diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293489a031aa300a605447e83b96341..ab4cf7c12c40ada26bd7a6e3e05a587e950c5aa5 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
*/
#define INTEL_PMC_MAX_GENERIC 32
-#define INTEL_PMC_MAX_FIXED 3
+#define INTEL_PMC_MAX_FIXED 4
#define INTEL_PMC_IDX_FIXED 32
#define X86_PMC_IDX_MAX 64
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 2da67b70ba989821db25e3190a5c68964f9e1c26..bc57b5988589adb7668a510e38e6b8fabb568ce1 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -184,10 +184,10 @@ static void therm_throt_process(bool new_event, int event, int level)
/* if we just entered the thermal event */
if (new_event) {
if (event == THERMAL_THROTTLING_EVENT)
- pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
- this_cpu,
- level == CORE_LEVEL ? "Core" : "Package",
- state->count);
+ pr_notice("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
+ this_cpu,
+ level == CORE_LEVEL ? "Core" : "Package",
+ state->count);
return;
}
if (old_event) {
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index b8c3f9e6af8994820c30b40889154f87511014e0..48e52a08997c0161805d87fba53624bc3ed40546 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2118,7 +2118,7 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page)
unsigned int err, i;
if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) {
- ata_dev_warn(dev, "ATA Identify Device Log not supported\n");
+ ata_dev_notice(dev, "ATA Identify Device Log not supported\n");
return false;
}
@@ -2192,7 +2192,7 @@ static void ata_dev_config_ncq_send_recv(struct ata_device *dev)
unsigned int err_mask;
if (!ata_log_supported(dev, ATA_LOG_NCQ_SEND_RECV)) {
- ata_dev_warn(dev, "NCQ Send/Recv Log not supported\n");
+ ata_dev_notice(dev, "NCQ Send/Recv Log not supported\n");
return;
}
err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV,
@@ -2221,8 +2221,8 @@ static void ata_dev_config_ncq_non_data(struct ata_device *dev)
unsigned int err_mask;
if (!ata_log_supported(dev, ATA_LOG_NCQ_NON_DATA)) {
- ata_dev_warn(dev,
- "NCQ Send/Recv Log not supported\n");
+ ata_dev_notice(dev,
+ "NCQ Send/Recv Log not supported\n");
return;
}
err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_NON_DATA,
@@ -2552,14 +2552,14 @@ int ata_dev_configure(struct ata_device *dev)
if (ata_id_is_cfa(id)) {
/* CPRM may make this media unusable */
if (id[ATA_ID_CFA_KEY_MGMT] & 1)
- ata_dev_warn(dev,
+ ata_dev_notice(dev,
"supports DRM functions and may not be fully accessible\n");
snprintf(revbuf, 7, "CFA");
} else {
snprintf(revbuf, 7, "ATA-%d", ata_id_major_version(id));
/* Warn the user if the device has TPM extensions */
if (ata_id_has_tpm(id))
- ata_dev_warn(dev,
+ ata_dev_notice(dev,
"supports DRM functions and may not be fully accessible\n");
}
@@ -2775,8 +2775,8 @@ int ata_dev_configure(struct ata_device *dev)
}
if ((dev->horkage & ATA_HORKAGE_FIRMWARE_WARN) && print_info) {
- ata_dev_warn(dev, "WARNING: device requires firmware update to be fully functional\n");
- ata_dev_warn(dev, " contact the vendor or visit http://ata.wiki.kernel.org\n");
+ ata_dev_notice(dev, "WARNING: device requires firmware update to be fully functional\n");
+ ata_dev_notice(dev, " contact the vendor or visit http://ata.wiki.kernel.org\n");
}
return 0;
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 8bfd27ec73d60d1d18a43f9bfcff29b4eb9a50a6..585e2e1c9c8f4760309e47f052e377da56135e9b 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -31,6 +31,9 @@ static struct kset *system_kset;
#define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr)
+#define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
+ struct driver_attribute driver_attr_##_name = \
+ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
static int __must_check bus_rescan_devices_helper(struct device *dev,
void *data);
@@ -195,7 +198,7 @@ static ssize_t unbind_store(struct device_driver *drv, const char *buf,
bus_put(bus);
return err;
}
-static DRIVER_ATTR_WO(unbind);
+static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, S_IWUSR, NULL, unbind_store);
/*
* Manually attach a device to a driver.
@@ -231,7 +234,7 @@ static ssize_t bind_store(struct device_driver *drv, const char *buf,
bus_put(bus);
return err;
}
-static DRIVER_ATTR_WO(bind);
+static DRIVER_ATTR_IGNORE_LOCKDEP(bind, S_IWUSR, NULL, bind_store);
static ssize_t show_drivers_autoprobe(struct bus_type *bus, char *buf)
{
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index e221861b3187c2fcbceb4b3ee58b70d2fca5fa53..8424b3a27e7eb53773b97f78157caf2cd4e35eb4 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -12,6 +12,7 @@
#include <linux/acpi.h>
#include <linux/pci.h>
#include <linux/usb/hcd.h>
+#include <linux/dmi.h>
#include "hub.h"
@@ -81,6 +82,20 @@ int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable)
}
EXPORT_SYMBOL_GPL(usb_acpi_set_power_state);
+static const struct dmi_system_id intel_icl_broken_acpi[] = {
+ {
+ .ident = "ICL RVP",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Ice Lake Client Platform"),
+ },
+ },
+
+ { }
+};
+
+static bool acpi_connection_type_broken;
+
static enum usb_port_connect_type usb_acpi_get_connect_type(acpi_handle handle,
struct acpi_pld_info *pld)
{
@@ -89,6 +104,10 @@ static enum usb_port_connect_type usb_acpi_get_connect_type(acpi_handle handle,
union acpi_object *upc;
acpi_status status;
+ /* Work around unknown ACPI instruction error on ICL RVP BIOSes. */
+ if (acpi_connection_type_broken)
+ return USB_PORT_CONNECT_TYPE_UNKNOWN;
+
/*
* According to 9.14 in ACPI Spec 6.2. _PLD indicates whether usb port
* is user visible and _UPC indicates whether it is connectable. If
@@ -235,6 +254,11 @@ static struct acpi_bus_type usb_acpi_bus = {
int usb_acpi_register(void)
{
+ if (dmi_check_system(intel_icl_broken_acpi)) {
+ pr_info("USB ACPI connection type broken.\n");
+ acpi_connection_type_broken = true;
+ }
+
return register_acpi_bus_type(&usb_acpi_bus);
}
diff --git a/include/linux/device.h b/include/linux/device.h
index 1b25c7a43f4cc85604fbb0e0becab482edcb84a4..41424d6e27c7222179a3d46e1a788a8d2a946d1e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -327,6 +327,7 @@ struct driver_attribute {
#define DRIVER_ATTR_WO(_name) \
struct driver_attribute driver_attr_##_name = __ATTR_WO(_name)
+
extern int __must_check driver_create_file(struct device_driver *driver,
const struct driver_attribute *attr);
extern void driver_remove_file(struct device_driver *driver,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 84530ab358c37ad876744d5ebda5d277dfb6d065..75912ae91fbbcdf9dd7f778b86b6885c41e92afc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9737,7 +9737,8 @@ void perf_pmu_unregister(struct pmu *pmu)
device_del(pmu->dev);
put_device(pmu->dev);
}
- free_pmu_context(pmu);
+ if (!find_pmu_context(pmu->task_ctx_nr))
+ free_pmu_context(pmu);
mutex_unlock(&pmus_lock);
}
EXPORT_SYMBOL_GPL(perf_pmu_unregister);
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 88c847a41c8ae78ea8fdfc75476b85c259466200..746aec91f5b8408ece6ce4edcf5b41a27adb1b7a 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -69,7 +69,7 @@ enum {
#else
#define MAX_LOCKDEP_ENTRIES 32768UL
-#define MAX_LOCKDEP_CHAINS_BITS 16
+#define MAX_LOCKDEP_CHAINS_BITS 17
/*
* Stack-trace: tightly packed array of stack backtrace
diff --git a/kernel/panic.c b/kernel/panic.c
index f6d549a29a5c85cfdc2de0f07e6f0e956a1268ce..9241f2240ea32e78cd8f375e805bb2a857e34da3 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -180,13 +180,6 @@ void panic(const char *fmt, ...)
buf[len - 1] = '\0';
pr_emerg("Kernel panic - not syncing: %s\n", buf);
-#ifdef CONFIG_DEBUG_BUGVERBOSE
- /*
- * Avoid nested stack-dumping if a panic occurs during oops processing
- */
- if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
- dump_stack();
-#endif
/*
* If we have crashed and we have a crash kernel loaded let it handle
@@ -221,6 +214,14 @@ void panic(const char *fmt, ...)
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+ /*
+ * Avoid nested stack-dumping if a panic occurs during oops processing
+ */
+ if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
+ dump_stack();
+#endif
+
/* Call flush even twice. It tries harder with a single online CPU */
printk_safe_flush_on_panic();
kmsg_dump(KMSG_DUMP_PANIC);
@@ -510,14 +511,9 @@ struct warn_args {
va_list args;
};
-void __warn(const char *file, int line, void *caller, unsigned taint,
- struct pt_regs *regs, struct warn_args *args)
+static void show_location(const char *file, int line, void *caller,
+ struct warn_args *args)
{
- disable_trace_on_warning();
-
- if (args)
- pr_warn(CUT_HERE);
-
if (file)
pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
raw_smp_processor_id(), current->pid, file, line,
@@ -528,6 +524,17 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
if (args)
vprintk(args->fmt, args->args);
+}
+
+void __warn(const char *file, int line, void *caller, unsigned taint,
+ struct pt_regs *regs, struct warn_args *args)
+{
+ disable_trace_on_warning();
+
+ if (args)
+ pr_warn(CUT_HERE);
+
+ show_location(file, line, caller, args);
if (panic_on_warn) {
/*
@@ -549,6 +556,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
print_irqtrace_events(current);
+ show_location(file, line, caller, args);
+
print_oops_end_marker();
/* Just a warning, don't kill lockdep. */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 5e3de28c7677396aaa4360dcf2f51fb9b365b626..d838ba908e0520f0f52cfc6d62e08f2e834742b9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -114,6 +114,13 @@ config TRACING
select EVENT_TRACING
select TRACE_CLOCK
+config GLOBAL_TRACE_BUF_SIZE
+ int
+ prompt "Global ftrace buffer size (for trace_printk)" if EXPERT
+ range 0 4194034
+ default 1441792 # 16384 * 88 (sizeof(struct print_entry))
+ depends on TRACING
+
config GENERIC_TRACER
bool
select TRACING
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ff1c4b20cd0a6d29209950fa006542c71b8c43ef..9ccbeaae959fa104ff1e1f67a1bff94648f7024b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -614,9 +614,7 @@ int tracing_is_enabled(void)
* to not have to wait for all that output. Anyway this can be
* boot time and run time configurable.
*/
-#define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */
-
-static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT;
+static unsigned long trace_buf_size = CONFIG_GLOBAL_TRACE_BUF_SIZE;
/* trace_types holds a link list of available tracers. */
static struct tracer *trace_types __read_mostly;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6589f60d50186aca3812be1a9ae3d8ba7369b87b..2fb50f7d982d527f7def54cb2c8de13dcba6f4a0 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -49,6 +49,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/oom.h>
+static bool task_will_free_mem(struct task_struct *task);
+
int sysctl_panic_on_oom;
int sysctl_oom_kill_allocating_task;
int sysctl_oom_dump_tasks = 1;
@@ -209,19 +211,27 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
+ /*
+ * If we cannot lock the task's mm, it is in the process of being
+ * removed, so select it as the target of the repear and see if it
+ * recovers enough memory to continue.
+ */
p = find_lock_task_mm(p);
if (!p)
- return 0;
+ return ULONG_MAX;
+
+ if (task_will_free_mem(p)) {
+ task_unlock(p);
+ return ULONG_MAX;
+ }
/*
* Do not even consider tasks which are explicitly marked oom
- * unkillable or have been already oom reaped or the are in
- * the middle of vfork
+ * unkillable or are in the middle of vfork (and so still share their
+ * parent's mm).
*/
adj = (long)p->signal->oom_score_adj;
- if (adj == OOM_SCORE_ADJ_MIN ||
- test_bit(MMF_OOM_SKIP, &p->mm->flags) ||
- in_vfork(p)) {
+ if (adj == OOM_SCORE_ADJ_MIN || in_vfork(p)) {
task_unlock(p);
return 0;
}
@@ -801,11 +811,12 @@ static bool task_will_free_mem(struct task_struct *task)
return false;
/*
- * This task has already been drained by the oom reaper so there are
- * only small chances it will free some more
+ * This task has already been selected for the oom reaper, but
+ * the reaper is unable to make progress. Continue to dogpile
+ * on top until it succeeds.
*/
if (test_bit(MMF_OOM_SKIP, &mm->flags))
- return false;
+ return true;
if (atomic_read(&mm->mm_users) <= 1)
return true;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 97d4b25d0373102a197ba1de455a944cf7204061..6e229053c783671ef3d8cca920af0b6d4e82cdaa 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -131,80 +131,27 @@ static void vunmap_page_range(unsigned long addr, unsigned long end)
} while (pgd++, addr = next, addr != end);
}
-static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, pgprot_t prot, struct page **pages, int *nr)
-{
- pte_t *pte;
-
- /*
- * nr is a running index into the array which helps higher level
- * callers keep track of where we're up to.
- */
-
- pte = pte_alloc_kernel(pmd, addr);
- if (!pte)
- return -ENOMEM;
- do {
- struct page *page = pages[*nr];
-
- if (WARN_ON(!pte_none(*pte)))
- return -EBUSY;
- if (WARN_ON(!page))
- return -ENOMEM;
- set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
- (*nr)++;
- } while (pte++, addr += PAGE_SIZE, addr != end);
- return 0;
-}
+struct vmap_page {
+ pgprot_t prot;
+ struct page **pages;
+ unsigned long count;
+};
-static int vmap_pmd_range(pud_t *pud, unsigned long addr,
- unsigned long end, pgprot_t prot, struct page **pages, int *nr)
+static int vmap_page(pte_t *pte, pgtable_t token,
+ unsigned long addr, void *data)
{
- pmd_t *pmd;
- unsigned long next;
+ struct vmap_page *v = data;
+ struct page *page;
- pmd = pmd_alloc(&init_mm, pud, addr);
- if (!pmd)
- return -ENOMEM;
- do {
- next = pmd_addr_end(addr, end);
- if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
- return -ENOMEM;
- } while (pmd++, addr = next, addr != end);
- return 0;
-}
+ if (WARN_ON(!pte_none(*pte)))
+ return -EBUSY;
-static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
- unsigned long end, pgprot_t prot, struct page **pages, int *nr)
-{
- pud_t *pud;
- unsigned long next;
-
- pud = pud_alloc(&init_mm, p4d, addr);
- if (!pud)
+ page = v->pages[v->count];
+ if (WARN_ON(!page))
return -ENOMEM;
- do {
- next = pud_addr_end(addr, end);
- if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
- return -ENOMEM;
- } while (pud++, addr = next, addr != end);
- return 0;
-}
-
-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
- unsigned long end, pgprot_t prot, struct page **pages, int *nr)
-{
- p4d_t *p4d;
- unsigned long next;
- p4d = p4d_alloc(&init_mm, pgd, addr);
- if (!p4d)
- return -ENOMEM;
- do {
- next = p4d_addr_end(addr, end);
- if (vmap_pud_range(p4d, addr, next, prot, pages, nr))
- return -ENOMEM;
- } while (p4d++, addr = next, addr != end);
+ set_pte_at(&init_mm, addr, pte, mk_pte(page, v->prot));
+ v->count++;
return 0;
}
@@ -217,22 +164,37 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
static int vmap_page_range_noflush(unsigned long start, unsigned long end,
pgprot_t prot, struct page **pages)
{
- pgd_t *pgd;
- unsigned long next;
- unsigned long addr = start;
- int err = 0;
- int nr = 0;
+ struct vmap_page v = { prot, pages };
+ int err;
- BUG_ON(addr >= end);
- pgd = pgd_offset_k(addr);
- do {
- next = pgd_addr_end(addr, end);
- err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr);
- if (err)
- return err;
- } while (pgd++, addr = next, addr != end);
+ if ((end - start) >> PAGE_SHIFT > INT_MAX)
+ return -EINVAL;
+
+ /* FIXME: See bugzilla link and
+ * https://www.spinics.net/lists/sparclinux/msg16581.html for why this
+ * is full of regrets.
+ *
+ * Quoting that mail:
+
+On Fri, 28 Oct 2016 21:15:48 +0100 Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> wrote:
+> > Bisect points to commit 0c79e3331f08 ("mm/vmalloc: replace opencoded 4-level
+> > page walkers"). Reverting this patch fixes the problem.
+>
+> Hmm, apply_to_pte_range() has a BUG_ON(pmd_huge(*pmd)) but the old
+> vmap_pte_range() does not and neither has the code to handle that case.
+> Presuming that the BUG_ON() there is actually meaningful.
+
+Thanks, I'll drop mm-vmalloc-replace-opencoded-4-level-page-walkers.patch for now.
+
+ * we never got any further with tracking this one down.
+ */
+ err = apply_to_page_range(&init_mm, start, end - start, vmap_page, &v);
+ if (unlikely(err)) {
+ vunmap_page_range(start, start + (v.count << PAGE_SHIFT));
+ return err;
+ }
- return nr;
+ return v.count;
}
static int vmap_page_range(unsigned long start, unsigned long end,
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index de1663f7d3ad6e2c06cd2e031036cef5979366a5..dfced88a0da12037135bf485baa04ac0966d34e4 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -456,7 +456,12 @@ static void dev_watchdog(struct timer_list *t)
}
}
- if (some_queue_timedout) {
+ /* The noise is pissing off our CI and upstream doesn't
+ * move on the bug report:
+ *
+ * https://bugzilla.kernel.org/show_bug.cgi?id=196399
+ */
+ if (some_queue_timedout && 0) {
WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
dev->name, netdev_drivername(dev), i);
dev->netdev_ops->ndo_tx_timeout(dev);