314c1f3661fdf95700386e5a
Link: https://lore.kernel.org/r/20230120165826.2469302-1-nathan@kernel.org
---
arch/x86/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 9cf07322875a4..73ed982d41000 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -14,13 +14,13 @@ endif
ifdef CONFIG_CC_IS_GCC
RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix)
RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
endif
ifdef CONFIG_CC_IS_CLANG
RETPOLINE_CFLAGS := -mretpoline-external-thunk
RETPOLINE_VDSO_CFLAGS := -mretpoline
endif
+RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix)
ifdef CONFIG_RETHUNK
RETHUNK_CFLAGS := -mfunction-return=thunk-extern
--
GitLab
From e38553bdc377e3e7a6caa9dd9770d8b644d8dac3 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 19 Jan 2023 12:37:47 +0800
Subject: [PATCH 1060/1167] net: fec: Use page_pool_put_full_page when freeing
rx buffers
The page_pool_release_page was used when freeing rx buffers, and this
function just unmaps the page (if mapped) and does not recycle the page.
So after hundreds of down/up the eth0, the system will out of memory.
For more details, please refer to the following reproduce steps and
bug logs. To solve this issue and refer to the doc of page pool, the
page_pool_put_full_page should be used to replace page_pool_release_page.
Because this API will try to recycle the page if the page refcnt equal to
1. After testing 20000 times, the issue can not be reproduced anymore
(about testing 391 times the issue will occur on i.MX8MN-EVK before).
Reproduce steps:
Create the test script and run the script. The script content is as
follows:
LOOPS=20000
i=1
while [ $i -le $LOOPS ]
do
echo "TINFO:ENET $curface up and down test $i times"
org_macaddr=$(cat /sys/class/net/eth0/address)
ifconfig eth0 down
ifconfig eth0 hw ether $org_macaddr up
i=$(expr $i + 1)
done
sleep 5
if cat /sys/class/net/eth0/operstate | grep 'up';then
echo "TEST PASS"
else
echo "TEST FAIL"
fi
Bug detail logs:
TINFO:ENET up and down test 391 times
[ 850.471205] Qualcomm Atheros AR8031/AR8033 30be0000.ethernet-1:00: attached PHY driver (mii_bus:phy_addr=30be0000.ethernet-1:00, irq=POLL)
[ 853.535318] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
[ 853.541694] fec 30be0000.ethernet eth0: Link is Up - 1Gbps/Full - flow control rx/tx
[ 870.590531] page_pool_release_retry() stalled pool shutdown 199 inflight 60 sec
[ 931.006557] page_pool_release_retry() stalled pool shutdown 199 inflight 120 sec
TINFO:ENET up and down test 392 times
[ 991.426544] page_pool_release_retry() stalled pool shutdown 192 inflight 181 sec
[ 1051.838531] page_pool_release_retry() stalled pool shutdown 170 inflight 241 sec
[ 1093.751217] Qualcomm Atheros AR8031/AR8033 30be0000.ethernet-1:00: attached PHY driver (mii_bus:phy_addr=30be0000.ethernet-1:00, irq=POLL)
[ 1096.446520] page_pool_release_retry() stalled pool shutdown 308 inflight 60 sec
[ 1096.831245] fec 30be0000.ethernet eth0: Link is Up - 1Gbps/Full - flow control rx/tx
[ 1096.839092] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
[ 1112.254526] page_pool_release_retry() stalled pool shutdown 103 inflight 302 sec
[ 1156.862533] page_pool_release_retry() stalled pool shutdown 308 inflight 120 sec
[ 1172.674516] page_pool_release_retry() stalled pool shutdown 103 inflight 362 sec
[ 1217.278532] page_pool_release_retry() stalled pool shutdown 308 inflight 181 sec
TINFO:ENET up and down test 393 times
[ 1233.086535] page_pool_release_retry() stalled pool shutdown 103 inflight 422 sec
[ 1277.698513] page_pool_release_retry() stalled pool shutdown 308 inflight 241 sec
[ 1293.502525] page_pool_release_retry() stalled pool shutdown 86 inflight 483 sec
[ 1338.110518] page_pool_release_retry() stalled pool shutdown 308 inflight 302 sec
[ 1353.918540] page_pool_release_retry() stalled pool shutdown 32 inflight 543 sec
[ 1361.179205] Qualcomm Atheros AR8031/AR8033 30be0000.ethernet-1:00: attached PHY driver (mii_bus:phy_addr=30be0000.ethernet-1:00, irq=POLL)
[ 1364.255298] fec 30be0000.ethernet eth0: Link is Up - 1Gbps/Full - flow control rx/tx
[ 1364.263189] IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
[ 1371.998532] page_pool_release_retry() stalled pool shutdown 310 inflight 60 sec
[ 1398.530542] page_pool_release_retry() stalled pool shutdown 308 inflight 362 sec
[ 1414.334539] page_pool_release_retry() stalled pool shutdown 16 inflight 604 sec
[ 1432.414520] page_pool_release_retry() stalled pool shutdown 310 inflight 120 sec
[ 1458.942523] page_pool_release_retry() stalled pool shutdown 308 inflight 422 sec
[ 1474.750521] page_pool_release_retry() stalled pool shutdown 16 inflight 664 sec
TINFO:ENET up and down test 394 times
[ 1492.830522] page_pool_release_retry() stalled pool shutdown 310 inflight 181 sec
[ 1519.358519] page_pool_release_retry() stalled pool shutdown 308 inflight 483 sec
[ 1535.166545] page_pool_release_retry() stalled pool shutdown 2 inflight 724 sec
[ 1537.090278] eth_test2.sh invoked oom-killer: gfp_mask=0x400dc0(GFP_KERNEL_ACCOUNT|__GFP_ZERO), order=0, oom_score_adj=0
[ 1537.101192] CPU: 3 PID: 2379 Comm: eth_test2.sh Tainted: G C 6.1.1+g56321e101aca #1
[ 1537.110249] Hardware name: NXP i.MX8MNano EVK board (DT)
[ 1537.115561] Call trace:
[ 1537.118005] dump_backtrace.part.0+0xe0/0xf0
[ 1537.122289] show_stack+0x18/0x40
[ 1537.125608] dump_stack_lvl+0x64/0x80
[ 1537.129276] dump_stack+0x18/0x34
[ 1537.132592] dump_header+0x44/0x208
[ 1537.136083] oom_kill_process+0x2b4/0x2c0
[ 1537.140097] out_of_memory+0xe4/0x594
[ 1537.143766] __alloc_pages+0xb68/0xd00
[ 1537.147521] alloc_pages+0xac/0x160
[ 1537.151013] __get_free_pages+0x14/0x40
[ 1537.154851] pgd_alloc+0x1c/0x30
[ 1537.158082] mm_init+0xf8/0x1d0
[ 1537.161228] mm_alloc+0x48/0x60
[ 1537.164368] alloc_bprm+0x7c/0x240
[ 1537.167777] do_execveat_common.isra.0+0x70/0x240
[ 1537.172486] __arm64_sys_execve+0x40/0x54
[ 1537.176502] invoke_syscall+0x48/0x114
[ 1537.180255] el0_svc_common.constprop.0+0xcc/0xec
[ 1537.184964] do_el0_svc+0x2c/0xd0
[ 1537.188280] el0_svc+0x2c/0x84
[ 1537.191340] el0t_64_sync_handler+0xf4/0x120
[ 1537.195613] el0t_64_sync+0x18c/0x190
[ 1537.199334] Mem-Info:
[ 1537.201620] active_anon:342 inactive_anon:10343 isolated_anon:0
[ 1537.201620] active_file:54 inactive_file:112 isolated_file:0
[ 1537.201620] unevictable:0 dirty:0 writeback:0
[ 1537.201620] slab_reclaimable:2620 slab_unreclaimable:7076
[ 1537.201620] mapped:1489 shmem:2473 pagetables:466
[ 1537.201620] sec_pagetables:0 bounce:0
[ 1537.201620] kernel_misc_reclaimable:0
[ 1537.201620] free:136672 free_pcp:96 free_cma:129241
[ 1537.240419] Node 0 active_anon:1368kB inactive_anon:41372kB active_file:216kB inactive_file:5052kB unevictable:0kB isolated(anon):0kB isolated(file):0kB s
[ 1537.271422] Node 0 DMA free:541636kB boost:0kB min:30000kB low:37500kB high:45000kB reserved_highatomic:0KB active_anon:1368kB inactive_anon:41372kB actiB
[ 1537.300219] lowmem_reserve[]: 0 0 0 0
[ 1537.303929] Node 0 DMA: 1015*4kB (UMEC) 743*8kB (UMEC) 417*16kB (UMEC) 235*32kB (UMEC) 116*64kB (UMEC) 25*128kB (UMEC) 4*256kB (UC) 2*512kB (UC) 0*1024kBB
[ 1537.323938] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=1048576kB
[ 1537.332708] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=32768kB
[ 1537.341292] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
[ 1537.349776] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=64kB
[ 1537.358087] 2939 total pagecache pages
[ 1537.361876] 0 pages in swap cache
[ 1537.365229] Free swap = 0kB
[ 1537.368147] Total swap = 0kB
[ 1537.371065] 516096 pages RAM
[ 1537.373959] 0 pages HighMem/MovableOnly
[ 1537.377834] 17302 pages reserved
[ 1537.381103] 163840 pages cma reserved
[ 1537.384809] 0 pages hwpoisoned
[ 1537.387902] Tasks state (memory values in pages):
[ 1537.392652] [ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name
[ 1537.401356] [ 201] 993 201 1130 72 45056 0 0 rpcbind
[ 1537.409772] [ 202] 0 202 4529 1640 77824 0 -250 systemd-journal
[ 1537.418861] [ 222] 0 222 4691 801 69632 0 -1000 systemd-udevd
[ 1537.427787] [ 248] 994 248 20914 130 65536 0 0 systemd-timesyn
[ 1537.436884] [ 497] 0 497 620 31 49152 0 0 atd
[ 1537.444938] [ 500] 0 500 854 77 53248 0 0 crond
[ 1537.453165] [ 503] 997 503 1470 160 49152 0 -900 dbus-daemon
[ 1537.461908] [ 505] 0 505 633 24 40960 0 0 firmwared
[ 1537.470491] [ 513] 0 513 2507 180 61440 0 0 ofonod
[ 1537.478800] [ 514] 990 514 69640 137 81920 0 0 parsec
[ 1537.487120] [ 533] 0 533 599 39 40960 0 0 syslogd
[ 1537.495518] [ 534] 0 534 4546 148 65536 0 0 systemd-logind
[ 1537.504560] [ 535] 0 535 690 24 45056 0 0 tee-supplicant
[ 1537.513564] [ 540] 996 540 2769 168 61440 0 0 systemd-network
[ 1537.522680] [ 566] 0 566 3878 228 77824 0 0 connmand
[ 1537.531168] [ 645] 998 645 1538 133 57344 0 0 avahi-daemon
[ 1537.540004] [ 646] 998 646 1461 64 57344 0 0 avahi-daemon
[ 1537.548846] [ 648] 992 648 781 41 45056 0 0 rpc.statd
[ 1537.557415] [ 650] 64371 650 590 23 45056 0 0 ninfod
[ 1537.565754] [ 653] 61563 653 555 24 45056 0 0 rdisc
[ 1537.573971] [ 655] 0 655 374569 2999 290816 0 -999 containerd
[ 1537.582621] [ 658] 0 658 1311 20 49152 0 0 agetty
[ 1537.590922] [ 663] 0 663 1529 97 49152 0 0 login
[ 1537.599138] [ 666] 0 666 3430 202 69632 0 0 wpa_supplicant
[ 1537.608147] [ 667] 0 667 2344 96 61440 0 0 systemd-userdbd
[ 1537.617240] [ 677] 0 677 2964 314 65536 0 100 systemd
[ 1537.625651] [ 679] 0 679 3720 646 73728 0 100 (sd-pam)
[ 1537.634138] [ 687] 0 687 1289 403 45056 0 0 sh
[ 1537.642108] [ 789] 0 789 970 93 45056 0 0 eth_test2.sh
[ 1537.650955] [ 2355] 0 2355 2346 94 61440 0 0 systemd-userwor
[ 1537.660046] [ 2356] 0 2356 2346 94 61440 0 0 systemd-userwor
[ 1537.669137] [ 2358] 0 2358 2346 95 57344 0 0 systemd-userwor
[ 1537.678258] [ 2379] 0 2379 970 93 45056 0 0 eth_test2.sh
[ 1537.687098] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0,global_oom,task_memcg=/user.slice/user-0.slice/user@0.service,tas0
[ 1537.703009] Out of memory: Killed process 679 ((sd-pam)) total-vm:14880kB, anon-rss:2584kB, file-rss:0kB, shmem-rss:0kB, UID:0 pgtables:72kB oom_score_ad0
[ 1553.246526] page_pool_release_retry() stalled pool shutdown 310 inflight 241 sec
Fixes: 95698ff6177b ("net: fec: using page pool to manage RX buffers")
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: shenwei wang <Shenwei.wang@nxp.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/freescale/fec_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 644f3c9637302..2341597408d12 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3191,7 +3191,7 @@ static void fec_enet_free_buffers(struct net_device *ndev)
for (q = 0; q < fep->num_rx_queues; q++) {
rxq = fep->rx_queue[q];
for (i = 0; i < rxq->bd.ring_size; i++)
- page_pool_release_page(rxq->page_pool, rxq->rx_skb_info[i].page);
+ page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false);
for (i = 0; i < XDP_STATS_TOTAL; i++)
rxq->stats[i] = 0;
--
GitLab
From 7c494a7749a7d6ee95cfae6a8c109c5d63103d88 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 19 Jan 2023 14:26:53 +0200
Subject: [PATCH 1061/1167] net: ethtool: netlink: introduce
ethnl_update_bool()
Due to the fact that the kernel-side data structures have been carried
over from the ioctl-based ethtool, we are now in the situation where we
have an ethnl_update_bool32() function, but the plain function that
operates on a boolean value kept in an actual u8 netlink attribute
doesn't exist.
With new ethtool features that are exposed solely over netlink, the
kernel data structures will use the "bool" type, so we will need this
kind of helper. Introduce it now; it's needed for things like
verify-disabled for the MAC merge configuration.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ethtool/netlink.h | 26 ++++++++++++++++++++++++++
1 file changed, 26 insertions(+)
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 3753787ba233b..744b3ab966b07 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -111,6 +111,32 @@ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr,
*mod = true;
}
+/**
+ * ethnl_update_bool() - update bool from NLA_U8 attribute
+ * @dst: value to update
+ * @attr: netlink attribute with new value or null
+ * @mod: pointer to bool for modification tracking
+ *
+ * Use the u8 value from NLA_U8 netlink attribute @attr to set bool variable
+ * pointed to by @dst to false (if zero) or 1 (if not); do nothing if @attr is
+ * null. Bool pointed to by @mod is set to true if this function changed the
+ * logical value of *dst, otherwise it is left as is.
+ */
+static inline void ethnl_update_bool(bool *dst, const struct nlattr *attr,
+ bool *mod)
+{
+ u8 val;
+
+ if (!attr)
+ return;
+ val = !!nla_get_u8(attr);
+ if (*dst == val)
+ return;
+
+ *dst = val;
+ *mod = true;
+}
+
/**
* ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute
* @dst: value to update
--
GitLab
From 9f535c870e493841ac7be390610ff2edec755762 Mon Sep 17 00:00:00 2001
From: Gergely Risko <gergely.risko@gmail.com>
Date: Thu, 19 Jan 2023 14:40:41 +0100
Subject: [PATCH 1062/1167] ipv6: fix reachability confirmation with proxy_ndp
When proxying IPv6 NDP requests, the adverts to the initial multicast
solicits are correct and working. On the other hand, when later a
reachability confirmation is requested (on unicast), no reply is sent.
This causes the neighbor entry expiring on the sending node, which is
mostly a non-issue, as a new multicast request is sent. There are
routers, where the multicast requests are intentionally delayed, and in
these environments the current implementation causes periodic packet
loss for the proxied endpoints.
The root cause is the erroneous decrease of the hop limit, as this
is checked in ndisc.c and no answer is generated when it's 254 instead
of the correct 255.
Cc: stable@vger.kernel.org
Fixes: 46c7655f0b56 ("ipv6: decrease hop limit counter in ip6_forward()")
Signed-off-by: Gergely Risko <gergely.risko@gmail.com>
Tested-by: Gergely Risko <gergely.risko@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/ip6_output.c | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 60fd91bb5171c..c314fdde0097c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -547,7 +547,20 @@ int ip6_forward(struct sk_buff *skb)
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0) {
- hdr->hop_limit--;
+ /* It's tempting to decrease the hop limit
+ * here by 1, as we do at the end of the
+ * function too.
+ *
+ * But that would be incorrect, as proxying is
+ * not forwarding. The ip6_input function
+ * will handle this packet locally, and it
+ * depends on the hop limit being unchanged.
+ *
+ * One example is the NDP hop limit, that
+ * always has to stay 255, but other would be
+ * similar checks around RA packets, where the
+ * user can even change the desired limit.
+ */
return ip6_input(skb);
} else if (proxied < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
--
GitLab
From b00c51ef8f72ced0965d021a291b98ff822c5337 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 22 Jan 2023 10:02:55 -0700
Subject: [PATCH 1063/1167] io_uring/net: cache provided buffer group value for
multishot receives
If we're using ring provided buffers with multishot receive, and we end
up doing an io-wq based issue at some points that also needs to select
a buffer, we'll lose the initially assigned buffer group as
io_ring_buffer_select() correctly clears the buffer group list as the
issue isn't serialized by the ctx uring_lock. This is fine for normal
receives as the request puts the buffer and finishes, but for multishot,
we will re-arm and do further receives. On the next trigger for this
multishot receive, the receive will try and pick from a buffer group
whose value is the same as the buffer ID of the las receive. That is
obviously incorrect, and will result in a premature -ENOUFS error for
the receive even if we had available buffers in the correct group.
Cache the buffer group value at prep time, so we can restore it for
future receives. This only needs doing for the above mentioned case, but
just do it by default to keep it easier to read.
Cc: stable@vger.kernel.org
Fixes: b3fdea6ecb55 ("io_uring: multishot recv")
Fixes: 9bb66906f23e ("io_uring: support multishot in recvmsg")
Cc: Dylan Yudaken <dylany@meta.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/net.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/io_uring/net.c b/io_uring/net.c
index fbc34a7c27439..90326b2799657 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -62,6 +62,7 @@ struct io_sr_msg {
u16 flags;
/* initialised and used only by !msg send variants */
u16 addr_len;
+ u16 buf_group;
void __user *addr;
/* used only for send zerocopy */
struct io_kiocb *notif;
@@ -580,6 +581,15 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (req->opcode == IORING_OP_RECV && sr->len)
return -EINVAL;
req->flags |= REQ_F_APOLL_MULTISHOT;
+ /*
+ * Store the buffer group for this multishot receive separately,
+ * as if we end up doing an io-wq based issue that selects a
+ * buffer, it has to be committed immediately and that will
+ * clear ->buf_list. This means we lose the link to the buffer
+ * list, and the eventual buffer put on completion then cannot
+ * restore it.
+ */
+ sr->buf_group = req->buf_index;
}
#ifdef CONFIG_COMPAT
@@ -596,6 +606,7 @@ static inline void io_recv_prep_retry(struct io_kiocb *req)
sr->done_io = 0;
sr->len = 0; /* get from the provided buffer */
+ req->buf_index = sr->buf_group;
}
/*
--
GitLab
From 2f62847cf6ae49a54515421f67b1badffaa805f3 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Wed, 18 Jan 2023 20:29:02 +0100
Subject: [PATCH 1064/1167] ARM: 9287/1: Reduce __thumb2__ definition to crypto
files that require it
Commit 1d2e9b67b001 ("ARM: 9265/1: pass -march= only to compiler") added
a __thumb2__ define to ASFLAGS to avoid build errors in the crypto code,
which relies on __thumb2__ for preprocessing. Commit 59e2cf8d21e0 ("ARM:
9275/1: Drop '-mthumb' from AFLAGS_ISA") followed up on this by removing
-mthumb from AFLAGS so that __thumb2__ would not be defined when the
default target was ARMv7 or newer.
Unfortunately, the second commit's fix assumes that the toolchain
defaults to -mno-thumb / -marm, which is not the case for Debian's
arm-linux-gnueabihf target, which defaults to -mthumb:
$ echo | arm-linux-gnueabihf-gcc -dM -E - | grep __thumb
#define __thumb2__ 1
#define __thumb__ 1
This target is used by several CI systems, which will still see
redefined macro warnings, despite '-mthumb' not being present in the
flags:
<command-line>: warning: "__thumb2__" redefined
<built-in>: note: this is the location of the previous definition
Remove the global AFLAGS __thumb2__ define and move it to the crypto
folder where it is required by the imported OpenSSL algorithms; the rest
of the kernel should use the internal CONFIG_THUMB2_KERNEL symbol to
know whether or not Thumb2 is being used or not. Be sure that __thumb2__
is undefined first so that there are no macro redefinition warnings.
Link: https://github.com/ClangBuiltLinux/linux/issues/1772
Reported-by: "kernelci.org bot" <bot@kernelci.org>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
Fixes: 59e2cf8d21e0 ("ARM: 9275/1: Drop '-mthumb' from AFLAGS_ISA")
Fixes: 1d2e9b67b001 ("ARM: 9265/1: pass -march= only to compiler")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
---
arch/arm/Makefile | 2 +-
arch/arm/crypto/Makefile | 7 ++++++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4067f51691442..955b0362cdfb7 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -132,7 +132,7 @@ AFLAGS_NOWARN :=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W)
ifeq ($(CONFIG_THUMB2_KERNEL),y)
CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN)
-AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2
+AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb
CFLAGS_ISA +=-mthumb
else
CFLAGS_ISA :=$(call cc-option,-marm,) $(AFLAGS_NOWARN)
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 971e74546fb1b..13e62c7c25dca 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -53,7 +53,12 @@ $(obj)/%-core.S: $(src)/%-armv4.pl
clean-files += poly1305-core.S sha256-core.S sha512-core.S
+aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1
+
+AFLAGS_sha256-core.o += $(aflags-thumb2-y)
+AFLAGS_sha512-core.o += $(aflags-thumb2-y)
+
# massage the perlasm code a bit so we only get the NEON routine if we need it
poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5
poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7
-AFLAGS_poly1305-core.o += $(poly1305-aflags-y)
+AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y)
--
GitLab
From 4bdbba54e9b1c769da8ded9abd209d765715e1d6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 20 Jan 2023 14:52:14 -0500
Subject: [PATCH 1065/1167] nfsd: don't free files unconditionally in
__nfsd_file_cache_purge
nfsd_file_cache_purge is called when the server is shutting down, in
which case, tearing things down is generally fine, but it also gets
called when the exports cache is flushed.
Instead of walking the cache and freeing everything unconditionally,
handle it the same as when we have a notification of conflicting access.
Fixes: ac3a2585f018 ("nfsd: rework refcounting in filecache")
Reported-by: Ruben Vestergaard <rubenv@drcmr.dk>
Reported-by: Torkil Svensgaard <torkil@drcmr.dk>
Reported-by: Shachar Kagan <skagan@nvidia.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Shachar Kagan <skagan@nvidia.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
fs/nfsd/filecache.c | 61 ++++++++++++++++++++++++++-------------------
1 file changed, 36 insertions(+), 25 deletions(-)
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 0ef0703490144..c0950edb26b0d 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -661,6 +661,39 @@ static struct shrinker nfsd_file_shrinker = {
.seeks = 1,
};
+/**
+ * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file
+ * @nf: nfsd_file to attempt to queue
+ * @dispose: private list to queue successfully-put objects
+ *
+ * Unhash an nfsd_file, try to get a reference to it, and then put that
+ * reference. If it's the last reference, queue it to the dispose list.
+ */
+static void
+nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
+ __must_hold(RCU)
+{
+ int decrement = 1;
+
+ /* If we raced with someone else unhashing, ignore it */
+ if (!nfsd_file_unhash(nf))
+ return;
+
+ /* If we can't get a reference, ignore it */
+ if (!nfsd_file_get(nf))
+ return;
+
+ /* Extra decrement if we remove from the LRU */
+ if (nfsd_file_lru_remove(nf))
+ ++decrement;
+
+ /* If refcount goes to 0, then put on the dispose list */
+ if (refcount_sub_and_test(decrement, &nf->nf_ref)) {
+ list_add(&nf->nf_lru, dispose);
+ trace_nfsd_file_closing(nf);
+ }
+}
+
/**
* nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode
* @inode: inode on which to close out nfsd_files
@@ -688,30 +721,11 @@ nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose)
rcu_read_lock();
do {
- int decrement = 1;
-
nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
nfsd_file_rhash_params);
if (!nf)
break;
-
- /* If we raced with someone else unhashing, ignore it */
- if (!nfsd_file_unhash(nf))
- continue;
-
- /* If we can't get a reference, ignore it */
- if (!nfsd_file_get(nf))
- continue;
-
- /* Extra decrement if we remove from the LRU */
- if (nfsd_file_lru_remove(nf))
- ++decrement;
-
- /* If refcount goes to 0, then put on the dispose list */
- if (refcount_sub_and_test(decrement, &nf->nf_ref)) {
- list_add(&nf->nf_lru, dispose);
- trace_nfsd_file_closing(nf);
- }
+ nfsd_file_cond_queue(nf, dispose);
} while (1);
rcu_read_unlock();
}
@@ -928,11 +942,8 @@ __nfsd_file_cache_purge(struct net *net)
nf = rhashtable_walk_next(&iter);
while (!IS_ERR_OR_NULL(nf)) {
- if (!net || nf->nf_net == net) {
- nfsd_file_unhash(nf);
- nfsd_file_lru_remove(nf);
- list_add(&nf->nf_lru, &dispose);
- }
+ if (!net || nf->nf_net == net)
+ nfsd_file_cond_queue(nf, &dispose);
nf = rhashtable_walk_next(&iter);
}
--
GitLab
From d63f11c02b8d3e54bdb65d8c309f73b7f474aec4 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sat, 21 Jan 2023 07:48:11 -0600
Subject: [PATCH 1066/1167] gpiolib-acpi: Don't set GPIOs for wakeup in S3 mode
commit 1796f808e4bb ("HID: i2c-hid: acpi: Stop setting wakeup_capable")
adjusted the policy to enable wakeup by default if the ACPI tables
indicated that a device was wake capable.
It was reported however that this broke suspend on at least two System76
systems in S3 mode and two Lenovo Gen2a systems, but only with S3.
When the machines are set to s2idle, wakeup behaves properly.
Configuring the GPIOs for wakeup with S3 doesn't work properly, so only
set it when the system supports low power idle.
Fixes: 1796f808e4bb ("HID: i2c-hid: acpi: Stop setting wakeup_capable")
Fixes: b38f2d5d9615c ("i2c: acpi: Use ACPI wake capability bit to set wake_irq")
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2357
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2162013
Reported-by: Nathan Smythe <ncsmythe@scruboak.org>
Tested-by: Nathan Smythe <ncsmythe@scruboak.org>
Suggested-by: Raul Rangel <rrangel@chromium.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpiolib-acpi.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index 9ef0f5641b521..17c53f484280f 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1104,7 +1104,8 @@ int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, in
dev_dbg(&adev->dev, "IRQ %d already in use\n", irq);
}
- if (wake_capable)
+ /* avoid suspend issues with GPIOs when systems are using S3 */
+ if (wake_capable && acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)
*wake_capable = info.wake_capable;
return irq;
--
GitLab
From 98e3528012cd571c48bbae7c7c0f868823254b6c Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Fri, 20 Jan 2023 17:43:54 +0000
Subject: [PATCH 1067/1167] nvme-fc: fix initialization order
ctrl->ops is used by nvme_alloc_admin_tag_set() but set by
nvme_init_ctrl() so reorder the calls to avoid a NULL pointer
dereference.
Fixes: 6dfba1c09c10 ("nvme-fc: use the tagset alloc/free helpers")
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/fc.c | 18 ++++++++----------
1 file changed, 8 insertions(+), 10 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 4564f16a0b203..456ee42a61334 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3521,13 +3521,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
nvme_fc_init_queue(ctrl, 0);
- ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
- &nvme_fc_admin_mq_ops,
- struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
- ctrl->lport->ops->fcprqst_priv_sz));
- if (ret)
- goto out_free_queues;
-
/*
* Would have been nice to init io queues tag set as well.
* However, we require interaction from the controller
@@ -3537,10 +3530,17 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
if (ret)
- goto out_cleanup_tagset;
+ goto out_free_queues;
/* at this point, teardown path changes to ref counting on nvme ctrl */
+ ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set,
+ &nvme_fc_admin_mq_ops,
+ struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
+ ctrl->lport->ops->fcprqst_priv_sz));
+ if (ret)
+ goto fail_ctrl;
+
spin_lock_irqsave(&rport->lock, flags);
list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
spin_unlock_irqrestore(&rport->lock, flags);
@@ -3592,8 +3592,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
return ERR_PTR(-EIO);
-out_cleanup_tagset:
- nvme_remove_admin_tag_set(&ctrl->ctrl);
out_free_queues:
kfree(ctrl->queues);
out_free_ida:
--
GitLab
From 75444cfffc12459273be70a56460035fb4c553f3 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 18 Jan 2023 17:52:39 -0800
Subject: [PATCH 1068/1167] drm/i915/mtl: Fix bcs default context
Commit 0d0e7d1eea9e ("drm/i915/mtl: Define engine context layouts")
added the engine context for Meteor Lake. In a second revision of the
patch it was believed the xcs offsets were wrong due to a tagging
issue in the spec. The first version was actually correct, as shown
by the intel_lrc_live_selftests/live_lrc_layout test:
i915: Running gt_lrc
i915: Running intel_lrc_live_selftests/live_lrc_layout
bcs0: LRI command mismatch at dword 1, expected 1108101d found 11081019
[drm:drm_helper_probe_single_connector_modes [drm_kms_helper]] [CONNECTOR:236:DP-1] disconnected
bcs0: HW register image:
[0000] 00000000 1108101d 00022244 ffff0008 00022034 00000088 00022030 00000088
...
bcs0: SW register image:
[0000] 00000000 11081019 00022244 00090009 00022034 00000000 00022030 00000000
The difference in the 2 additional dwords (0x1d vs 0x19) are the offsets
0x120 / 0x124 that are indeed part of the context image.
Bspec: 45585
Fixes: 0d0e7d1eea9e ("drm/i915/mtl: Define engine context layouts")
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230111235531.3353815-2-radhakrishna.sripada@intel.com
(cherry picked from commit ca54a9a32da0f0ef7e5cbcd111b66f3c9d78b7d2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/gt/intel_lrc.c | 37 +----------------------------
1 file changed, 1 insertion(+), 36 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7771a19008c60..bbeeb6dde7aee 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = {
END
};
-static const u8 mtl_xcs_offsets[] = {
- NOP(1),
- LRI(13, POSTED),
- REG16(0x244),
- REG(0x034),
- REG(0x030),
- REG(0x038),
- REG(0x03c),
- REG(0x168),
- REG(0x140),
- REG(0x110),
- REG(0x1c0),
- REG(0x1c4),
- REG(0x1c8),
- REG(0x180),
- REG16(0x2b4),
- NOP(4),
-
- NOP(1),
- LRI(9, POSTED),
- REG16(0x3a8),
- REG16(0x28c),
- REG16(0x288),
- REG16(0x284),
- REG16(0x280),
- REG16(0x27c),
- REG16(0x278),
- REG16(0x274),
- REG16(0x270),
-
- END
-};
-
static const u8 gen8_rcs_offsets[] = {
NOP(1),
LRI(14, POSTED),
@@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
else
return gen8_rcs_offsets;
} else {
- if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
- return mtl_xcs_offsets;
- else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+ if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
return dg2_xcs_offsets;
else if (GRAPHICS_VER(engine->i915) >= 12)
return gen12_xcs_offsets;
--
GitLab
From 2255bbcdc39d5b0311968f86614ae4f25fdd465d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jan 2023 17:37:29 +0100
Subject: [PATCH 1069/1167] drm/i915/selftest: fix intel_selftest_modify_policy
argument types
The definition of intel_selftest_modify_policy() does not match the
declaration, as gcc-13 points out:
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c:29:5: error: conflicting types for 'intel_selftest_modify_policy' due to enum/integer mismatch; have 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, u32)' {aka 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, unsigned int)'} [-Werror=enum-int-mismatch]
29 | int intel_selftest_modify_policy(struct intel_engine_cs *engine,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c:11:
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h:28:5: note: previous declaration of 'intel_selftest_modify_policy' with type 'int(struct intel_engine_cs *, struct intel_selftest_saved_policy *, enum selftest_scheduler_modify)'
28 | int intel_selftest_modify_policy(struct intel_engine_cs *engine,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
Change the type in the definition to match.
Fixes: 617e87c05c72 ("drm/i915/selftest: Fix hangcheck self test for GuC submission")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230117163743.1003219-1-arnd@kernel.org
(cherry picked from commit 8d7eb8ed3f83f248e01a4f548d9c500a950a2c2d)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 310fb83c527eb..2990dd4d4a0d8 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -28,8 +28,7 @@ struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt)
int intel_selftest_modify_policy(struct intel_engine_cs *engine,
struct intel_selftest_saved_policy *saved,
- u32 modify_type)
-
+ enum selftest_scheduler_modify modify_type)
{
int err;
--
GitLab
From d77596d432cc4142520af32b5388d512e52e0edb Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 19 Jan 2023 17:37:43 +0100
Subject: [PATCH 1070/1167] ACPI: video: Add backlight=native DMI quirk for HP
Pavilion g6-1d80nr
The HP Pavilion g6-1d80nr predates Windows 8, so it defaults to using
acpi_video# for backlight control, but this is non functional on
this model.
Add a DMI quirk to use the native backlight interface which does
work properly.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/video_detect.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 65cec7bb6d961..447d792781e29 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -618,6 +618,15 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "UX303UB"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* HP Pavilion g6-1d80nr / B4U19UA */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"),
+ DMI_MATCH(DMI_PRODUCT_SKU, "B4U19UA"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Samsung N150P */
--
GitLab
From 9dcb34234b8235144c96103266317da33321077e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 19 Jan 2023 17:37:44 +0100
Subject: [PATCH 1071/1167] ACPI: video: Add backlight=native DMI quirk for HP
EliteBook 8460p
The HP EliteBook 8460p predates Windows 8, so it defaults to using
acpi_video# for backlight control.
Starting with the 6.1.y kernels the native radeon_bl0 backlight is hidden
in this case instead of relying on userspace preferring acpi_video# over
native backlight devices.
It turns out that for the acpi_video# interface to work on
the HP EliteBook 8460p, the brightness needs to be set at least once
through the native interface, which now no longer is done breaking
backlight control.
The native interface however always works without problems, so add
a quirk to use native backlight on the EliteBook 8460p to fix this.
Fixes: fb1836c91317 ("ACPI: video: Prefer native over vendor")
Link: https://bugzilla.redhat.com/show_bug.cgi?id=2161428
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/video_detect.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 447d792781e29..aa6196e5e574c 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -618,6 +618,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "UX303UB"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* HP EliteBook 8460p */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8460p"),
+ },
+ },
{
.callback = video_detect_force_native,
/* HP Pavilion g6-1d80nr / B4U19UA */
--
GitLab
From e6b3086fddc0065a5ffb947d4d29dd0e6efc327b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 19 Jan 2023 18:24:41 +0100
Subject: [PATCH 1072/1167] ACPI: video: Add backlight=native DMI quirk for
Asus U46E
The Asus U46E backlight tables have a set of interesting problems:
1. Its ACPI tables do make _OSI ("Windows 2012") checks, so
acpi_osi_is_win8() should return true.
But the tables have 2 sets of _OSI calls, one from the usual global
_INI method setting a global OSYS variable and a second set of _OSI
calls from a MSOS method and the MSOS method is the only one calling
_OSI ("Windows 2012").
The MSOS method only gets called in the following cases:
1. From some Asus specific WMI methods
2. From _DOD, which only runs after acpi_video_get_backlight_type()
has already been called by the i915 driver
3. From other ACPI video bus methods which never run (see below)
4. From some EC query callbacks
So when i915 calls acpi_video_get_backlight_type() MSOS has never run
and acpi_osi_is_win8() returns false, so acpi_video_get_backlight_type()
returns acpi_video as the desired backlight type, which causes
the intel_backlight device to not register.
2. _DOD effectively does this:
Return (Package (0x01)
{
0x0400
})
causing acpi_video_device_in_dod() to return false, which causes
the acpi_video backlight device to not register.
Leaving the user with no backlight device at all. Note that before 6.1.y
the i915 driver would register the intel_backlight device unconditionally
and since that then was the only backlight device userspace would use that.
Add a backlight=native DMI quirk for this special laptop to restore
the old (and working) behavior of the intel_backlight device registering.
Fixes: fb1836c91317 ("ACPI: video: Prefer native over vendor")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
drivers/acpi/video_detect.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index aa6196e5e574c..64eab35037c3a 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -610,6 +610,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "GA503"),
},
},
+ {
+ .callback = video_detect_force_native,
+ /* Asus U46E */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "U46E"),
+ },
+ },
{
.callback = video_detect_force_native,
/* Asus UX303UB */
--
GitLab
From c9e6978e2725a7d4b6cd23b2facd3f11422c0643 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 14 Jan 2023 23:38:32 +0100
Subject: [PATCH 1073/1167] netfilter: nft_set_rbtree: Switch to node list walk
for overlap detection
...instead of a tree descent, which became overly complicated in an
attempt to cover cases where expired or inactive elements would affect
comparisons with the new element being inserted.
Further, it turned out that it's probably impossible to cover all those
cases, as inactive nodes might entirely hide subtrees consisting of a
complete interval plus a node that makes the current insertion not
overlap.
To speed up the overlap check, descent the tree to find a greater
element that is closer to the key value to insert. Then walk down the
node list for overlap detection. Starting the overlap check from
rb_first() unconditionally is slow, it takes 10 times longer due to the
full linear traversal of the list.
Moreover, perform garbage collection of expired elements when walking
down the node list to avoid bogus overlap reports.
For the insertion operation itself, this essentially reverts back to the
implementation before commit 7c84d41416d8 ("netfilter: nft_set_rbtree:
Detect partial overlaps on insertion"), except that cases of complete
overlap are already handled in the overlap detection phase itself, which
slightly simplifies the loop to find the insertion point.
Based on initial patch from Stefano Brivio, including text from the
original patch description too.
Fixes: 7c84d41416d8 ("netfilter: nft_set_rbtree: Detect partial overlaps on insertion")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_rbtree.c | 316 ++++++++++++++++++++-------------
1 file changed, 189 insertions(+), 127 deletions(-)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 7325bee7d1442..217225e13faf7 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe)
return !nft_rbtree_interval_end(rbe);
}
-static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
- const struct nft_rbtree_elem *interval)
+static int nft_rbtree_cmp(const struct nft_set *set,
+ const struct nft_rbtree_elem *e1,
+ const struct nft_rbtree_elem *e2)
{
- return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0;
+ return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext),
+ set->klen);
}
static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
@@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
const struct nft_rbtree_elem *rbe, *interval = NULL;
u8 genmask = nft_genmask_cur(net);
const struct rb_node *parent;
- const void *this;
int d;
parent = rcu_dereference_raw(priv->root.rb_node);
@@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- this = nft_set_ext_key(&rbe->ext);
- d = memcmp(this, key, set->klen);
+ d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen);
if (d < 0) {
parent = rcu_dereference_raw(parent->rb_left);
if (interval &&
- nft_rbtree_equal(set, this, interval) &&
+ !nft_rbtree_cmp(set, rbe, interval) &&
nft_rbtree_interval_end(rbe) &&
nft_rbtree_interval_start(interval))
continue;
@@ -215,154 +215,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set,
return rbe;
}
+static int nft_rbtree_gc_elem(const struct nft_set *__set,
+ struct nft_rbtree *priv,
+ struct nft_rbtree_elem *rbe)
+{
+ struct nft_set *set = (struct nft_set *)__set;
+ struct rb_node *prev = rb_prev(&rbe->node);
+ struct nft_rbtree_elem *rbe_prev;
+ struct nft_set_gc_batch *gcb;
+
+ gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC);
+ if (!gcb)
+ return -ENOMEM;
+
+ /* search for expired end interval coming before this element. */
+ do {
+ rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node);
+ if (nft_rbtree_interval_end(rbe_prev))
+ break;
+
+ prev = rb_prev(prev);
+ } while (prev != NULL);
+
+ rb_erase(&rbe_prev->node, &priv->root);
+ rb_erase(&rbe->node, &priv->root);
+ atomic_sub(2, &set->nelems);
+
+ nft_set_gc_batch_add(gcb, rbe);
+ nft_set_gc_batch_complete(gcb);
+
+ return 0;
+}
+
+static bool nft_rbtree_update_first(const struct nft_set *set,
+ struct nft_rbtree_elem *rbe,
+ struct rb_node *first)
+{
+ struct nft_rbtree_elem *first_elem;
+
+ first_elem = rb_entry(first, struct nft_rbtree_elem, node);
+ /* this element is closest to where the new element is to be inserted:
+ * update the first element for the node list path.
+ */
+ if (nft_rbtree_cmp(set, rbe, first_elem) < 0)
+ return true;
+
+ return false;
+}
+
static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *new,
struct nft_set_ext **ext)
{
- bool overlap = false, dup_end_left = false, dup_end_right = false;
+ struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
+ struct rb_node *node, *parent, **p, *first = NULL;
struct nft_rbtree *priv = nft_set_priv(set);
u8 genmask = nft_genmask_next(net);
- struct nft_rbtree_elem *rbe;
- struct rb_node *parent, **p;
- int d;
+ int d, err;
- /* Detect overlaps as we descend the tree. Set the flag in these cases:
- *
- * a1. _ _ __>| ?_ _ __| (insert end before existing end)
- * a2. _ _ ___| ?_ _ _>| (insert end after existing end)
- * a3. _ _ ___? >|_ _ __| (insert start before existing end)
- *
- * and clear it later on, as we eventually reach the points indicated by
- * '?' above, in the cases described below. We'll always meet these
- * later, locally, due to tree ordering, and overlaps for the intervals
- * that are the closest together are always evaluated last.
- *
- * b1. _ _ __>| !_ _ __| (insert end before existing start)
- * b2. _ _ ___| !_ _ _>| (insert end after existing start)
- * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf)
- * '--' no nodes falling in this range
- * b4. >|_ _ ! (insert start before existing start)
- *
- * Case a3. resolves to b3.:
- * - if the inserted start element is the leftmost, because the '0'
- * element in the tree serves as end element
- * - otherwise, if an existing end is found immediately to the left. If
- * there are existing nodes in between, we need to further descend the
- * tree before we can conclude the new start isn't causing an overlap
- *
- * or to b4., which, preceded by a3., means we already traversed one or
- * more existing intervals entirely, from the right.
- *
- * For a new, rightmost pair of elements, we'll hit cases b3. and b2.,
- * in that order.
- *
- * The flag is also cleared in two special cases:
- *
- * b5. |__ _ _!|<_ _ _ (insert start right before existing end)
- * b6. |__ _ >|!__ _ _ (insert end right after existing start)
- *
- * which always happen as last step and imply that no further
- * overlapping is possible.
- *
- * Another special case comes from the fact that start elements matching
- * an already existing start element are allowed: insertion is not
- * performed but we return -EEXIST in that case, and the error will be
- * cleared by the caller if NLM_F_EXCL is not present in the request.
- * This way, request for insertion of an exact overlap isn't reported as
- * error to userspace if not desired.
- *
- * However, if the existing start matches a pre-existing start, but the
- * end element doesn't match the corresponding pre-existing end element,
- * we need to report a partial overlap. This is a local condition that
- * can be noticed without need for a tracking flag, by checking for a
- * local duplicated end for a corresponding start, from left and right,
- * separately.
+ /* Descend the tree to search for an existing element greater than the
+ * key value to insert that is greater than the new element. This is the
+ * first element to walk the ordered elements to find possible overlap.
*/
-
parent = NULL;
p = &priv->root.rb_node;
while (*p != NULL) {
parent = *p;
rbe = rb_entry(parent, struct nft_rbtree_elem, node);
- d = memcmp(nft_set_ext_key(&rbe->ext),
- nft_set_ext_key(&new->ext),
- set->klen);
+ d = nft_rbtree_cmp(set, rbe, new);
+
if (d < 0) {
p = &parent->rb_left;
-
- if (nft_rbtree_interval_start(new)) {
- if (nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext) && !*p)
- overlap = false;
- } else {
- if (dup_end_left && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_right = true;
- continue;
- }
- }
} else if (d > 0) {
- p = &parent->rb_right;
+ if (!first ||
+ nft_rbtree_update_first(set, rbe, first))
+ first = &rbe->node;
- if (nft_rbtree_interval_end(new)) {
- if (dup_end_right && !*p)
- return -ENOTEMPTY;
-
- overlap = nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext,
- genmask) &&
- !nft_set_elem_expired(&rbe->ext);
-
- if (overlap) {
- dup_end_left = true;
- continue;
- }
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- overlap = nft_rbtree_interval_end(rbe);
- }
+ p = &parent->rb_right;
} else {
- if (nft_rbtree_interval_end(rbe) &&
- nft_rbtree_interval_start(new)) {
+ if (nft_rbtree_interval_end(rbe))
p = &parent->rb_left;
-
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_rbtree_interval_start(rbe) &&
- nft_rbtree_interval_end(new)) {
+ else
p = &parent->rb_right;
+ }
+ }
+
+ if (!first)
+ first = rb_first(&priv->root);
+
+ /* Detect overlap by going through the list of valid tree nodes.
+ * Values stored in the tree are in reversed order, starting from
+ * highest to lowest value.
+ */
+ for (node = first; node != NULL; node = rb_next(node)) {
+ rbe = rb_entry(node, struct nft_rbtree_elem, node);
+
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
- if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext))
- overlap = false;
- } else if (nft_set_elem_active(&rbe->ext, genmask) &&
- !nft_set_elem_expired(&rbe->ext)) {
- *ext = &rbe->ext;
- return -EEXIST;
- } else {
- overlap = false;
- if (nft_rbtree_interval_end(rbe))
- p = &parent->rb_left;
- else
- p = &parent->rb_right;
+ /* perform garbage collection to avoid bogus overlap reports. */
+ if (nft_set_elem_expired(&rbe->ext)) {
+ err = nft_rbtree_gc_elem(set, priv, rbe);
+ if (err < 0)
+ return err;
+
+ continue;
+ }
+
+ d = nft_rbtree_cmp(set, rbe, new);
+ if (d == 0) {
+ /* Matching end element: no need to look for an
+ * overlapping greater or equal element.
+ */
+ if (nft_rbtree_interval_end(rbe)) {
+ rbe_le = rbe;
+ break;
+ }
+
+ /* first element that is greater or equal to key value. */
+ if (!rbe_ge) {
+ rbe_ge = rbe;
+ continue;
+ }
+
+ /* this is a closer more or equal element, update it. */
+ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) {
+ rbe_ge = rbe;
+ continue;
}
+
+ /* element is equal to key value, make sure flags are
+ * the same, an existing more or equal start element
+ * must not be replaced by more or equal end element.
+ */
+ if ((nft_rbtree_interval_start(new) &&
+ nft_rbtree_interval_start(rbe_ge)) ||
+ (nft_rbtree_interval_end(new) &&
+ nft_rbtree_interval_end(rbe_ge))) {
+ rbe_ge = rbe;
+ continue;
+ }
+ } else if (d > 0) {
+ /* annotate element greater than the new element. */
+ rbe_ge = rbe;
+ continue;
+ } else if (d < 0) {
+ /* annotate element less than the new element. */
+ rbe_le = rbe;
+ break;
}
+ }
- dup_end_left = dup_end_right = false;
+ /* - new start element matching existing start element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) &&
+ nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) {
+ *ext = &rbe_ge->ext;
+ return -EEXIST;
+ }
+
+ /* - new end element matching existing end element: full overlap
+ * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given.
+ */
+ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) &&
+ nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) {
+ *ext = &rbe_le->ext;
+ return -EEXIST;
}
- if (overlap)
+ /* - new start element with existing closest, less or equal key value
+ * being a start element: partial overlap, reported as -ENOTEMPTY.
+ * Anonymous sets allow for two consecutive start element since they
+ * are constant, skip them to avoid bogus overlap reports.
+ */
+ if (!nft_set_is_anonymous(set) && rbe_le &&
+ nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new))
+ return -ENOTEMPTY;
+
+ /* - new end element with existing closest, less or equal key value
+ * being a end element: partial overlap, reported as -ENOTEMPTY.
+ */
+ if (rbe_le &&
+ nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new))
return -ENOTEMPTY;
+ /* - new end element with existing closest, greater or equal key value
+ * being an end element: partial overlap, reported as -ENOTEMPTY
+ */
+ if (rbe_ge &&
+ nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new))
+ return -ENOTEMPTY;
+
+ /* Accepted element: pick insertion point depending on key value */
+ parent = NULL;
+ p = &priv->root.rb_node;
+ while (*p != NULL) {
+ parent = *p;
+ rbe = rb_entry(parent, struct nft_rbtree_elem, node);
+ d = nft_rbtree_cmp(set, rbe, new);
+
+ if (d < 0)
+ p = &parent->rb_left;
+ else if (d > 0)
+ p = &parent->rb_right;
+ else if (nft_rbtree_interval_end(rbe))
+ p = &parent->rb_left;
+ else
+ p = &parent->rb_right;
+ }
+
rb_link_node_rcu(&new->node, parent, p);
rb_insert_color(&new->node, &priv->root);
return 0;
--
GitLab
From 5d235d6ce75c12a7fdee375eb211e4116f7ab01b Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 14 Jan 2023 23:49:46 +0100
Subject: [PATCH 1074/1167] netfilter: nft_set_rbtree: skip elements in
transaction from garbage collection
Skip interference with an ongoing transaction, do not perform garbage
collection on inactive elements. Reset annotated previous end interval
if the expired element is marked as busy (control plane removed the
element right before expiration).
Fixes: 8d8540c4f5e0 ("netfilter: nft_set_rbtree: add timeout support")
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_set_rbtree.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 217225e13faf7..19ea4d3c35535 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -563,23 +563,37 @@ static void nft_rbtree_gc(struct work_struct *work)
struct nft_rbtree *priv;
struct rb_node *node;
struct nft_set *set;
+ struct net *net;
+ u8 genmask;
priv = container_of(work, struct nft_rbtree, gc_work.work);
set = nft_set_container_of(priv);
+ net = read_pnet(&set->net);
+ genmask = nft_genmask_cur(net);
write_lock_bh(&priv->lock);
write_seqcount_begin(&priv->count);
for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
rbe = rb_entry(node, struct nft_rbtree_elem, node);
+ if (!nft_set_elem_active(&rbe->ext, genmask))
+ continue;
+
+ /* elements are reversed in the rbtree for historical reasons,
+ * from highest to lowest value, that is why end element is
+ * always visited before the start element.
+ */
if (nft_rbtree_interval_end(rbe)) {
rbe_end = rbe;
continue;
}
if (!nft_set_elem_expired(&rbe->ext))
continue;
- if (nft_set_elem_mark_busy(&rbe->ext))
+
+ if (nft_set_elem_mark_busy(&rbe->ext)) {
+ rbe_end = NULL;
continue;
+ }
if (rbe_prev) {
rb_erase(&rbe_prev->node, &priv->root);
--
GitLab
From c1bb9484e3b05166880da8574504156ccbd0549e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jan 2023 12:59:53 +0000
Subject: [PATCH 1075/1167] netlink: annotate data races around nlk->portid
syzbot reminds us netlink_getname() runs locklessly [1]
This first patch annotates the race against nlk->portid.
Following patches take care of the remaining races.
[1]
BUG: KCSAN: data-race in netlink_getname / netlink_insert
write to 0xffff88814176d310 of 4 bytes by task 2315 on cpu 1:
netlink_insert+0xf1/0x9a0 net/netlink/af_netlink.c:583
netlink_autobind+0xae/0x180 net/netlink/af_netlink.c:856
netlink_sendmsg+0x444/0x760 net/netlink/af_netlink.c:1895
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg net/socket.c:734 [inline]
____sys_sendmsg+0x38f/0x500 net/socket.c:2476
___sys_sendmsg net/socket.c:2530 [inline]
__sys_sendmsg+0x19a/0x230 net/socket.c:2559
__do_sys_sendmsg net/socket.c:2568 [inline]
__se_sys_sendmsg net/socket.c:2566 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2566
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
read to 0xffff88814176d310 of 4 bytes by task 2316 on cpu 0:
netlink_getname+0xcd/0x1a0 net/netlink/af_netlink.c:1144
__sys_getsockname+0x11d/0x1b0 net/socket.c:2026
__do_sys_getsockname net/socket.c:2041 [inline]
__se_sys_getsockname net/socket.c:2038 [inline]
__x64_sys_getsockname+0x3e/0x50 net/socket.c:2038
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0x00000000 -> 0xc9a49780
Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 2316 Comm: syz-executor.2 Not tainted 6.2.0-rc3-syzkaller-00030-ge8f60cd7db24-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/netlink/af_netlink.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bca2a470ccad5..4aea89f7d700a 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -580,7 +580,9 @@ static int netlink_insert(struct sock *sk, u32 portid)
if (nlk_sk(sk)->bound)
goto err;
- nlk_sk(sk)->portid = portid;
+ /* portid can be read locklessly from netlink_getname(). */
+ WRITE_ONCE(nlk_sk(sk)->portid, portid);
+
sock_hold(sk);
err = __netlink_insert(table, sk);
@@ -1141,7 +1143,8 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
nladdr->nl_pid = nlk->dst_portid;
nladdr->nl_groups = netlink_group_mask(nlk->dst_group);
} else {
- nladdr->nl_pid = nlk->portid;
+ /* Paired with WRITE_ONCE() in netlink_insert() */
+ nladdr->nl_pid = READ_ONCE(nlk->portid);
netlink_lock_table();
nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0;
netlink_unlock_table();
--
GitLab
From 004db64d185a5f23dfb891d7701e23713b2420ee Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jan 2023 12:59:54 +0000
Subject: [PATCH 1076/1167] netlink: annotate data races around dst_portid and
dst_group
netlink_getname(), netlink_sendmsg() and netlink_getsockbyportid()
can read nlk->dst_portid and nlk->dst_group while another
thread is changing them.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/netlink/af_netlink.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 4aea89f7d700a..b5b8c6a5fc342 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1099,8 +1099,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
if (addr->sa_family == AF_UNSPEC) {
sk->sk_state = NETLINK_UNCONNECTED;
- nlk->dst_portid = 0;
- nlk->dst_group = 0;
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, 0);
+ WRITE_ONCE(nlk->dst_group, 0);
return 0;
}
if (addr->sa_family != AF_NETLINK)
@@ -1122,8 +1123,9 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
if (err == 0) {
sk->sk_state = NETLINK_CONNECTED;
- nlk->dst_portid = nladdr->nl_pid;
- nlk->dst_group = ffs(nladdr->nl_groups);
+ /* dst_portid and dst_group can be read locklessly */
+ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid);
+ WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups));
}
return err;
@@ -1140,8 +1142,9 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
nladdr->nl_pad = 0;
if (peer) {
- nladdr->nl_pid = nlk->dst_portid;
- nladdr->nl_groups = netlink_group_mask(nlk->dst_group);
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ nladdr->nl_pid = READ_ONCE(nlk->dst_portid);
+ nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group));
} else {
/* Paired with WRITE_ONCE() in netlink_insert() */
nladdr->nl_pid = READ_ONCE(nlk->portid);
@@ -1171,8 +1174,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
+ /* dst_portid can be changed in netlink_connect() */
if (sock->sk_state == NETLINK_CONNECTED &&
- nlk->dst_portid != nlk_sk(ssk)->portid) {
+ READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
}
@@ -1889,8 +1893,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
goto out;
netlink_skb_flags |= NETLINK_SKB_DST;
} else {
- dst_portid = nlk->dst_portid;
- dst_group = nlk->dst_group;
+ /* Paired with WRITE_ONCE() in netlink_connect() */
+ dst_portid = READ_ONCE(nlk->dst_portid);
+ dst_group = READ_ONCE(nlk->dst_group);
}
/* Paired with WRITE_ONCE() in netlink_insert() */
--
GitLab
From 9b663b5cbb15b494ef132a3c937641c90646eb73 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jan 2023 12:59:55 +0000
Subject: [PATCH 1077/1167] netlink: annotate data races around sk_state
netlink_getsockbyportid() reads sk_state while a concurrent
netlink_connect() can change its value.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/netlink/af_netlink.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index b5b8c6a5fc342..c642776597531 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1098,7 +1098,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
return -EINVAL;
if (addr->sa_family == AF_UNSPEC) {
- sk->sk_state = NETLINK_UNCONNECTED;
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED);
/* dst_portid and dst_group can be read locklessly */
WRITE_ONCE(nlk->dst_portid, 0);
WRITE_ONCE(nlk->dst_group, 0);
@@ -1122,7 +1123,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
err = netlink_autobind(sock);
if (err == 0) {
- sk->sk_state = NETLINK_CONNECTED;
+ /* paired with READ_ONCE() in netlink_getsockbyportid() */
+ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED);
/* dst_portid and dst_group can be read locklessly */
WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid);
WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups));
@@ -1174,8 +1176,8 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid)
/* Don't bother queuing skb if kernel socket has no input function */
nlk = nlk_sk(sock);
- /* dst_portid can be changed in netlink_connect() */
- if (sock->sk_state == NETLINK_CONNECTED &&
+ /* dst_portid and sk_state can be changed in netlink_connect() */
+ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED &&
READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) {
sock_put(sock);
return ERR_PTR(-ECONNREFUSED);
--
GitLab
From 1d1d63b612801b3f0a39b7d4467cad0abd60e5c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jan 2023 13:30:40 +0000
Subject: [PATCH 1078/1167] ipv4: prevent potential spectre v1 gadget in
ip_metrics_convert()
if (!type)
continue;
if (type > RTAX_MAX)
return -EINVAL;
...
metrics[type - 1] = val;
@type being used as an array index, we need to prevent
cpu speculation or risk leaking kernel memory content.
Fixes: 6cf9dfd3bd62 ("net: fib: move metrics parsing to a helper")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230120133040.3623463-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/metrics.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 7fcfdfd8f9def..0e3ee1532848c 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/netlink.h>
+#include <linux/nospec.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/ip.h>
@@ -25,6 +26,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
return -EINVAL;
}
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
--
GitLab
From 5e9398a26a92fc402d82ce1f97cc67d832527da0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jan 2023 13:31:40 +0000
Subject: [PATCH 1079/1167] ipv4: prevent potential spectre v1 gadget in
fib_metrics_match()
if (!type)
continue;
if (type > RTAX_MAX)
return false;
...
fi_val = fi->fib_metrics->metrics[type - 1];
@type being used as an array index, we need to prevent
cpu speculation or risk leaking kernel memory content.
Fixes: 5f9ae3d9e7e4 ("ipv4: do metrics match when looking up and deleting a route")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230120133140.3624204-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/ipv4/fib_semantics.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ce9ff3c62e840..3bb890a40ed73 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -30,6 +30,7 @@
#include <linux/slab.h>
#include <linux/netlink.h>
#include <linux/hash.h>
+#include <linux/nospec.h>
#include <net/arp.h>
#include <net/inet_dscp.h>
@@ -1022,6 +1023,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
if (type > RTAX_MAX)
return false;
+ type = array_index_nospec(type, RTAX_MAX + 1);
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
bool ecn_ca = false;
--
GitLab
From 360fdc999d92db4a4adbba0db8641396dc9f1b13 Mon Sep 17 00:00:00 2001
From: Ahmad Fatoum <a.fatoum@pengutronix.de>
Date: Fri, 20 Jan 2023 12:09:32 +0100
Subject: [PATCH 1080/1167] net: dsa: microchip: fix probe of I2C-connected
KSZ8563
Starting with commit eee16b147121 ("net: dsa: microchip: perform the
compatibility check for dev probed"), the KSZ switch driver now bails
out if it thinks the DT compatible doesn't match the actual chip ID
read back from the hardware:
ksz9477-switch 1-005f: Device tree specifies chip KSZ9893 but found
KSZ8563, please fix it!
For the KSZ8563, which used ksz_switch_chips[KSZ9893], this was fine
at first, because it indeed shares the same chip id as the KSZ9893.
Commit b44908095612 ("net: dsa: microchip: add separate struct
ksz_chip_data for KSZ8563 chip") started differentiating KSZ9893
compatible chips by consulting the 0x1F register. The resulting breakage
was fixed for the SPI driver in the same commit by introducing the
appropriate ksz_switch_chips[KSZ8563], but not for the I2C driver.
Fix this for I2C-connected KSZ8563 now to get it probing again.
Fixes: b44908095612 ("net: dsa: microchip: add separate struct ksz_chip_data for KSZ8563 chip").
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Ahmad Fatoum <a.fatoum@pengutronix.de>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Link: https://lore.kernel.org/r/20230120110933.1151054-1-a.fatoum@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/dsa/microchip/ksz9477_i2c.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c
index c1a633ca1e6d8..e315f669ec061 100644
--- a/drivers/net/dsa/microchip/ksz9477_i2c.c
+++ b/drivers/net/dsa/microchip/ksz9477_i2c.c
@@ -104,7 +104,7 @@ static const struct of_device_id ksz9477_dt_ids[] = {
},
{
.compatible = "microchip,ksz8563",
- .data = &ksz_switch_chips[KSZ9893]
+ .data = &ksz_switch_chips[KSZ8563]
},
{
.compatible = "microchip,ksz9567",
--
GitLab
From 8a4f6d023221c4b052ddfa1db48b27871bad6e96 Mon Sep 17 00:00:00 2001
From: Alexandru Tachici <alexandru.tachici@analog.com>
Date: Fri, 20 Jan 2023 11:08:46 +0200
Subject: [PATCH 1081/1167] net: ethernet: adi: adin1110: Fix multicast
offloading
Driver marked broadcast/multicast frames as offloaded incorrectly.
Mark them as offloaded only when HW offloading has been enabled.
This should happen only for ADIN2111 when both ports are bridged
by the software.
Fixes: bc93e19d088b ("net: ethernet: adi: Add ADIN1110 support")
Signed-off-by: Alexandru Tachici <alexandru.tachici@analog.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20230120090846.18172-1-alexandru.tachici@analog.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/adi/adin1110.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 0805f249fff29..c26b8597945b5 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -356,7 +356,7 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv)
if ((port_priv->flags & IFF_ALLMULTI && rxb->pkt_type == PACKET_MULTICAST) ||
(port_priv->flags & IFF_BROADCAST && rxb->pkt_type == PACKET_BROADCAST))
- rxb->offload_fwd_mark = 1;
+ rxb->offload_fwd_mark = port_priv->priv->forwarding;
netif_rx(rxb);
--
GitLab
From bce4affe30b297bfa3092bb53e879c0bd86901ab Mon Sep 17 00:00:00 2001
From: Mat Martineau <mathew.j.martineau@linux.intel.com>
Date: Fri, 20 Jan 2023 15:11:21 -0800
Subject: [PATCH 1082/1167] MAINTAINERS: Update MPTCP maintainer list and
CREDITS
My responsibilities at Intel have changed, so I'm handing off exclusive
MPTCP subsystem maintainer duties to Matthieu. It has been a privilege
to see MPTCP through its initial upstreaming and first few years in the
upstream kernel!
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Link: https://lore.kernel.org/r/20230120231121.36121-1-mathew.j.martineau@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
CREDITS | 7 +++++++
MAINTAINERS | 1 -
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/CREDITS b/CREDITS
index 4e302a459ddf0..acac06b6563e2 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2489,6 +2489,13 @@ D: XF86_Mach8
D: XF86_8514
D: cfdisk (curses based disk partitioning program)
+N: Mat Martineau
+E: mat@martineau.name
+D: MPTCP subsystem co-maintainer 2020-2023
+D: Keyctl restricted keyring and Diffie-Hellman UAPI
+D: Bluetooth L2CAP ERTM mode and AMP
+S: USA
+
N: John S. Marvin
E: jsm@fc.hp.com
D: PA-RISC port
diff --git a/MAINTAINERS b/MAINTAINERS
index f8ef124a941bc..fdc81ee6df1f4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14633,7 +14633,6 @@ F: net/netfilter/xt_SECMARK.c
F: net/netlabel/
NETWORKING [MPTCP]
-M: Mat Martineau <mathew.j.martineau@linux.intel.com>
M: Matthieu Baerts <matthieu.baerts@tessares.net>
L: netdev@vger.kernel.org
L: mptcp@lists.linux.dev
--
GitLab
From a9993591fa94246b16b444eea55d84c54608282a Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Tue, 24 Jan 2023 02:47:18 +0100
Subject: [PATCH 1083/1167] netfilter: conntrack: fix vtag checks for
ABORT/SHUTDOWN_COMPLETE
RFC 9260, Sec 8.5.1 states that for ABORT/SHUTDOWN_COMPLETE, the chunk
MUST be accepted if the vtag of the packet matches its own tag and the
T bit is not set OR if it is set to its peer's vtag and the T bit is set
in chunk flags. Otherwise the packet MUST be silently dropped.
Update vtag verification for ABORT/SHUTDOWN_COMPLETE based on the above
description.
Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.")
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_proto_sctp.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index d88b92a8ffca8..2b2c549ba6789 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -424,22 +424,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) {
/* Special cases of Verification tag check (Sec 8.5.1) */
if (sch->type == SCTP_CID_INIT) {
- /* Sec 8.5.1 (A) */
+ /* (A) vtag MUST be zero */
if (sh->vtag != 0)
goto out_unlock;
} else if (sch->type == SCTP_CID_ABORT) {
- /* Sec 8.5.1 (B) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir])
+ /* (B) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) {
- /* Sec 8.5.1 (C) */
- if (sh->vtag != ct->proto.sctp.vtag[dir] &&
- sh->vtag != ct->proto.sctp.vtag[!dir] &&
- sch->flags & SCTP_CHUNK_FLAG_T)
+ /* (C) vtag MUST match own vtag if T flag is unset OR
+ * MUST match peer's vtag if T flag is set
+ */
+ if ((!(sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) ||
+ ((sch->flags & SCTP_CHUNK_FLAG_T) &&
+ sh->vtag != ct->proto.sctp.vtag[!dir]))
goto out_unlock;
} else if (sch->type == SCTP_CID_COOKIE_ECHO) {
- /* Sec 8.5.1 (D) */
+ /* (D) vtag must be same as init_vtag as found in INIT_ACK */
if (sh->vtag != ct->proto.sctp.vtag[dir])
goto out_unlock;
} else if (sch->type == SCTP_CID_HEARTBEAT) {
--
GitLab
From 98ee0077452527f971567db01386de3c3d97ce13 Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Tue, 24 Jan 2023 02:47:19 +0100
Subject: [PATCH 1084/1167] netfilter: conntrack: fix bug in
for_each_sctp_chunk
skb_header_pointer() will return NULL if offset + sizeof(_sch) exceeds
skb->len, so this offset < skb->len test is redundant.
if sch->length == 0, this will end up in an infinite loop, add a check
for sch->length > 0
Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_proto_sctp.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 2b2c549ba6789..c561c1213704f 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -160,8 +160,8 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
#define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \
for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \
- (offset) < (skb)->len && \
- ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \
+ ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))) && \
+ (sch)->length; \
(offset) += (ntohs((sch)->length) + 3) & ~3, (count)++)
/* Some validity checks to make sure the chunks are fine */
--
GitLab
From 13bd9b31a969b03c8ec1d4eb0f2b9aebd30ebfd8 Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Tue, 24 Jan 2023 02:47:20 +0100
Subject: [PATCH 1085/1167] Revert "netfilter: conntrack: add sctp DATA_SENT
state"
This reverts commit (bff3d0534804: "netfilter: conntrack: add sctp
DATA_SENT state")
Using DATA/SACK to detect a new connection on secondary/alternate paths
works only on new connections, while a HEARTBEAT is required on
connection re-use. It is probably consistent to wait for HEARTBEAT to
create a secondary connection in conntrack.
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../uapi/linux/netfilter/nf_conntrack_sctp.h | 1 -
.../linux/netfilter/nfnetlink_cttimeout.h | 1 -
net/netfilter/nf_conntrack_proto_sctp.c | 102 ++++++++----------
net/netfilter/nf_conntrack_standalone.c | 8 --
4 files changed, 42 insertions(+), 70 deletions(-)
diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
index c742469afe21c..edc6ddab0de6a 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
@@ -16,7 +16,6 @@ enum sctp_conntrack {
SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
SCTP_CONNTRACK_HEARTBEAT_SENT,
SCTP_CONNTRACK_HEARTBEAT_ACKED,
- SCTP_CONNTRACK_DATA_SENT,
SCTP_CONNTRACK_MAX
};
diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
index 94e74034706d9..6b20fb22717b2 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
@@ -95,7 +95,6 @@ enum ctattr_timeout_sctp {
CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
CTA_TIMEOUT_SCTP_HEARTBEAT_SENT,
CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED,
- CTA_TIMEOUT_SCTP_DATA_SENT,
__CTA_TIMEOUT_SCTP_MAX
};
#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index c561c1213704f..01cf3e06f042e 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -60,7 +60,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
[SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS,
- [SCTP_CONNTRACK_DATA_SENT] = 30 SECS,
};
#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1
@@ -75,7 +74,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
#define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT
#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT
#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED
-#define sDS SCTP_CONNTRACK_DATA_SENT
#define sIV SCTP_CONNTRACK_MAX
/*
@@ -98,10 +96,9 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite
CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of
the SHUTDOWN chunk. Connection is closed.
HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow.
-HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction
- opposite to that of the HEARTBEAT/DATA chunk. Secondary connection
- is established.
-DATA_SENT - We have seen a DATA/SACK in a new flow.
+HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to
+ that of the HEARTBEAT chunk. Secondary connection is
+ established.
*/
/* TODO
@@ -115,38 +112,36 @@ cookie echoed to closed.
*/
/* SCTP conntrack state transitions */
-static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = {
+static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */
-/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW},
-/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},
-/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
-/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL},
-/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA},
-/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/
-/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */
-/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */
-/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL},
-/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS},
-/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS},
-/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
+/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
+/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
+/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
+/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA},
+/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/
+/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */
+/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */
+/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA},
+/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
+/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}
},
{
/* REPLY */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */
-/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */
-/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV},
-/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV},
-/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV},
-/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */
-/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV},
-/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV},
-/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA},
-/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA},
-/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA},
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
+/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
+/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
+/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
+/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
+/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
+/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA},
+/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */
+/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA},
+/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA},
+/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
+/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA}
}
};
@@ -258,11 +253,6 @@ static int sctp_new_state(enum ip_conntrack_dir dir,
pr_debug("SCTP_CID_HEARTBEAT_ACK");
i = 10;
break;
- case SCTP_CID_DATA:
- case SCTP_CID_SACK:
- pr_debug("SCTP_CID_DATA/SACK");
- i = 11;
- break;
default:
/* Other chunks like DATA or SACK do not change the state */
pr_debug("Unknown chunk type, Will stay in %s\n",
@@ -316,9 +306,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
ih->init_tag);
ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag;
- } else if (sch->type == SCTP_CID_HEARTBEAT ||
- sch->type == SCTP_CID_DATA ||
- sch->type == SCTP_CID_SACK) {
+ } else if (sch->type == SCTP_CID_HEARTBEAT) {
pr_debug("Setting vtag %x for secondary conntrack\n",
sh->vtag);
ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
@@ -404,19 +392,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
if (!sctp_new(ct, skb, sh, dataoff))
return -NF_ACCEPT;
- } else {
- /* Check the verification tag (Sec 8.5) */
- if (!test_bit(SCTP_CID_INIT, map) &&
- !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) &&
- !test_bit(SCTP_CID_COOKIE_ECHO, map) &&
- !test_bit(SCTP_CID_ABORT, map) &&
- !test_bit(SCTP_CID_SHUTDOWN_ACK, map) &&
- !test_bit(SCTP_CID_HEARTBEAT, map) &&
- !test_bit(SCTP_CID_HEARTBEAT_ACK, map) &&
- sh->vtag != ct->proto.sctp.vtag[dir]) {
- pr_debug("Verification tag check failed\n");
- goto out;
- }
+ }
+
+ /* Check the verification tag (Sec 8.5) */
+ if (!test_bit(SCTP_CID_INIT, map) &&
+ !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) &&
+ !test_bit(SCTP_CID_COOKIE_ECHO, map) &&
+ !test_bit(SCTP_CID_ABORT, map) &&
+ !test_bit(SCTP_CID_SHUTDOWN_ACK, map) &&
+ !test_bit(SCTP_CID_HEARTBEAT, map) &&
+ !test_bit(SCTP_CID_HEARTBEAT_ACK, map) &&
+ sh->vtag != ct->proto.sctp.vtag[dir]) {
+ pr_debug("Verification tag check failed\n");
+ goto out;
}
old_state = new_state = SCTP_CONNTRACK_NONE;
@@ -483,11 +471,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
} else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) {
ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED;
}
- } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) {
- if (ct->proto.sctp.vtag[dir] == 0) {
- pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir);
- ct->proto.sctp.vtag[dir] = sh->vtag;
- }
}
old_state = ct->proto.sctp.state;
@@ -708,7 +691,6 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = {
[CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 },
[CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 },
[CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 },
- [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 },
};
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0250725e38a44..bca839ab1ae8d 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -602,7 +602,6 @@ enum nf_ct_sysctl_index {
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED,
- NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT,
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
@@ -893,12 +892,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = {
- .procname = "nf_conntrack_sctp_timeout_data_sent",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
@@ -1043,7 +1036,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
XASSIGN(SHUTDOWN_ACK_SENT, sn);
XASSIGN(HEARTBEAT_SENT, sn);
XASSIGN(HEARTBEAT_ACKED, sn);
- XASSIGN(DATA_SENT, sn);
#undef XASSIGN
#endif
}
--
GitLab
From a44b7651489f26271ac784b70895e8a85d0cebf4 Mon Sep 17 00:00:00 2001
From: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Date: Tue, 24 Jan 2023 02:47:21 +0100
Subject: [PATCH 1086/1167] netfilter: conntrack: unify established states for
SCTP paths
An SCTP endpoint can start an association through a path and tear it
down over another one. That means the initial path will not see the
shutdown sequence, and the conntrack entry will remain in ESTABLISHED
state for 5 days.
By merging the HEARTBEAT_ACKED and ESTABLISHED states into one
ESTABLISHED state, there remains no difference between a primary or
secondary path. The timeout for the merged ESTABLISHED state is set to
210 seconds (hb_interval * max_path_retrans + rto_max). So, even if a
path doesn't see the shutdown sequence, it will expire in a reasonable
amount of time.
With this change in place, there is now more than one state from which
we can transition to ESTABLISHED, COOKIE_ECHOED and HEARTBEAT_SENT, so
handle the setting of ASSURED bit whenever a state change has happened
and the new state is ESTABLISHED. Removed the check for dir==REPLY since
the transition to ESTABLISHED can happen only in the reply direction.
Fixes: 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.")
Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@est.tech>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
.../networking/nf_conntrack-sysctl.rst | 10 +-
.../uapi/linux/netfilter/nf_conntrack_sctp.h | 2 +-
.../linux/netfilter/nfnetlink_cttimeout.h | 2 +-
net/netfilter/nf_conntrack_proto_sctp.c | 93 ++++++++-----------
net/netfilter/nf_conntrack_standalone.c | 8 --
5 files changed, 44 insertions(+), 71 deletions(-)
diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst
index 49db1d11d7c4a..8b1045c3b59e0 100644
--- a/Documentation/networking/nf_conntrack-sysctl.rst
+++ b/Documentation/networking/nf_conntrack-sysctl.rst
@@ -173,7 +173,9 @@ nf_conntrack_sctp_timeout_cookie_echoed - INTEGER (seconds)
default 3
nf_conntrack_sctp_timeout_established - INTEGER (seconds)
- default 432000 (5 days)
+ default 210
+
+ Default is set to (hb_interval * path_max_retrans + rto_max)
nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds)
default 0.3
@@ -190,12 +192,6 @@ nf_conntrack_sctp_timeout_heartbeat_sent - INTEGER (seconds)
This timeout is used to setup conntrack entry on secondary paths.
Default is set to hb_interval.
-nf_conntrack_sctp_timeout_heartbeat_acked - INTEGER (seconds)
- default 210
-
- This timeout is used to setup conntrack entry on secondary paths.
- Default is set to (hb_interval * path_max_retrans + rto_max)
-
nf_conntrack_udp_timeout - INTEGER (seconds)
default 30
diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
index edc6ddab0de6a..2d6f80d75ae74 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h
@@ -15,7 +15,7 @@ enum sctp_conntrack {
SCTP_CONNTRACK_SHUTDOWN_RECD,
SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
SCTP_CONNTRACK_HEARTBEAT_SENT,
- SCTP_CONNTRACK_HEARTBEAT_ACKED,
+ SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */
SCTP_CONNTRACK_MAX
};
diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
index 6b20fb22717b2..aa805e6d4e284 100644
--- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
+++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h
@@ -94,7 +94,7 @@ enum ctattr_timeout_sctp {
CTA_TIMEOUT_SCTP_SHUTDOWN_RECD,
CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
CTA_TIMEOUT_SCTP_HEARTBEAT_SENT,
- CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED,
+ CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */
__CTA_TIMEOUT_SCTP_MAX
};
#define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1)
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 01cf3e06f042e..945dd40e70773 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -27,22 +27,16 @@
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_timeout.h>
-/* FIXME: Examine ipfilter's timeouts and conntrack transitions more
- closely. They're more complex. --RR
-
- And so for me for SCTP :D -Kiran */
-
static const char *const sctp_conntrack_names[] = {
- "NONE",
- "CLOSED",
- "COOKIE_WAIT",
- "COOKIE_ECHOED",
- "ESTABLISHED",
- "SHUTDOWN_SENT",
- "SHUTDOWN_RECD",
- "SHUTDOWN_ACK_SENT",
- "HEARTBEAT_SENT",
- "HEARTBEAT_ACKED",
+ [SCTP_CONNTRACK_NONE] = "NONE",
+ [SCTP_CONNTRACK_CLOSED] = "CLOSED",
+ [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT",
+ [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED",
+ [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED",
+ [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT",
+ [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD",
+ [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT",
+ [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT",
};
#define SECS * HZ
@@ -54,12 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
[SCTP_CONNTRACK_CLOSED] = 10 SECS,
[SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS,
[SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS,
- [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS,
+ [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS,
[SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000,
[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS,
[SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS,
- [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS,
};
#define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1
@@ -73,7 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = {
#define sSR SCTP_CONNTRACK_SHUTDOWN_RECD
#define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT
#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT
-#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED
#define sIV SCTP_CONNTRACK_MAX
/*
@@ -96,9 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite
CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of
the SHUTDOWN chunk. Connection is closed.
HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow.
-HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to
- that of the HEARTBEAT chunk. Secondary connection is
- established.
*/
/* TODO
@@ -115,33 +104,33 @@ cookie echoed to closed.
static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
{
/* ORIGINAL */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA},
-/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},
-/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
-/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS},
-/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA},
-/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/
-/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */
-/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */
-/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA},
-/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
-/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW},
+/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},
+/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL},
+/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA},
+/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/
+/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */
+/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */
+/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL},
+/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
},
{
/* REPLY */
-/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */
-/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */
-/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},
-/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL},
-/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR},
-/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA},
-/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA},
-/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */
-/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA},
-/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA},
-/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA},
-/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA}
+/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */
+/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */
+/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV},
+/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV},
+/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV},
+/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV},
+/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV},
+/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */
+/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV},
+/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV},
+/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS},
+/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES},
}
};
@@ -508,8 +497,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
}
ct->proto.sctp.state = new_state;
- if (old_state != new_state)
+ if (old_state != new_state) {
nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
+ if (new_state == SCTP_CONNTRACK_ESTABLISHED &&
+ !test_and_set_bit(IPS_ASSURED_BIT, &ct->status))
+ nf_conntrack_event_cache(IPCT_ASSURED, ct);
+ }
}
spin_unlock_bh(&ct->lock);
@@ -523,14 +516,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct,
nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
- if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&
- dir == IP_CT_DIR_REPLY &&
- new_state == SCTP_CONNTRACK_ESTABLISHED) {
- pr_debug("Setting assured bit\n");
- set_bit(IPS_ASSURED_BIT, &ct->status);
- nf_conntrack_event_cache(IPCT_ASSURED, ct);
- }
-
return NF_ACCEPT;
out_unlock:
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index bca839ab1ae8d..460294bd4b606 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -601,7 +601,6 @@ enum nf_ct_sysctl_index {
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT,
- NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED,
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
@@ -886,12 +885,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = {
- .procname = "nf_conntrack_sctp_timeout_heartbeat_acked",
- .maxlen = sizeof(unsigned int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
#endif
#ifdef CONFIG_NF_CT_PROTO_DCCP
[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
@@ -1035,7 +1028,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
XASSIGN(SHUTDOWN_RECD, sn);
XASSIGN(SHUTDOWN_ACK_SENT, sn);
XASSIGN(HEARTBEAT_SENT, sn);
- XASSIGN(HEARTBEAT_ACKED, sn);
#undef XASSIGN
#endif
}
--
GitLab
From cc88ad784e42398b8845594fe3aa720d0cc1c40c Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Sat, 21 Jan 2023 20:24:17 +0100
Subject: [PATCH 1087/1167] drm/fb-helper: Check fb_deferred_io_init() return
value
The fb_deferred_io_init() can fail and return an errno code but currently
there is no check for its return value.
Fix that and propagate to errno to the caller in the case of a failure.
Fixes: d536540f304c ("drm/fb-helper: Add generic fbdev emulation .fb_probe function")
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230121192418.2814955-3-javierm@redhat.com
---
drivers/gpu/drm/drm_fbdev_generic.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c
index ab86956692795..97e00f27d2d68 100644
--- a/drivers/gpu/drm/drm_fbdev_generic.c
+++ b/drivers/gpu/drm/drm_fbdev_generic.c
@@ -223,7 +223,9 @@ static int drm_fbdev_fb_probe(struct drm_fb_helper *fb_helper,
fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST;
fbi->fbdefio = &drm_fbdev_defio;
- fb_deferred_io_init(fbi);
+ ret = fb_deferred_io_init(fbi);
+ if (ret)
+ return ret;
} else {
/* buffer is mapped for HW framebuffer */
ret = drm_client_buffer_vmap(fb_helper->buffer, &map);
--
GitLab
From d6591da5f3ff284a376d56b5f7a48a34e9cb159d Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Sat, 21 Jan 2023 20:24:18 +0100
Subject: [PATCH 1088/1167] drm/fb-helper: Use a per-driver FB deferred I/O
handler
The DRM fbdev emulation layer sets the struct fb_info .fbdefio field to
a struct fb_deferred_io pointer, that is shared across all drivers that
use the generic drm_fbdev_generic_setup() helper function.
It is a problem because the fbdev core deferred I/O logic assumes that
the struct fb_deferred_io data is not shared between devices, and it's
stored there state such as the list of pages touched and a mutex that
is use to synchronize between the fb_deferred_io_track_page() function
that track the dirty pages and fb_deferred_io_work() workqueue handler
doing the actual deferred I/O.
The latter can lead to the following error, since it may happen that two
drivers are probed and then one is removed, which causes the mutex bo be
destroyed and not existing anymore by the time the other driver tries to
grab it for the fbdev deferred I/O logic:
[ 369.756553] ------------[ cut here ]------------
[ 369.756604] DEBUG_LOCKS_WARN_ON(lock->magic != lock)
[ 369.756631] WARNING: CPU: 2 PID: 1023 at kernel/locking/mutex.c:582 __mutex_lock+0x348/0x424
[ 369.756744] Modules linked in: nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ip
v6 nf_defrag_ipv4 ip_set nf_tables nfnetlink qrtr btsdio bluetooth sunrpc brcmfmac snd_soc_hdmi_codec cpufreq_dt cfg80211 vfat fat vc4 rfkill brcmutil raspberrypi_cpufreq i2c_bcm2835 iproc_rng200 bcm2711_thermal snd_soc_core snd_pcm_dmaen
gine leds_gpio nvmem_rmem joydev hid_cherry uas usb_storage gpio_raspberrypi_exp v3d snd_pcm raspberrypi_hwmon gpu_sched bcm2835_wdt broadcom bcm_phy_lib snd_timer genet snd mdio_bcm_unimac clk_bcm2711_dvp soundcore drm_display_helper pci
e_brcmstb cec ip6_tables ip_tables fuse
[ 369.757400] CPU: 2 PID: 1023 Comm: fbtest Not tainted 5.19.0-rc6+ #94
[ 369.757455] Hardware name: raspberrypi,4-model-b Raspberry Pi 4 Model B Rev 1.4/Raspberry Pi 4 Model B Rev 1.4, BIOS 2022.10 10/01/2022
[ 369.757538] pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 369.757596] pc : __mutex_lock+0x348/0x424
[ 369.757635] lr : __mutex_lock+0x348/0x424
[ 369.757672] sp : ffff80000953bb00
[ 369.757703] x29: ffff80000953bb00 x28: ffff17fdc087c000 x27: 0000000000000002
[ 369.757771] x26: ffff17fdc349f9b0 x25: fffffc5ff72e0100 x24: 0000000000000000
[ 369.757838] x23: 0000000000000000 x22: 0000000000000002 x21: ffffa618df636f10
[ 369.757903] x20: ffff80000953bb68 x19: ffffa618e0f18138 x18: 0000000000000001
[ 369.757968] x17: 0000000020000000 x16: 0000000000000002 x15: 0000000000000000
[ 369.758032] x14: 0000000000000000 x13: 284e4f5f4e524157 x12: 5f534b434f4c5f47
[ 369.758097] x11: 00000000ffffdfff x10: ffffa618e0c79f88 x9 : ffffa618de472484
[ 369.758162] x8 : 000000000002ffe8 x7 : c0000000ffffdfff x6 : 00000000000affa8
[ 369.758227] x5 : 0000000000001fff x4 : 0000000000000000 x3 : 0000000000000027
[ 369.758292] x2 : 0000000000000001 x1 : ffff17fdc087c000 x0 : 0000000000000028
[ 369.758357] Call trace:
[ 369.758383] __mutex_lock+0x348/0x424
[ 369.758420] mutex_lock_nested+0x4c/0x5c
[ 369.758459] fb_deferred_io_mkwrite+0x78/0x1d8
[ 369.758507] do_page_mkwrite+0x5c/0x19c
[ 369.758550] wp_page_shared+0x70/0x1a0
[ 369.758590] do_wp_page+0x3d0/0x510
[ 369.758628] handle_pte_fault+0x1c0/0x1e0
[ 369.758670] __handle_mm_fault+0x250/0x380
[ 369.758712] handle_mm_fault+0x17c/0x3a4
[ 369.758753] do_page_fault+0x158/0x530
[ 369.758792] do_mem_abort+0x50/0xa0
[ 369.758831] el0_da+0x78/0x19c
[ 369.758864] el0t_64_sync_handler+0xbc/0x150
[ 369.758904] el0t_64_sync+0x190/0x194
[ 369.758942] irq event stamp: 11395
[ 369.758973] hardirqs last enabled at (11395): [<ffffa618de472554>] __up_console_sem+0x74/0x80
[ 369.759042] hardirqs last disabled at (11394): [<ffffa618de47254c>] __up_console_sem+0x6c/0x80
[ 369.760554] softirqs last enabled at (11392): [<ffffa618de330a74>] __do_softirq+0x4c4/0x6b8
[ 369.762060] softirqs last disabled at (11383): [<ffffa618de3c9124>] __irq_exit_rcu+0x104/0x214
[ 369.763564] ---[ end trace 0000000000000000 ]---
Fixes: d536540f304c ("drm/fb-helper: Add generic fbdev emulation .fb_probe function")
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230121192418.2814955-4-javierm@redhat.com
---
drivers/gpu/drm/drm_fbdev_generic.c | 11 +++++------
include/drm/drm_fb_helper.h | 12 ++++++++++++
2 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c
index 97e00f27d2d68..593aa3283792b 100644
--- a/drivers/gpu/drm/drm_fbdev_generic.c
+++ b/drivers/gpu/drm/drm_fbdev_generic.c
@@ -171,11 +171,6 @@ static const struct fb_ops drm_fbdev_fb_ops = {
.fb_imageblit = drm_fbdev_fb_imageblit,
};
-static struct fb_deferred_io drm_fbdev_defio = {
- .delay = HZ / 20,
- .deferred_io = drm_fb_helper_deferred_io,
-};
-
/*
* This function uses the client API to create a framebuffer backed by a dumb buffer.
*/
@@ -222,7 +217,11 @@ static int drm_fbdev_fb_probe(struct drm_fb_helper *fb_helper,
return -ENOMEM;
fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST;
- fbi->fbdefio = &drm_fbdev_defio;
+ /* Set a default deferred I/O handler */
+ fb_helper->fbdefio.delay = HZ / 20;
+ fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+ fbi->fbdefio = &fb_helper->fbdefio;
ret = fb_deferred_io_init(fbi);
if (ret)
return ret;
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index b111dc7ada78d..095370ef029de 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -208,6 +208,18 @@ struct drm_fb_helper {
* the smem_start field should always be cleared to zero.
*/
bool hint_leak_smem_start;
+
+#ifdef CONFIG_FB_DEFERRED_IO
+ /**
+ * @fbdefio:
+ *
+ * Temporary storage for the driver's FB deferred I/O handler. If the
+ * driver uses the DRM fbdev emulation layer, this is set by the core
+ * to a generic deferred I/O handler if a driver is preferring to use
+ * a shadow buffer.
+ */
+ struct fb_deferred_io fbdefio;
+#endif
};
static inline struct drm_fb_helper *
--
GitLab
From 409db27e3a2eb5e8ef7226ca33be33361b3ed1c9 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 20 Jan 2023 15:19:27 -0800
Subject: [PATCH 1089/1167] netrom: Fix use-after-free of a listening socket.
syzbot reported a use-after-free in do_accept(), precisely nr_accept()
as sk_prot_alloc() allocated the memory and sock_put() frees it. [0]
The issue could happen if the heartbeat timer is fired and
nr_heartbeat_expiry() calls nr_destroy_socket(), where a socket
has SOCK_DESTROY or a listening socket has SOCK_DEAD.
In this case, the first condition cannot be true. SOCK_DESTROY is
flagged in nr_release() only when the file descriptor is close()d,
but accept() is being called for the listening socket, so the second
condition must be true.
Usually, the AF_NETROM listener neither starts timers nor sets
SOCK_DEAD. However, the condition is met if connect() fails before
listen(). connect() starts the t1 timer and heartbeat timer, and
t1timer calls nr_disconnect() when timeout happens. Then, SOCK_DEAD
is set, and if we call listen(), the heartbeat timer calls
nr_destroy_socket().
nr_connect
nr_establish_data_link(sk)
nr_start_t1timer(sk)
nr_start_heartbeat(sk)
nr_t1timer_expiry
nr_disconnect(sk, ETIMEDOUT)
nr_sk(sk)->state = NR_STATE_0
sk->sk_state = TCP_CLOSE
sock_set_flag(sk, SOCK_DEAD)
nr_listen
if (sk->sk_state != TCP_LISTEN)
sk->sk_state = TCP_LISTEN
nr_heartbeat_expiry
switch (nr->state)
case NR_STATE_0
if (sk->sk_state == TCP_LISTEN &&
sock_flag(sk, SOCK_DEAD))
nr_destroy_socket(sk)
This path seems expected, and nr_destroy_socket() is called to clean
up resources. Initially, there was sock_hold() before nr_destroy_socket()
so that the socket would not be freed, but the commit 517a16b1a88b
("netrom: Decrease sock refcount when sock timers expire") accidentally
removed it.
To fix use-after-free, let's add sock_hold().
[0]:
BUG: KASAN: use-after-free in do_accept+0x483/0x510 net/socket.c:1848
Read of size 8 at addr ffff88807978d398 by task syz-executor.3/5315
CPU: 0 PID: 5315 Comm: syz-executor.3 Not tainted 6.2.0-rc3-syzkaller-00165-gd9fc1511728c #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106
print_address_description mm/kasan/report.c:306 [inline]
print_report+0x15e/0x461 mm/kasan/report.c:417
kasan_report+0xbf/0x1f0 mm/kasan/report.c:517
do_accept+0x483/0x510 net/socket.c:1848
__sys_accept4_file net/socket.c:1897 [inline]
__sys_accept4+0x9a/0x120 net/socket.c:1927
__do_sys_accept net/socket.c:1944 [inline]
__se_sys_accept net/socket.c:1941 [inline]
__x64_sys_accept+0x75/0xb0 net/socket.c:1941
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
RIP: 0033:0x7fa436a8c0c9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fa437784168 EFLAGS: 00000246 ORIG_RAX: 000000000000002b
RAX: ffffffffffffffda RBX: 00007fa436bac050 RCX: 00007fa436a8c0c9
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000005
RBP: 00007fa436ae7ae9 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007ffebc6700df R14: 00007fa437784300 R15: 0000000000022000
</TASK>
Allocated by task 5294:
kasan_save_stack+0x22/0x40 mm/kasan/common.c:45
kasan_set_track+0x25/0x30 mm/kasan/common.c:52
____kasan_kmalloc mm/kasan/common.c:371 [inline]
____kasan_kmalloc mm/kasan/common.c:330 [inline]
__kasan_kmalloc+0xa3/0xb0 mm/kasan/common.c:380
kasan_kmalloc include/linux/kasan.h:211 [inline]
__do_kmalloc_node mm/slab_common.c:968 [inline]
__kmalloc+0x5a/0xd0 mm/slab_common.c:981
kmalloc include/linux/slab.h:584 [inline]
sk_prot_alloc+0x140/0x290 net/core/sock.c:2038
sk_alloc+0x3a/0x7a0 net/core/sock.c:2091
nr_create+0xb6/0x5f0 net/netrom/af_netrom.c:433
__sock_create+0x359/0x790 net/socket.c:1515
sock_create net/socket.c:1566 [inline]
__sys_socket_create net/socket.c:1603 [inline]
__sys_socket_create net/socket.c:1588 [inline]
__sys_socket+0x133/0x250 net/socket.c:1636
__do_sys_socket net/socket.c:1649 [inline]
__se_sys_socket net/socket.c:1647 [inline]
__x64_sys_socket+0x73/0xb0 net/socket.c:1647
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
Freed by task 14:
kasan_save_stack+0x22/0x40 mm/kasan/common.c:45
kasan_set_track+0x25/0x30 mm/kasan/common.c:52
kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:518
____kasan_slab_free mm/kasan/common.c:236 [inline]
____kasan_slab_free+0x13b/0x1a0 mm/kasan/common.c:200
kasan_slab_free include/linux/kasan.h:177 [inline]
__cache_free mm/slab.c:3394 [inline]
__do_kmem_cache_free mm/slab.c:3580 [inline]
__kmem_cache_free+0xcd/0x3b0 mm/slab.c:3587
sk_prot_free net/core/sock.c:2074 [inline]
__sk_destruct+0x5df/0x750 net/core/sock.c:2166
sk_destruct net/core/sock.c:2181 [inline]
__sk_free+0x175/0x460 net/core/sock.c:2192
sk_free+0x7c/0xa0 net/core/sock.c:2203
sock_put include/net/sock.h:1991 [inline]
nr_heartbeat_expiry+0x1d7/0x460 net/netrom/nr_timer.c:148
call_timer_fn+0x1da/0x7c0 kernel/time/timer.c:1700
expire_timers+0x2c6/0x5c0 kernel/time/timer.c:1751
__run_timers kernel/time/timer.c:2022 [inline]
__run_timers kernel/time/timer.c:1995 [inline]
run_timer_softirq+0x326/0x910 kernel/time/timer.c:2035
__do_softirq+0x1fb/0xadc kernel/softirq.c:571
Fixes: 517a16b1a88b ("netrom: Decrease sock refcount when sock timers expire")
Reported-by: syzbot+5fafd5cfe1fc91f6b352@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20230120231927.51711-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/netrom/nr_timer.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index a8da88db7893f..4e7c968cde2dc 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -121,6 +121,7 @@ static void nr_heartbeat_expiry(struct timer_list *t)
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
+ sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
goto out;
--
GitLab
From 83bcf3e52e9cfc727df33f1055ef0618c91719d0 Mon Sep 17 00:00:00 2001
From: Koba Ko <koba.ko@canonical.com>
Date: Tue, 17 Jan 2023 20:34:36 +0800
Subject: [PATCH 1090/1167] platform/x86: dell-wmi: Add a keymap for KEY_MUTE
in type 0x0010 table
Some platforms send the speaker-mute key from EC. dell-wmi can't
recognize it.
Add a new keymap for KEY_MUTE in type 0x0010 table.
Signed-off-by: Koba Ko <koba.ko@canonical.com>
Link: https://lore.kernel.org/r/20230117123436.200440-1-koba.ko@canonical.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/dell/dell-wmi-base.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c
index 0a259a27459f6..502783a7adb11 100644
--- a/drivers/platform/x86/dell/dell-wmi-base.c
+++ b/drivers/platform/x86/dell/dell-wmi-base.c
@@ -261,6 +261,9 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = {
{ KE_KEY, 0x57, { KEY_BRIGHTNESSDOWN } },
{ KE_KEY, 0x58, { KEY_BRIGHTNESSUP } },
+ /*Speaker Mute*/
+ { KE_KEY, 0x109, { KEY_MUTE} },
+
/* Mic mute */
{ KE_KEY, 0x150, { KEY_MICMUTE } },
--
GitLab
From 3ee5447b2048c8389ed899838a40b40180d50906 Mon Sep 17 00:00:00 2001
From: Rishit Bansal <rishitbansal0@gmail.com>
Date: Sat, 21 Jan 2023 03:42:14 +0530
Subject: [PATCH 1091/1167] platform/x86: hp-wmi: Handle Omen Key event
Add support to map the "HP Omen Key" to KEY_PROG2. Laptops in the HP
Omen Series open the HP Omen Command Center application on windows. But,
on linux it fails with the following message from the hp-wmi driver:
[ 5143.415714] hp_wmi: Unknown event_id - 29 - 0x21a5
Also adds support to map Fn+Esc to KEY_FN_ESC. This currently throws the
following message on the hp-wmi driver:
[ 6082.143785] hp_wmi: Unknown key code - 0x21a7
There is also a "Win-Lock" key on HP Omen Laptops which supports
Enabling and Disabling the Windows key, which trigger commands 0x21a4
and 0x121a4 respectively, but I wasn't able to find any KEY in input.h
to map this to.
Signed-off-by: Rishit Bansal <rishitbansal0@gmail.com>
Link: https://lore.kernel.org/r/20230120221214.24426-1-rishitbansal0@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/hp/hp-wmi.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 0a99058be8130..4a3851332ef2c 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -90,6 +90,7 @@ enum hp_wmi_event_ids {
HPWMI_PEAKSHIFT_PERIOD = 0x0F,
HPWMI_BATTERY_CHARGE_PERIOD = 0x10,
HPWMI_SANITIZATION_MODE = 0x17,
+ HPWMI_OMEN_KEY = 0x1D,
HPWMI_SMART_EXPERIENCE_APP = 0x21,
};
@@ -216,6 +217,8 @@ static const struct key_entry hp_wmi_keymap[] = {
{ KE_KEY, 0x213b, { KEY_INFO } },
{ KE_KEY, 0x2169, { KEY_ROTATE_DISPLAY } },
{ KE_KEY, 0x216a, { KEY_SETUP } },
+ { KE_KEY, 0x21a5, { KEY_PROG2 } }, /* HP Omen Key */
+ { KE_KEY, 0x21a7, { KEY_FN_ESC } },
{ KE_KEY, 0x21a9, { KEY_TOUCHPAD_OFF } },
{ KE_KEY, 0x121a9, { KEY_TOUCHPAD_ON } },
{ KE_KEY, 0x231b, { KEY_HELP } },
@@ -810,6 +813,7 @@ static void hp_wmi_notify(u32 value, void *context)
case HPWMI_SMART_ADAPTER:
break;
case HPWMI_BEZEL_BUTTON:
+ case HPWMI_OMEN_KEY:
key_code = hp_wmi_read_int(HPWMI_HOTKEY_QUERY);
if (key_code < 0)
break;
--
GitLab
From a410429a3b7e748a9db9f357e71e2e085a21c902 Mon Sep 17 00:00:00 2001
From: Kevin Kuriakose <kevinmkuriakose@gmail.com>
Date: Thu, 19 Jan 2023 20:39:25 +0530
Subject: [PATCH 1092/1167] platform/x86: gigabyte-wmi: add support for B450M
DS3H WIFI-CF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
To the best of my knowledge this is the same board as the B450M DS3H-CF,
but with an added WiFi card. Name obtained using dmidecode, tested
with force_load on v6.1.6
Signed-off-by: Kevin Kuriakose <kevinmkuriakose@gmail.com>
Acked-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20230119150925.31962-1-kevinmkuriakose@gmail.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/gigabyte-wmi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c
index 5e7e6659a8497..322cfaeda17ba 100644
--- a/drivers/platform/x86/gigabyte-wmi.c
+++ b/drivers/platform/x86/gigabyte-wmi.c
@@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev)
static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"),
+ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
--
GitLab
From fdcc0602d64f22185f61c70747214b630049cc33 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 20 Jan 2023 15:34:41 +0100
Subject: [PATCH 1093/1167] platform/x86: asus-wmi: Fix kbd_dock_devid
tablet-switch reporting
Commit 1ea0d3b46798 ("platform/x86: asus-wmi: Simplify tablet-mode-switch
handling") unified the asus-wmi tablet-switch handling, but it did not take
into account that the value returned for the kbd_dock_devid WMI method is
inverted where as the other ones are not inverted.
This causes asus-wmi to report an inverted tablet-switch state for devices
which use the kbd_dock_devid, which causes libinput to ignore touchpad
events while the affected T10x model 2-in-1s are docked.
Add inverting of the return value in the kbd_dock_devid case to fix this.
Fixes: 1ea0d3b46798 ("platform/x86: asus-wmi: Simplify tablet-mode-switch handling")
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230120143441.527334-1-hdegoede@redhat.com
---
drivers/platform/x86/asus-wmi.c | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 104188d70988c..1038dfdcdd325 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -225,6 +225,7 @@ struct asus_wmi {
int tablet_switch_event_code;
u32 tablet_switch_dev_id;
+ bool tablet_switch_inverted;
enum fan_type fan_type;
enum fan_type gpu_fan_type;
@@ -493,6 +494,13 @@ static bool asus_wmi_dev_is_present(struct asus_wmi *asus, u32 dev_id)
}
/* Input **********************************************************************/
+static void asus_wmi_tablet_sw_report(struct asus_wmi *asus, bool value)
+{
+ input_report_switch(asus->inputdev, SW_TABLET_MODE,
+ asus->tablet_switch_inverted ? !value : value);
+ input_sync(asus->inputdev);
+}
+
static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event_code)
{
struct device *dev = &asus->platform_device->dev;
@@ -501,7 +509,7 @@ static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event
result = asus_wmi_get_devstate_simple(asus, dev_id);
if (result >= 0) {
input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE);
- input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
+ asus_wmi_tablet_sw_report(asus, result);
asus->tablet_switch_dev_id = dev_id;
asus->tablet_switch_event_code = event_code;
} else if (result == -ENODEV) {
@@ -534,6 +542,7 @@ static int asus_wmi_input_init(struct asus_wmi *asus)
case asus_wmi_no_tablet_switch:
break;
case asus_wmi_kbd_dock_devid:
+ asus->tablet_switch_inverted = true;
asus_wmi_tablet_sw_init(asus, ASUS_WMI_DEVID_KBD_DOCK, NOTIFY_KBD_DOCK_CHANGE);
break;
case asus_wmi_lid_flip_devid:
@@ -573,10 +582,8 @@ static void asus_wmi_tablet_mode_get_state(struct asus_wmi *asus)
return;
result = asus_wmi_get_devstate_simple(asus, asus->tablet_switch_dev_id);
- if (result >= 0) {
- input_report_switch(asus->inputdev, SW_TABLET_MODE, result);
- input_sync(asus->inputdev);
- }
+ if (result >= 0)
+ asus_wmi_tablet_sw_report(asus, result);
}
/* dGPU ********************************************************************/
--
GitLab
From 8e60615e8932167057b363c11a7835da7f007106 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 20 Jan 2023 13:15:18 -0600
Subject: [PATCH 1094/1167] platform/x86/amd: pmc: Disable IRQ1 wakeup for
RN/CZN
By default when the system is configured for low power idle in the FADT
the keyboard is set up as a wake source. This matches the behavior that
Windows uses for Modern Standby as well.
It has been reported that a variety of AMD based designs there are
spurious wakeups are happening where two IRQ sources are active.
For example:
```
PM: Triggering wakeup from IRQ 9
PM: Triggering wakeup from IRQ 1
```
In these designs IRQ 9 is the ACPI SCI and IRQ 1 is the keyboard.
One way to trigger this problem is to suspend the laptop and then unplug
the AC adapter. The SOC will be in a hardware sleep state and plugging
in the AC adapter returns control to the kernel's s2idle loop.
Normally if just IRQ 9 was active the s2idle loop would advance any EC
transactions and no other IRQ being active would cause the s2idle loop
to put the SOC back into hardware sleep state.
When this bug occurred IRQ 1 is also active even if no keyboard activity
occurred. This causes the s2idle loop to break and the system to wake.
This is a platform firmware bug triggering IRQ1 without keyboard activity.
This occurs in Windows as well, but Windows will enter "SW DRIPS" and
then with no activity enters back into "HW DRIPS" (hardware sleep state).
This issue affects Renoir, Lucienne, Cezanne, and Barcelo platforms. It
does not happen on newer systems such as Mendocino or Rembrandt.
It's been fixed in newer platform firmware. To avoid triggering the bug
on older systems check the SMU F/W version and adjust the policy at suspend
time for s2idle wakeup from keyboard on these systems. A lot of thought
and experimentation has been given around the timing of disabling IRQ1,
and to make it work the "suspend" PM callback is restored.
Reported-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Reported-by: Xaver Hugl <xaver.hugl@gmail.com>
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2115
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/1951
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20230120191519.15926-1-mario.limonciello@amd.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/amd/pmc.c | 50 ++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c
index 8d924986381be..be1b49824edbd 100644
--- a/drivers/platform/x86/amd/pmc.c
+++ b/drivers/platform/x86/amd/pmc.c
@@ -22,6 +22,7 @@
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/rtc.h>
+#include <linux/serio.h>
#include <linux/suspend.h>
#include <linux/seq_file.h>
#include <linux/uaccess.h>
@@ -653,6 +654,33 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
return -EINVAL;
}
+static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev)
+{
+ struct device *d;
+ int rc;
+
+ if (!pdev->major) {
+ rc = amd_pmc_get_smu_version(pdev);
+ if (rc)
+ return rc;
+ }
+
+ if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
+ return 0;
+
+ d = bus_find_device_by_name(&serio_bus, NULL, "serio0");
+ if (!d)
+ return 0;
+ if (device_may_wakeup(d)) {
+ dev_info_once(d, "Disabling IRQ1 wakeup source to avoid platform firmware bug\n");
+ disable_irq_wake(1);
+ device_set_wakeup_enable(d, false);
+ }
+ put_device(d);
+
+ return 0;
+}
+
static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg)
{
struct rtc_device *rtc_device;
@@ -782,6 +810,25 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = {
.check = amd_pmc_s2idle_check,
.restore = amd_pmc_s2idle_restore,
};
+
+static int __maybe_unused amd_pmc_suspend_handler(struct device *dev)
+{
+ struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
+
+ if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+ int rc = amd_pmc_czn_wa_irq1(pdev);
+
+ if (rc) {
+ dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc);
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL);
+
#endif
static const struct pci_device_id pmc_pci_ids[] = {
@@ -980,6 +1027,9 @@ static struct platform_driver amd_pmc_driver = {
.name = "amd_pmc",
.acpi_match_table = amd_pmc_acpi_ids,
.dev_groups = pmc_groups,
+#ifdef CONFIG_SUSPEND
+ .pm = &amd_pmc_pm,
+#endif
},
.probe = amd_pmc_probe,
.remove = amd_pmc_remove,
--
GitLab
From 062c1394cbda95b0c51839b5221c7267e1e7f57e Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 20 Jan 2023 13:15:19 -0600
Subject: [PATCH 1095/1167] platform/x86/amd: pmc: Add a module parameter to
disable workarounds
Some users may want to live with the bugs that exist in platform
firmware and have workarounds in AMD PMC driver.
To allow them to bypass these workarounds, introduce a module
parameter.
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20230120191519.15926-2-mario.limonciello@amd.com
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/amd/pmc.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c
index be1b49824edbd..3cbb01ec10e32 100644
--- a/drivers/platform/x86/amd/pmc.c
+++ b/drivers/platform/x86/amd/pmc.c
@@ -161,6 +161,10 @@ static bool enable_stb;
module_param(enable_stb, bool, 0644);
MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism");
+static bool disable_workarounds;
+module_param(disable_workarounds, bool, 0644);
+MODULE_PARM_DESC(disable_workarounds, "Disable workarounds for platform bugs");
+
static struct amd_pmc_dev pmc;
static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret);
static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf);
@@ -743,8 +747,8 @@ static void amd_pmc_s2idle_prepare(void)
/* Reset and Start SMU logging - to monitor the s0i3 stats */
amd_pmc_setup_smu_logging(pdev);
- /* Activate CZN specific RTC functionality */
- if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+ /* Activate CZN specific platform bug workarounds */
+ if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
rc = amd_pmc_verify_czn_rtc(pdev, &arg);
if (rc) {
dev_err(pdev->dev, "failed to set RTC: %d\n", rc);
@@ -815,7 +819,7 @@ static int __maybe_unused amd_pmc_suspend_handler(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
- if (pdev->cpu_id == AMD_CPU_ID_CZN) {
+ if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) {
int rc = amd_pmc_czn_wa_irq1(pdev);
if (rc) {
--
GitLab
From ce95010ef62d4bf470928969bafc9070ae98cbb1 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 23 Jan 2023 14:28:24 +0100
Subject: [PATCH 1096/1167] platform/x86: hp-wmi: Fix cast to smaller integer
type warning
Fix the following compiler warning:
drivers/platform/x86/hp/hp-wmi.c:551:24: warning: cast to smaller integer
type 'enum hp_wmi_radio' from 'void *' [-Wvoid-pointer-to-enum-cast]
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230123132824.660062-1-hdegoede@redhat.com
---
drivers/platform/x86/hp/hp-wmi.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 4a3851332ef2c..2ef201b625b38 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -551,7 +551,7 @@ static int __init hp_wmi_enable_hotkeys(void)
static int hp_wmi_set_block(void *data, bool blocked)
{
- enum hp_wmi_radio r = (enum hp_wmi_radio) data;
+ enum hp_wmi_radio r = (long)data;
int query = BIT(r + 8) | ((!blocked) << r);
int ret;
--
GitLab
From 39f5a81f7ad80eb3fbcbfd817c6552db9de5504d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 24 Jan 2023 11:57:52 +0100
Subject: [PATCH 1097/1167] platform/x86: apple-gmux: Move port defines to
apple-gmux.h
This is a preparation patch for adding a new static inline
apple_gmux_detect() helper which actually checks a supported
gmux is present, rather then only checking an ACPI device with
the HID is there as apple_gmux_present() does.
Fixes: 21245df307cb ("ACPI: video: Add Apple GMUX brightness control detection")
Link: https://lore.kernel.org/platform-driver-x86/20230123113750.462144-1-hdegoede@redhat.com/
Reported-by: Emmanouil Kouroupakis <kartebi@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230124105754.62167-2-hdegoede@redhat.com
---
drivers/platform/x86/apple-gmux.c | 23 -----------------------
include/linux/apple-gmux.h | 23 +++++++++++++++++++++++
2 files changed, 23 insertions(+), 23 deletions(-)
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index ca33df7ea550e..a0af01f6a0fd4 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -64,29 +64,6 @@ struct apple_gmux_data {
static struct apple_gmux_data *apple_gmux_data;
-/*
- * gmux port offsets. Many of these are not yet used, but may be in the
- * future, and it's useful to have them documented here anyhow.
- */
-#define GMUX_PORT_VERSION_MAJOR 0x04
-#define GMUX_PORT_VERSION_MINOR 0x05
-#define GMUX_PORT_VERSION_RELEASE 0x06
-#define GMUX_PORT_SWITCH_DISPLAY 0x10
-#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11
-#define GMUX_PORT_INTERRUPT_ENABLE 0x14
-#define GMUX_PORT_INTERRUPT_STATUS 0x16
-#define GMUX_PORT_SWITCH_DDC 0x28
-#define GMUX_PORT_SWITCH_EXTERNAL 0x40
-#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41
-#define GMUX_PORT_DISCRETE_POWER 0x50
-#define GMUX_PORT_MAX_BRIGHTNESS 0x70
-#define GMUX_PORT_BRIGHTNESS 0x74
-#define GMUX_PORT_VALUE 0xc2
-#define GMUX_PORT_READ 0xd0
-#define GMUX_PORT_WRITE 0xd4
-
-#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4)
-
#define GMUX_INTERRUPT_ENABLE 0xff
#define GMUX_INTERRUPT_DISABLE 0x00
diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h
index ddb10aa67b143..80efaaf89e072 100644
--- a/include/linux/apple-gmux.h
+++ b/include/linux/apple-gmux.h
@@ -11,6 +11,29 @@
#define GMUX_ACPI_HID "APP000B"
+/*
+ * gmux port offsets. Many of these are not yet used, but may be in the
+ * future, and it's useful to have them documented here anyhow.
+ */
+#define GMUX_PORT_VERSION_MAJOR 0x04
+#define GMUX_PORT_VERSION_MINOR 0x05
+#define GMUX_PORT_VERSION_RELEASE 0x06
+#define GMUX_PORT_SWITCH_DISPLAY 0x10
+#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11
+#define GMUX_PORT_INTERRUPT_ENABLE 0x14
+#define GMUX_PORT_INTERRUPT_STATUS 0x16
+#define GMUX_PORT_SWITCH_DDC 0x28
+#define GMUX_PORT_SWITCH_EXTERNAL 0x40
+#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41
+#define GMUX_PORT_DISCRETE_POWER 0x50
+#define GMUX_PORT_MAX_BRIGHTNESS 0x70
+#define GMUX_PORT_BRIGHTNESS 0x74
+#define GMUX_PORT_VALUE 0xc2
+#define GMUX_PORT_READ 0xd0
+#define GMUX_PORT_WRITE 0xd4
+
+#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4)
+
#if IS_ENABLED(CONFIG_APPLE_GMUX)
/**
--
GitLab
From d143908f80f3e5d164ac3342f73d6b9f536e8b4d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 24 Jan 2023 11:57:53 +0100
Subject: [PATCH 1098/1167] platform/x86: apple-gmux: Add apple_gmux_detect()
helper
Add a new (static inline) apple_gmux_detect() helper to apple-gmux.h
which can be used for gmux detection instead of apple_gmux_present().
The latter is not really reliable since an ACPI device with a HID
of APP000B is present on some devices without a gmux at all, as well
as on devices with a newer (unsupported) MMIO based gmux model.
This causes apple_gmux_present() to return false-positives on
a number of different Apple laptop models.
This new helper uses the same probing as the actual apple-gmux
driver, so that it does not return false positives.
To avoid code duplication the gmux_probe() function of the actual
driver is also moved over to using the new apple_gmux_detect() helper.
This avoids false positives (vs _HID + IO region detection) on:
MacBookPro5,4
https://pastebin.com/8Xjq7RhS
MacBookPro8,1
https://linux-hardware.org/?probe=e513cfbadb&log=dmesg
MacBookPro9,2
https://bugzilla.kernel.org/attachment.cgi?id=278961
MacBookPro10,2
https://lkml.org/lkml/2014/9/22/657
MacBookPro11,2
https://forums.fedora-fr.org/viewtopic.php?id=70142
MacBookPro11,4
https://raw.githubusercontent.com/im-0/investigate-card-reader-suspend-problem-on-mbp11.4/master/test-16/dmesg
Fixes: 21245df307cb ("ACPI: video: Add Apple GMUX brightness control detection")
Link: https://lore.kernel.org/platform-driver-x86/20230123113750.462144-1-hdegoede@redhat.com/
Reported-by: Emmanouil Kouroupakis <kartebi@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230124105754.62167-3-hdegoede@redhat.com
---
drivers/platform/x86/apple-gmux.c | 70 +++++++------------------
include/linux/apple-gmux.h | 86 ++++++++++++++++++++++++++++++-
2 files changed, 102 insertions(+), 54 deletions(-)
diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c
index a0af01f6a0fd4..9333f82cfa8a0 100644
--- a/drivers/platform/x86/apple-gmux.c
+++ b/drivers/platform/x86/apple-gmux.c
@@ -226,23 +226,6 @@ static void gmux_write32(struct apple_gmux_data *gmux_data, int port,
gmux_pio_write32(gmux_data, port, val);
}
-static bool gmux_is_indexed(struct apple_gmux_data *gmux_data)
-{
- u16 val;
-
- outb(0xaa, gmux_data->iostart + 0xcc);
- outb(0x55, gmux_data->iostart + 0xcd);
- outb(0x00, gmux_data->iostart + 0xce);
-
- val = inb(gmux_data->iostart + 0xcc) |
- (inb(gmux_data->iostart + 0xcd) << 8);
-
- if (val == 0x55aa)
- return true;
-
- return false;
-}
-
/**
* DOC: Backlight control
*
@@ -582,60 +565,43 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
int ret = -ENXIO;
acpi_status status;
unsigned long long gpe;
+ bool indexed = false;
+ u32 version;
if (apple_gmux_data)
return -EBUSY;
+ if (!apple_gmux_detect(pnp, &indexed)) {
+ pr_info("gmux device not present\n");
+ return -ENODEV;
+ }
+
gmux_data = kzalloc(sizeof(*gmux_data), GFP_KERNEL);
if (!gmux_data)
return -ENOMEM;
pnp_set_drvdata(pnp, gmux_data);
res = pnp_get_resource(pnp, IORESOURCE_IO, 0);
- if (!res) {
- pr_err("Failed to find gmux I/O resource\n");
- goto err_free;
- }
-
gmux_data->iostart = res->start;
gmux_data->iolen = resource_size(res);
- if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
- pr_err("gmux I/O region too small (%lu < %u)\n",
- gmux_data->iolen, GMUX_MIN_IO_LEN);
- goto err_free;
- }
-
if (!request_region(gmux_data->iostart, gmux_data->iolen,
"Apple gmux")) {
pr_err("gmux I/O already in use\n");
goto err_free;
}
- /*
- * Invalid version information may indicate either that the gmux
- * device isn't present or that it's a new one that uses indexed
- * io
- */
-
- ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR);
- ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR);
- ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE);
- if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) {
- if (gmux_is_indexed(gmux_data)) {
- u32 version;
- mutex_init(&gmux_data->index_lock);
- gmux_data->indexed = true;
- version = gmux_read32(gmux_data,
- GMUX_PORT_VERSION_MAJOR);
- ver_major = (version >> 24) & 0xff;
- ver_minor = (version >> 16) & 0xff;
- ver_release = (version >> 8) & 0xff;
- } else {
- pr_info("gmux device not present\n");
- ret = -ENODEV;
- goto err_release;
- }
+ if (indexed) {
+ mutex_init(&gmux_data->index_lock);
+ gmux_data->indexed = true;
+ version = gmux_read32(gmux_data, GMUX_PORT_VERSION_MAJOR);
+ ver_major = (version >> 24) & 0xff;
+ ver_minor = (version >> 16) & 0xff;
+ ver_release = (version >> 8) & 0xff;
+ } else {
+ ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR);
+ ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR);
+ ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE);
}
pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor,
ver_release, (gmux_data->indexed ? "indexed" : "classic"));
diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h
index 80efaaf89e072..1f68b49bcd688 100644
--- a/include/linux/apple-gmux.h
+++ b/include/linux/apple-gmux.h
@@ -8,6 +8,8 @@
#define LINUX_APPLE_GMUX_H
#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/pnp.h>
#define GMUX_ACPI_HID "APP000B"
@@ -35,14 +37,89 @@
#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4)
#if IS_ENABLED(CONFIG_APPLE_GMUX)
+static inline bool apple_gmux_is_indexed(unsigned long iostart)
+{
+ u16 val;
+
+ outb(0xaa, iostart + 0xcc);
+ outb(0x55, iostart + 0xcd);
+ outb(0x00, iostart + 0xce);
+
+ val = inb(iostart + 0xcc) | (inb(iostart + 0xcd) << 8);
+ if (val == 0x55aa)
+ return true;
+
+ return false;
+}
/**
- * apple_gmux_present() - detect if gmux is built into the machine
+ * apple_gmux_detect() - detect if gmux is built into the machine
+ *
+ * @pnp_dev: Device to probe or NULL to use the first matching device
+ * @indexed_ret: Returns (by reference) if the gmux is indexed or not
+ *
+ * Detect if a supported gmux device is present by actually probing it.
+ * This avoids the false positives returned on some models by
+ * apple_gmux_present().
+ *
+ * Return: %true if a supported gmux ACPI device is detected and the kernel
+ * was configured with CONFIG_APPLE_GMUX, %false otherwise.
+ */
+static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret)
+{
+ u8 ver_major, ver_minor, ver_release;
+ struct device *dev = NULL;
+ struct acpi_device *adev;
+ struct resource *res;
+ bool indexed = false;
+ bool ret = false;
+
+ if (!pnp_dev) {
+ adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1);
+ if (!adev)
+ return false;
+
+ dev = get_device(acpi_get_first_physical_node(adev));
+ acpi_dev_put(adev);
+ if (!dev)
+ return false;
+
+ pnp_dev = to_pnp_dev(dev);
+ }
+
+ res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0);
+ if (!res || resource_size(res) < GMUX_MIN_IO_LEN)
+ goto out;
+
+ /*
+ * Invalid version information may indicate either that the gmux
+ * device isn't present or that it's a new one that uses indexed io.
+ */
+ ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR);
+ ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR);
+ ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE);
+ if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) {
+ indexed = apple_gmux_is_indexed(res->start);
+ if (!indexed)
+ goto out;
+ }
+
+ if (indexed_ret)
+ *indexed_ret = indexed;
+
+ ret = true;
+out:
+ put_device(dev);
+ return ret;
+}
+
+/**
+ * apple_gmux_present() - check if gmux ACPI device is present
*
* Drivers may use this to activate quirks specific to dual GPU MacBook Pros
* and Mac Pros, e.g. for deferred probing, runtime pm and backlight.
*
- * Return: %true if gmux is present and the kernel was configured
+ * Return: %true if gmux ACPI device is present and the kernel was configured
* with CONFIG_APPLE_GMUX, %false otherwise.
*/
static inline bool apple_gmux_present(void)
@@ -57,6 +134,11 @@ static inline bool apple_gmux_present(void)
return false;
}
+static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret)
+{
+ return false;
+}
+
#endif /* !CONFIG_APPLE_GMUX */
#endif /* LINUX_APPLE_GMUX_H */
--
GitLab
From b0935f110cff5d70da05c5cb1670bee0b07b631c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 24 Jan 2023 11:57:54 +0100
Subject: [PATCH 1099/1167] ACPI: video: Fix apple gmux detection
Some apple laptop models have an ACPI device with a HID of APP000B
and that device has an IO resource (so it does not describe the new
unsupported MMIO based gmux type), but there actually is no gmux
in the laptop at all.
The gmux_probe() function of the actual apple-gmux driver has code
to detect this, this code has been factored out into a new
apple_gmux_detect() helper in apple-gmux.h.
Use this new function to fix acpi_video_get_backlight_type() wrongly
returning apple_gmux as type on the following laptops:
MacBookPro5,4
https://pastebin.com/8Xjq7RhS
MacBookPro8,1
https://linux-hardware.org/?probe=e513cfbadb&log=dmesg
MacBookPro9,2
https://bugzilla.kernel.org/attachment.cgi?id=278961
MacBookPro10,2
https://lkml.org/lkml/2014/9/22/657
MacBookPro11,2
https://forums.fedora-fr.org/viewtopic.php?id=70142
MacBookPro11,4
https://raw.githubusercontent.com/im-0/investigate-card-reader-suspend-problem-on-mbp11.4/mast
Fixes: 21245df307cb ("ACPI: video: Add Apple GMUX brightness control detection")
Link: https://lore.kernel.org/platform-driver-x86/20230123113750.462144-1-hdegoede@redhat.com/
Reported-by: Emmanouil Kouroupakis <kartebi@gmail.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20230124105754.62167-4-hdegoede@redhat.com
---
drivers/acpi/video_detect.c | 24 +++---------------------
1 file changed, 3 insertions(+), 21 deletions(-)
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 65cec7bb6d961..8626869c49040 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -110,26 +110,6 @@ static bool nvidia_wmi_ec_supported(void)
}
#endif
-static bool apple_gmux_backlight_present(void)
-{
- struct acpi_device *adev;
- struct device *dev;
-
- adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1);
- if (!adev)
- return false;
-
- dev = acpi_get_first_physical_node(adev);
- if (!dev)
- return false;
-
- /*
- * drivers/platform/x86/apple-gmux.c only supports old style
- * Apple GMUX with an IO-resource.
- */
- return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL;
-}
-
/* Force to use vendor driver when the ACPI device is known to be
* buggy */
static int video_detect_force_vendor(const struct dmi_system_id *d)
@@ -766,6 +746,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native)
{
static DEFINE_MUTEX(init_mutex);
static bool nvidia_wmi_ec_present;
+ static bool apple_gmux_present;
static bool native_available;
static bool init_done;
static long video_caps;
@@ -779,6 +760,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native)
ACPI_UINT32_MAX, find_video, NULL,
&video_caps, NULL);
nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
+ apple_gmux_present = apple_gmux_detect(NULL, NULL);
init_done = true;
}
if (native)
@@ -800,7 +782,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native)
if (nvidia_wmi_ec_present)
return acpi_backlight_nvidia_wmi_ec;
- if (apple_gmux_backlight_present())
+ if (apple_gmux_present)
return acpi_backlight_apple_gmux;
/* Use ACPI video if available, except when native should be preferred. */
--
GitLab
From facd61053cff100973921d4d45d47cf53c747ec6 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 20 Jan 2023 12:55:04 +0100
Subject: [PATCH 1100/1167] fuse: fixes after adapting to new posix acl api
This cycle we ported all filesystems to the new posix acl api. While
looking at further simplifications in this area to remove the last
remnants of the generic dummy posix acl handlers we realized that we
regressed fuse daemons that don't set FUSE_POSIX_ACL but still make use
of posix acls.
With the change to a dedicated posix acl api interacting with posix acls
doesn't go through the old xattr codepaths anymore and instead only
relies the get acl and set acl inode operations.
Before this change fuse daemons that don't set FUSE_POSIX_ACL were able
to get and set posix acl albeit with two caveats. First, that posix acls
aren't cached. And second, that they aren't used for permission checking
in the vfs.
We regressed that use-case as we currently refuse to retrieve any posix
acls if they aren't enabled via FUSE_POSIX_ACL. So older fuse daemons
would see a change in behavior.
We can restore the old behavior in multiple ways. We could change the
new posix acl api and look for a dedicated xattr handler and if we find
one prefer that over the dedicated posix acl api. That would break the
consistency of the new posix acl api so we would very much prefer not to
do that.
We could introduce a new ACL_*_CACHE sentinel that would instruct the
vfs permission checking codepath to not call into the filesystem and
ignore acls.
But a more straightforward fix for v6.2 is to do the same thing that
Overlayfs does and give fuse a separate get acl method for permission
checking. Overlayfs uses this to express different needs for vfs
permission lookup and acl based retrieval via the regular system call
path as well. Let fuse do the same for now. This way fuse can continue
to refuse to retrieve posix acls for daemons that don't set
FUSE_POSXI_ACL for permission checking while allowing a fuse server to
retrieve it via the usual system calls.
In the future, we could extend the get acl inode operation to not just
pass a simple boolean to indicate rcu lookup but instead make it a flag
argument. Then in addition to passing the information that this is an
rcu lookup to the filesystem we could also introduce a flag that tells
the filesystem that this is a request from the vfs to use these acls for
permission checking. Then fuse could refuse the get acl request for
permission checking when the daemon doesn't have FUSE_POSIX_ACL set in
the same get acl method. This would also help Overlayfs and allow us to
remove the second method for it as well.
But since that change is more invasive as we need to update the get acl
inode operation for multiple filesystems we should not do this as a fix
for v6.2. Instead we will do this for the v6.3 merge window.
Fwiw, since posix acls are now always correctly translated in the new
posix acl api we could also allow them to be used for daemons without
FUSE_POSIX_ACL that are not mounted on the host. But this is behavioral
change and again if dones should be done for v6.3. For now, let's just
restore the original behavior.
A nice side-effect of this change is that for fuse daemons with and
without FUSE_POSIX_ACL the same code is used for posix acls in a
backwards compatible way. This also means we can remove the legacy xattr
handlers completely. We've also added comments to explain the expected
behavior for daemons without FUSE_POSIX_ACL into the code.
Fixes: 318e66856dde ("xattr: use posix acl api")
Signed-off-by: Seth Forshee (Digital Ocean) <sforshee@kernel.org>
Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
---
fs/fuse/acl.c | 68 +++++++++++++++++++++++++++++++++++++++++++-----
fs/fuse/dir.c | 6 +++--
fs/fuse/fuse_i.h | 6 ++---
fs/fuse/inode.c | 21 +++++++--------
fs/fuse/xattr.c | 51 ------------------------------------
5 files changed, 78 insertions(+), 74 deletions(-)
diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c
index a4850aee2639f..ad670369955f6 100644
--- a/fs/fuse/acl.c
+++ b/fs/fuse/acl.c
@@ -11,9 +11,10 @@
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
-struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu)
+static struct posix_acl *__fuse_get_acl(struct fuse_conn *fc,
+ struct user_namespace *mnt_userns,
+ struct inode *inode, int type, bool rcu)
{
- struct fuse_conn *fc = get_fuse_conn(inode);
int size;
const char *name;
void *value = NULL;
@@ -25,7 +26,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu)
if (fuse_is_bad(inode))
return ERR_PTR(-EIO);
- if (!fc->posix_acl || fc->no_getxattr)
+ if (fc->no_getxattr)
return NULL;
if (type == ACL_TYPE_ACCESS)
@@ -53,6 +54,46 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu)
return acl;
}
+static inline bool fuse_no_acl(const struct fuse_conn *fc,
+ const struct inode *inode)
+{
+ /*
+ * Refuse interacting with POSIX ACLs for daemons that
+ * don't support FUSE_POSIX_ACL and are not mounted on
+ * the host to retain backwards compatibility.
+ */
+ return !fc->posix_acl && (i_user_ns(inode) != &init_user_ns);
+}
+
+struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, int type)
+{
+ struct inode *inode = d_inode(dentry);
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (fuse_no_acl(fc, inode))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ return __fuse_get_acl(fc, mnt_userns, inode, type, false);
+}
+
+struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ /*
+ * FUSE daemons before FUSE_POSIX_ACL was introduced could get and set
+ * POSIX ACLs without them being used for permission checking by the
+ * vfs. Retain that behavior for backwards compatibility as there are
+ * filesystems that do all permission checking for acls in the daemon
+ * and not in the kernel.
+ */
+ if (!fc->posix_acl)
+ return NULL;
+
+ return __fuse_get_acl(fc, &init_user_ns, inode, type, rcu);
+}
+
int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
struct posix_acl *acl, int type)
{
@@ -64,7 +105,7 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
if (fuse_is_bad(inode))
return -EIO;
- if (!fc->posix_acl || fc->no_setxattr)
+ if (fc->no_setxattr || fuse_no_acl(fc, inode))
return -EOPNOTSUPP;
if (type == ACL_TYPE_ACCESS)
@@ -99,7 +140,13 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
return ret;
}
- if (!vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) &&
+ /*
+ * Fuse daemons without FUSE_POSIX_ACL never changed the passed
+ * through POSIX ACLs. Such daemons don't expect setgid bits to
+ * be stripped.
+ */
+ if (fc->posix_acl &&
+ !vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) &&
!capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID))
extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
@@ -108,8 +155,15 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
} else {
ret = fuse_removexattr(inode, name);
}
- forget_all_cached_acls(inode);
- fuse_invalidate_attr(inode);
+
+ if (fc->posix_acl) {
+ /*
+ * Fuse daemons without FUSE_POSIX_ACL never cached POSIX ACLs
+ * and didn't invalidate attributes. Retain that behavior.
+ */
+ forget_all_cached_acls(inode);
+ fuse_invalidate_attr(inode);
+ }
return ret;
}
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index cd1a071b625ab..2725fb54328e5 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1942,7 +1942,8 @@ static const struct inode_operations fuse_dir_inode_operations = {
.permission = fuse_permission,
.getattr = fuse_getattr,
.listxattr = fuse_listxattr,
- .get_inode_acl = fuse_get_acl,
+ .get_inode_acl = fuse_get_inode_acl,
+ .get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
.fileattr_get = fuse_fileattr_get,
.fileattr_set = fuse_fileattr_set,
@@ -1964,7 +1965,8 @@ static const struct inode_operations fuse_common_inode_operations = {
.permission = fuse_permission,
.getattr = fuse_getattr,
.listxattr = fuse_listxattr,
- .get_inode_acl = fuse_get_acl,
+ .get_inode_acl = fuse_get_inode_acl,
+ .get_acl = fuse_get_acl,
.set_acl = fuse_set_acl,
.fileattr_get = fuse_fileattr_get,
.fileattr_set = fuse_fileattr_set,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index c673faefdcb9c..46797a171a84f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1264,11 +1264,11 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);
int fuse_removexattr(struct inode *inode, const char *name);
extern const struct xattr_handler *fuse_xattr_handlers[];
-extern const struct xattr_handler *fuse_acl_xattr_handlers[];
-extern const struct xattr_handler *fuse_no_acl_xattr_handlers[];
struct posix_acl;
-struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu);
+struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu);
+struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns,
+ struct dentry *dentry, int type);
int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
struct posix_acl *acl, int type);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6b3beda16c1ba..de9b9ec5ce810 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -311,7 +311,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
fuse_dax_dontcache(inode, attr->flags);
}
-static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
+static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr,
+ struct fuse_conn *fc)
{
inode->i_mode = attr->mode & S_IFMT;
inode->i_size = attr->size;
@@ -333,6 +334,12 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
new_decode_dev(attr->rdev));
} else
BUG();
+ /*
+ * Ensure that we don't cache acls for daemons without FUSE_POSIX_ACL
+ * so they see the exact same behavior as before.
+ */
+ if (!fc->posix_acl)
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
}
static int fuse_inode_eq(struct inode *inode, void *_nodeidp)
@@ -372,7 +379,7 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
if (!inode)
return NULL;
- fuse_init_inode(inode, attr);
+ fuse_init_inode(inode, attr, fc);
get_fuse_inode(inode)->nodeid = nodeid;
inode->i_flags |= S_AUTOMOUNT;
goto done;
@@ -388,7 +395,7 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
if (!fc->writeback_cache || !S_ISREG(attr->mode))
inode->i_flags |= S_NOCMTIME;
inode->i_generation = generation;
- fuse_init_inode(inode, attr);
+ fuse_init_inode(inode, attr, fc);
unlock_new_inode(inode);
} else if (fuse_stale_inode(inode, generation, attr)) {
/* nodeid was reused, any I/O on the old inode should fail */
@@ -1174,7 +1181,6 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
if ((flags & FUSE_POSIX_ACL)) {
fc->default_permissions = 1;
fc->posix_acl = 1;
- fm->sb->s_xattr = fuse_acl_xattr_handlers;
}
if (flags & FUSE_CACHE_SYMLINKS)
fc->cache_symlinks = 1;
@@ -1420,13 +1426,6 @@ static void fuse_sb_defaults(struct super_block *sb)
if (sb->s_user_ns != &init_user_ns)
sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER;
sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
-
- /*
- * If we are not in the initial user namespace posix
- * acls must be translated.
- */
- if (sb->s_user_ns != &init_user_ns)
- sb->s_xattr = fuse_no_acl_xattr_handlers;
}
static int fuse_fill_super_submount(struct super_block *sb,
diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
index 0d3e7177fce0a..9fe571ab569ed 100644
--- a/fs/fuse/xattr.c
+++ b/fs/fuse/xattr.c
@@ -203,27 +203,6 @@ static int fuse_xattr_set(const struct xattr_handler *handler,
return fuse_setxattr(inode, name, value, size, flags, 0);
}
-static bool no_xattr_list(struct dentry *dentry)
-{
- return false;
-}
-
-static int no_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
-{
- return -EOPNOTSUPP;
-}
-
-static int no_xattr_set(const struct xattr_handler *handler,
- struct user_namespace *mnt_userns,
- struct dentry *dentry, struct inode *nodee,
- const char *name, const void *value,
- size_t size, int flags)
-{
- return -EOPNOTSUPP;
-}
-
static const struct xattr_handler fuse_xattr_handler = {
.prefix = "",
.get = fuse_xattr_get,
@@ -234,33 +213,3 @@ const struct xattr_handler *fuse_xattr_handlers[] = {
&fuse_xattr_handler,
NULL
};
-
-const struct xattr_handler *fuse_acl_xattr_handlers[] = {
- &posix_acl_access_xattr_handler,
- &posix_acl_default_xattr_handler,
- &fuse_xattr_handler,
- NULL
-};
-
-static const struct xattr_handler fuse_no_acl_access_xattr_handler = {
- .name = XATTR_NAME_POSIX_ACL_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .list = no_xattr_list,
- .get = no_xattr_get,
- .set = no_xattr_set,
-};
-
-static const struct xattr_handler fuse_no_acl_default_xattr_handler = {
- .name = XATTR_NAME_POSIX_ACL_DEFAULT,
- .flags = ACL_TYPE_ACCESS,
- .list = no_xattr_list,
- .get = no_xattr_get,
- .set = no_xattr_set,
-};
-
-const struct xattr_handler *fuse_no_acl_xattr_handlers[] = {
- &fuse_no_acl_access_xattr_handler,
- &fuse_no_acl_default_xattr_handler,
- &fuse_xattr_handler,
- NULL
-};
--
GitLab
From 8be9fbd5345da52f4a74f7f81d55ff9fa0a2958e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 3 Jan 2023 12:49:11 +0000
Subject: [PATCH 1101/1167] ftrace: Export ftrace_free_filter() to modules
Setting filters on an ftrace ops results in some memory being allocated
for the filter hashes, which must be freed before the ops can be freed.
This can be done by removing every individual element of the hash by
calling ftrace_set_filter_ip() or ftrace_set_filter_ips() with `remove`
set, but this is somewhat error prone as it's easy to forget to remove
an element.
Make it easier to clean this up by exporting ftrace_free_filter(), which
can be used to clean up all of the filter hashes after an ftrace_ops has
been unregistered.
Using this, fix the ftrace-direct* samples to free hashes prior to being
unloaded. All other code either removes individual filters explicitly or
is built-in and already calls ftrace_free_filter().
Link: https://lkml.kernel.org/r/20230103124912.2948963-3-mark.rutland@arm.com
Cc: stable@vger.kernel.org
Cc: Florent Revest <revest@chromium.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Fixes: e1067a07cfbc ("ftrace/samples: Add module to test multi direct modify interface")
Fixes: 5fae941b9a6f ("ftrace/samples: Add multi direct interface test module")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/ftrace.c | 23 ++++++++++++++++++++-
samples/ftrace/ftrace-direct-multi-modify.c | 1 +
samples/ftrace/ftrace-direct-multi.c | 1 +
3 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 442438b93fe98..750aa3f08b25a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1248,12 +1248,17 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
call_rcu(&hash->rcu, __free_ftrace_hash_rcu);
}
+/**
+ * ftrace_free_filter - remove all filters for an ftrace_ops
+ * @ops - the ops to remove the filters from
+ */
void ftrace_free_filter(struct ftrace_ops *ops)
{
ftrace_ops_init(ops);
free_ftrace_hash(ops->func_hash->filter_hash);
free_ftrace_hash(ops->func_hash->notrace_hash);
}
+EXPORT_SYMBOL_GPL(ftrace_free_filter);
static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
{
@@ -5839,6 +5844,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi);
*
* Filters denote which functions should be enabled when tracing is enabled
* If @ip is NULL, it fails to update filter.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
int remove, int reset)
@@ -5858,7 +5867,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
*
* Filters denote which functions should be enabled when tracing is enabled
* If @ips array or any ip specified within is NULL , it fails to update filter.
- */
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
+*/
int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips,
unsigned int cnt, int remove, int reset)
{
@@ -5900,6 +5913,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
*
* Filters denote which functions should be enabled when tracing is enabled.
* If @buf is NULL and reset is set, all functions will be enabled for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
@@ -5919,6 +5936,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
* Notrace Filters denote which functions should not be enabled when tracing
* is enabled. If @buf is NULL and reset is set, all functions will be enabled
* for tracing.
+ *
+ * This can allocate memory which must be freed before @ops can be freed,
+ * either by removing each filtered addr or by using
+ * ftrace_free_filter(@ops).
*/
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c
index d52370cad0b6e..a825dbd2c9cfd 100644
--- a/samples/ftrace/ftrace-direct-multi-modify.c
+++ b/samples/ftrace/ftrace-direct-multi-modify.c
@@ -152,6 +152,7 @@ static void __exit ftrace_direct_multi_exit(void)
{
kthread_stop(simple_tsk);
unregister_ftrace_direct_multi(&direct, my_tramp);
+ ftrace_free_filter(&direct);
}
module_init(ftrace_direct_multi_init);
diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c
index ec1088922517d..d955a26506053 100644
--- a/samples/ftrace/ftrace-direct-multi.c
+++ b/samples/ftrace/ftrace-direct-multi.c
@@ -79,6 +79,7 @@ static int __init ftrace_direct_multi_init(void)
static void __exit ftrace_direct_multi_exit(void)
{
unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp);
+ ftrace_free_filter(&direct);
}
module_init(ftrace_direct_multi_init);
--
GitLab
From 3bb06eb6e9acf7c4a3e1b5bc87aed398ff8e2253 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Wed, 4 Jan 2023 16:14:12 -0500
Subject: [PATCH 1102/1167] tracing: Make sure trace_printk() can output as
soon as it can be used
Currently trace_printk() can be used as soon as early_trace_init() is
called from start_kernel(). But if a crash happens, and
"ftrace_dump_on_oops" is set on the kernel command line, all you get will
be:
[ 0.456075] <idle>-0 0dN.2. 347519us : Unknown type 6
[ 0.456075] <idle>-0 0dN.2. 353141us : Unknown type 6
[ 0.456075] <idle>-0 0dN.2. 358684us : Unknown type 6
This is because the trace_printk() event (type 6) hasn't been registered
yet. That gets done via an early_initcall(), which may be early, but not
early enough.
Instead of registering the trace_printk() event (and other ftrace events,
which are not trace events) via an early_initcall(), have them registered at
the same time that trace_printk() can be used. This way, if there is a
crash before early_initcall(), then the trace_printk()s will actually be
useful.
Link: https://lkml.kernel.org/r/20230104161412.019f6c55@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Fixes: e725c731e3bb1 ("tracing: Split tracing initialization into two for early initialization")
Reported-by: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace.c | 2 ++
kernel/trace/trace.h | 1 +
kernel/trace/trace_output.c | 3 +--
3 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a555a861b9781..78ed5f1baa8cd 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -10295,6 +10295,8 @@ void __init early_trace_init(void)
static_key_enable(&tracepoint_printk_key.key);
}
tracer_alloc_buffers();
+
+ init_events();
}
void __init trace_init(void)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e46a49269be20..4eb6d6b97a9fd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1490,6 +1490,7 @@ extern void trace_event_enable_cmd_record(bool enable);
extern void trace_event_enable_tgid_record(bool enable);
extern int event_trace_init(void);
+extern int init_events(void);
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
extern void __trace_early_add_events(struct trace_array *tr);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 57a13b61f1865..bd475a00f96d1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1535,7 +1535,7 @@ static struct trace_event *events[] __initdata = {
NULL
};
-__init static int init_events(void)
+__init int init_events(void)
{
struct trace_event *event;
int i, ret;
@@ -1548,4 +1548,3 @@ __init static int init_events(void)
return 0;
}
-early_initcall(init_events);
--
GitLab
From d968117a7e8e5572762eacbdbca13bc96710e9a3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 24 Jan 2023 17:44:14 +0100
Subject: [PATCH 1103/1167] Revert "Merge branch 'ethtool-mac-merge'"
This reverts commit 0ad999c1eec879f06cc52ef7df4d0dbee4a2d7eb, reversing
changes made to e38553bdc377e3e7a6caa9dd9770d8b644d8dac3.
It was not intended for net.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
net/ethtool/netlink.h | 26 --------------------------
1 file changed, 26 deletions(-)
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 744b3ab966b07..3753787ba233b 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -111,32 +111,6 @@ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr,
*mod = true;
}
-/**
- * ethnl_update_bool() - update bool from NLA_U8 attribute
- * @dst: value to update
- * @attr: netlink attribute with new value or null
- * @mod: pointer to bool for modification tracking
- *
- * Use the u8 value from NLA_U8 netlink attribute @attr to set bool variable
- * pointed to by @dst to false (if zero) or 1 (if not); do nothing if @attr is
- * null. Bool pointed to by @mod is set to true if this function changed the
- * logical value of *dst, otherwise it is left as is.
- */
-static inline void ethnl_update_bool(bool *dst, const struct nlattr *attr,
- bool *mod)
-{
- u8 val;
-
- if (!attr)
- return;
- val = !!nla_get_u8(attr);
- if (*dst == val)
- return;
-
- *dst = val;
- *mod = true;
-}
-
/**
* ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute
* @dst: value to update
--
GitLab
From 7ae4ba7195b1bac04a4210a499da9d8c63b0ba9c Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Google)" <rostedt@goodmis.org>
Date: Mon, 23 Jan 2023 11:22:52 -0500
Subject: [PATCH 1104/1167] ftrace/scripts: Update the instructions for
ftrace-bisect.sh
The instructions for the ftrace-bisect.sh script, which is used to find
what function is being traced that is causing a kernel crash, and possibly
a triple fault reboot, uses the old method. In 5.1, a new feature was
added that let the user write in the index into available_filter_functions
that maps to the function a user wants to set in set_ftrace_filter (or
set_ftrace_notrace). This takes O(1) to set, as suppose to writing a
function name, which takes O(n) (where n is the number of functions in
available_filter_functions).
The ftrace-bisect.sh requires setting half of the functions in
available_filter_functions, which is O(n^2) using the name method to enable
and can take several minutes to complete. The number method is O(n) which
takes less than a second to complete. Using the number method for any
kernel 5.1 and after is the proper way to do the bisect.
Update the usage to reflect the new change, as well as using the
/sys/kernel/tracing path instead of the obsolete debugfs path.
Link: https://lkml.kernel.org/r/20230123112252.022003dd@gandalf.local.home
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Fixes: f79b3f338564e ("ftrace: Allow enabling of filters via index of available_filter_functions")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
scripts/tracing/ftrace-bisect.sh | 34 ++++++++++++++++++++++++--------
1 file changed, 26 insertions(+), 8 deletions(-)
diff --git a/scripts/tracing/ftrace-bisect.sh b/scripts/tracing/ftrace-bisect.sh
index 926701162bc83..bb4f59262bbe9 100755
--- a/scripts/tracing/ftrace-bisect.sh
+++ b/scripts/tracing/ftrace-bisect.sh
@@ -12,7 +12,7 @@
# (note, if this is a problem with function_graph tracing, then simply
# replace "function" with "function_graph" in the following steps).
#
-# # cd /sys/kernel/debug/tracing
+# # cd /sys/kernel/tracing
# # echo schedule > set_ftrace_filter
# # echo function > current_tracer
#
@@ -20,22 +20,40 @@
#
# # echo nop > current_tracer
#
-# # cat available_filter_functions > ~/full-file
+# Starting with v5.1 this can be done with numbers, making it much faster:
+#
+# The old (slow) way, for kernels before v5.1.
+#
+# [old-way] # cat available_filter_functions > ~/full-file
+#
+# [old-way] *** Note *** this process will take several minutes to update the
+# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we
+# [old-way] are dealing with thousands of functions. So go have coffee, talk
+# [old-way] with your coworkers, read facebook. And eventually, this operation
+# [old-way] will end.
+#
+# The new way (using numbers) is an O(n) operation, and usually takes less than a second.
+#
+# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file
+#
+# This will create a sequence of numbers that match the functions in
+# available_filter_functions, and when echoing in a number into the
+# set_ftrace_filter file, it will enable the corresponding function in
+# O(1) time. Making enabling all functions O(n) where n is the number of
+# functions to enable.
+#
+# For either the new or old way, the rest of the operations remain the same.
+#
# # ftrace-bisect ~/full-file ~/test-file ~/non-test-file
# # cat ~/test-file > set_ftrace_filter
#
-# *** Note *** this will take several minutes. Setting multiple functions is
-# an O(n^2) operation, and we are dealing with thousands of functions. So go
-# have coffee, talk with your coworkers, read facebook. And eventually, this
-# operation will end.
-#
# # echo function > current_tracer
#
# If it crashes, we know that ~/test-file has a bad function.
#
# Reboot back to test kernel.
#
-# # cd /sys/kernel/debug/tracing
+# # cd /sys/kernel/tracing
# # mv ~/test-file ~/full-file
#
# If it didn't crash.
--
GitLab
From ac28d0a0f40782d216f6aaaf22e0d8bded06a435 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 24 Jan 2023 10:16:47 -0800
Subject: [PATCH 1105/1167] tracing: Kconfig: Fix spelling/grammar/punctuation
Fix some editorial nits in trace Kconfig.
Link: https://lkml.kernel.org/r/20230124181647.15902-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/Kconfig | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 197545241ab83..d7043043f59c8 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -933,8 +933,8 @@ config RING_BUFFER_RECORD_RECURSION
default y
help
The ring buffer has its own internal recursion. Although when
- recursion happens it wont cause harm because of the protection,
- but it does cause an unwanted overhead. Enabling this option will
+ recursion happens it won't cause harm because of the protection,
+ but it does cause unwanted overhead. Enabling this option will
place where recursion was detected into the ftrace "recursed_functions"
file.
@@ -1017,8 +1017,8 @@ config RING_BUFFER_STARTUP_TEST
The test runs for 10 seconds. This will slow your boot time
by at least 10 more seconds.
- At the end of the test, statics and more checks are done.
- It will output the stats of each per cpu buffer. What
+ At the end of the test, statistics and more checks are done.
+ It will output the stats of each per cpu buffer: What
was written, the sizes, what was read, what was lost, and
other similar details.
--
GitLab
From 5a5754a4997c372292e57ed631807131c63cebaf Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 24 Jan 2023 09:17:38 -0800
Subject: [PATCH 1106/1167] nvme-pci: flush initial scan_work for async probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
The nvme device may have a namespace with the root partition, so make
sure we've completed scanning before returning from the async probe.
Fixes: eac3ef262941 ("nvme-pci: split the initial probe from the rest path")
Reported-by: Klaus Jensen <its@irrelevant.dk>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Klaus Jensen <k.jensen@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/pci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 1ff8843bc4b36..c734934c407cc 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3102,6 +3102,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
nvme_start_ctrl(&dev->ctrl);
nvme_put_ctrl(&dev->ctrl);
+ flush_work(&dev->ctrl.scan_work);
return 0;
out_disable:
--
GitLab
From 6757a7abe47bcb12cb2d45661067e182424b0ee3 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Mon, 23 Jan 2023 09:21:10 -0800
Subject: [PATCH 1107/1167] thermal: intel: int340x: Protect trip temperature
from concurrent updates
Trip temperatures are read using ACPI methods and stored in the memory
during zone initializtion and when the firmware sends a notification for
change. This trip temperature is returned when the thermal core calls via
callback get_trip_temp().
But it is possible that while updating the memory copy of the trips when
the firmware sends a notification for change, thermal core is reading the
trip temperature via the callback get_trip_temp(). This may return invalid
trip temperature.
To address this add a mutex to protect the invalid temperature reads in
the callback get_trip_temp() and int340x_thermal_read_trips().
Fixes: 5fbf7f27fa3d ("Thermal/int340x: Add common thermal zone handler")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: 5.0+ <stable@vger.kernel.org> # 5.0+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
.../int340x_thermal/int340x_thermal_zone.c | 18 +++++++++++++++---
.../int340x_thermal/int340x_thermal_zone.h | 1 +
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 62c0aa5d07837..852f6c579af5c 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -44,11 +44,13 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone,
int trip, int *temp)
{
struct int34x_thermal_zone *d = zone->devdata;
- int i;
+ int i, ret = 0;
if (d->override_ops && d->override_ops->get_trip_temp)
return d->override_ops->get_trip_temp(zone, trip, temp);
+ mutex_lock(&d->trip_mutex);
+
if (trip < d->aux_trip_nr)
*temp = d->aux_trips[trip];
else if (trip == d->crt_trip_id)
@@ -66,10 +68,12 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone,
}
}
if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+ mutex_unlock(&d->trip_mutex);
+
+ return ret;
}
static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
@@ -180,6 +184,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone)
int trip_cnt = int34x_zone->aux_trip_nr;
int i;
+ mutex_lock(&int34x_zone->trip_mutex);
+
int34x_zone->crt_trip_id = -1;
if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT",
&int34x_zone->crt_temp))
@@ -207,6 +213,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone)
int34x_zone->act_trips[i].valid = true;
}
+ mutex_unlock(&int34x_zone->trip_mutex);
+
return trip_cnt;
}
EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
@@ -230,6 +238,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
if (!int34x_thermal_zone)
return ERR_PTR(-ENOMEM);
+ mutex_init(&int34x_thermal_zone->trip_mutex);
+
int34x_thermal_zone->adev = adev;
int34x_thermal_zone->override_ops = override_ops;
@@ -281,6 +291,7 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
kfree(int34x_thermal_zone->aux_trips);
err_trip_alloc:
+ mutex_destroy(&int34x_thermal_zone->trip_mutex);
kfree(int34x_thermal_zone);
return ERR_PTR(ret);
}
@@ -292,6 +303,7 @@ void int340x_thermal_zone_remove(struct int34x_thermal_zone
thermal_zone_device_unregister(int34x_thermal_zone->zone);
acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
kfree(int34x_thermal_zone->aux_trips);
+ mutex_destroy(&int34x_thermal_zone->trip_mutex);
kfree(int34x_thermal_zone);
}
EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h
index 3b4971df1b33b..8f9872afd0d3c 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h
@@ -32,6 +32,7 @@ struct int34x_thermal_zone {
struct thermal_zone_device_ops *override_ops;
void *priv_data;
struct acpi_lpat_conversion_table *lpat_table;
+ struct mutex trip_mutex;
};
struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *,
--
GitLab
From 854f0912f813c3b7a4d35517658ca7f1511a69e2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 24 Jan 2023 09:23:56 -0800
Subject: [PATCH 1108/1167] ext4: make xattr char unsignedness in hash explicit
Commit f3bbac32475b ("ext4: deal with legacy signed xattr name hash
values") added a hashing function for the legacy case of having the
xattr hash calculated using a signed 'char' type. It left the unsigned
case alone, since it's all implicitly handled by the '-funsigned-char'
compiler option.
However, there's been some noise about back-porting it all into stable
kernels that lack the '-funsigned-char', so let's just make that at
least possible by making the whole 'this uses unsigned char' very
explicit in the code itself. Whether such a back-port is really
warranted or not, I'll leave to others, but at least together with this
change it is technically sensible.
Also, add a 'pr_warn_once()' for reporting the "hey, signedness for this
hash calculation has changed" issue. Hopefully it never triggers except
for that xfstests generic/454 test-case, but even if it does it's just
good information to have.
If for no other reason than "we can remove the legacy signed hash code
entirely if nobody ever sees the message any more".
Cc: Sasha Levin <sashal@kernel.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Andreas Dilger <adilger@dilger.ca>
Cc: Theodore Ts'o <tytso@mit.edu>,
Cc: Jason Donenfeld <Jason@zx2c4.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
fs/ext4/xattr.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 69a1b8c6a2eca..a2f04a3808db5 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -482,11 +482,12 @@ ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
*/
e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len,
&tmp_data, 1);
- if (e_hash == entry->e_hash)
- return 0;
-
/* Still no match - bad */
- return -EFSCORRUPTED;
+ if (e_hash != entry->e_hash)
+ return -EFSCORRUPTED;
+
+ /* Let people know about old hash */
+ pr_warn_once("ext4: filesystem with signed xattr name hash");
}
return 0;
}
@@ -3096,7 +3097,7 @@ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
while (name_len--) {
hash = (hash << NAME_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
- *name++;
+ (unsigned char)*name++;
}
while (value_count--) {
hash = (hash << VALUE_HASH_SHIFT) ^
--
GitLab
From 0254127ab977e70798707a7a2b757c9f3c971210 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 5 Dec 2022 11:35:57 +0100
Subject: [PATCH 1109/1167] module: Don't wait for GOING modules
During a system boot, it can happen that the kernel receives a burst of
requests to insert the same module but loading it eventually fails
during its init call. For instance, udev can make a request to insert
a frequency module for each individual CPU when another frequency module
is already loaded which causes the init function of the new module to
return an error.
Since commit 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for
modules that have finished loading"), the kernel waits for modules in
MODULE_STATE_GOING state to finish unloading before making another
attempt to load the same module.
This creates unnecessary work in the described scenario and delays the
boot. In the worst case, it can prevent udev from loading drivers for
other devices and might cause timeouts of services waiting on them and
subsequently a failed boot.
This patch attempts a different solution for the problem 6e6de3dee51a
was trying to solve. Rather than waiting for the unloading to complete,
it returns a different error code (-EBUSY) for modules in the GOING
state. This should avoid the error situation that was described in
6e6de3dee51a (user space attempting to load a dependent module because
the -EEXIST error code would suggest to user space that the first module
had been loaded successfully), while avoiding the delay situation too.
This has been tested on linux-next since December 2022 and passes
all kmod selftests except test 0009 with module compression enabled
but it has been confirmed that this issue has existed and has gone
unnoticed since prior to this commit and can also be reproduced without
module compression with a simple usleep(5000000) on tools/modprobe.c [0].
These failures are caused by hitting the kernel mod_concurrent_max and can
happen either due to a self inflicted kernel module auto-loead DoS somehow
or on a system with large CPU count and each CPU count incorrectly triggering
many module auto-loads. Both of those issues need to be fixed in-kernel.
[0] https://lore.kernel.org/all/Y9A4fiobL6IHp%2F%2FP@bombadil.infradead.org/
Fixes: 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading")
Co-developed-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Cc: stable@vger.kernel.org
Reviewed-by: Petr Mladek <pmladek@suse.com>
[mcgrof: enhance commit log with testing and kmod test result interpretation ]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
kernel/module/main.c | 26 +++++++++++++++++++++-----
1 file changed, 21 insertions(+), 5 deletions(-)
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 48568a0f5651c..4ac3fe43e6c8f 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2393,7 +2393,8 @@ static bool finished_loading(const char *name)
sched_annotate_sleep();
mutex_lock(&module_mutex);
mod = find_module_all(name, strlen(name), true);
- ret = !mod || mod->state == MODULE_STATE_LIVE;
+ ret = !mod || mod->state == MODULE_STATE_LIVE
+ || mod->state == MODULE_STATE_GOING;
mutex_unlock(&module_mutex);
return ret;
@@ -2569,20 +2570,35 @@ static int add_unformed_module(struct module *mod)
mod->state = MODULE_STATE_UNFORMED;
-again:
mutex_lock(&module_mutex);
old = find_module_all(mod->name, strlen(mod->name), true);
if (old != NULL) {
- if (old->state != MODULE_STATE_LIVE) {
+ if (old->state == MODULE_STATE_COMING
+ || old->state == MODULE_STATE_UNFORMED) {
/* Wait in case it fails to load. */
mutex_unlock(&module_mutex);
err = wait_event_interruptible(module_wq,
finished_loading(mod->name));
if (err)
goto out_unlocked;
- goto again;
+
+ /* The module might have gone in the meantime. */
+ mutex_lock(&module_mutex);
+ old = find_module_all(mod->name, strlen(mod->name),
+ true);
}
- err = -EEXIST;
+
+ /*
+ * We are here only when the same module was being loaded. Do
+ * not try to load it again right now. It prevents long delays
+ * caused by serialized module load failures. It might happen
+ * when more devices of the same type trigger load of
+ * a particular module.
+ */
+ if (old && old->state == MODULE_STATE_LIVE)
+ err = -EEXIST;
+ else
+ err = -EBUSY;
goto out;
}
mod_update_bounds(mod);
--
GitLab
From 685b64e4d6da4be8b4595654a57db663b3d1dfc2 Mon Sep 17 00:00:00 2001
From: Chuang Wang <nashuiliang@gmail.com>
Date: Tue, 27 Dec 2022 10:30:36 +0800
Subject: [PATCH 1110/1167] tracing/osnoise: Use built-in RCU list checking
list_for_each_entry_rcu() has built-in RCU and lock checking.
Pass cond argument to list_for_each_entry_rcu() to silence false lockdep
warning when CONFIG_PROVE_RCU_LIST is enabled.
Execute as follow:
[tracing]# echo osnoise > current_tracer
[tracing]# echo 1 > tracing_on
[tracing]# echo 0 > tracing_on
The trace_types_lock is held when osnoise_tracer_stop() or
timerlat_tracer_stop() are called in the non-RCU read side section.
So, pass lockdep_is_held(&trace_types_lock) to silence false lockdep
warning.
Link: https://lkml.kernel.org/r/20221227023036.784337-1-nashuiliang@gmail.com
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Fixes: dae181349f1e ("tracing/osnoise: Support a list of trace_array *tr")
Acked-by: Daniel Bristot de Oliveira <bristot@kernel.org>
Signed-off-by: Chuang Wang <nashuiliang@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace_osnoise.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 94c1b5eb1dc02..210e1f1683929 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -147,9 +147,8 @@ static void osnoise_unregister_instance(struct trace_array *tr)
* register/unregister serialization is provided by trace's
* trace_types_lock.
*/
- lockdep_assert_held(&trace_types_lock);
-
- list_for_each_entry_rcu(inst, &osnoise_instances, list) {
+ list_for_each_entry_rcu(inst, &osnoise_instances, list,
+ lockdep_is_held(&trace_types_lock)) {
if (inst->tr == tr) {
list_del_rcu(&inst->list);
found = 1;
--
GitLab
From 8b152e9150d07a885f95e1fd401fc81af202d9a4 Mon Sep 17 00:00:00 2001
From: Natalia Petrova <n.petrova@fintech.ru>
Date: Wed, 11 Jan 2023 15:04:09 +0300
Subject: [PATCH 1111/1167] trace_events_hist: add check for return value of
'create_hist_field'
Function 'create_hist_field' is called recursively at
trace_events_hist.c:1954 and can return NULL-value that's why we have
to check it to avoid null pointer dereference.
Found by Linux Verification Center (linuxtesting.org) with SVACE.
Link: https://lkml.kernel.org/r/20230111120409.4111-1-n.petrova@fintech.ru
Cc: stable@vger.kernel.org
Fixes: 30350d65ac56 ("tracing: Add variable support to hist triggers")
Signed-off-by: Natalia Petrova <n.petrova@fintech.ru>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace_events_hist.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index fcaf226b77446..5edbf6b1da3f3 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1988,6 +1988,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 :
HIST_FIELD_FN_BUCKET;
hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
+ if (!hist_field->operands[0])
+ goto free;
hist_field->size = hist_field->operands[0]->size;
hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL);
if (!hist_field->type)
--
GitLab
From ca0f2cfc495d9b614ac6431d7029f1f140403155 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 24 Jan 2023 10:16:55 -0800
Subject: [PATCH 1112/1167] lib: Kconfig: fix spellos
Fix spelling in lib/ Kconfig files.
(reported by codespell)
Link: https://lkml.kernel.org/r/20230124181655.16269-1-rdunlap@infradead.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Marco Elver <elver@google.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: kasan-dev@googlegroups.com
Reviewed-by: Marco Elver <elver@google.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
lib/Kconfig.debug | 2 +-
lib/Kconfig.kcsan | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 881c3f84e88a3..6426dbf99c122 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1917,7 +1917,7 @@ config FUNCTION_ERROR_INJECTION
help
Add fault injections into various functions that are annotated with
ALLOW_ERROR_INJECTION() in the kernel. BPF may also modify the return
- value of theses functions. This is useful to test error paths of code.
+ value of these functions. This is useful to test error paths of code.
If unsure, say N
diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan
index 375575a5a0e3c..4dedd61e5192d 100644
--- a/lib/Kconfig.kcsan
+++ b/lib/Kconfig.kcsan
@@ -194,7 +194,7 @@ config KCSAN_WEAK_MEMORY
Enable support for modeling a subset of weak memory, which allows
detecting a subset of data races due to missing memory barriers.
- Depends on KCSAN_STRICT, because the options strenghtening certain
+ Depends on KCSAN_STRICT, because the options strengthening certain
plain accesses by default (depending on !KCSAN_STRICT) reduce the
ability to detect any data races invoving reordered accesses, in
particular reordered writes.
--
GitLab
From ea4fdbaa2f7798cb25adbe4fd52ffc6356f097bb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 23 Jan 2023 08:45:52 +0000
Subject: [PATCH 1113/1167] net/sched: sch_taprio: do not schedule in
taprio_reset()
As reported by syzbot and hinted by Vinicius, I should not have added
a qdisc_synchronize() call in taprio_reset()
taprio_reset() can be called with qdisc spinlock held (and BH disabled)
as shown in included syzbot report [1].
Only taprio_destroy() needed this synchronization, as explained
in the blamed commit changelog.
[1]
BUG: scheduling while atomic: syz-executor150/5091/0x00000202
2 locks held by syz-executor150/5091:
Modules linked in:
Preemption disabled at:
[<0000000000000000>] 0x0
Kernel panic - not syncing: scheduling while atomic: panic_on_warn set ...
CPU: 1 PID: 5091 Comm: syz-executor150 Not tainted 6.2.0-rc3-syzkaller-00219-g010a74f52203 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/12/2023
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106
panic+0x2cc/0x626 kernel/panic.c:318
check_panic_on_warn.cold+0x19/0x35 kernel/panic.c:238
__schedule_bug.cold+0xd5/0xfe kernel/sched/core.c:5836
schedule_debug kernel/sched/core.c:5865 [inline]
__schedule+0x34e4/0x5450 kernel/sched/core.c:6500
schedule+0xde/0x1b0 kernel/sched/core.c:6682
schedule_timeout+0x14e/0x2a0 kernel/time/timer.c:2167
schedule_timeout_uninterruptible kernel/time/timer.c:2201 [inline]
msleep+0xb6/0x100 kernel/time/timer.c:2322
qdisc_synchronize include/net/sch_generic.h:1295 [inline]
taprio_reset+0x93/0x270 net/sched/sch_taprio.c:1703
qdisc_reset+0x10c/0x770 net/sched/sch_generic.c:1022
dev_reset_queue+0x92/0x130 net/sched/sch_generic.c:1285
netdev_for_each_tx_queue include/linux/netdevice.h:2464 [inline]
dev_deactivate_many+0x36d/0x9f0 net/sched/sch_generic.c:1351
dev_deactivate+0xed/0x1b0 net/sched/sch_generic.c:1374
qdisc_graft+0xe4a/0x1380 net/sched/sch_api.c:1080
tc_modify_qdisc+0xb6b/0x19a0 net/sched/sch_api.c:1689
rtnetlink_rcv_msg+0x43e/0xca0 net/core/rtnetlink.c:6141
netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2564
netlink_unicast_kernel net/netlink/af_netlink.c:1330 [inline]
netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1356
netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1932
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg+0xd3/0x120 net/socket.c:734
____sys_sendmsg+0x712/0x8c0 net/socket.c:2476
___sys_sendmsg+0x110/0x1b0 net/socket.c:2530
__sys_sendmsg+0xf7/0x1c0 net/socket.c:2559
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
Fixes: 3a415d59c1db ("net/sched: sch_taprio: fix possible use-after-free")
Link: https://lore.kernel.org/netdev/167387581653.2747.13878941339893288655.git-patchwork-notify@kernel.org/T/
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Link: https://lore.kernel.org/r/20230123084552.574396-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sched/sch_taprio.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 9a11a499ea2df..c322a61eaeeac 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1700,7 +1700,6 @@ static void taprio_reset(struct Qdisc *sch)
int i;
hrtimer_cancel(&q->advance_timer);
- qdisc_synchronize(sch);
if (q->qdiscs) {
for (i = 0; i < dev->num_tx_queues; i++)
--
GitLab
From 458e279f861d3f61796894cd158b780765a1569f Mon Sep 17 00:00:00 2001
From: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Date: Mon, 23 Jan 2023 14:59:33 -0300
Subject: [PATCH 1114/1167] sctp: fail if no bound addresses can be used for a
given scope
Currently, if you bind the socket to something like:
servaddr.sin6_family = AF_INET6;
servaddr.sin6_port = htons(0);
servaddr.sin6_scope_id = 0;
inet_pton(AF_INET6, "::1", &servaddr.sin6_addr);
And then request a connect to:
connaddr.sin6_family = AF_INET6;
connaddr.sin6_port = htons(20000);
connaddr.sin6_scope_id = if_nametoindex("lo");
inet_pton(AF_INET6, "fe88::1", &connaddr.sin6_addr);
What the stack does is:
- bind the socket
- create a new asoc
- to handle the connect
- copy the addresses that can be used for the given scope
- try to connect
But the copy returns 0 addresses, and the effect is that it ends up
trying to connect as if the socket wasn't bound, which is not the
desired behavior. This unexpected behavior also allows KASLR leaks
through SCTP diag interface.
The fix here then is, if when trying to copy the addresses that can
be used for the scope used in connect() it returns 0 addresses, bail
out. This is what TCP does with a similar reproducer.
Reported-by: Pietro Borrello <borrello@diag.uniroma1.it>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Link: https://lore.kernel.org/r/9fcd182f1099f86c6661f3717f63712ddd1c676c.1674496737.git.marcelo.leitner@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
net/sctp/bind_addr.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 59e653b528b1f..6b95d3ba8fe1c 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -73,6 +73,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest,
}
}
+ /* If somehow no addresses were found that can be used with this
+ * scope, it's an error.
+ */
+ if (list_empty(&dest->address_list))
+ error = -ENETUNREACH;
+
out:
if (error)
sctp_bind_addr_clean(dest);
--
GitLab
From 418e53401e478a743cf33b1c32ea0728f0afef66 Mon Sep 17 00:00:00 2001
From: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Date: Mon, 23 Jan 2023 16:57:14 -0800
Subject: [PATCH 1115/1167] ice: move devlink port creation/deletion
Commit a286ba738714 ("ice: reorder PF/representor devlink
port register/unregister flows") moved the code to create
and destroy the devlink PF port. This was fine, but created
a corner case issue in the case of ice_register_netdev()
failing. In that case, the driver would end up calling
ice_devlink_destroy_pf_port() twice.
Additionally, it makes no sense to tie creation of the devlink
PF port to the creation of the netdev so separate out the
code to create/destroy the devlink PF port from the netdev
code. This makes it a cleaner interface.
Fixes: a286ba738714 ("ice: reorder PF/representor devlink port register/unregister flows")
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Tested-by: Gurucharan G <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20230124005714.3996270-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/intel/ice/ice_lib.c | 3 ---
drivers/net/ethernet/intel/ice/ice_main.c | 25 +++++++++++++++--------
2 files changed, 17 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 94aa834cd9a6b..a596e07b3ce9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3235,9 +3235,6 @@ int ice_vsi_release(struct ice_vsi *vsi)
}
}
- if (vsi->type == ICE_VSI_PF)
- ice_devlink_destroy_pf_port(pf);
-
if (vsi->type == ICE_VSI_VF &&
vsi->agg_node && vsi->agg_node->valid)
vsi->agg_node->num_vsis--;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a9a7f8b52140b..237ede2cffb0a 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4590,7 +4590,7 @@ static void ice_print_wake_reason(struct ice_pf *pf)
}
/**
- * ice_register_netdev - register netdev and devlink port
+ * ice_register_netdev - register netdev
* @pf: pointer to the PF struct
*/
static int ice_register_netdev(struct ice_pf *pf)
@@ -4602,11 +4602,6 @@ static int ice_register_netdev(struct ice_pf *pf)
if (!vsi || !vsi->netdev)
return -EIO;
- err = ice_devlink_create_pf_port(pf);
- if (err)
- goto err_devlink_create;
-
- SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
err = register_netdev(vsi->netdev);
if (err)
goto err_register_netdev;
@@ -4617,8 +4612,6 @@ static int ice_register_netdev(struct ice_pf *pf)
return 0;
err_register_netdev:
- ice_devlink_destroy_pf_port(pf);
-err_devlink_create:
free_netdev(vsi->netdev);
vsi->netdev = NULL;
clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
@@ -4636,6 +4629,7 @@ static int
ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
{
struct device *dev = &pdev->dev;
+ struct ice_vsi *vsi;
struct ice_pf *pf;
struct ice_hw *hw;
int i, err;
@@ -4918,6 +4912,18 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
pcie_print_link_status(pf->pdev);
probe_done:
+ err = ice_devlink_create_pf_port(pf);
+ if (err)
+ goto err_create_pf_port;
+
+ vsi = ice_get_main_vsi(pf);
+ if (!vsi || !vsi->netdev) {
+ err = -EINVAL;
+ goto err_netdev_reg;
+ }
+
+ SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
+
err = ice_register_netdev(pf);
if (err)
goto err_netdev_reg;
@@ -4955,6 +4961,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
err_devlink_reg_param:
ice_devlink_unregister_params(pf);
err_netdev_reg:
+ ice_devlink_destroy_pf_port(pf);
+err_create_pf_port:
err_send_version_unroll:
ice_vsi_release_all(pf);
err_alloc_sw_unroll:
@@ -5083,6 +5091,7 @@ static void ice_remove(struct pci_dev *pdev)
ice_setup_mc_magic_wake(pf);
ice_vsi_release_all(pf);
mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
+ ice_devlink_destroy_pf_port(pf);
ice_set_wake(pf);
ice_free_irq_msix_misc(pf);
ice_for_each_vsi(pf, i) {
--
GitLab
From ca0254998be4d74cf6add70ccfab0d2dbd362a10 Mon Sep 17 00:00:00 2001
From: Liao Chang <liaochang1@huawei.com>
Date: Mon, 16 Jan 2023 14:43:42 +0800
Subject: [PATCH 1116/1167] riscv/kprobe: Fix instruction simulation of JALR
Set kprobe at 'jalr 1140(ra)' of vfs_write results in the following
crash:
[ 32.092235] Unable to handle kernel access to user memory without uaccess routines at virtual address 00aaaaaad77b1170
[ 32.093115] Oops [#1]
[ 32.093251] Modules linked in:
[ 32.093626] CPU: 0 PID: 135 Comm: ftracetest Not tainted 6.2.0-rc2-00013-gb0aa5e5df0cb-dirty #16
[ 32.093985] Hardware name: riscv-virtio,qemu (DT)
[ 32.094280] epc : ksys_read+0x88/0xd6
[ 32.094855] ra : ksys_read+0xc0/0xd6
[ 32.095016] epc : ffffffff801cda80 ra : ffffffff801cdab8 sp : ff20000000d7bdc0
[ 32.095227] gp : ffffffff80f14000 tp : ff60000080f9cb40 t0 : ffffffff80f13e80
[ 32.095500] t1 : ffffffff8000c29c t2 : ffffffff800dbc54 s0 : ff20000000d7be60
[ 32.095716] s1 : 0000000000000000 a0 : ffffffff805a64ae a1 : ffffffff80a83708
[ 32.095921] a2 : ffffffff80f160a0 a3 : 0000000000000000 a4 : f229b0afdb165300
[ 32.096171] a5 : f229b0afdb165300 a6 : ffffffff80eeebd0 a7 : 00000000000003ff
[ 32.096411] s2 : ff6000007ff76800 s3 : fffffffffffffff7 s4 : 00aaaaaad77b1170
[ 32.096638] s5 : ffffffff80f160a0 s6 : ff6000007ff76800 s7 : 0000000000000030
[ 32.096865] s8 : 00ffffffc3d97be0 s9 : 0000000000000007 s10: 00aaaaaad77c9410
[ 32.097092] s11: 0000000000000000 t3 : ffffffff80f13e48 t4 : ffffffff8000c29c
[ 32.097317] t5 : ffffffff8000c29c t6 : ffffffff800dbc54
[ 32.097505] status: 0000000200000120 badaddr: 00aaaaaad77b1170 cause: 000000000000000d
[ 32.098011] [<ffffffff801cdb72>] ksys_write+0x6c/0xd6
[ 32.098222] [<ffffffff801cdc06>] sys_write+0x2a/0x38
[ 32.098405] [<ffffffff80003c76>] ret_from_syscall+0x0/0x2
Since the rs1 and rd might be the same one, such as 'jalr 1140(ra)',
hence it requires obtaining the target address from rs1 followed by
updating rd.
Fixes: c22b0bcb1dd0 ("riscv: Add kprobes supported")
Signed-off-by: Liao Chang <liaochang1@huawei.com>
Reviewed-by: Guo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20230116064342.2092136-1-liaochang1@huawei.com
[Palmer: Pick Guo's cleanup]
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/kernel/probes/simulate-insn.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c
index d73e96f6ed7c5..a20568bd1f1a8 100644
--- a/arch/riscv/kernel/probes/simulate-insn.c
+++ b/arch/riscv/kernel/probes/simulate-insn.c
@@ -71,11 +71,11 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *reg
u32 rd_index = (opcode >> 7) & 0x1f;
u32 rs1_index = (opcode >> 15) & 0x1f;
- ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
+ ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
if (!ret)
return ret;
- ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr);
+ ret = rv_insn_reg_set_val(regs, rd_index, addr + 4);
if (!ret)
return ret;
--
GitLab
From 85eee6341abb81ac6a35062ffd5c3029eb53be6b Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 24 Jan 2023 13:29:14 -0800
Subject: [PATCH 1117/1167] nvme: fix passthrough csi check
The namespace head saves the Command Set Indicator enum, so use that
instead of the Command Set Selected. The two values are not the same.
Fixes: 831ed60c2aca2d ("nvme: also return I/O command effects from nvme_command_effects")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/nvme/host/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d307ae4d8a575..2990ed331a1aa 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1093,7 +1093,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
if (ns) {
if (ns->head->effects)
effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
- if (ns->head->ids.csi == NVME_CAP_CSS_NVM)
+ if (ns->head->ids.csi == NVME_CSI_NVM)
effects |= nvme_known_nvm_effects(opcode);
if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
dev_warn_once(ctrl->device,
--
GitLab
From f2b0b5210f67c56a3bcdf92ff665fb285d6e0067 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <v4bel@theori.io>
Date: Mon, 23 Jan 2023 11:43:23 -0800
Subject: [PATCH 1118/1167] net/x25: Fix to not accept on connected socket
When listen() and accept() are called on an x25 socket
that connect() succeeds, accept() succeeds immediately.
This is because x25_connect() queues the skb to
sk->sk_receive_queue, and x25_accept() dequeues it.
This creates a child socket with the sk of the parent
x25 socket, which can cause confusion.
Fix x25_listen() to return -EINVAL if the socket has
already been successfully connect()ed to avoid this issue.
Signed-off-by: Hyunwoo Kim <v4bel@theori.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/x25/af_x25.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 3b55502b29657..5c7ad301d742e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -482,6 +482,12 @@ static int x25_listen(struct socket *sock, int backlog)
int rc = -EOPNOTSUPP;
lock_sock(sk);
+ if (sock->state != SS_UNCONNECTED) {
+ rc = -EINVAL;
+ release_sock(sk);
+ return rc;
+ }
+
if (sk->sk_state != TCP_LISTEN) {
memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN);
sk->sk_max_ack_backlog = backlog;
--
GitLab
From 1bc5d819f0b9784043ea08570e1b21107aa35739 Mon Sep 17 00:00:00 2001
From: Mark Pearson <mpearson-lenovo@squebb.ca>
Date: Tue, 24 Jan 2023 10:36:23 -0500
Subject: [PATCH 1119/1167] platform/x86: thinkpad_acpi: Fix profile modes on
Intel platforms
My last commit to fix profile mode displays on AMD platforms caused
an issue on Intel platforms - sorry!
In it I was reading the current functional mode (MMC, PSC, AMT) from
the BIOS but didn't account for the fact that on some of our Intel
platforms I use a different API which returns just the profile and not
the functional mode.
This commit fixes it so that on Intel platforms it knows the functional
mode is always MMC.
I also fixed a potential problem that a platform may try to set the mode
for both MMC and PSC - which was incorrect.
Tested on X1 Carbon 9 (Intel) and Z13 (AMD).
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216963
Fixes: fde5f74ccfc7 ("platform/x86: thinkpad_acpi: Fix profile mode display in AMT mode")
Cc: stable@vger.kernel.org
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://lore.kernel.org/r/20230124153623.145188-1-mpearson-lenovo@squebb.ca
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
---
drivers/platform/x86/thinkpad_acpi.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index a95946800ae9d..02860c32625e7 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -10496,8 +10496,7 @@ static int dytc_profile_set(struct platform_profile_handler *pprof,
if (err)
goto unlock;
}
- }
- if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
+ } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output);
if (err)
goto unlock;
@@ -10525,14 +10524,16 @@ static void dytc_profile_refresh(void)
err = dytc_command(DYTC_CMD_MMC_GET, &output);
else
err = dytc_cql_command(DYTC_CMD_GET, &output);
- } else if (dytc_capabilities & BIT(DYTC_FC_PSC))
+ funcmode = DYTC_FUNCTION_MMC;
+ } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
err = dytc_command(DYTC_CMD_GET, &output);
-
+ /* Check if we are PSC mode, or have AMT enabled */
+ funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF;
+ }
mutex_unlock(&dytc_mutex);
if (err)
return;
- funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF;
perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
convert_dytc_to_profile(funcmode, perfmode, &profile);
if (profile != dytc_current_profile) {
--
GitLab
From 37870358616ca7fdb1e90ad1cdd791655ec54414 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Tue, 24 Jan 2023 18:20:26 +0300
Subject: [PATCH 1120/1167] gpio: mxc: Unlock on error path in mxc_flip_edge()
We recently added locking to this function but one error path was
over looked. Drop the lock before returning.
Fixes: e5464277625c ("gpio: mxc: Protect GPIO irqchip RMW with bgpio spinlock")
Signed-off-by: Dan Carpenter <error27@gmail.com>
Acked-by: Marek Vasut <marex@denx.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-mxc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 6f673b2f2a1bf..9d0cec4b82a33 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -249,10 +249,11 @@ static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio)
} else {
pr_err("mxc: invalid configuration for GPIO %d: %x\n",
gpio, edge);
- return;
+ goto unlock;
}
writel(val | (edge << (bit << 1)), reg);
+unlock:
raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags);
}
--
GitLab
From 0f04cdbdb210000a97c773b28b598fa8ac3aafa4 Mon Sep 17 00:00:00 2001
From: Nikita Shubin <nikita.shubin@maquefel.me>
Date: Wed, 25 Jan 2023 11:30:24 +0300
Subject: [PATCH 1121/1167] gpio: ep93xx: Fix port F hwirq numbers in handler
Fix wrong translation of irq numbers in port F handler, as ep93xx hwirqs
increased by 1, we should simply decrease them by 1 in translation.
Fixes: 482c27273f52 ("ARM: ep93xx: renumber interrupts")
Signed-off-by: Nikita Shubin <nikita.shubin@maquefel.me>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-ep93xx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 2e17797091133..7edcdc5750802 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -148,7 +148,7 @@ static void ep93xx_gpio_f_irq_handler(struct irq_desc *desc)
*/
struct irq_chip *irqchip = irq_desc_get_chip(desc);
unsigned int irq = irq_desc_get_irq(desc);
- int port_f_idx = ((irq + 1) & 7) ^ 4; /* {19..22,47..50} -> {0..7} */
+ int port_f_idx = (irq & 7) ^ 4; /* {20..23,48..51} -> {0..7} */
int gpio_irq = EP93XX_GPIO_F_IRQ_BASE + port_f_idx;
chained_irq_enter(irqchip, desc);
--
GitLab
From 216f37366e86a6ddd34ed842cac3354f579ef48e Mon Sep 17 00:00:00 2001
From: Nikita Shubin <nikita.shubin@maquefel.me>
Date: Wed, 25 Jan 2023 11:30:25 +0300
Subject: [PATCH 1122/1167] gpio: ep93xx: Make irqchip immutable
This turns the Cirrus ep93xx gpio irqchip immutable.
Preserve per-chip labels by adding an ->irq_print_chip() callback.
Signed-off-by: Nikita Shubin <nikita.shubin@maquefel.me>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-ep93xx.c | 34 +++++++++++++++++++++-------------
1 file changed, 21 insertions(+), 13 deletions(-)
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 7edcdc5750802..192be99b13923 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -17,6 +17,7 @@
#include <linux/slab.h>
#include <linux/gpio/driver.h>
#include <linux/bitops.h>
+#include <linux/seq_file.h>
#define EP93XX_GPIO_F_INT_STATUS 0x5c
#define EP93XX_GPIO_A_INT_STATUS 0xa0
@@ -40,7 +41,6 @@
#define EP93XX_GPIO_F_IRQ_BASE 80
struct ep93xx_gpio_irq_chip {
- struct irq_chip ic;
u8 irq_offset;
u8 int_unmasked;
u8 int_enabled;
@@ -185,6 +185,7 @@ static void ep93xx_gpio_irq_mask_ack(struct irq_data *d)
ep93xx_gpio_update_int_params(epg, eic);
writeb(port_mask, epg->base + eic->irq_offset + EP93XX_INT_EOI_OFFSET);
+ gpiochip_disable_irq(gc, irqd_to_hwirq(d));
}
static void ep93xx_gpio_irq_mask(struct irq_data *d)
@@ -195,6 +196,7 @@ static void ep93xx_gpio_irq_mask(struct irq_data *d)
eic->int_unmasked &= ~BIT(d->irq & 7);
ep93xx_gpio_update_int_params(epg, eic);
+ gpiochip_disable_irq(gc, irqd_to_hwirq(d));
}
static void ep93xx_gpio_irq_unmask(struct irq_data *d)
@@ -203,6 +205,7 @@ static void ep93xx_gpio_irq_unmask(struct irq_data *d)
struct ep93xx_gpio_irq_chip *eic = to_ep93xx_gpio_irq_chip(gc);
struct ep93xx_gpio *epg = gpiochip_get_data(gc);
+ gpiochip_enable_irq(gc, irqd_to_hwirq(d));
eic->int_unmasked |= BIT(d->irq & 7);
ep93xx_gpio_update_int_params(epg, eic);
}
@@ -320,15 +323,25 @@ static int ep93xx_gpio_set_config(struct gpio_chip *gc, unsigned offset,
return 0;
}
-static void ep93xx_init_irq_chip(struct device *dev, struct irq_chip *ic)
+static void ep93xx_irq_print_chip(struct irq_data *data, struct seq_file *p)
{
- ic->irq_ack = ep93xx_gpio_irq_ack;
- ic->irq_mask_ack = ep93xx_gpio_irq_mask_ack;
- ic->irq_mask = ep93xx_gpio_irq_mask;
- ic->irq_unmask = ep93xx_gpio_irq_unmask;
- ic->irq_set_type = ep93xx_gpio_irq_type;
+ struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+
+ seq_printf(p, dev_name(gc->parent));
}
+static const struct irq_chip gpio_eic_irq_chip = {
+ .name = "ep93xx-gpio-eic",
+ .irq_ack = ep93xx_gpio_irq_ack,
+ .irq_mask = ep93xx_gpio_irq_mask,
+ .irq_unmask = ep93xx_gpio_irq_unmask,
+ .irq_mask_ack = ep93xx_gpio_irq_mask_ack,
+ .irq_set_type = ep93xx_gpio_irq_type,
+ .irq_print_chip = ep93xx_irq_print_chip,
+ .flags = IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc,
struct platform_device *pdev,
struct ep93xx_gpio *epg,
@@ -359,12 +372,7 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc,
if (!egc->eic)
return -ENOMEM;
egc->eic->irq_offset = bank->irq;
- ic = &egc->eic->ic;
- ic->name = devm_kasprintf(dev, GFP_KERNEL, "gpio-irq-%s", bank->label);
- if (!ic->name)
- return -ENOMEM;
- ep93xx_init_irq_chip(dev, ic);
- girq->chip = ic;
+ gpio_irq_chip_set_chip(girq, &gpio_eic_irq_chip);
}
if (bank->has_irq) {
--
GitLab
From c2b6cdee1d13ffbb24baca3c9b8a572d6b541e4e Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Tue, 24 Jan 2023 09:02:10 +0900
Subject: [PATCH 1123/1167] net: ravb: Fix lack of register setting after
system resumed for Gen3
After system entered Suspend to RAM, registers setting of this
hardware is reset because the SoC will be turned off. On R-Car Gen3
(info->ccc_gac), ravb_ptp_init() is called in ravb_probe() only. So,
after system resumed, it lacks of the initial settings for ptp. So,
add ravb_ptp_{init,stop}() into ravb_{resume,suspend}().
Fixes: f5d7837f96e5 ("ravb: ptp: Add CONFIG mode support")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/renesas/ravb_main.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index b4e0fc7f65bdf..3f61100c02f4f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -2973,6 +2973,9 @@ static int __maybe_unused ravb_suspend(struct device *dev)
else
ret = ravb_close(ndev);
+ if (priv->info->ccc_gac)
+ ravb_ptp_stop(ndev);
+
return ret;
}
@@ -3011,6 +3014,9 @@ static int __maybe_unused ravb_resume(struct device *dev)
/* Restore descriptor base address table */
ravb_write(ndev, priv->desc_bat_dma, DBAT);
+ if (priv->info->ccc_gac)
+ ravb_ptp_init(ndev, priv->pdev);
+
if (netif_running(ndev)) {
if (priv->wol_enabled) {
ret = ravb_wol_restore(ndev);
--
GitLab
From f3c07758c9007a6bfff5290d9e19d3c41930c897 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Tue, 24 Jan 2023 09:02:11 +0900
Subject: [PATCH 1124/1167] net: ravb: Fix possible hang if RIS2_QFF1 happen
Since this driver enables the interrupt by RIC2_QFE1, this driver
should clear the interrupt flag if it happens. Otherwise, the interrupt
causes to hang the system.
Note that this also fix a minor coding style (a comment indentation)
around the fixed code.
Fixes: c156633f1353 ("Renesas Ethernet AVB driver proper")
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/renesas/ravb_main.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 3f61100c02f4f..0f54849a38235 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1101,14 +1101,14 @@ static void ravb_error_interrupt(struct net_device *ndev)
ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS);
if (eis & EIS_QFS) {
ris2 = ravb_read(ndev, RIS2);
- ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED),
+ ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED),
RIS2);
/* Receive Descriptor Empty int */
if (ris2 & RIS2_QFF0)
priv->stats[RAVB_BE].rx_over_errors++;
- /* Receive Descriptor Empty int */
+ /* Receive Descriptor Empty int */
if (ris2 & RIS2_QFF1)
priv->stats[RAVB_NC].rx_over_errors++;
--
GitLab
From de8a6b15d9654c3e4f672d76da9d9df8ee06331d Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Tue, 24 Jan 2023 10:01:03 +0800
Subject: [PATCH 1125/1167] net: mctp: add an explicit reference from a
mctp_sk_key to sock
Currently, we correlate the mctp_sk_key lifetime to the sock lifetime
through the sock hash/unhash operations, but this is pretty tenuous, and
there are cases where we may have a temporary reference to an unhashed
sk.
This change makes the reference more explicit, by adding a hold on the
sock when it's associated with a mctp_sk_key, released on final key
unref.
Fixes: 73c618456dc5 ("mctp: locking, lifetime and validity changes for sk_keys")
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mctp/route.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/net/mctp/route.c b/net/mctp/route.c
index f9a80b82dc511..ce10ba7ae8393 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -147,6 +147,7 @@ static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk,
key->valid = true;
spin_lock_init(&key->lock);
refcount_set(&key->refs, 1);
+ sock_hold(key->sk);
return key;
}
@@ -165,6 +166,7 @@ void mctp_key_unref(struct mctp_sk_key *key)
mctp_dev_release_key(key->dev, key);
spin_unlock_irqrestore(&key->lock, flags);
+ sock_put(key->sk);
kfree(key);
}
@@ -419,14 +421,14 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
* this function.
*/
rc = mctp_key_add(key, msk);
- if (rc) {
- kfree(key);
- } else {
+ if (!rc)
trace_mctp_key_acquire(key);
- /* we don't need to release key->lock on exit */
- mctp_key_unref(key);
- }
+ /* we don't need to release key->lock on exit, so
+ * clean up here and suppress the unlock via
+ * setting to NULL
+ */
+ mctp_key_unref(key);
key = NULL;
} else {
--
GitLab
From 5f41ae6fca9d40ab3cb9b0507931ef7a9b3ea50b Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Tue, 24 Jan 2023 10:01:04 +0800
Subject: [PATCH 1126/1167] net: mctp: move expiry timer delete to unhash
Currently, we delete the key expiry timer (in sk->close) before
unhashing the sk. This means that another thread may find the sk through
its presence on the key list, and re-queue the timer.
This change moves the timer deletion to the unhash, after we have made
the key no longer observable, so the timer cannot be re-queued.
Fixes: 7b14e15ae6f4 ("mctp: Implement a timeout for tags")
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mctp/af_mctp.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index fc9e728b6333a..fb6ae3110528a 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -544,9 +544,6 @@ static int mctp_sk_init(struct sock *sk)
static void mctp_sk_close(struct sock *sk, long timeout)
{
- struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
-
- del_timer_sync(&msk->key_expiry);
sk_common_release(sk);
}
@@ -581,6 +578,12 @@ static void mctp_sk_unhash(struct sock *sk)
__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED);
}
spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
+
+ /* Since there are no more tag allocations (we have removed all of the
+ * keys), stop any pending expiry events. the timer cannot be re-queued
+ * as the sk is no longer observable
+ */
+ del_timer_sync(&msk->key_expiry);
}
static struct proto mctp_proto = {
--
GitLab
From 6e54ea37e344f145665c2dc3cc534b92529e8de5 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 24 Jan 2023 10:01:05 +0800
Subject: [PATCH 1127/1167] net: mctp: hold key reference when looking up a
general key
Currently, we have a race where we look up a sock through a "general"
(ie, not directly associated with the (src,dest,tag) tuple) key, then
drop the key reference while still holding the key's sock.
This change expands the key reference until we've finished using the
sock, and hence the sock reference too.
Commit message changes from Jeremy Kerr <jk@codeconstruct.com.au>.
Reported-by: Noam Rathaus <noamr@ssd-disclosure.com>
Fixes: 73c618456dc5 ("mctp: locking, lifetime and validity changes for sk_keys")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mctp/route.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/net/mctp/route.c b/net/mctp/route.c
index ce10ba7ae8393..06c0de21984d9 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -317,8 +317,8 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
{
+ struct mctp_sk_key *key, *any_key = NULL;
struct net *net = dev_net(skb->dev);
- struct mctp_sk_key *key;
struct mctp_sock *msk;
struct mctp_hdr *mh;
unsigned long f;
@@ -363,13 +363,11 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
* key for reassembly - we'll create a more specific
* one for future packets if required (ie, !EOM).
*/
- key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
- if (key) {
- msk = container_of(key->sk,
+ any_key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f);
+ if (any_key) {
+ msk = container_of(any_key->sk,
struct mctp_sock, sk);
- spin_unlock_irqrestore(&key->lock, f);
- mctp_key_unref(key);
- key = NULL;
+ spin_unlock_irqrestore(&any_key->lock, f);
}
}
@@ -475,6 +473,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
spin_unlock_irqrestore(&key->lock, f);
mctp_key_unref(key);
}
+ if (any_key)
+ mctp_key_unref(any_key);
out:
if (rc)
kfree_skb(skb);
--
GitLab
From b98e1a04e27fddfdc808bf46fe78eca30db89ab3 Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Tue, 24 Jan 2023 10:01:06 +0800
Subject: [PATCH 1128/1167] net: mctp: mark socks as dead on unhash, prevent
re-add
Once a socket has been unhashed, we want to prevent it from being
re-used in a sk_key entry as part of a routing operation.
This change marks the sk as SOCK_DEAD on unhash, which prevents addition
into the net's key list.
We need to do this during the key add path, rather than key lookup, as
we release the net keys_lock between those operations.
Fixes: 4a992bbd3650 ("mctp: Implement message fragmentation & reassembly")
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/mctp/af_mctp.c | 1 +
net/mctp/route.c | 6 ++++++
2 files changed, 7 insertions(+)
diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index fb6ae3110528a..45bbe3e54cc28 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -577,6 +577,7 @@ static void mctp_sk_unhash(struct sock *sk)
spin_lock_irqsave(&key->lock, fl2);
__mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED);
}
+ sock_set_flag(sk, SOCK_DEAD);
spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
/* Since there are no more tag allocations (we have removed all of the
diff --git a/net/mctp/route.c b/net/mctp/route.c
index 06c0de21984d9..f51a05ec71624 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -179,6 +179,11 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
spin_lock_irqsave(&net->mctp.keys_lock, flags);
+ if (sock_flag(&msk->sk, SOCK_DEAD)) {
+ rc = -EINVAL;
+ goto out_unlock;
+ }
+
hlist_for_each_entry(tmp, &net->mctp.keys, hlist) {
if (mctp_key_match(tmp, key->local_addr, key->peer_addr,
key->tag)) {
@@ -200,6 +205,7 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
hlist_add_head(&key->sklist, &msk->keys);
}
+out_unlock:
spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
return rc;
--
GitLab
From acd7e9ee57c880b99671dd99680cb707b7b5b0ee Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 25 Jan 2023 13:17:42 +0100
Subject: [PATCH 1129/1167] thermal: intel: int340x: Add locking to
int340x_thermal_get_trip_type()
In order to prevent int340x_thermal_get_trip_type() from possibly
racing with int340x_thermal_read_trips() invoked by int3403_notify()
add locking to it in analogy with int340x_thermal_get_trip_temp().
Fixes: 6757a7abe47b ("thermal: intel: int340x: Protect trip temperature from concurrent updates")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
.../intel/int340x_thermal/int340x_thermal_zone.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 852f6c579af5c..0a4eaa307156d 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -81,11 +81,13 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
enum thermal_trip_type *type)
{
struct int34x_thermal_zone *d = zone->devdata;
- int i;
+ int i, ret = 0;
if (d->override_ops && d->override_ops->get_trip_type)
return d->override_ops->get_trip_type(zone, trip, type);
+ mutex_lock(&d->trip_mutex);
+
if (trip < d->aux_trip_nr)
*type = THERMAL_TRIP_PASSIVE;
else if (trip == d->crt_trip_id)
@@ -103,10 +105,12 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
}
}
if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+ mutex_unlock(&d->trip_mutex);
+
+ return ret;
}
static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
--
GitLab
From c1d6105869464635d8a2bcf87a43c05f4c0cfca4 Mon Sep 17 00:00:00 2001
From: Ley Foon Tan <leyfoon.tan@starfivetech.com>
Date: Thu, 5 Jan 2023 11:37:05 +0800
Subject: [PATCH 1130/1167] riscv: Move call to init_cpu_topology() to later
initialization stage
If "capacity-dmips-mhz" is present in a CPU DT node,
topology_parse_cpu_capacity() will fail to allocate memory. arm64, with
which this code path is shared, does not call
topology_parse_cpu_capacity() until later in boot where memory
allocation is available. While "capacity-dmips-mhz" is not yet a valid
property on RISC-V, invalid properties should be ignored rather than
cause issues. Move init_cpu_topology(), which calls
topology_parse_cpu_capacity(), to a later initialization stage, to match
arm64.
As a side effect of this change, RISC-V is "protected" from changes to
core topology code that would work on arm64 where memory allocation is
safe but on RISC-V isn't.
Fixes: 03f11f03dbfe ("RISC-V: Parse cpu topology during boot.")
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Signed-off-by: Ley Foon Tan <leyfoon.tan@starfivetech.com>
Link: https://lore.kernel.org/r/20230105033705.3946130-1-leyfoon.tan@starfivetech.com
[Palmer: use Conor's commit text]
Link: https://lore.kernel.org/linux-riscv/20230104183033.755668-1-pierre.gondois@arm.com/T/#me592d4c8b9508642954839f0077288a353b0b9b2
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
arch/riscv/kernel/smpboot.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 3373df413c882..ddb2afba6d255 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -39,7 +39,6 @@ static DECLARE_COMPLETION(cpu_running);
void __init smp_prepare_boot_cpu(void)
{
- init_cpu_topology();
}
void __init smp_prepare_cpus(unsigned int max_cpus)
@@ -48,6 +47,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
int ret;
unsigned int curr_cpuid;
+ init_cpu_topology();
+
curr_cpuid = smp_processor_id();
store_cpu_topology(curr_cpuid);
numa_store_cpu_info(curr_cpuid);
--
GitLab
From d5090d91ec929a79b52e5a98144d85dea40d4438 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 7 Jan 2023 18:12:38 -0800
Subject: [PATCH 1131/1167] tracing/filter: fix kernel-doc warnings
Use the 'struct' keyword for a struct's kernel-doc notation and
use the correct function parameter name to eliminate kernel-doc
warnings:
kernel/trace/trace_events_filter.c:136: warning: cannot understand function prototype: 'struct prog_entry '
kerne/trace/trace_events_filter.c:155: warning: Excess function parameter 'when_to_branch' description in 'update_preds'
Also correct some trivial punctuation problems.
Link: https://lkml.kernel.org/r/20230108021238.16398-1-rdunlap@infradead.org
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace_events_filter.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 96acc2b71ac74..e095c3b3a50d3 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -128,7 +128,7 @@ static bool is_not(const char *str)
}
/**
- * prog_entry - a singe entry in the filter program
+ * struct prog_entry - a singe entry in the filter program
* @target: Index to jump to on a branch (actually one minus the index)
* @when_to_branch: The value of the result of the predicate to do a branch
* @pred: The predicate to execute.
@@ -140,16 +140,16 @@ struct prog_entry {
};
/**
- * update_preds- assign a program entry a label target
+ * update_preds - assign a program entry a label target
* @prog: The program array
* @N: The index of the current entry in @prog
- * @when_to_branch: What to assign a program entry for its branch condition
+ * @invert: What to assign a program entry for its branch condition
*
* The program entry at @N has a target that points to the index of a program
* entry that can have its target and when_to_branch fields updated.
* Update the current program entry denoted by index @N target field to be
* that of the updated entry. This will denote the entry to update if
- * we are processing an "||" after an "&&"
+ * we are processing an "||" after an "&&".
*/
static void update_preds(struct prog_entry *prog, int N, int invert)
{
--
GitLab
From 34226fc6889e0e2fe8480bf3a0b43ac992bbee94 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 3 Jan 2023 12:49:10 +0000
Subject: [PATCH 1132/1167] ftrace: Maintain samples/ftrace
There's no entry in MAINTAINERS for samples/ftrace. Add one so that the
FTRACE maintainers are kept in the loop.
Link: https://lkml.kernel.org/r/20230103124912.2948963-2-mark.rutland@arm.com
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
MAINTAINERS | 1 +
1 file changed, 1 insertion(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index f781f936ae35b..70be8603c8d39 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8570,6 +8570,7 @@ F: kernel/trace/fgraph.c
F: arch/*/*/*/*ftrace*
F: arch/*/*/*ftrace*
F: include/*/ftrace.h
+F: samples/ftrace
FUNGIBLE ETHERNET DRIVERS
M: Dimitris Michailidis <dmichail@fungible.com>
--
GitLab
From ae3edea88e6c1bbb8b41ef958f79a7a44ab45f7c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 16 Jan 2023 16:16:12 +0000
Subject: [PATCH 1133/1167] rv: remove redundant initialization of pointer ptr
The pointer ptr is being initialized with a value that is never read,
it is being updated later on a call to strim. Remove the extraneous
initialization.
Link: https://lkml.kernel.org/r/20230116161612.77192-1-colin.i.king@gmail.com
Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/rv/rv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 6c97cc2d754aa..7e9061828c240 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -516,7 +516,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user
struct rv_monitor_def *mdef;
int retval = -EINVAL;
bool enable = true;
- char *ptr = buff;
+ char *ptr;
int len;
if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1)
--
GitLab
From 78020233418518faa72fba11f40e1d53b9e88a2e Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Fri, 20 Jan 2023 08:36:24 +0900
Subject: [PATCH 1134/1167] bootconfig: Update MAINTAINERS file to add tree and
mailing list
Since the bootconfig related changes will be handled on linux-trace
tree, add the tree and mailing lists for EXTRA BOOT CONFIG.
Link: https://lkml.kernel.org/r/167417138436.2333752.6988808113120359923.stgit@devnote3
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
MAINTAINERS | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 70be8603c8d39..e64ba36ced788 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7894,7 +7894,11 @@ F: include/linux/extcon/
EXTRA BOOT CONFIG
M: Masami Hiramatsu <mhiramat@kernel.org>
+L: linux-kernel@vger.kernel.org
+L: linux-trace-kernel@vger.kernel.org
+Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/
S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
F: Documentation/admin-guide/bootconfig.rst
F: fs/proc/bootconfig.c
F: include/linux/bootconfig.h
--
GitLab
From b7ab9161cf5ddc42a288edf9d1a61f3bdffe17c7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 25 Jan 2023 14:02:13 +0000
Subject: [PATCH 1135/1167] cifs: Fix oops due to uncleared server->smbd_conn
in reconnect
In smbd_destroy(), clear the server->smbd_conn pointer after freeing the
smbd_connection struct that it points to so that reconnection doesn't get
confused.
Fixes: 8ef130f9ec27 ("CIFS: SMBD: Implement function to destroy a SMB Direct connection")
Cc: stable@vger.kernel.org
Reviewed-by: Paulo Alcantara (SUSE) <pc@cjr.nz>
Acked-by: Tom Talpey <tom@talpey.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Long Li <longli@microsoft.com>
Cc: Pavel Shilovsky <piastryyy@gmail.com>
Cc: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/cifs/smbdirect.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 90789aaa6567e..8c816b25ce7c6 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -1405,6 +1405,7 @@ void smbd_destroy(struct TCP_Server_Info *server)
destroy_workqueue(info->workqueue);
log_rdma_event(INFO, "rdma session destroyed\n");
kfree(info);
+ server->smbd_conn = NULL;
}
/*
--
GitLab
From a49fb7218ed84a4c5e6c56b9fd933498b9730912 Mon Sep 17 00:00:00 2001
From: Doug Smythies <dsmythies@telus.net>
Date: Sat, 21 Jan 2023 08:41:35 -0800
Subject: [PATCH 1136/1167] selftests: amd-pstate: Don't delete source files
via Makefile
Revert the portion of a recent Makefile change that incorrectly
deletes source files when doing "make clean".
Fixes: ba2d788aa873 ("selftests: amd-pstate: Trigger tbench benchmark and test cpus")
Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Sedat Dilek <sedat.dilek@gmail.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Doug Smythies <dsmythies@telus.net>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
tools/testing/selftests/amd-pstate/Makefile | 5 -----
1 file changed, 5 deletions(-)
diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile
index 5f195ee756d67..5fd1424db37d8 100644
--- a/tools/testing/selftests/amd-pstate/Makefile
+++ b/tools/testing/selftests/amd-pstate/Makefile
@@ -7,11 +7,6 @@ all:
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-ifeq (x86,$(ARCH))
-TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
-TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
-endif
-
TEST_PROGS := run.sh
TEST_FILES := basic.sh tbench.sh gitsource.sh
--
GitLab
From 2de3769830346e68b3de0f4abc0d8e2625ad9dac Mon Sep 17 00:00:00 2001
From: Jonathan Kim <jonathan.kim@amd.com>
Date: Thu, 19 Jan 2023 18:42:03 -0500
Subject: [PATCH 1137/1167] drm/amdgpu: remove unconditional trap enable on add
gfx11 queues
Rebase of driver has incorrect unconditional trap enablement
for GFX11 when adding mes queues.
Reported-by: Graham Sider <graham.sider@amd.com>
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Graham Sider <graham.sider@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 970b066b37bb9..3a8fe8a24d3a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -196,7 +196,6 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes,
mes_add_queue_pkt.trap_handler_addr = input->tba_addr;
mes_add_queue_pkt.tma_addr = input->tma_addr;
mes_add_queue_pkt.is_kfd_process = input->is_kfd_process;
- mes_add_queue_pkt.trap_en = 1;
/* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */
mes_add_queue_pkt.is_aql_queue = input->is_aql_queue;
--
GitLab
From 15b207d0abdcbb2271774aa99d9a290789159e75 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Fri, 20 Jan 2023 11:21:53 +0800
Subject: [PATCH 1138/1167] drm/amd/pm: add missing AllowIHInterrupt message
mapping for SMU13.0.0
Add SMU13.0.0 AllowIHInterrupt message mapping.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 6.1.x
---
drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index 4c20d17e7416e..cf96c3f2affe4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -145,6 +145,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] =
MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel,
PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0),
MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0),
+ MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0),
};
static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = {
--
GitLab
From 08fbe3c24fd2f0706c0eb907c71e26f10e5d8c6a Mon Sep 17 00:00:00 2001
From: Li Ma <li.ma@amd.com>
Date: Fri, 20 Jan 2023 15:38:33 +0800
Subject: [PATCH 1139/1167] drm/amdgpu: enable imu firmware for GC 11.0.4
The GC 11.0.4 needs load IMU to power up GFX before loads GFX firmware.
Signed-off-by: Li Ma <li.ma@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/imu_v11_0.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index 95548c512f4fb..077c53c6cc08b 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -35,6 +35,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin");
static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
{
--
GitLab
From f0f7743624e77abe419ff1971b50e44ac1482421 Mon Sep 17 00:00:00 2001
From: Li Ma <li.ma@amd.com>
Date: Fri, 20 Jan 2023 15:41:22 +0800
Subject: [PATCH 1140/1167] drm/amdgpu: declare firmware for new MES 11.0.4
To support new mes ip block
Signed-off-by: Li Ma <li.ma@amd.com>
Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 3a8fe8a24d3a3..5dff79e8f3011 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -40,6 +40,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin");
static int mes_v11_0_hw_fini(void *handle);
static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev);
--
GitLab
From 1119e1f9636b76aef14068c7fd0b4d55132b86b8 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Wed, 23 Nov 2022 14:50:16 -0500
Subject: [PATCH 1141/1167] drm/amdgpu/display/mst: Fix mst_state->pbn_div and
slot count assignments
Looks like I made a pretty big mistake here without noticing: it seems when
I moved the assignments of mst_state->pbn_div I completely missed the fact
that the reason for us calling drm_dp_mst_update_slots() earlier was to
account for the fact that we need to call this function using info from the
root MST connector, instead of just trying to do this from each MST
encoder's atomic check function. Otherwise, we end up filling out all of
DC's link information with zeroes.
So, let's restore that and hopefully fix this DSC regression.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2171
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Fixes: 4d07b0bc4034 ("drm/display/dp_mst: Move all payload info into the atomic state")
Cc: stable@vger.kernel.org # 6.1
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Tested-by: Didier Raboud <odyx@debian.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 24 +++++++++++++++++++
.../display/amdgpu_dm/amdgpu_dm_mst_types.c | 5 ----
2 files changed, 24 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 4d42033a703fa..0f14b6d71d35e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9490,6 +9490,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
struct drm_connector_state *old_con_state, *new_con_state;
struct drm_crtc *crtc;
struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+ struct drm_dp_mst_topology_mgr *mgr;
+ struct drm_dp_mst_topology_state *mst_state;
struct drm_plane *plane;
struct drm_plane_state *old_plane_state, *new_plane_state;
enum dc_status status;
@@ -9745,6 +9747,28 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
lock_and_validation_needed = true;
}
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+ /* set the slot info for each mst_state based on the link encoding format */
+ for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) {
+ struct amdgpu_dm_connector *aconnector;
+ struct drm_connector *connector;
+ struct drm_connector_list_iter iter;
+ u8 link_coding_cap;
+
+ drm_connector_list_iter_begin(dev, &iter);
+ drm_for_each_connector_iter(connector, &iter) {
+ if (connector->index == mst_state->mgr->conn_base_id) {
+ aconnector = to_amdgpu_dm_connector(connector);
+ link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link);
+ drm_dp_mst_update_slots(mst_state, link_coding_cap);
+
+ break;
+ }
+ }
+ drm_connector_list_iter_end(&iter);
+ }
+#endif
+
/**
* Streams and planes are reset when there are changes that affect
* bandwidth. Anything that affects bandwidth needs to go through
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index d7a044e797305..abdbd4352f6f3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -903,11 +903,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
if (IS_ERR(mst_state))
return PTR_ERR(mst_state);
- mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link);
-#if defined(CONFIG_DRM_AMD_DC_DCN)
- drm_dp_mst_update_slots(mst_state, dc_link_dp_mst_decide_link_encoding_format(dc_link));
-#endif
-
/* Set up params */
for (i = 0; i < dc_state->stream_count; i++) {
struct dc_dsc_policy dsc_policy = {0};
--
GitLab
From cb1e0b015f56b8f3c7f5ce33ff4b782ee5674512 Mon Sep 17 00:00:00 2001
From: Wayne Lin <Wayne.Lin@amd.com>
Date: Fri, 9 Dec 2022 19:05:33 +0800
Subject: [PATCH 1142/1167] drm/amdgpu/display/mst: limit payload to be updated
one by one
[Why]
amdgpu expects to update payload table for one stream one time
by calling dm_helpers_dp_mst_write_payload_allocation_table().
Currently, it get modified to try to update HW payload table
at once by referring mst_state.
[How]
This is just a quick workaround. Should find way to remove the
temporary struct dc_dp_mst_stream_allocation_table later if set
struct link_mst_stream_allocatio directly is possible.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2171
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Fixes: 4d07b0bc4034 ("drm/display/dp_mst: Move all payload info into the atomic state")
Cc: stable@vger.kernel.org # 6.1
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Tested-by: Didier Raboud <odyx@debian.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
.../amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 51 ++++++++++++++-----
1 file changed, 39 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 6994c9a1ed858..5cff56bb8f560 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -120,23 +120,50 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
}
static void
-fill_dc_mst_payload_table_from_drm(struct drm_dp_mst_topology_state *mst_state,
- struct amdgpu_dm_connector *aconnector,
+fill_dc_mst_payload_table_from_drm(struct dc_link *link,
+ bool enable,
+ struct drm_dp_mst_atomic_payload *target_payload,
struct dc_dp_mst_stream_allocation_table *table)
{
struct dc_dp_mst_stream_allocation_table new_table = { 0 };
struct dc_dp_mst_stream_allocation *sa;
- struct drm_dp_mst_atomic_payload *payload;
+ struct link_mst_stream_allocation_table copy_of_link_table =
+ link->mst_stream_alloc_table;
+
+ int i;
+ int current_hw_table_stream_cnt = copy_of_link_table.stream_count;
+ struct link_mst_stream_allocation *dc_alloc;
+
+ /* TODO: refactor to set link->mst_stream_alloc_table directly if possible.*/
+ if (enable) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[current_hw_table_stream_cnt];
+ dc_alloc->vcp_id = target_payload->vcpi;
+ dc_alloc->slot_count = target_payload->time_slots;
+ } else {
+ for (i = 0; i < copy_of_link_table.stream_count; i++) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[i];
+
+ if (dc_alloc->vcp_id == target_payload->vcpi) {
+ dc_alloc->vcp_id = 0;
+ dc_alloc->slot_count = 0;
+ break;
+ }
+ }
+ ASSERT(i != copy_of_link_table.stream_count);
+ }
/* Fill payload info*/
- list_for_each_entry(payload, &mst_state->payloads, next) {
- if (payload->delete)
- continue;
-
- sa = &new_table.stream_allocations[new_table.stream_count];
- sa->slot_count = payload->time_slots;
- sa->vcp_id = payload->vcpi;
- new_table.stream_count++;
+ for (i = 0; i < MAX_CONTROLLER_NUM; i++) {
+ dc_alloc =
+ ©_of_link_table.stream_allocations[i];
+ if (dc_alloc->vcp_id > 0 && dc_alloc->slot_count > 0) {
+ sa = &new_table.stream_allocations[new_table.stream_count];
+ sa->slot_count = dc_alloc->slot_count;
+ sa->vcp_id = dc_alloc->vcp_id;
+ new_table.stream_count++;
+ }
}
/* Overwrite the old table */
@@ -185,7 +212,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
* AUX message. The sequence is slot 1-63 allocated sequence for each
* stream. AMD ASIC stream slot allocation should follow the same
* sequence. copy DRM MST allocation to dc */
- fill_dc_mst_payload_table_from_drm(mst_state, aconnector, proposed_table);
+ fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table);
return true;
}
--
GitLab
From f85c5e25fd28fe0bf6d6d0563cf83758a4e05c8f Mon Sep 17 00:00:00 2001
From: Wayne Lin <Wayne.Lin@amd.com>
Date: Mon, 12 Dec 2022 15:41:18 +0800
Subject: [PATCH 1143/1167] drm/amdgpu/display/mst: update mst_mgr relevant
variable when long HPD
[Why & How]
Now the vc_start_slot is controlled at drm side. When we
service a long HPD, we still need to run
dm_helpers_dp_mst_write_payload_allocation_table() to update
drm mst_mgr's relevant variable. Otherwise, on the next plug-in,
payload will get assigned with a wrong start slot.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2171
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Fixes: 4d07b0bc4034 ("drm/display/dp_mst: Move all payload info into the atomic state")
Cc: stable@vger.kernel.org # 6.1
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Tested-by: Didier Raboud <odyx@debian.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/dc/core/dc_link.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 342e906ae26e4..c88f044666fee 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -3995,10 +3995,13 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0);
int i;
bool mst_mode = (link->type == dc_connection_mst_branch);
+ /* adjust for drm changes*/
+ bool update_drm_mst_state = true;
const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
const struct dc_link_settings empty_link_settings = {0};
DC_LOGGER_INIT(link->ctx->logger);
+
/* deallocate_mst_payload is called before disable link. When mode or
* disable/enable monitor, new stream is created which is not in link
* stream[] yet. For this, payload is not allocated yet, so de-alloc
@@ -4014,7 +4017,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
&empty_link_settings,
avg_time_slots_per_mtp);
- if (mst_mode) {
+ if (mst_mode || update_drm_mst_state) {
/* when link is in mst mode, reply on mst manager to remove
* payload
*/
@@ -4077,11 +4080,18 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
stream->ctx,
stream);
+ if (!update_drm_mst_state)
+ dm_helpers_dp_mst_send_payload_allocation(
+ stream->ctx,
+ stream,
+ false);
+ }
+
+ if (update_drm_mst_state)
dm_helpers_dp_mst_send_payload_allocation(
stream->ctx,
stream,
false);
- }
return DC_OK;
}
--
GitLab
From d8bf2df715bb8ac964f91fe8bf67c37c5d916463 Mon Sep 17 00:00:00 2001
From: Wayne Lin <Wayne.Lin@amd.com>
Date: Wed, 28 Dec 2022 14:50:43 +0800
Subject: [PATCH 1144/1167] drm/display/dp_mst: Correct the kref of port.
[why & how]
We still need to refer to port while removing payload at commit_tail.
we should keep the kref till then to release.
Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/2171
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Fixes: 4d07b0bc4034 ("drm/display/dp_mst: Move all payload info into the atomic state")
Cc: stable@vger.kernel.org # 6.1
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Tested-by: Didier Raboud <odyx@debian.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/display/drm_dp_mst_topology.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 51a46689cda70..4ca37261584a9 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -3372,6 +3372,9 @@ void drm_dp_remove_payload(struct drm_dp_mst_topology_mgr *mgr,
mgr->payload_count--;
mgr->next_start_slot -= payload->time_slots;
+
+ if (payload->delete)
+ drm_dp_mst_put_port_malloc(payload->port);
}
EXPORT_SYMBOL(drm_dp_remove_payload);
@@ -4327,7 +4330,6 @@ int drm_dp_atomic_release_time_slots(struct drm_atomic_state *state,
drm_dbg_atomic(mgr->dev, "[MST PORT:%p] TU %d -> 0\n", port, payload->time_slots);
if (!payload->delete) {
- drm_dp_mst_put_port_malloc(port);
payload->pbn = 0;
payload->delete = true;
topology_state->payload_mask &= ~BIT(payload->vcpi - 1);
--
GitLab
From 4b069553246f993c4221e382d0d0ae34f5ba730e Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Wed, 11 Jan 2023 14:56:22 -0500
Subject: [PATCH 1145/1167] drm/amd/display: Fix timing not changning when
freesync video is enabled
[Why&How]
Switching between certain modes that are freesync video modes and those
are not freesync video modes result in timing not changing as seen by
the monitor due to incorrect timing being driven.
The issue is fixed by ensuring that when a non freesync video mode is
set, we reset the freesync status on the crtc.
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Alan Liu <HaoPing.Liu@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0f14b6d71d35e..ead47bc626016 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8881,6 +8881,13 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm,
if (!dm_old_crtc_state->stream)
goto skip_modeset;
+ /* Unset freesync video if it was active before */
+ if (dm_old_crtc_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) {
+ dm_new_crtc_state->freesync_config.state = VRR_STATE_INACTIVE;
+ dm_new_crtc_state->freesync_config.fixed_refresh_in_uhz = 0;
+ }
+
+ /* Now check if we should set freesync video mode */
if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state,
old_crtc_state)) {
--
GitLab
From 4acf1de35f41549e60c3c02a8defa7cb95eabdf2 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 6 Jan 2023 19:47:05 -0800
Subject: [PATCH 1146/1167] kunit: memcpy: Split slow memcpy tests into
MEMCPY_SLOW_KUNIT_TEST
Since the long memcpy tests may stall a system for tens of seconds
in virtualized architecture environments, split those tests off under
CONFIG_MEMCPY_SLOW_KUNIT_TEST so they can be separately disabled.
Reported-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/lkml/20221226195206.GA2626419@roeck-us.net
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-and-tested-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: David Gow <davidgow@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
lib/Kconfig.debug | 9 +++++++++
lib/memcpy_kunit.c | 2 ++
2 files changed, 11 insertions(+)
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 881c3f84e88a3..149d6403b8a9b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2566,6 +2566,15 @@ config MEMCPY_KUNIT_TEST
If unsure, say N.
+config MEMCPY_SLOW_KUNIT_TEST
+ bool "Include exhaustive memcpy tests"
+ depends on MEMCPY_KUNIT_TEST
+ default y
+ help
+ Some memcpy tests are quite exhaustive in checking for overlaps
+ and bit ranges. These can be very slow, so they are split out
+ as a separate config, in case they need to be disabled.
+
config IS_SIGNED_TYPE_KUNIT_TEST
tristate "Test is_signed_type() macro" if !KUNIT_ALL_TESTS
depends on KUNIT
diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c
index 89128551448d1..887926f047312 100644
--- a/lib/memcpy_kunit.c
+++ b/lib/memcpy_kunit.c
@@ -309,6 +309,8 @@ static void set_random_nonzero(struct kunit *test, u8 *byte)
static void init_large(struct kunit *test)
{
+ if (!IS_ENABLED(CONFIG_MEMCPY_SLOW_KUNIT_TEST))
+ kunit_skip(test, "Slow test skipped. Enable with CONFIG_MEMCPY_SLOW_KUNIT_TEST=y");
/* Get many bit patterns. */
get_random_bytes(large_src, ARRAY_SIZE(large_src));
--
GitLab
From e6a71160cc145e18ab45195abf89884112e02dfb Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 18 Jan 2023 12:21:35 -0800
Subject: [PATCH 1147/1167] gcc-plugins: Reorganize gimple includes for GCC 13
The gimple-iterator.h header must be included before gimple-fold.h
starting with GCC 13. Reorganize gimple headers to work for all GCC
versions.
Reported-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/all/20230113173033.4380-1-palmer@rivosinc.com/
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
scripts/gcc-plugins/gcc-common.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index 9a1895747b153..84c730da36dd3 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -71,7 +71,9 @@
#include "varasm.h"
#include "stor-layout.h"
#include "internal-fn.h"
+#include "gimple.h"
#include "gimple-expr.h"
+#include "gimple-iterator.h"
#include "gimple-fold.h"
#include "context.h"
#include "tree-ssa-alias.h"
@@ -85,10 +87,8 @@
#include "tree-eh.h"
#include "stmt.h"
#include "gimplify.h"
-#include "gimple.h"
#include "tree-phinodes.h"
#include "tree-cfg.h"
-#include "gimple-iterator.h"
#include "gimple-ssa.h"
#include "ssa-iterators.h"
--
GitLab
From be0d8f48ad97f5b775b0af3310343f676dbf318a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 5 Jan 2023 22:02:33 -0800
Subject: [PATCH 1148/1167] bcache: Silence memcpy() run-time false positive
warnings
struct bkey has internal padding in a union, but it isn't always named
the same (e.g. key ## _pad, key_p, etc). This makes it extremely hard
for the compiler to reason about the available size of copies done
against such keys. Use unsafe_memcpy() for now, to silence the many
run-time false positive warnings:
memcpy: detected field-spanning write (size 264) of single field "&i->j" at drivers/md/bcache/journal.c:152 (size 240)
memcpy: detected field-spanning write (size 24) of single field "&b->key" at drivers/md/bcache/btree.c:939 (size 16)
memcpy: detected field-spanning write (size 24) of single field "&temp.key" at drivers/md/bcache/extents.c:428 (size 16)
Reported-by: Alexandre Pereira <alexpereira@disroot.org>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216785
Acked-by: Coly Li <colyli@suse.de>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: linux-bcache@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20230106060229.never.047-kees@kernel.org
---
drivers/md/bcache/bcache_ondisk.h | 3 ++-
drivers/md/bcache/journal.c | 3 ++-
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/md/bcache/bcache_ondisk.h b/drivers/md/bcache/bcache_ondisk.h
index 97413586195b4..f96034e0ba4f2 100644
--- a/drivers/md/bcache/bcache_ondisk.h
+++ b/drivers/md/bcache/bcache_ondisk.h
@@ -106,7 +106,8 @@ static inline unsigned long bkey_bytes(const struct bkey *k)
return bkey_u64s(k) * sizeof(__u64);
}
-#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src))
+#define bkey_copy(_dest, _src) unsafe_memcpy(_dest, _src, bkey_bytes(_src), \
+ /* bkey is always padded */)
static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
{
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index e5da469a42357..c182c21de2e81 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -149,7 +149,8 @@ reread: left = ca->sb.bucket_size - offset;
bytes, GFP_KERNEL);
if (!i)
return -ENOMEM;
- memcpy(&i->j, j, bytes);
+ unsafe_memcpy(&i->j, j, bytes,
+ /* "bytes" was calculated by set_bytes() above */);
/* Add to the location after 'where' points to */
list_add(&i->list, where);
ret = 1;
--
GitLab
From 19398821b25a9cde564265262e680ae1c2351be7 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 20 Jan 2023 16:26:12 -0800
Subject: [PATCH 1149/1167] cxl/pmem: Fix nvdimm unregistration when cxl_pmem
driver is absent
The cxl_pmem.ko module houses the driver for both cxl_nvdimm_bridge
objects and cxl_nvdimm objects. When the core creates a cxl_nvdimm it
arranges for it to be autoremoved when the bridge goes down. However, if
the bridge never initialized because the cxl_pmem.ko module never
loaded, it sets up a the following crash scenario:
BUG: kernel NULL pointer dereference, address: 0000000000000478
[..]
RIP: 0010:cxl_nvdimm_probe+0x99/0x140 [cxl_pmem]
[..]
Call Trace:
<TASK>
cxl_bus_probe+0x17/0x50 [cxl_core]
really_probe+0xde/0x380
__driver_probe_device+0x78/0x170
driver_probe_device+0x1f/0x90
__driver_attach+0xd2/0x1c0
bus_for_each_dev+0x79/0xc0
bus_add_driver+0x1b1/0x200
driver_register+0x89/0xe0
cxl_pmem_init+0x50/0xff0 [cxl_pmem]
It turns out the recent rework to simplify nvdimm probing obviated the
need to unregister cxl_nvdimm objects at cxl_nvdimm_bridge ->remove()
time. Leave the cxl_nvdimm device registered until the hosting
cxl_memdev departs. The alternative is that the cxl_memdev needs to be
reattached whenever the cxl_nvdimm_bridge attach state cycles, which is
awkward and unnecessary.
The only requirement is to make sure that when the cxl_nvdimm_bridge
goes away any dependent cxl_nvdimm objects are shutdown. Handle that in
unregister_nvdimm_bus().
With these registration entanglements removed there is no longer a need
to pre-load the cxl_pmem module in cxl_acpi.
Fixes: cb9cfff82f6a ("cxl/acpi: Simplify cxl_nvdimm_bridge probing")
Reported-by: Gregory Price <gregory.price@memverge.com>
Debugged-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167426077263.3955046.9695309346988027311.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
drivers/cxl/acpi.c | 1 -
drivers/cxl/core/pmem.c | 42 ++++-------------------------------------
drivers/cxl/pmem.c | 24 +++++++++++++++++++++++
3 files changed, 28 insertions(+), 39 deletions(-)
diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index ad0849af42d79..13cde44c60860 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -736,4 +736,3 @@ module_exit(cxl_acpi_exit);
MODULE_LICENSE("GPL v2");
MODULE_IMPORT_NS(CXL);
MODULE_IMPORT_NS(ACPI);
-MODULE_SOFTDEP("pre: cxl_pmem");
diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index f3d2169b67311..c2e4b10937884 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -227,34 +227,16 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb,
return cxl_nvd;
}
-static void cxl_nvd_unregister(void *_cxl_nvd)
+static void cxlmd_release_nvdimm(void *_cxlmd)
{
- struct cxl_nvdimm *cxl_nvd = _cxl_nvd;
- struct cxl_memdev *cxlmd = cxl_nvd->cxlmd;
+ struct cxl_memdev *cxlmd = _cxlmd;
+ struct cxl_nvdimm *cxl_nvd = cxlmd->cxl_nvd;
struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
- /*
- * Either the bridge is in ->remove() context under the device_lock(),
- * or cxlmd_release_nvdimm() is cancelling the bridge's release action
- * for @cxl_nvd and doing it itself (while manually holding the bridge
- * lock).
- */
- device_lock_assert(&cxl_nvb->dev);
cxl_nvd->cxlmd = NULL;
cxlmd->cxl_nvd = NULL;
+ cxlmd->cxl_nvb = NULL;
device_unregister(&cxl_nvd->dev);
-}
-
-static void cxlmd_release_nvdimm(void *_cxlmd)
-{
- struct cxl_memdev *cxlmd = _cxlmd;
- struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb;
-
- device_lock(&cxl_nvb->dev);
- if (cxlmd->cxl_nvd)
- devm_release_action(&cxl_nvb->dev, cxl_nvd_unregister,
- cxlmd->cxl_nvd);
- device_unlock(&cxl_nvb->dev);
put_device(&cxl_nvb->dev);
}
@@ -293,22 +275,6 @@ int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd)
dev_dbg(&cxlmd->dev, "register %s\n", dev_name(dev));
- /*
- * The two actions below arrange for @cxl_nvd to be deleted when either
- * the top-level PMEM bridge goes down, or the endpoint device goes
- * through ->remove().
- */
- device_lock(&cxl_nvb->dev);
- if (cxl_nvb->dev.driver)
- rc = devm_add_action_or_reset(&cxl_nvb->dev, cxl_nvd_unregister,
- cxl_nvd);
- else
- rc = -ENXIO;
- device_unlock(&cxl_nvb->dev);
-
- if (rc)
- goto err_alloc;
-
/* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */
return devm_add_action_or_reset(&cxlmd->dev, cxlmd_release_nvdimm, cxlmd);
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index eedefebc42839..08bbbac9a6d08 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -225,11 +225,35 @@ static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc,
return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len);
}
+static int detach_nvdimm(struct device *dev, void *data)
+{
+ struct cxl_nvdimm *cxl_nvd;
+ bool release = false;
+
+ if (!is_cxl_nvdimm(dev))
+ return 0;
+
+ device_lock(dev);
+ if (!dev->driver)
+ goto out;
+
+ cxl_nvd = to_cxl_nvdimm(dev);
+ if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data)
+ release = true;
+out:
+ device_unlock(dev);
+ if (release)
+ device_release_driver(dev);
+ return 0;
+}
+
static void unregister_nvdimm_bus(void *_cxl_nvb)
{
struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb;
struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus;
+ bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, detach_nvdimm);
+
cxl_nvb->nvdimm_bus = NULL;
nvdimm_bus_unregister(nvdimm_bus);
}
--
GitLab
From 62c487b53a7ff31e322cf2874d3796b8202c54a5 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 25 Jan 2023 00:13:20 +0900
Subject: [PATCH 1150/1167] ksmbd: limit pdu length size according to
connection status
Stream protocol length will never be larger than 16KB until session setup.
After session setup, the size of requests will not be larger than
16KB + SMB2 MAX WRITE size. This patch limits these invalidly oversized
requests and closes the connection immediately.
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Cc: stable@vger.kernel.org
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-18259
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/connection.c | 17 +++++++++++++++--
fs/ksmbd/smb2pdu.h | 5 +++--
2 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c
index fd0a288af299e..56be077e5d8ac 100644
--- a/fs/ksmbd/connection.c
+++ b/fs/ksmbd/connection.c
@@ -280,7 +280,7 @@ int ksmbd_conn_handler_loop(void *p)
{
struct ksmbd_conn *conn = (struct ksmbd_conn *)p;
struct ksmbd_transport *t = conn->transport;
- unsigned int pdu_size;
+ unsigned int pdu_size, max_allowed_pdu_size;
char hdr_buf[4] = {0,};
int size;
@@ -305,13 +305,26 @@ int ksmbd_conn_handler_loop(void *p)
pdu_size = get_rfc1002_len(hdr_buf);
ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size);
+ if (conn->status == KSMBD_SESS_GOOD)
+ max_allowed_pdu_size =
+ SMB3_MAX_MSGSIZE + conn->vals->max_write_size;
+ else
+ max_allowed_pdu_size = SMB3_MAX_MSGSIZE;
+
+ if (pdu_size > max_allowed_pdu_size) {
+ pr_err_ratelimited("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n",
+ pdu_size, max_allowed_pdu_size,
+ conn->status);
+ break;
+ }
+
/*
* Check if pdu size is valid (min : smb header size,
* max : 0x00FFFFFF).
*/
if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE ||
pdu_size > MAX_STREAM_PROT_LEN) {
- continue;
+ break;
}
/* 4 for rfc1002 length field */
diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h
index aa5dbe54f5a18..0c8a770fe3189 100644
--- a/fs/ksmbd/smb2pdu.h
+++ b/fs/ksmbd/smb2pdu.h
@@ -24,8 +24,9 @@
#define SMB21_DEFAULT_IOSIZE (1024 * 1024)
#define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024)
-#define SMB3_MIN_IOSIZE (64 * 1024)
-#define SMB3_MAX_IOSIZE (8 * 1024 * 1024)
+#define SMB3_MIN_IOSIZE (64 * 1024)
+#define SMB3_MAX_IOSIZE (8 * 1024 * 1024)
+#define SMB3_MAX_MSGSIZE (4 * 4096)
/*
* Definitions for SMB2 Protocol Data Units (network frames)
--
GitLab
From a34dc4a9b9e2fb3a45c179a60bb0b26539c96189 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 25 Jan 2023 00:09:02 +0900
Subject: [PATCH 1151/1167] ksmbd: downgrade ndr version error message to debug
When user switch samba to ksmbd, The following message flood is coming
when accessing files. Samba seems to changs dos attribute version to v5.
This patch downgrade ndr version error message to debug.
$ dmesg
...
[68971.766914] ksmbd: v5 version is not supported
[68971.779808] ksmbd: v5 version is not supported
[68971.871544] ksmbd: v5 version is not supported
[68971.910135] ksmbd: v5 version is not supported
...
Cc: stable@vger.kernel.org
Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3")
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
fs/ksmbd/ndr.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c
index 0ae8d08d85a87..4d9e0b54e3dbf 100644
--- a/fs/ksmbd/ndr.c
+++ b/fs/ksmbd/ndr.c
@@ -242,7 +242,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da)
return ret;
if (da->version != 3 && da->version != 4) {
- pr_err("v%d version is not supported\n", da->version);
+ ksmbd_debug(VFS, "v%d version is not supported\n", da->version);
return -EINVAL;
}
@@ -251,7 +251,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da)
return ret;
if (da->version != version2) {
- pr_err("ndr version mismatched(version: %d, version2: %d)\n",
+ ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n",
da->version, version2);
return -EINVAL;
}
@@ -457,7 +457,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl)
if (ret)
return ret;
if (acl->version != 4) {
- pr_err("v%d version is not supported\n", acl->version);
+ ksmbd_debug(VFS, "v%d version is not supported\n", acl->version);
return -EINVAL;
}
@@ -465,7 +465,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl)
if (ret)
return ret;
if (acl->version != version2) {
- pr_err("ndr version mismatched(version: %d, version2: %d)\n",
+ ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n",
acl->version, version2);
return -EINVAL;
}
--
GitLab
From 6c4ca03bd890566d873e3593b32d034bf2f5a087 Mon Sep 17 00:00:00 2001
From: David Christensen <drc@linux.vnet.ibm.com>
Date: Tue, 24 Jan 2023 13:53:39 -0500
Subject: [PATCH 1152/1167] net/tg3: resolve deadlock in tg3_reset_task()
during EEH
During EEH error injection testing, a deadlock was encountered in the tg3
driver when tg3_io_error_detected() was attempting to cancel outstanding
reset tasks:
crash> foreach UN bt
...
PID: 159 TASK: c0000000067c6000 CPU: 8 COMMAND: "eehd"
...
#5 [c00000000681f990] __cancel_work_timer at c00000000019fd18
#6 [c00000000681fa30] tg3_io_error_detected at c00800000295f098 [tg3]
#7 [c00000000681faf0] eeh_report_error at c00000000004e25c
...
PID: 290 TASK: c000000036e5f800 CPU: 6 COMMAND: "kworker/6:1"
...
#4 [c00000003721fbc0] rtnl_lock at c000000000c940d8
#5 [c00000003721fbe0] tg3_reset_task at c008000002969358 [tg3]
#6 [c00000003721fc60] process_one_work at c00000000019e5c4
...
PID: 296 TASK: c000000037a65800 CPU: 21 COMMAND: "kworker/21:1"
...
#4 [c000000037247bc0] rtnl_lock at c000000000c940d8
#5 [c000000037247be0] tg3_reset_task at c008000002969358 [tg3]
#6 [c000000037247c60] process_one_work at c00000000019e5c4
...
PID: 655 TASK: c000000036f49000 CPU: 16 COMMAND: "kworker/16:2"
...:1
#4 [c0000000373ebbc0] rtnl_lock at c000000000c940d8
#5 [c0000000373ebbe0] tg3_reset_task at c008000002969358 [tg3]
#6 [c0000000373ebc60] process_one_work at c00000000019e5c4
...
Code inspection shows that both tg3_io_error_detected() and
tg3_reset_task() attempt to acquire the RTNL lock at the beginning of
their code blocks. If tg3_reset_task() should happen to execute between
the times when tg3_io_error_deteced() acquires the RTNL lock and
tg3_reset_task_cancel() is called, a deadlock will occur.
Moving tg3_reset_task_cancel() call earlier within the code block, prior
to acquiring RTNL, prevents this from happening, but also exposes another
deadlock issue where tg3_reset_task() may execute AFTER
tg3_io_error_detected() has executed:
crash> foreach UN bt
PID: 159 TASK: c0000000067d2000 CPU: 9 COMMAND: "eehd"
...
#4 [c000000006867a60] rtnl_lock at c000000000c940d8
#5 [c000000006867a80] tg3_io_slot_reset at c0080000026c2ea8 [tg3]
#6 [c000000006867b00] eeh_report_reset at c00000000004de88
...
PID: 363 TASK: c000000037564000 CPU: 6 COMMAND: "kworker/6:1"
...
#3 [c000000036c1bb70] msleep at c000000000259e6c
#4 [c000000036c1bba0] napi_disable at c000000000c6b848
#5 [c000000036c1bbe0] tg3_reset_task at c0080000026d942c [tg3]
#6 [c000000036c1bc60] process_one_work at c00000000019e5c4
...
This issue can be avoided by aborting tg3_reset_task() if EEH error
recovery is already in progress.
Fixes: db84bf43ef23 ("tg3: tg3_reset_task() needs to use rtnl_lock to synchronize")
Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://lore.kernel.org/r/20230124185339.225806-1-drc@linux.vnet.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/broadcom/tg3.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 59debdc344a50..58747292521d8 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -11166,7 +11166,7 @@ static void tg3_reset_task(struct work_struct *work)
rtnl_lock();
tg3_full_lock(tp, 0);
- if (!netif_running(tp->dev)) {
+ if (tp->pcierr_recovery || !netif_running(tp->dev)) {
tg3_flag_clear(tp, RESET_TASK_PENDING);
tg3_full_unlock(tp);
rtnl_unlock();
@@ -18101,6 +18101,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
netdev_info(netdev, "PCI I/O error detected\n");
+ /* Want to make sure that the reset task doesn't run */
+ tg3_reset_task_cancel(tp);
+
rtnl_lock();
/* Could be second call or maybe we don't have netdev yet */
@@ -18117,9 +18120,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev,
tg3_timer_stop(tp);
- /* Want to make sure that the reset task doesn't run */
- tg3_reset_task_cancel(tp);
-
netif_device_detach(netdev);
/* Clean up software state, even if MMIO is blocked */
--
GitLab
From 3d53aaef4332245044b2f3688ac0ea10436c719c Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Tue, 24 Jan 2023 20:14:40 +0100
Subject: [PATCH 1153/1167] tsnep: Fix TX queue stop/wake for multiple queues
netif_stop_queue() and netif_wake_queue() act on TX queue 0. This is ok
as long as only a single TX queue is supported. But support for multiple
TX queues was introduced with 762031375d5c and I missed to adapt stop
and wake of TX queues.
Use netif_stop_subqueue() and netif_tx_wake_queue() to act on specific
TX queue.
Fixes: 762031375d5c ("tsnep: Support multiple TX/RX queue pairs")
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://lore.kernel.org/r/20230124191440.56887-1-gerhard@engleder-embedded.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/ethernet/engleder/tsnep_main.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index bf0190e1d2ea4..00e2108f2ca4c 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -450,7 +450,7 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
/* ring full, shall not happen because queue is stopped if full
* below
*/
- netif_stop_queue(tx->adapter->netdev);
+ netif_stop_subqueue(tx->adapter->netdev, tx->queue_index);
spin_unlock_irqrestore(&tx->lock, flags);
@@ -493,7 +493,7 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
if (tsnep_tx_desc_available(tx) < (MAX_SKB_FRAGS + 1)) {
/* ring can get full with next frame */
- netif_stop_queue(tx->adapter->netdev);
+ netif_stop_subqueue(tx->adapter->netdev, tx->queue_index);
}
spin_unlock_irqrestore(&tx->lock, flags);
@@ -503,11 +503,14 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb,
static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
{
+ struct tsnep_tx_entry *entry;
+ struct netdev_queue *nq;
unsigned long flags;
int budget = 128;
- struct tsnep_tx_entry *entry;
- int count;
int length;
+ int count;
+
+ nq = netdev_get_tx_queue(tx->adapter->netdev, tx->queue_index);
spin_lock_irqsave(&tx->lock, flags);
@@ -564,8 +567,8 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
} while (likely(budget));
if ((tsnep_tx_desc_available(tx) >= ((MAX_SKB_FRAGS + 1) * 2)) &&
- netif_queue_stopped(tx->adapter->netdev)) {
- netif_wake_queue(tx->adapter->netdev);
+ netif_tx_queue_stopped(nq)) {
+ netif_tx_wake_queue(nq);
}
spin_unlock_irqrestore(&tx->lock, flags);
--
GitLab
From aee2770d199a969b205e7b60125d5af47e3bdee0 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Tue, 24 Jan 2023 15:51:26 +0100
Subject: [PATCH 1154/1167] docs: networking: Fix bridge documentation URL
Current documentation URL [1] is no longer valid.
[1] https://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://lore.kernel.org/r/20230124145127.189221-1-ivecera@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
Documentation/networking/bridge.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst
index 4aef9cddde2fd..c859f3c1636ed 100644
--- a/Documentation/networking/bridge.rst
+++ b/Documentation/networking/bridge.rst
@@ -8,7 +8,7 @@ In order to use the Ethernet bridging functionality, you'll need the
userspace tools.
Documentation for Linux bridging is on:
- http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
+ https://wiki.linuxfoundation.org/networking/bridge
The bridge-utilities are maintained at:
git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git
--
GitLab
From 7083df59abbc2b7500db312cac706493be0273ff Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 24 Jan 2023 11:11:57 +0100
Subject: [PATCH 1155/1167] net: mdio-mux-meson-g12a: force internal PHY off on
mux switch
Force the internal PHY off then on when switching to the internal path.
This fixes problems where the PHY ID is not properly set.
Fixes: 7090425104db ("net: phy: add amlogic g12a mdio mux support")
Suggested-by: Qi Duan <qi.duan@amlogic.com>
Co-developed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20230124101157.232234-1-jbrunet@baylibre.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
drivers/net/mdio/mdio-mux-meson-g12a.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c
index 4a2e94faf57e2..c4542ecf56230 100644
--- a/drivers/net/mdio/mdio-mux-meson-g12a.c
+++ b/drivers/net/mdio/mdio-mux-meson-g12a.c
@@ -4,6 +4,7 @@
*/
#include <linux/bitfield.h>
+#include <linux/delay.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/device.h>
@@ -150,6 +151,7 @@ static const struct clk_ops g12a_ephy_pll_ops = {
static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv)
{
+ u32 value;
int ret;
/* Enable the phy clock */
@@ -163,18 +165,25 @@ static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv)
/* Initialize ephy control */
writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0);
- writel(FIELD_PREP(PHY_CNTL1_ST_MODE, 3) |
- FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) |
- FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) |
- PHY_CNTL1_CLK_EN |
- PHY_CNTL1_CLKFREQ |
- PHY_CNTL1_PHY_ENB,
- priv->regs + ETH_PHY_CNTL1);
+
+ /* Make sure we get a 0 -> 1 transition on the enable bit */
+ value = FIELD_PREP(PHY_CNTL1_ST_MODE, 3) |
+ FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) |
+ FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) |
+ PHY_CNTL1_CLK_EN |
+ PHY_CNTL1_CLKFREQ;
+ writel(value, priv->regs + ETH_PHY_CNTL1);
writel(PHY_CNTL2_USE_INTERNAL |
PHY_CNTL2_SMI_SRC_MAC |
PHY_CNTL2_RX_CLK_EPHY,
priv->regs + ETH_PHY_CNTL2);
+ value |= PHY_CNTL1_PHY_ENB;
+ writel(value, priv->regs + ETH_PHY_CNTL1);
+
+ /* The phy needs a bit of time to power up */
+ mdelay(10);
+
return 0;
}
--
GitLab
From a428eb4b99ab80454f06ad256b25e930fe8a4954 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jan 2023 18:30:38 +0000
Subject: [PATCH 1156/1167] Partially revert "perf/arm-cmn: Optimise DTC
counter accesses"
It turns out the optimisation implemented by commit 4f2c3872dde5 is
totally broken, since all the places that consume hw->dtcs_used for
events other than cycle count are still not expecting it to be sparsely
populated, and fail to read all the relevant DTC counters correctly if
so.
If implemented correctly, the optimisation potentially saves up to 3
register reads per event update, which is reasonably significant for
events targeting a single node, but still not worth a massive amount of
additional code complexity overall. Getting it right within the current
design looks a fair bit more involved than it was ever intended to be,
so let's just make a functional revert which restores the old behaviour
while still backporting easily.
Fixes: 4f2c3872dde5 ("perf/arm-cmn: Optimise DTC counter accesses")
Reported-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/b41bb4ed7283c3d8400ce5cf5e6ec94915e6750f.1674498637.git.robin.murphy@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
drivers/perf/arm-cmn.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index b80a9b74662b1..1deb61b22bc76 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -1576,7 +1576,6 @@ static int arm_cmn_event_init(struct perf_event *event)
hw->dn++;
continue;
}
- hw->dtcs_used |= arm_cmn_node_to_xp(cmn, dn)->dtc;
hw->num_dns++;
if (bynodeid)
break;
@@ -1589,6 +1588,12 @@ static int arm_cmn_event_init(struct perf_event *event)
nodeid, nid.x, nid.y, nid.port, nid.dev, type);
return -EINVAL;
}
+ /*
+ * Keep assuming non-cycles events count in all DTC domains; turns out
+ * it's hard to make a worthwhile optimisation around this, short of
+ * going all-in with domain-local counter allocation as well.
+ */
+ hw->dtcs_used = (1U << cmn->num_dtcs) - 1;
return arm_cmn_validate_group(cmn, event);
}
--
GitLab
From 8e4ff684762b6503db45e8906e258faee080c336 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 26 Jan 2023 19:53:46 +0800
Subject: [PATCH 1157/1167] block: ublk: move ublk_chr_class destroying after
devices are removed
The 'ublk_chr_class' is needed when deleting ublk char devices in
ublk_exit(), so move it after devices(idle) are removed.
Fixes the following warning reported by Harris, James R:
[ 859.178950] sysfs group 'power' not found for kobject 'ublkc0'
[ 859.178962] WARNING: CPU: 3 PID: 1109 at fs/sysfs/group.c:278 sysfs_remove_group+0x9c/0xb0
Reported-by: "Harris, James R" <james.r.harris@intel.com>
Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver")
Link: https://lore.kernel.org/linux-block/Y9JlFmSgDl3+zy3N@T590/T/#t
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Jim Harris <james.r.harris@intel.com>
Link: https://lore.kernel.org/r/20230126115346.263344-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/block/ublk_drv.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 17b677b5d3b22..e546932046309 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2092,13 +2092,12 @@ static void __exit ublk_exit(void)
struct ublk_device *ub;
int id;
- class_destroy(ublk_chr_class);
-
- misc_deregister(&ublk_misc);
-
idr_for_each_entry(&ublk_index_idr, ub, id)
ublk_remove(ub);
+ class_destroy(ublk_chr_class);
+ misc_deregister(&ublk_misc);
+
idr_destroy(&ublk_index_idr);
unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS);
}
--
GitLab
From 262b42e02d1e0b5ad1b33e9b9842e178c16231de Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 26 Jan 2023 10:05:39 -0800
Subject: [PATCH 1158/1167] treewide: fix up files incorrectly marked
executable
I'm not exactly clear on what strange workflow causes people to do it,
but clearly occasionally some files end up being committed as executable
even though they clearly aren't.
This is a reprise of commit 90fda63fa115 ("treewide: fix up files
incorrectly marked executable"), just with a different set of files (but
with the same trivial shell scripting).
So apparently we need to re-do this every five years or so, and Joe
needs to just keep reminding me to do so ;)
Reported-by: Joe Perches <joe@perches.com>
Fixes: 523375c943e5 ("drm/vmwgfx: Port vmwgfx to arm64")
Fixes: 5c439937775d ("ASoC: codecs: add support for ES8326")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h | 0
sound/soc/codecs/es8326.c | 0
sound/soc/codecs/es8326.h | 0
3 files changed, 0 insertions(+), 0 deletions(-)
mode change 100755 => 100644 drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h
mode change 100755 => 100644 sound/soc/codecs/es8326.c
mode change 100755 => 100644 sound/soc/codecs/es8326.h
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h
old mode 100755
new mode 100644
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
old mode 100755
new mode 100644
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
old mode 100755
new mode 100644
--
GitLab
From f439a959dcfb6b39d6fd4b85ca1110a1d1de1587 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 27 Jan 2023 12:15:13 +1000
Subject: [PATCH 1159/1167] amdgpu: fix build on non-DCN platforms.
This fixes the build here locally on my 32-bit arm build.
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ead47bc626016..af37bc6ed1f56 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9497,8 +9497,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
struct drm_connector_state *old_con_state, *new_con_state;
struct drm_crtc *crtc;
struct drm_crtc_state *old_crtc_state, *new_crtc_state;
- struct drm_dp_mst_topology_mgr *mgr;
- struct drm_dp_mst_topology_state *mst_state;
struct drm_plane *plane;
struct drm_plane_state *old_plane_state, *new_plane_state;
enum dc_status status;
@@ -9506,6 +9504,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
bool lock_and_validation_needed = false;
struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
#if defined(CONFIG_DRM_AMD_DC_DCN)
+ struct drm_dp_mst_topology_mgr *mgr;
+ struct drm_dp_mst_topology_state *mst_state;
struct dsc_mst_fairness_vars vars[MAX_PIPES];
#endif
--
GitLab
From b710ef411048cdbd0fb279b9529af2731fe97022 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 27 Jan 2023 10:35:05 +0100
Subject: [PATCH 1160/1167] gpio: ep93xx: remove unused variable
This one was left behind by a previous cleanup patch:
drivers/gpio/gpio-ep93xx.c: In function 'ep93xx_gpio_add_bank':
drivers/gpio/gpio-ep93xx.c:366:34: error: unused variable 'ic' [-Werror=unused-variable]
Fixes: 216f37366e86 ("gpio: ep93xx: Make irqchip immutable")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
drivers/gpio/gpio-ep93xx.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 192be99b13923..6cedf46efec6c 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -363,8 +363,6 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc,
girq = &gc->irq;
if (bank->has_irq || bank->has_hierarchical_irq) {
- struct irq_chip *ic;
-
gc->set_config = ep93xx_gpio_set_config;
egc->eic = devm_kcalloc(dev, 1,
sizeof(*egc->eic),
--
GitLab
From 677d85e1a1ee69fa05ccea83847309484be3781c Mon Sep 17 00:00:00 2001
From: Ivo Borisov Shopov <ivoshopov@gmail.com>
Date: Thu, 26 Jan 2023 15:10:33 +0200
Subject: [PATCH 1161/1167] tools: gpio: fix -c option of gpio-event-mon
Following line should listen for a rising edge and exit after the first
one since '-c 1' is provided.
# gpio-event-mon -n gpiochip1 -o 0 -r -c 1
It works with kernel 4.19 but it doesn't work with 5.10. In 5.10 the
above command doesn't exit after the first rising edge it keep listening
for an event forever. The '-c 1' is not taken into an account.
The problem is in commit 62757c32d5db ("tools: gpio: add multi-line
monitoring to gpio-event-mon").
Before this commit the iterator 'i' in monitor_device() is used for
counting of the events (loops). In the case of the above command (-c 1)
we should start from 0 and increment 'i' only ones and hit the 'break'
statement and exit the process. But after the above commit counting
doesn't start from 0, it start from 1 when we listen on one line.
It is because 'i' is used from one more purpose, counting of lines
(num_lines) and it isn't restore to 0 after following code
for (i = 0; i < num_lines; i++)
gpiotools_set_bit(&values.mask, i);
Restore the initial value of the iterator to 0 in order to allow counting
of loops to work for any cases.
Fixes: 62757c32d5db ("tools: gpio: add multi-line monitoring to gpio-event-mon")
Signed-off-by: Ivo Borisov Shopov <ivoshopov@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
[Bartosz: tweak the commit message]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
tools/gpio/gpio-event-mon.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c
index 6c122952c5892..5dee2b98ab604 100644
--- a/tools/gpio/gpio-event-mon.c
+++ b/tools/gpio/gpio-event-mon.c
@@ -86,6 +86,7 @@ int monitor_device(const char *device_name,
gpiotools_test_bit(values.bits, i));
}
+ i = 0;
while (1) {
struct gpio_v2_line_event event;
--
GitLab
From ef5c600adb1d985513d2b612cc90403a148ff287 Mon Sep 17 00:00:00 2001
From: Dylan Yudaken <dylany@meta.com>
Date: Fri, 27 Jan 2023 02:59:11 -0800
Subject: [PATCH 1162/1167] io_uring: always prep_async for drain requests
Drain requests all go through io_drain_req, which has a quick exit in case
there is nothing pending (ie the drain is not useful). In that case it can
run the issue the request immediately.
However for safety it queues it through task work.
The problem is that in this case the request is run asynchronously, but
the async work has not been prepared through io_req_prep_async.
This has not been a problem up to now, as the task work always would run
before returning to userspace, and so the user would not have a chance to
race with it.
However - with IORING_SETUP_DEFER_TASKRUN - this is no longer the case and
the work might be defered, giving userspace a chance to change data being
referred to in the request.
Instead _always_ prep_async for drain requests, which is simpler anyway
and removes this issue.
Cc: stable@vger.kernel.org
Fixes: c0e0d6ba25f1 ("io_uring: add IORING_SETUP_DEFER_TASKRUN")
Signed-off-by: Dylan Yudaken <dylany@meta.com>
Link: https://lore.kernel.org/r/20230127105911.2420061-1-dylany@meta.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
io_uring/io_uring.c | 18 ++++++++----------
1 file changed, 8 insertions(+), 10 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 0a4efada9b3c3..db623b3185c82 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1765,17 +1765,12 @@ static __cold void io_drain_req(struct io_kiocb *req)
}
spin_unlock(&ctx->completion_lock);
- ret = io_req_prep_async(req);
- if (ret) {
-fail:
- io_req_defer_failed(req, ret);
- return;
- }
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
ret = -ENOMEM;
- goto fail;
+ io_req_defer_failed(req, ret);
+ return;
}
spin_lock(&ctx->completion_lock);
@@ -2048,13 +2043,16 @@ static void io_queue_sqe_fallback(struct io_kiocb *req)
req->flags &= ~REQ_F_HARDLINK;
req->flags |= REQ_F_LINK;
io_req_defer_failed(req, req->cqe.res);
- } else if (unlikely(req->ctx->drain_active)) {
- io_drain_req(req);
} else {
int ret = io_req_prep_async(req);
- if (unlikely(ret))
+ if (unlikely(ret)) {
io_req_defer_failed(req, ret);
+ return;
+ }
+
+ if (unlikely(req->ctx->drain_active))
+ io_drain_req(req);
else
io_queue_iowq(req, NULL);
}
--
GitLab
From baabaa505563362b71f2637aedd7b807d270656c Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 24 Jan 2023 16:41:18 +0100
Subject: [PATCH 1163/1167] ovl: fix tmpfile leak
Missed an error cleanup.
Reported-by: syzbot+fd749a7ea127a84e0ffd@syzkaller.appspotmail.com
Fixes: 2b1a77461f16 ("ovl: use vfs_tmpfile_open() helper")
Cc: <stable@vger.kernel.org> # v6.1
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
fs/overlayfs/copy_up.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 6e4e65ee050d6..140f2742074d4 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -792,7 +792,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c)
if (!c->metacopy && c->stat.size) {
err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size);
if (err)
- return err;
+ goto out_fput;
}
err = ovl_copy_up_metadata(c, temp);
--
GitLab
From 4f11ada10d0ad3fd53e2bd67806351de63a4f9c3 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 24 Jan 2023 16:41:18 +0100
Subject: [PATCH 1164/1167] ovl: fail on invalid uid/gid mapping at copy up
If st_uid/st_gid doesn't have a mapping in the mounter's user_ns, then
copy-up should fail, just like it would fail if the mounter task was doing
the copy using "cp -a".
There's a corner case where the "cp -a" would succeed but copy up fail: if
there's a mapping of the invalid uid/gid (65534 by default) in the user
namespace. This is because stat(2) will return this value if the mapping
doesn't exist in the current user_ns and "cp -a" will in turn be able to
create a file with this uid/gid.
This behavior would be inconsistent with POSIX ACL's, which return -1 for
invalid uid/gid which result in a failed copy.
For consistency and simplicity fail the copy of the st_uid/st_gid are
invalid.
Fixes: 459c7c565ac3 ("ovl: unprivieged mounts")
Cc: <stable@vger.kernel.org> # v5.11
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Seth Forshee <sforshee@kernel.org>
---
fs/overlayfs/copy_up.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 140f2742074d4..c14e90764e356 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -1011,6 +1011,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
if (err)
return err;
+ if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) ||
+ !kgid_has_mapping(current_user_ns(), ctx.stat.gid))
+ return -EOVERFLOW;
+
ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags);
if (parent) {
--
GitLab
From c96618275234ad03d44eafe9f8844305bb44fda4 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 28 Jan 2023 11:17:57 -0800
Subject: [PATCH 1165/1167] Fix up more non-executable files marked executable
Joe found another DT file that shouldn't be executable, and that
frustrated me enough that I went hunting with this script:
git ls-files -s |
grep '^100755' |
cut -f2 |
xargs grep -L '^#!'
and that found another file that shouldn't have been marked executable
either, despite being in the scripts directory.
Maybe these two are the last ones at least for now. But I'm sure we'll
be back in a few years, fixing things up again.
Fixes: 8c6789f4e2d4 ("ASoC: dt-bindings: Add Everest ES8326 audio CODEC")
Fixes: 4d8e5cd233db ("locking/atomics: Fix scripts/atomic/ script permissions")
Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
Documentation/devicetree/bindings/sound/everest,es8326.yaml | 0
scripts/atomic/atomics.tbl | 0
2 files changed, 0 insertions(+), 0 deletions(-)
mode change 100755 => 100644 Documentation/devicetree/bindings/sound/everest,es8326.yaml
mode change 100755 => 100644 scripts/atomic/atomics.tbl
diff --git a/Documentation/devicetree/bindings/sound/everest,es8326.yaml b/Documentation/devicetree/bindings/sound/everest,es8326.yaml
old mode 100755
new mode 100644
diff --git a/scripts/atomic/atomics.tbl b/scripts/atomic/atomics.tbl
old mode 100755
new mode 100644
--
GitLab
From 95e7a450b8190673675836bfef236262ceff084a Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Fri, 13 Jan 2023 18:33:45 +0100
Subject: [PATCH 1166/1167] Revert "mm/compaction: fix set skip in
fast_find_migrateblock"
This reverts commit 7efc3b7261030da79001c00d92bc3392fd6c664c.
We have got openSUSE reports (Link 1) for 6.1 kernel with khugepaged
stalling CPU for long periods of time. Investigation of tracepoint data
shows that compaction is stuck in repeating fast_find_migrateblock()
based migrate page isolation, and then fails to migrate all isolated
pages.
Commit 7efc3b726103 ("mm/compaction: fix set skip in fast_find_migrateblock")
was suspected as it was merged in 6.1 and in theory can indeed remove a
termination condition for fast_find_migrateblock() under certain
conditions, as it removes a place that always marks a scanned pageblock
from being re-scanned. There are other such places, but those can be
skipped under certain conditions, which seems to match the tracepoint
data.
Testing of revert also appears to have resolved the issue, thus revert
the commit until a more robust solution for the original problem is
developed.
It's also likely this will fix qemu stalls with 6.1 kernel reported in
Link 2, but that is not yet confirmed.
Link: https://bugzilla.suse.com/show_bug.cgi?id=1206848
Link: https://lore.kernel.org/kvm/b8017e09-f336-3035-8344-c549086c2340@kernel.org/
Link: https://lore.kernel.org/lkml/20230125134434.18017-1-mgorman@techsingularity.net/
Fixes: 7efc3b726103 ("mm/compaction: fix set skip in fast_find_migrateblock")
Cc: <stable@vger.kernel.org>
Tested-by: Pedro Falcato <pedro.falcato@gmail.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
mm/compaction.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/compaction.c b/mm/compaction.c
index ca1603524bbe0..8238e83385a79 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1839,6 +1839,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
pfn = cc->zone->zone_start_pfn;
cc->fast_search_fail = 0;
found_block = true;
+ set_pageblock_skip(freepage);
break;
}
}
--
GitLab
From 6d796c50f84ca79f1722bb131799e5a5710c4700 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 29 Jan 2023 13:59:43 -0800
Subject: [PATCH 1167/1167] Linux 6.2-rc6
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index c1ead4cd2342a..749bb455546e4 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
--
GitLab