diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml
index 62c3bd4cb28d89f36d994fce9dd58292c68ec801..7257fd0ae4da87151f909d60d99f12cc93381b28 100644
--- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml
@@ -51,7 +51,6 @@ properties:
Video port for MIPI DPI output (panel or connector).
required:
- - port@0
- port@1
required:
diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml
index 5216c27fc0ada58881235761037162c5873ed0c6..a412a1da950fb9e5aeb33da06ea1733d0324ec58 100644
--- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml
@@ -39,7 +39,6 @@ properties:
Video port for MIPI DPI output (panel or connector).
required:
- - port@0
- port@1
required:
diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml
index f29789994b1804f46e25f888e2b845778eb6e475..c2df8d28aaf5f594b6e1fac2e277ecd161b6f581 100644
--- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml
+++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml
@@ -83,6 +83,8 @@ properties:
required:
- compatible
- reg
+ - width-mm
+ - height-mm
- panel-timing
unevaluatedProperties: false
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 55006678394a2b8333308a3ed69ce6aec5e02a98..36a76cbe90954f0e9c9985e981f564e9eda2de58 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -185,6 +185,12 @@ DMA Fence Chain
.. kernel-doc:: include/linux/dma-fence-chain.h
:internal:
+DMA Fence unwrap
+~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: include/linux/dma-fence-unwrap.h
+ :internal:
+
DMA Fence uABI/Sync File
~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 511805dbeb75f785d153b07fe37c73b6ec26ed8e..4c9eb53ba3f896f2b3b7dee06b938e9c04f09053 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -12,6 +12,7 @@ dmabuf_selftests-y := \
selftest.o \
st-dma-fence.o \
st-dma-fence-chain.o \
+ st-dma-fence-unwrap.o \
st-dma-resv.o
obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o
diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index cb1bacb5a42b543599b35a670f023e7b777c7e41..5c8a7084577b547799890b8b75905d27e8622f96 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
struct dma_fence_array *array;
size_t size = sizeof(*array);
+ WARN_ON(!num_fences || !fences);
+
/* Allocate the callback structures behind the array. */
size += num_fences * sizeof(struct dma_fence_array_cb);
array = kzalloc(size, GFP_KERNEL);
@@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context)
return true;
}
EXPORT_SYMBOL(dma_fence_match_context);
+
+struct dma_fence *dma_fence_array_first(struct dma_fence *head)
+{
+ struct dma_fence_array *array;
+
+ if (!head)
+ return NULL;
+
+ array = to_dma_fence_array(head);
+ if (!array)
+ return head;
+
+ if (!array->num_fences)
+ return NULL;
+
+ return array->fences[0];
+}
+EXPORT_SYMBOL(dma_fence_array_first);
+
+struct dma_fence *dma_fence_array_next(struct dma_fence *head,
+ unsigned int index)
+{
+ struct dma_fence_array *array = to_dma_fence_array(head);
+
+ if (!array || index >= array->num_fences)
+ return NULL;
+
+ return array->fences[index];
+}
+EXPORT_SYMBOL(dma_fence_array_next);
diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h
index 97d73aaa31daa1d72a96222cac7c7a5d177453b0..851965867d9c7f2251f901d499133f531981a92b 100644
--- a/drivers/dma-buf/selftests.h
+++ b/drivers/dma-buf/selftests.h
@@ -12,4 +12,5 @@
selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */
selftest(dma_fence, dma_fence)
selftest(dma_fence_chain, dma_fence_chain)
+selftest(dma_fence_unwrap, dma_fence_unwrap)
selftest(dma_resv, dma_resv)
diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c
new file mode 100644
index 0000000000000000000000000000000000000000..039f016b57be766d903298781a9a91422d84c15e
--- /dev/null
+++ b/drivers/dma-buf/st-dma-fence-unwrap.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ */
+
+#include <linux/dma-fence-unwrap.h>
+#if 0
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/random.h>
+#endif
+
+#include "selftest.h"
+
+#define CHAIN_SZ (4 << 10)
+
+static inline struct mock_fence {
+ struct dma_fence base;
+ spinlock_t lock;
+} *to_mock_fence(struct dma_fence *f) {
+ return container_of(f, struct mock_fence, base);
+}
+
+static const char *mock_name(struct dma_fence *f)
+{
+ return "mock";
+}
+
+static const struct dma_fence_ops mock_ops = {
+ .get_driver_name = mock_name,
+ .get_timeline_name = mock_name,
+};
+
+static struct dma_fence *mock_fence(void)
+{
+ struct mock_fence *f;
+
+ f = kmalloc(sizeof(*f), GFP_KERNEL);
+ if (!f)
+ return NULL;
+
+ spin_lock_init(&f->lock);
+ dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0);
+
+ return &f->base;
+}
+
+static struct dma_fence *mock_array(unsigned int num_fences, ...)
+{
+ struct dma_fence_array *array;
+ struct dma_fence **fences;
+ va_list valist;
+ int i;
+
+ fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL);
+ if (!fences)
+ return NULL;
+
+ va_start(valist, num_fences);
+ for (i = 0; i < num_fences; ++i)
+ fences[i] = va_arg(valist, typeof(*fences));
+ va_end(valist);
+
+ array = dma_fence_array_create(num_fences, fences,
+ dma_fence_context_alloc(1),
+ 1, false);
+ if (!array)
+ goto cleanup;
+ return &array->base;
+
+cleanup:
+ for (i = 0; i < num_fences; ++i)
+ dma_fence_put(fences[i]);
+ kfree(fences);
+ return NULL;
+}
+
+static struct dma_fence *mock_chain(struct dma_fence *prev,
+ struct dma_fence *fence)
+{
+ struct dma_fence_chain *f;
+
+ f = dma_fence_chain_alloc();
+ if (!f) {
+ dma_fence_put(prev);
+ dma_fence_put(fence);
+ return NULL;
+ }
+
+ dma_fence_chain_init(f, prev, fence, 1);
+ return &f->base;
+}
+
+static int sanitycheck(void *arg)
+{
+ struct dma_fence *f, *chain, *array;
+ int err = 0;
+
+ f = mock_fence();
+ if (!f)
+ return -ENOMEM;
+
+ array = mock_array(1, f);
+ if (!array)
+ return -ENOMEM;
+
+ chain = mock_chain(NULL, array);
+ if (!chain)
+ return -ENOMEM;
+
+ dma_fence_signal(f);
+ dma_fence_put(chain);
+ return err;
+}
+
+static int unwrap_array(void *arg)
+{
+ struct dma_fence *fence, *f1, *f2, *array;
+ struct dma_fence_unwrap iter;
+ int err = 0;
+
+ f1 = mock_fence();
+ if (!f1)
+ return -ENOMEM;
+
+ f2 = mock_fence();
+ if (!f2) {
+ dma_fence_put(f1);
+ return -ENOMEM;
+ }
+
+ array = mock_array(2, f1, f2);
+ if (!array)
+ return -ENOMEM;
+
+ dma_fence_unwrap_for_each(fence, &iter, array) {
+ if (fence == f1) {
+ f1 = NULL;
+ } else if (fence == f2) {
+ f2 = NULL;
+ } else {
+ pr_err("Unexpected fence!\n");
+ err = -EINVAL;
+ }
+ }
+
+ if (f1 || f2) {
+ pr_err("Not all fences seen!\n");
+ err = -EINVAL;
+ }
+
+ dma_fence_signal(f1);
+ dma_fence_signal(f2);
+ dma_fence_put(array);
+ return 0;
+}
+
+static int unwrap_chain(void *arg)
+{
+ struct dma_fence *fence, *f1, *f2, *chain;
+ struct dma_fence_unwrap iter;
+ int err = 0;
+
+ f1 = mock_fence();
+ if (!f1)
+ return -ENOMEM;
+
+ f2 = mock_fence();
+ if (!f2) {
+ dma_fence_put(f1);
+ return -ENOMEM;
+ }
+
+ chain = mock_chain(f1, f2);
+ if (!chain)
+ return -ENOMEM;
+
+ dma_fence_unwrap_for_each(fence, &iter, chain) {
+ if (fence == f1) {
+ f1 = NULL;
+ } else if (fence == f2) {
+ f2 = NULL;
+ } else {
+ pr_err("Unexpected fence!\n");
+ err = -EINVAL;
+ }
+ }
+
+ if (f1 || f2) {
+ pr_err("Not all fences seen!\n");
+ err = -EINVAL;
+ }
+
+ dma_fence_signal(f1);
+ dma_fence_signal(f2);
+ dma_fence_put(chain);
+ return 0;
+}
+
+static int unwrap_chain_array(void *arg)
+{
+ struct dma_fence *fence, *f1, *f2, *array, *chain;
+ struct dma_fence_unwrap iter;
+ int err = 0;
+
+ f1 = mock_fence();
+ if (!f1)
+ return -ENOMEM;
+
+ f2 = mock_fence();
+ if (!f2) {
+ dma_fence_put(f1);
+ return -ENOMEM;
+ }
+
+ array = mock_array(2, f1, f2);
+ if (!array)
+ return -ENOMEM;
+
+ chain = mock_chain(NULL, array);
+ if (!chain)
+ return -ENOMEM;
+
+ dma_fence_unwrap_for_each(fence, &iter, chain) {
+ if (fence == f1) {
+ f1 = NULL;
+ } else if (fence == f2) {
+ f2 = NULL;
+ } else {
+ pr_err("Unexpected fence!\n");
+ err = -EINVAL;
+ }
+ }
+
+ if (f1 || f2) {
+ pr_err("Not all fences seen!\n");
+ err = -EINVAL;
+ }
+
+ dma_fence_signal(f1);
+ dma_fence_signal(f2);
+ dma_fence_put(chain);
+ return 0;
+}
+
+int dma_fence_unwrap(void)
+{
+ static const struct subtest tests[] = {
+ SUBTEST(sanitycheck),
+ SUBTEST(unwrap_array),
+ SUBTEST(unwrap_chain),
+ SUBTEST(unwrap_chain_array),
+ };
+
+ return subtests(tests, NULL);
+}
diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c
index 394e6e1e968604801d0468442fd4ba6e871dc447..514d213261df3d8f579dedec1269c353b84a7f0a 100644
--- a/drivers/dma-buf/sync_file.c
+++ b/drivers/dma-buf/sync_file.c
@@ -5,6 +5,7 @@
* Copyright (C) 2012 Google, Inc.
*/
+#include <linux/dma-fence-unwrap.h>
#include <linux/export.h>
#include <linux/file.h>
#include <linux/fs.h>
@@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file,
return 0;
}
-static struct dma_fence **get_fences(struct sync_file *sync_file,
- int *num_fences)
-{
- if (dma_fence_is_array(sync_file->fence)) {
- struct dma_fence_array *array = to_dma_fence_array(sync_file->fence);
-
- *num_fences = array->num_fences;
- return array->fences;
- }
-
- *num_fences = 1;
- return &sync_file->fence;
-}
-
static void add_fence(struct dma_fence **fences,
int *i, struct dma_fence *fence)
{
@@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences,
static struct sync_file *sync_file_merge(const char *name, struct sync_file *a,
struct sync_file *b)
{
+ struct dma_fence *a_fence, *b_fence, **fences;
+ struct dma_fence_unwrap a_iter, b_iter;
+ unsigned int index, num_fences;
struct sync_file *sync_file;
- struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences;
- int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences;
sync_file = sync_file_alloc();
if (!sync_file)
return NULL;
- a_fences = get_fences(a, &a_num_fences);
- b_fences = get_fences(b, &b_num_fences);
- if (a_num_fences > INT_MAX - b_num_fences)
- goto err;
+ num_fences = 0;
+ dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence)
+ ++num_fences;
+ dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence)
+ ++num_fences;
- num_fences = a_num_fences + b_num_fences;
+ if (num_fences > INT_MAX)
+ goto err_free_sync_file;
fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL);
if (!fences)
- goto err;
+ goto err_free_sync_file;
/*
- * Assume sync_file a and b are both ordered and have no
- * duplicates with the same context.
+ * We can't guarantee that fences in both a and b are ordered, but it is
+ * still quite likely.
*
- * If a sync_file can only be created with sync_file_merge
- * and sync_file_create, this is a reasonable assumption.
+ * So attempt to order the fences as we pass over them and merge fences
+ * with the same context.
*/
- for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) {
- struct dma_fence *pt_a = a_fences[i_a];
- struct dma_fence *pt_b = b_fences[i_b];
- if (pt_a->context < pt_b->context) {
- add_fence(fences, &i, pt_a);
+ index = 0;
+ for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter),
+ b_fence = dma_fence_unwrap_first(b->fence, &b_iter);
+ a_fence || b_fence; ) {
+
+ if (!b_fence) {
+ add_fence(fences, &index, a_fence);
+ a_fence = dma_fence_unwrap_next(&a_iter);
+
+ } else if (!a_fence) {
+ add_fence(fences, &index, b_fence);
+ b_fence = dma_fence_unwrap_next(&b_iter);
+
+ } else if (a_fence->context < b_fence->context) {
+ add_fence(fences, &index, a_fence);
+ a_fence = dma_fence_unwrap_next(&a_iter);
- i_a++;
- } else if (pt_a->context > pt_b->context) {
- add_fence(fences, &i, pt_b);
+ } else if (b_fence->context < a_fence->context) {
+ add_fence(fences, &index, b_fence);
+ b_fence = dma_fence_unwrap_next(&b_iter);
+
+ } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno,
+ a_fence->ops)) {
+ add_fence(fences, &index, a_fence);
+ a_fence = dma_fence_unwrap_next(&a_iter);
+ b_fence = dma_fence_unwrap_next(&b_iter);
- i_b++;
} else {
- if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno,
- pt_a->ops))
- add_fence(fences, &i, pt_a);
- else
- add_fence(fences, &i, pt_b);
-
- i_a++;
- i_b++;
+ add_fence(fences, &index, b_fence);
+ a_fence = dma_fence_unwrap_next(&a_iter);
+ b_fence = dma_fence_unwrap_next(&b_iter);
}
}
- for (; i_a < a_num_fences; i_a++)
- add_fence(fences, &i, a_fences[i_a]);
-
- for (; i_b < b_num_fences; i_b++)
- add_fence(fences, &i, b_fences[i_b]);
-
- if (i == 0)
- fences[i++] = dma_fence_get(a_fences[0]);
+ if (index == 0)
+ fences[index++] = dma_fence_get_stub();
- if (num_fences > i) {
- nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL);
- if (!nfences)
- goto err;
+ if (num_fences > index) {
+ struct dma_fence **tmp;
- fences = nfences;
+ /* Keep going even when reducing the size failed */
+ tmp = krealloc_array(fences, index, sizeof(*fences),
+ GFP_KERNEL);
+ if (tmp)
+ fences = tmp;
}
- if (sync_file_set_fence(sync_file, fences, i) < 0)
- goto err;
+ if (sync_file_set_fence(sync_file, fences, index) < 0)
+ goto err_put_fences;
strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name));
return sync_file;
-err:
- while (i)
- dma_fence_put(fences[--i]);
+err_put_fences:
+ while (index)
+ dma_fence_put(fences[--index]);
kfree(fences);
+
+err_free_sync_file:
fput(sync_file->file);
return NULL;
-
}
static int sync_file_release(struct inode *inode, struct file *file)
@@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence,
static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
unsigned long arg)
{
- struct sync_file_info info;
struct sync_fence_info *fence_info = NULL;
- struct dma_fence **fences;
+ struct dma_fence_unwrap iter;
+ struct sync_file_info info;
+ unsigned int num_fences;
+ struct dma_fence *fence;
+ int ret;
__u32 size;
- int num_fences, ret, i;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
return -EFAULT;
@@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
if (info.flags || info.pad)
return -EINVAL;
- fences = get_fences(sync_file, &num_fences);
+ num_fences = 0;
+ dma_fence_unwrap_for_each(fence, &iter, sync_file->fence)
+ ++num_fences;
/*
* Passing num_fences = 0 means that userspace doesn't want to
@@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file,
if (!fence_info)
return -ENOMEM;
- for (i = 0; i < num_fences; i++) {
- int status = sync_fill_fence_info(fences[i], &fence_info[i]);
+ num_fences = 0;
+ dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) {
+ int status;
+
+ status = sync_fill_fence_info(fence, &fence_info[num_fences++]);
info.status = info.status <= 0 ? info.status : status;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
index 5b393622f59205700acf687179841e7e0b0b8f5b..a0f0a17e224fe554aeff766a5dc3dcc5b4b2144d 100644
--- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h
+++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
@@ -119,6 +119,7 @@
#define CONNECTOR_OBJECT_ID_eDP 0x14
#define CONNECTOR_OBJECT_ID_MXM 0x15
#define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16
+#define CONNECTOR_OBJECT_ID_USBC 0x17
/* deleted */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3987ecb24ef4fd50749c7944b4cec7d8f8346517..49f734137f158a6aecc6f362f9d62e1ef601fde1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev,
struct amdgpu_ring *ring)
{
#ifdef CONFIG_X86_64
- if (adev->flags & AMD_IS_APU)
+ if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev))
return;
#endif
if (adev->gmc.xgmi.connected_to_cpu)
@@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
struct amdgpu_ring *ring)
{
#ifdef CONFIG_X86_64
- if (adev->flags & AMD_IS_APU)
+ if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev))
return;
#endif
if (adev->gmc.xgmi.connected_to_cpu)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index bb1c025d90019a443d8f53cf596520b08988cf17..b03663f42cc9161ef6f24446850cce1568a25f1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy,
* Maximum number of processes that HWS can schedule concurrently. The maximum is the
* number of VMIDs assigned to the HWS, which is also the default.
*/
-int hws_max_conc_proc = 8;
+int hws_max_conc_proc = -1;
module_param(hws_max_conc_proc, int, 0444);
MODULE_PARM_DESC(hws_max_conc_proc,
"Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 8fe9399762242185c0d1e6a597beff027507ed6e..28a736c507bb3f84e956203d2c115b8afdc160de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev,
* adev->gfx.mec.num_pipe_per_mec
* adev->gfx.mec.num_queue_per_pipe;
- while (queue_bit-- >= 0) {
+ while (--queue_bit >= 0) {
if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap))
continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index ca2cfb65f9763b640d8d90a9bd71d0cebc0bd620..a66a0881a934bb0ff3a8d2e551a262be02df739e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(9, 0, 1):
+ case IP_VERSION(9, 3, 0):
case IP_VERSION(9, 4, 0):
case IP_VERSION(9, 4, 1):
case IP_VERSION(9, 4, 2):
+ case IP_VERSION(10, 3, 3):
+ case IP_VERSION(10, 3, 4):
+ case IP_VERSION(10, 3, 5):
+ case IP_VERSION(10, 3, 6):
+ case IP_VERSION(10, 3, 7):
/*
* noretry = 0 will cause kfd page fault tests fail
* for some ASICs, so set default to 1 for these ASICs.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 25731719c627d6cd7f8ae8b85fb093e521596a5a..940752488330f64f8a3cdc267d399843d3158d5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem,
*/
void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
{
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
struct dma_fence *fence = NULL;
struct amdgpu_bo *abo;
int r;
@@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo)
amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo);
if (bo->resource->mem_type != TTM_PL_VRAM ||
- !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE))
+ !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) ||
+ adev->in_suspend || adev->shutdown)
return;
if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv)))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 5320bb0883d85f352867289911f67eaf64740926..317d80209e9581bb7d3f767306959b6a199ba763 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib);
void amdgpu_ring_commit(struct amdgpu_ring *ring);
void amdgpu_ring_undo(struct amdgpu_ring *ring);
int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
- unsigned int ring_size, struct amdgpu_irq_src *irq_src,
- unsigned int irq_type, unsigned int prio,
+ unsigned int max_dw, struct amdgpu_irq_src *irq_src,
+ unsigned int irq_type, unsigned int hw_prio,
atomic_t *sched_score);
void amdgpu_ring_fini(struct amdgpu_ring *ring);
void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index e2fde88aaf5e3d1f5aed612ce3c813c4fecc9acb..f06fb7f882e2ec125dd4ef8316e5cf9e4cf382dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -159,6 +159,7 @@
#define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8)
#define AMDGPU_VCN_SW_RING_FLAG (1 << 9)
#define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10)
+#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11)
#define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001
#define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001
@@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging {
uint32_t size;
};
+struct amdgpu_fw_shared_smu_interface_info {
+ uint8_t smu_interface_type;
+ uint8_t padding[3];
+};
+
struct amdgpu_fw_shared {
uint32_t present_flag_0;
uint8_t pad[44];
@@ -287,6 +293,7 @@ struct amdgpu_fw_shared {
struct amdgpu_fw_shared_multi_queue multi_queue;
struct amdgpu_fw_shared_sw_ring sw_ring;
struct amdgpu_fw_shared_fw_logging fw_log;
+ struct amdgpu_fw_shared_smu_interface_info smu_interface_info;
};
struct amdgpu_vcn_fwlog {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f4c6accd32263c537dabbd10fbdf6d8ea874778e..9426e252d8aa6c67618b8244d3791e3e37ce0e28 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210),
@@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210),
@@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = {
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210),
@@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(10, 3, 1):
case IP_VERSION(10, 3, 3):
+ case IP_VERSION(10, 3, 7):
preempt_disable();
clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh);
clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 3c1d440824a73c30db584d73857509a9134cbdda..5228421b0f724745f111737d6a79f418cb2f595c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev)
adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
#ifdef CONFIG_X86_64
- if (adev->flags & AMD_IS_APU) {
+ if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) {
adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev);
adev->gmc.aper_size = adev->gmc.real_vram_size;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 344d819b4c1b6e9b03d772adefee87ac2ac956ef..979da6f510e886ffba16b323d5c19c72035869c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
#ifdef CONFIG_X86_64
- if (adev->flags & AMD_IS_APU &&
- adev->gmc.real_vram_size > adev->gmc.aper_size) {
+ if ((adev->flags & AMD_IS_APU) &&
+ adev->gmc.real_vram_size > adev->gmc.aper_size &&
+ !amdgpu_passthrough(adev)) {
adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
adev->gmc.aper_size = adev->gmc.real_vram_size;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ca9841d5669fb9829cf6471b51b918d43835a195..1932a3e4af7e2e75dd530e416459e85993470b04 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
#ifdef CONFIG_X86_64
- if (adev->flags & AMD_IS_APU) {
+ if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) {
adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22;
adev->gmc.aper_size = adev->gmc.real_vram_size;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 431742eb78110acd28507e85673cf4e94eda4a9f..6009fbfdcc198bcdf82aa5a3bc127163741bd27d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
*/
/* check whether both host-gpu and gpu-gpu xgmi links exist */
- if ((adev->flags & AMD_IS_APU) ||
+ if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) ||
(adev->gmc.xgmi.supported &&
adev->gmc.xgmi.connected_to_cpu)) {
adev->gmc.aper_base =
@@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle)
amdgpu_gem_force_release(adev);
amdgpu_vm_manager_fini(adev);
amdgpu_gart_table_vram_free(adev);
- amdgpu_bo_unref(&adev->gmc.pdb0_bo);
+ amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0);
amdgpu_bo_fini(adev);
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index dff54190b96c7971463dc0bc479ce35db86f0dbc..f0fbcda76f5e398e40464b1a3b949160056d6d5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -24,6 +24,7 @@
#include <linux/firmware.h>
#include "amdgpu.h"
+#include "amdgpu_cs.h"
#include "amdgpu_vcn.h"
#include "amdgpu_pm.h"
#include "soc15.h"
@@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
.set_powergating_state = vcn_v1_0_set_powergating_state,
};
+/*
+ * It is a hardware issue that VCN can't handle a GTT TMZ buffer on
+ * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain
+ * before command submission as a workaround.
+ */
+static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser,
+ struct amdgpu_job *job,
+ uint64_t addr)
+{
+ struct ttm_operation_ctx ctx = { false, false };
+ struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
+ struct amdgpu_vm *vm = &fpriv->vm;
+ struct amdgpu_bo_va_mapping *mapping;
+ struct amdgpu_bo *bo;
+ int r;
+
+ addr &= AMDGPU_GMC_HOLE_MASK;
+ if (addr & 0x7) {
+ DRM_ERROR("VCN messages must be 8 byte aligned!\n");
+ return -EINVAL;
+ }
+
+ mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE);
+ if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo)
+ return -EINVAL;
+
+ bo = mapping->bo_va->base.bo;
+ if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED))
+ return 0;
+
+ amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
+ r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+ if (r) {
+ DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r);
+ return r;
+ }
+
+ return r;
+}
+
+static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
+ struct amdgpu_job *job,
+ struct amdgpu_ib *ib)
+{
+ uint32_t msg_lo = 0, msg_hi = 0;
+ int i, r;
+
+ if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE))
+ return 0;
+
+ for (i = 0; i < ib->length_dw; i += 2) {
+ uint32_t reg = amdgpu_ib_get_value(ib, i);
+ uint32_t val = amdgpu_ib_get_value(ib, i + 1);
+
+ if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) {
+ msg_lo = val;
+ } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) {
+ msg_hi = val;
+ } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) {
+ r = vcn_v1_0_validate_bo(p, job,
+ ((u64)msg_hi) << 32 | msg_lo);
+ if (r)
+ return r;
+ }
+ }
+
+ return 0;
+}
+
static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_VCN_DEC,
.align_mask = 0xf,
@@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
.get_rptr = vcn_v1_0_dec_ring_get_rptr,
.get_wptr = vcn_v1_0_dec_ring_get_wptr,
.set_wptr = vcn_v1_0_dec_ring_set_wptr,
+ .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place,
.emit_frame_size =
6 + 6 + /* hdp invalidate / flush */
SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index c87263ed20ecb8a17d3b8bfaa9ca1d352035ae43..cb5f0a12333f308d2ec358014ec5cf206f305d11 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle)
cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) |
cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB);
fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED);
+ fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG;
+ if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2))
+ fw_shared->smu_interface_info.smu_interface_type = 2;
+ else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1))
+ fw_shared->smu_interface_info.smu_interface_type = 1;
if (amdgpu_vcnfw_log)
amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
@@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx
AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect);
/* VCN global tiling registers */
- WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET(
- UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+ WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
+ UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
}
static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst)
@@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
{
+ struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
uint32_t tmp;
+ vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state);
+
/* Wait for power status to be 1 */
SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1,
UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 339e12c94cfff496be946947397dcfc4a91a3f8e..62aa6c9d5123df2a36d65df29910dd6a13b0d14c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
}
/* Verify module parameters regarding mapped process number*/
- if ((hws_max_conc_proc < 0)
- || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) {
- dev_err(kfd_device,
- "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n",
- hws_max_conc_proc, kfd->vm_info.vmid_num_kfd,
- kfd->vm_info.vmid_num_kfd);
+ if (hws_max_conc_proc >= 0)
+ kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd);
+ else
kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd;
- } else
- kfd->max_proc_per_quantum = hws_max_conc_proc;
/* calculate max size of mqds needed for queues */
size = max_num_of_queues_per_device *
@@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
goto kfd_doorbell_error;
}
- kfd->hive_id = kfd->adev->gmc.xgmi.hive_id;
+ if (amdgpu_use_xgmi_p2p)
+ kfd->hive_id = kfd->adev->gmc.xgmi.hive_id;
kfd->noretry = kfd->adev->gmc.noretry;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index deecccebe5b64ceb78f152aac6ad3fbfdff82766..64f4a51cc880e77f80268d2c947c9dc8c94cfa70 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events)
event_waiters = kmalloc_array(num_events,
sizeof(struct kfd_event_waiter),
GFP_KERNEL);
+ if (!event_waiters)
+ return NULL;
for (i = 0; (event_waiters) && (i < num_events) ; i++) {
init_wait(&event_waiters[i].wait);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index e4beebb1c80a21ed62b5c0abca0a373aed9bce35..f2e1d506ba211f04c35104e692d5bb197dc0df10 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
return ret;
}
- ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client,
- O_RDWR);
- if (ret < 0) {
- kfifo_free(&client->fifo);
- kfree(client);
- return ret;
- }
- *fd = ret;
-
init_waitqueue_head(&client->wait_queue);
spin_lock_init(&client->lock);
client->events = 0;
@@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd)
list_add_rcu(&client->list, &dev->smi_clients);
spin_unlock(&dev->smi_lock);
+ ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client,
+ O_RDWR);
+ if (ret < 0) {
+ spin_lock(&dev->smi_lock);
+ list_del_rcu(&client->list);
+ spin_unlock(&dev->smi_lock);
+
+ synchronize_rcu();
+
+ kfifo_free(&client->fifo);
+ kfree(client);
+ return ret;
+ }
+ *fd = ret;
+
return 0;
}
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 b30656959fd862324591d3d3ad73ff465ab642b6..62139ff35476c3a94f1fb31a3393d8ec75b0450e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2714,7 +2714,8 @@ static int dm_resume(void *handle)
* this is the case when traversing through already created
* MST connectors, should be skipped
*/
- if (aconnector->mst_port)
+ if (aconnector->dc_link &&
+ aconnector->dc_link->type == dc_connection_mst_branch)
continue;
mutex_lock(&aconnector->hpd_lock);
@@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap
max - min);
}
-static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
int bl_idx,
u32 user_brightness)
{
@@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx);
}
- return rc ? 0 : 1;
+ if (rc)
+ dm->actual_brightness[bl_idx] = user_brightness;
}
static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
@@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
/* restore the backlight level */
for (i = 0; i < dm->num_of_edps; i++) {
if (dm->backlight_dev[i] &&
- (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i]))
+ (dm->actual_brightness[i] != dm->brightness[i]))
amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
}
#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 6a908d736d6ac9065fc340e6e6151fff03d036f9..7e44b04294488a39560da4a8d4da1033f492bef4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -540,6 +540,12 @@ struct amdgpu_display_manager {
* cached backlight values.
*/
u32 brightness[AMDGPU_DM_MAX_NUM_EDP];
+ /**
+ * @actual_brightness:
+ *
+ * last successfully applied backlight values.
+ */
+ u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP];
};
enum dsc_clock_force_state {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index edda572dc57017520e4e2e19cc78c67de6331479..8be4c19706285ffbaa933cdd3dae9bdd7f768957 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params(
struct integrated_info *bios_info,
const DpmClocks_315_t *clock_table)
{
- int i, j;
+ int i;
struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
- uint32_t max_dispclk = 0, max_dppclk = 0;
-
- j = -1;
-
- ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL);
-
- /* Find lowest DPM, FCLK is filled in reverse order*/
-
- for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) {
- if (clock_table->DfPstateTable[i].FClk != 0) {
- j = i;
- break;
+ uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0;
+ struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
+
+ max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled);
+ max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled);
+ max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled);
+
+ /* Find highest fclk pstate */
+ for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) {
+ if (clock_table->DfPstateTable[i].FClk > max_fclk) {
+ max_fclk = clock_table->DfPstateTable[i].FClk;
+ max_pstate = i;
}
}
- if (j == -1) {
- /* clock table is all 0s, just use our own hardcode */
- ASSERT(0);
- return;
- }
-
- bw_params->clk_table.num_entries = j + 1;
-
- /* dispclk and dppclk can be max at any voltage, same number of levels for both */
- if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
- clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) {
- max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled);
- max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled);
- } else {
- ASSERT(0);
- }
+ /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */
+ for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+ int j;
+ uint32_t min_fclk = clock_table->DfPstateTable[0].FClk;
- for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) {
- int temp;
+ for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) {
+ if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i]
+ && clock_table->DfPstateTable[j].FClk < min_fclk) {
+ min_fclk = clock_table->DfPstateTable[j].FClk;
+ min_pstate = j;
+ }
+ }
- bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk;
- bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk;
- bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage;
+ bw_params->clk_table.entries[i].fclk_mhz = min_fclk;
+ bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk;
+ bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage;
+ bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
+ bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
+ bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
+ bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
bw_params->clk_table.entries[i].wck_ratio = 1;
- temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage);
- if (temp)
- bw_params->clk_table.entries[i].dcfclk_mhz = temp;
- temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage);
- if (temp)
- bw_params->clk_table.entries[i].socclk_mhz = temp;
+ };
+
+ /* Make sure to include at least one entry and highest pstate */
+ if (max_pstate != min_pstate) {
+ bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+ bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk;
+ bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage;
+ bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage(
+ clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage);
+ bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage(
+ clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage);
bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
+ bw_params->clk_table.entries[i].wck_ratio = 1;
+ i++;
}
+ bw_params->clk_table.num_entries = i;
+
+ /* Include highest socclk */
+ if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk)
+ bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk;
+ /* Set any 0 clocks to max default setting. Not an issue for
+ * power since we aren't doing switching in such case anyway
+ */
+ for (i = 0; i < bw_params->clk_table.num_entries; i++) {
+ if (!bw_params->clk_table.entries[i].fclk_mhz) {
+ bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
+ bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz;
+ bw_params->clk_table.entries[i].voltage = def_max.voltage;
+ }
+ if (!bw_params->clk_table.entries[i].dcfclk_mhz)
+ bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz;
+ if (!bw_params->clk_table.entries[i].socclk_mhz)
+ bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz;
+ if (!bw_params->clk_table.entries[i].dispclk_mhz)
+ bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz;
+ if (!bw_params->clk_table.entries[i].dppclk_mhz)
+ bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz;
+ }
bw_params->vram_type = bios_info->memory_type;
bw_params->num_channels = bios_info->ma_channel_number;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
index 880ffea2afc6a1df3822a12c5ec3d8e673ea6354..2600313fea5797321a81688a20f028721cd2fcfb 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
@@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D
#define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ
#define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ
#define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ
-#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency
-#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ
+#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency
+#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ
#define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected
#define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power
#define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event
@@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr)
return (dprefclk_get_mhz * 1000);
}
-int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr)
+int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr)
{
int fclk_get_mhz = -1;
if (clk_mgr->smu_present) {
fclk_get_mhz = dcn315_smu_send_msg_with_param(
clk_mgr,
- VBIOSSMC_MSG_GetFclkFrequency,
+ VBIOSSMC_MSG_GetDtbclkFreq,
0);
}
return (fclk_get_mhz * 1000);
}
+
+void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable)
+{
+ if (!clk_mgr->smu_present)
+ return;
+
+ dcn315_smu_send_msg_with_param(
+ clk_mgr,
+ VBIOSSMC_MSG_SetDtbClk,
+ enable);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h
index 66fa42f8dd189768e414d42cd8d2506ce4d63553..5aa3275ac7d88c879c86958fafcd793be746386d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h
@@ -37,6 +37,7 @@
#define NUM_SOC_VOLTAGE_LEVELS 4
#define NUM_DF_PSTATE_LEVELS 4
+
typedef struct {
uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz)
uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz)
@@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr);
void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz);
void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr);
int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr);
-int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr);
+int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr);
+void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable);
#endif /* DAL_DC_315_SMU_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index f6e19efea7568de940803065da576aab11b85fc9..c436db416708e3f8f857e9cc5d8abbcc6f34d77d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream(
if (stream_update->mst_bw_update)
su_flags->bits.mst_bw = 1;
+ if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc))
+ su_flags->bits.crtc_timing_adjust = 1;
if (su_flags->raw != 0)
overall_type = UPDATE_TYPE_FULL;
@@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
if (update->vrr_infopacket)
stream->vrr_infopacket = *update->vrr_infopacket;
+ if (update->crtc_timing_adjust)
+ stream->adjust = *update->crtc_timing_adjust;
+
if (update->dpms_off)
stream->dpms_off = *update->dpms_off;
@@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo
if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause)
pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst);
}
+/*
+ * dc_extended_blank_supported: Decide whether extended blank is supported
+ *
+ * Extended blank is a freesync optimization feature to be enabled in the future.
+ * During the extra vblank period gained from freesync, we have the ability to enter z9/z10.
+ *
+ * @param [in] dc: Current DC state
+ * @return: Indicate whether extended blank is supported (true or false)
+ */
+bool dc_extended_blank_supported(struct dc *dc)
+{
+ return dc->debug.extended_blank_optimization && !dc->debug.disable_z10
+ && dc->caps.zstate_support && dc->caps.is_apu;
+}
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 cb87dd643180876011b4855557a56a410db5a713..bbaa5abdf88859a3d77cec38acaeabd2a1c400c4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link,
destrictive = false;
}
}
- } else if (dc_is_hdmi_signal(link->local_sink->sink_signal))
- destrictive = true;
+ }
return destrictive;
}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 351081f574cb7bb6755412c69b9fc1271cdf41eb..22dabe596dfcc1123ff5314b2d2351e43c9b5fe6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link)
&link->dpcd_caps.cable_id, &usbc_cable_id);
}
+/* DPRX may take some time to respond to AUX messages after HPD asserted.
+ * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600).
+ */
+static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms)
+{
+ enum dc_status status = DC_ERROR_UNEXPECTED;
+ uint8_t dpcd_data = 0;
+ uint64_t start_ts = 0;
+ uint64_t current_ts = 0;
+ uint64_t time_taken_ms = 0;
+ enum dc_connection_type type = dc_connection_none;
+
+ status = core_link_read_dpcd(
+ link,
+ DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV,
+ &dpcd_data,
+ sizeof(dpcd_data));
+
+ if (status != DC_OK) {
+ DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.",
+ __func__,
+ timeout_ms);
+ start_ts = dm_get_timestamp(link->ctx);
+
+ do {
+ if (!dc_link_detect_sink(link, &type) || type == dc_connection_none)
+ break;
+
+ dpcd_data = DP_SET_POWER_D3;
+ status = core_link_write_dpcd(
+ link,
+ DP_SET_POWER,
+ &dpcd_data,
+ sizeof(dpcd_data));
+
+ dpcd_data = DP_SET_POWER_D0;
+ status = core_link_write_dpcd(
+ link,
+ DP_SET_POWER,
+ &dpcd_data,
+ sizeof(dpcd_data));
+
+ current_ts = dm_get_timestamp(link->ctx);
+ time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000);
+ } while (status != DC_OK && time_taken_ms < timeout_ms);
+
+ DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s",
+ __func__,
+ (status == DC_OK) ? "succeeded" : "failed",
+ time_taken_ms,
+ (type == dc_connection_none) ? ". Unplugged." : ".");
+ }
+
+ return status;
+}
+
static bool retrieve_link_cap(struct dc_link *link)
{
/* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16,
@@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link)
dc_link_aux_try_to_configure_timeout(link->ddc,
LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD);
+ /* Try to ensure AUX channel active before proceeding. */
+ if (link->dc->debug.aux_wake_wa.bits.enable_wa) {
+ uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms;
+
+ if (link->dc->debug.aux_wake_wa.bits.use_default_timeout)
+ timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS;
+ status = wa_try_to_wake_dprx(link, timeout_ms);
+ }
+
is_lttpr_present = dp_retrieve_lttpr_cap(link);
/* Read DP tunneling information. */
status = dpcd_get_tunneling_device_data(link);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 7af153434e9e4578b7217d83db2cd0b109d70cb7..d251c3f3a7140434078a7f12443f3d049ba726bb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged(
if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
return false;
- // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks
- if (old_stream->audio_info.mode_count != stream->audio_info.mode_count)
+ /*compare audio info*/
+ if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0)
return false;
return true;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 4ffab7bb1098b6548f092f5f6ac6f7d664097b2a..77ef9d1f9ea88e6327dc870170ee4005c8118aae 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -188,6 +188,7 @@ struct dc_caps {
bool psp_setup_panel_mode;
bool extended_aux_timeout_support;
bool dmcub_support;
+ bool zstate_support;
uint32_t num_of_internal_disp;
enum dp_protocol_version max_dp_protocol_version;
unsigned int mall_size_per_mem_channel;
@@ -525,6 +526,22 @@ union dpia_debug_options {
uint32_t raw;
};
+/* AUX wake work around options
+ * 0: enable/disable work around
+ * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS
+ * 15-2: reserved
+ * 31-16: timeout in ms
+ */
+union aux_wake_wa_options {
+ struct {
+ uint32_t enable_wa : 1;
+ uint32_t use_default_timeout : 1;
+ uint32_t rsvd: 14;
+ uint32_t timeout_ms : 16;
+ } bits;
+ uint32_t raw;
+};
+
struct dc_debug_data {
uint32_t ltFailCount;
uint32_t i2cErrorCount;
@@ -703,13 +720,15 @@ struct dc_debug_options {
bool enable_driver_sequence_debug;
enum det_size crb_alloc_policy;
int crb_alloc_policy_min_disp_count;
-#if defined(CONFIG_DRM_AMD_DC_DCN)
bool disable_z10;
+#if defined(CONFIG_DRM_AMD_DC_DCN)
bool enable_z9_disable_interface;
bool enable_sw_cntl_psr;
union dpia_debug_options dpia_debug;
#endif
bool apply_vendor_specific_lttpr_wa;
+ bool extended_blank_optimization;
+ union aux_wake_wa_options aux_wake_wa;
bool ignore_dpref_ss;
uint8_t psr_power_use_phy_fsm;
};
@@ -1369,6 +1388,8 @@ struct dc_sink_init_data {
bool converter_disable_audio;
};
+bool dc_extended_blank_supported(struct dc *dc);
+
struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params);
/* Newer interfaces */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 99a750f561f81cb71a7092a329e9505bc4eb7653..c4168c11257c310778ef1e08e00635bed6aabffc 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -131,6 +131,7 @@ union stream_update_flags {
uint32_t wb_update:1;
uint32_t dsc_changed : 1;
uint32_t mst_bw : 1;
+ uint32_t crtc_timing_adjust : 1;
} bits;
uint32_t raw;
@@ -289,6 +290,7 @@ struct dc_stream_update {
struct dc_3dlut *lut3d_func;
struct test_pattern *pending_test_pattern;
+ struct dc_crtc_timing_adjust *crtc_timing_adjust;
};
bool dc_is_stream_unchanged(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index c3e141c19a77e4957eb3a9debdddcb4ba8ac8ed3..781334b395ba898fef512d6b9cecf33b64cd2089 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc)
link->link_status.link_active = true;
}
- /* Power gate DSCs */
- if (!is_optimized_init_done) {
- for (i = 0; i < res_pool->res_cap->num_dsc; i++)
- if (hws->funcs.dsc_pg_control != NULL)
- hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
- }
-
/* we want to turn off all dp displays before doing detection */
dc_link_blank_all_dp_displays(dc);
+ if (hws->funcs.enable_power_gating_plane)
+ hws->funcs.enable_power_gating_plane(dc->hwseq, true);
+
/* If taking control over from VBIOS, we may want to optimize our first
* mode set, so we need to skip powering down pipes until we know which
* pipes we want to use.
@@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc)
REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
}
- if (hws->funcs.enable_power_gating_plane)
- hws->funcs.enable_power_gating_plane(dc->hwseq, true);
if (dc->clk_mgr->funcs->notify_wm_ranges)
dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr);
@@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size,
{
struct dc_context *dc_ctx = dc->ctx;
int i, master = -1, embedded = -1;
- struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0};
+ struct dc_crtc_timing *hw_crtc_timing;
uint64_t phase[MAX_PIPES];
uint64_t modulo[MAX_PIPES];
unsigned int pclk;
@@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size,
uint32_t dp_ref_clk_100hz =
dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10;
+ hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL);
+ if (!hw_crtc_timing)
+ return master;
+
if (dc->config.vblank_alignment_dto_params &&
dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) {
embedded_h_total =
@@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size,
}
}
+
+ kfree(hw_crtc_timing);
return master;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index ab910deed4812bbcd227b80ac266942488e4adf6..4290eaf11a043d02a318101754f41159503e3d6f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth(
struct dc_state *context)
{
struct hubbub *hubbub = dc->res_pool->hubbub;
+ int i;
/* program dchubbub watermarks */
hubbub->funcs->program_watermarks(hubbub,
@@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth(
dc->clk_mgr,
context,
true);
+ if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) {
+ for (i = 0; i < dc->res_pool->pipe_count; ++i) {
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+ if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank
+ && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max
+ && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total)
+ pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp,
+ pipe_ctx->dlg_regs.optimized_min_dst_y_next_start);
+ }
+ }
/* increase compbuf size */
if (hubbub->funcs->program_compbuf_size)
hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index d473708d53999d108304987abfa6c390870b2279..7802d603f79600d2cc53324b867dbdafc9d38319 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags(
/*If need split for odm but 4 way split already*/
if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe)
|| !pipe->next_odm_pipe)) {
- ASSERT(0); /* NOT expected yet */
merge[i] = true; /* 4 -> 2 ODM */
} else if (split[i] == 0 && pipe->prev_odm_pipe) {
ASSERT(0); /* NOT expected yet */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 61273265677223494031329f18d186f7b5d424d6..3fe4bfbb98a0732fe862222704110e690b707f3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.clock_trace = true,
.disable_pplib_clock_request = true,
.min_disp_clk_khz = 100000,
- .pipe_split_policy = MPC_SPLIT_DYNAMIC,
+ .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
.force_single_disp_pipe_split = false,
.disable_dcc = DCC_ENABLE,
.vsr_support = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index ed0a0e5fd80539e46c184c6d6de036ba2e9ae349..f61ec87638443e377922fdd7c58865f9e23c5b6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc)
/* we want to turn off all dp displays before doing detection */
dc_link_blank_all_dp_displays(dc);
+ if (hws->funcs.enable_power_gating_plane)
+ hws->funcs.enable_power_gating_plane(dc->hwseq, true);
+
/* If taking control over from VBIOS, we may want to optimize our first
* mode set, so we need to skip powering down pipes until we know which
* pipes we want to use.
@@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc)
REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
}
- if (hws->funcs.enable_power_gating_plane)
- hws->funcs.enable_power_gating_plane(dc->hwseq, true);
if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks)
dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
index 3e6d6ebd199ee79b7c2c72c57d6de6ca7e20641b..51c5f3685470a3aa158a122850095406a3f524fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c
@@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31,
hubbub31->detile_buf_size = det_size_kb * 1024;
hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024;
hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB;
+
+ hubbub31->debug_test_index_pstate = 0x6;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c
index 53b792b997b7e82b14535cc138791bef13dc8a2e..8ae6117953ca001ee1bb9244b09a129458e11f18 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c
@@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset)
REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset);
}
+void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized)
+{
+ struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+
+ REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized);
+}
+
static struct hubp_funcs dcn31_hubp_funcs = {
.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
@@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = {
.set_unbounded_requesting = hubp31_set_unbounded_requesting,
.hubp_soft_reset = hubp31_soft_reset,
.hubp_in_blank = hubp1_in_blank,
+ .program_extended_blank = hubp31_program_extended_blank,
};
bool hubp31_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 4be2286809093be0ce48747d59fc3ea2edf95ae4..631d8ac63aa41ba07dbff59c1dd7dfcd0f3a9b20 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc)
/* we want to turn off all dp displays before doing detection */
dc_link_blank_all_dp_displays(dc);
+ if (hws->funcs.enable_power_gating_plane)
+ hws->funcs.enable_power_gating_plane(dc->hwseq, true);
+
/* If taking control over from VBIOS, we may want to optimize our first
* mode set, so we need to skip powering down pipes until we know which
* pipes we want to use.
@@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc)
REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
}
- if (hws->funcs.enable_power_gating_plane)
- hws->funcs.enable_power_gating_plane(dc->hwseq, true);
if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks)
dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub);
@@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane(
bool enable)
{
bool force_on = true; /* disable power gating */
+ uint32_t org_ip_request_cntl = 0;
if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate)
force_on = false;
+ REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
+ if (org_ip_request_cntl == 0)
+ REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
/* DCHUBP0/1/2/3/4/5 */
REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
/* DPP0/1/2/3/4/5 */
REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
force_on = true; /* disable power gating */
if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate)
@@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane(
/* DCS0/1/2/3/4/5 */
REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
- REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000);
+
+ if (org_ip_request_cntl == 0)
+ REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
}
void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c
index 8afe2130d7c54ff911acf8df48e0ab5714f42ecb..e05527a3a8ba26776ae52999f46768d648c33f3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c
@@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc)
static bool optc31_disable_crtc(struct timing_generator *optc)
{
struct optc *optc1 = DCN10TG_FROM_TG(optc);
-
/* disable otg request until end of the first line
* in the vertical blank region
*/
@@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc)
REG_WAIT(OTG_CLOCK_CONTROL,
OTG_BUSY, 0,
1, 100000);
+ optc1_clear_optc_underflow(optc);
return true;
}
@@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc)
OTG_BUSY, 0,
1, 100000);
+ /* clear the false state */
+ optc1_clear_optc_underflow(optc);
+
return true;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 89b7b6b7254ac8ea97d1bac7acce2fd14d44349f..63934ecf6be84207a3ba839d86564f7088604ec7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc,
BW_VAL_TRACE_COUNT();
+ DC_FP_START();
out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate);
+ DC_FP_END();
// Disable fast_validate to set min dcfclk in alculate_wm_and_dlg
if (pipe_cnt == 0)
@@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct(
dc->caps.extended_aux_timeout_support = true;
dc->caps.dmcub_support = true;
dc->caps.is_apu = true;
+ dc->caps.zstate_support = true;
/* Color pipeline capabilities */
dc->caps.color.dpp.dcn_arch = 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 2f6122153bdb53f75f798e3f674519f3dfc0a018..f93af45aeab4b44a90196e45b19628cbe4b6d391 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc
{
int plane_count;
int i;
+ unsigned int optimized_min_dst_y_next_start_us;
plane_count = 0;
+ optimized_min_dst_y_next_start_us = 0;
for (i = 0; i < dc->res_pool->pipe_count; i++) {
if (context->res_ctx.pipe_ctx[i].plane_state)
plane_count++;
@@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc
struct dc_link *link = context->streams[0]->sink->link;
struct dc_stream_status *stream_status = &context->stream_status[0];
+ if (dc_extended_blank_supported(dc)) {
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ if (context->res_ctx.pipe_ctx[i].stream == context->streams[0]
+ && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max
+ && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) {
+ optimized_min_dst_y_next_start_us =
+ context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us;
+ break;
+ }
+ }
+ }
/* zstate only supported on PWRSEQ0 and when there's <2 planes*/
if (link->link_index != 0 || stream_status->plane_count > 1)
return DCN_ZSTATE_SUPPORT_DISALLOW;
- if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
+ if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000)
return DCN_ZSTATE_SUPPORT_ALLOW;
else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr)
return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
@@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params(
!= dm_dram_clock_change_unsupported;
context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
- context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context);
-
context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz)
@@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params(
&pipes[pipe_idx].pipe);
pipe_idx++;
}
+ context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context);
}
static void swizzle_to_dml_params(
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index e0fecf127bd5a9baecbd753685f9ac1c02117df7..53d760e169e61f5763ff2e5fab4f053453675b85 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params(
float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA
float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA
+ int blank_lines;
memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs));
memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs));
@@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params(
dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start;
disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2));
+ blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1);
+ if (blank_lines < 0)
+ blank_lines = 0;
+ if (blank_lines != 0) {
+ disp_dlg_regs->optimized_min_dst_y_next_start_us =
+ ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz;
+ disp_dlg_regs->optimized_min_dst_y_next_start =
+ (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2));
+ } else {
+ // use unoptimized value
+ disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start;
+ }
ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18));
dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 59f0a61c33cf9018deb5d792bd76a5d6619420e4..2df660cd8801b34dbd7b33a385571f16230b8838 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st {
unsigned int refcyc_h_blank_end;
unsigned int dlg_vblank_end;
unsigned int min_dst_y_next_start;
+ unsigned int optimized_min_dst_y_next_start;
+ unsigned int optimized_min_dst_y_next_start_us;
unsigned int refcyc_per_htotal;
unsigned int refcyc_x_after_scaler;
unsigned int dst_y_after_scaler;
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index efc2339f1fa00b4e901a247043e4dab793619ef2..4385d19bc489193f5f93575092d9fa9da7d95eca 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -864,11 +864,11 @@ static bool setup_dsc_config(
min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h);
}
+ is_dsc_possible = (min_slices_h <= max_slices_h);
+
if (pic_width % min_slices_h != 0)
min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first?
- is_dsc_possible = (min_slices_h <= max_slices_h);
-
if (min_slices_h == 0 && max_slices_h == 0)
is_dsc_possible = false;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index ab9939db8cea881040b1f4577c0a5730ea62e695..44f167d2584f522e10104f0a7e15de83b45efb8d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -33,6 +33,7 @@
#define MAX_MTP_SLOT_COUNT 64
#define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50
#define TRAINING_AUX_RD_INTERVAL 100 //us
+#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX.
struct dc_link;
struct dc_stream_state;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index e45b7993c5c574861aff875ca890ca1d3e9982e9..ad69d78c4ac347bf0c5256f02e1cf357add6ff24 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -195,6 +195,9 @@ struct hubp_funcs {
void (*hubp_set_flip_int)(struct hubp *hubp);
+ void (*program_extended_blank)(struct hubp *hubp,
+ unsigned int min_dst_y_next_start_optimized);
+
void (*hubp_wait_pipe_read_start)(struct hubp *hubp);
};
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index b691aa45e84fbcec96c418d9df3fa7ec327eada5..79bc207415bcb0b0a259642a20429c923d374d4d 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -100,7 +100,8 @@ enum vsc_packet_revision {
//PB7 = MD0
#define MASK_VTEM_MD0__VRR_EN 0x01
#define MASK_VTEM_MD0__M_CONST 0x02
-#define MASK_VTEM_MD0__RESERVED2 0x0C
+#define MASK_VTEM_MD0__QMS_EN 0x04
+#define MASK_VTEM_MD0__RESERVED2 0x08
#define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0
//MD1
@@ -109,7 +110,7 @@ enum vsc_packet_revision {
//MD2
#define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03
#define MASK_VTEM_MD2__RB 0x04
-#define MASK_VTEM_MD2__RESERVED3 0xF8
+#define MASK_VTEM_MD2__NEXT_TFR 0xF8
//MD3
#define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 89fbee568be4ac514d5110536928ce379ca33c8f..5504d81c77b775bb47e6cc3934effddb37cd3aba 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
if (!pp_funcs || !pp_funcs->get_asic_baco_capability)
return false;
+ /* Don't use baco for reset in S3.
+ * This is a workaround for some platforms
+ * where entering BACO during suspend
+ * seems to cause reboots or hangs.
+ * This might be related to the fact that BACO controls
+ * power to the whole GPU including devices like audio and USB.
+ * Powering down/up everything may adversely affect these other
+ * devices. Needs more investigation.
+ */
+ if (adev->in_s3)
+ return false;
mutex_lock(&adev->pm.mutex);
@@ -500,6 +511,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size)
struct smu_context *smu = adev->powerplay.pp_handle;
int ret = 0;
+ if (!is_support_sw_smu(adev))
+ return -EOPNOTSUPP;
+
mutex_lock(&adev->pm.mutex);
ret = smu_send_hbm_bad_pages_num(smu, size);
mutex_unlock(&adev->pm.mutex);
@@ -512,6 +526,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si
struct smu_context *smu = adev->powerplay.pp_handle;
int ret = 0;
+ if (!is_support_sw_smu(adev))
+ return -EOPNOTSUPP;
+
mutex_lock(&adev->pm.mutex);
ret = smu_send_hbm_bad_channel_flag(smu, size);
mutex_unlock(&adev->pm.mutex);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 9ddd8491ff00847d5c0becbcdec1be4fa3edcb50..ede71de2343dcfba4952c9f20ad62c5614b64e12 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinFclkByFreq,
hwmgr->display_config->num_display > 3 ?
- data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk :
+ (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) :
min_mclk,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinSocclkByFreq,
- data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetHardMinVcn,
@@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxFclkByFreq,
- data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk,
+ data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxSocclkByFreq,
- data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk,
+ data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100,
NULL);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_SetSoftMaxVcn,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
index 7bfac029e51382e6c331e5591b1c1f7505f0e9cc..b81711c4ff3358c126742c05137e40269f49b8d9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
@@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu,
return -EINVAL;
}
- if (sclk_min && sclk_max) {
+ if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) {
ret = smu_v13_0_5_set_soft_freq_limited_range(smu,
SMU_SCLK,
sclk_min,
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 026e4e29a0f374436a839303c019eef0541fb45a..f4df344509a87245d97f701433a4de41dc702d08 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -214,6 +214,29 @@ int drm_of_encoder_active_endpoint(struct device_node *node,
}
EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint);
+static int find_panel_or_bridge(struct device_node *node,
+ struct drm_panel **panel,
+ struct drm_bridge **bridge)
+{
+ if (panel) {
+ *panel = of_drm_find_panel(node);
+ if (!IS_ERR(*panel))
+ return 0;
+
+ /* Clear the panel pointer in case of error. */
+ *panel = NULL;
+ }
+
+ /* No panel found yet, check for a bridge next. */
+ if (bridge) {
+ *bridge = of_drm_find_bridge(node);
+ if (*bridge)
+ return 0;
+ }
+
+ return -EPROBE_DEFER;
+}
+
/**
* drm_of_find_panel_or_bridge - return connected panel or bridge device
* @np: device tree node containing encoder output ports
@@ -236,66 +259,44 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
struct drm_panel **panel,
struct drm_bridge **bridge)
{
- int ret = -EPROBE_DEFER;
- struct device_node *remote;
+ struct device_node *node;
+ int ret;
if (!panel && !bridge)
return -EINVAL;
+
if (panel)
*panel = NULL;
-
- /**
- * Devices can also be child nodes when we also control that device
- * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device).
- *
- * Lookup for a child node of the given parent that isn't either port
- * or ports.
- */
- for_each_available_child_of_node(np, remote) {
- if (of_node_name_eq(remote, "port") ||
- of_node_name_eq(remote, "ports"))
- continue;
-
- goto of_find_panel_or_bridge;
+ if (bridge)
+ *bridge = NULL;
+
+ /* Check for a graph on the device node first. */
+ if (of_graph_is_present(np)) {
+ node = of_graph_get_remote_node(np, port, endpoint);
+ if (node) {
+ ret = find_panel_or_bridge(node, panel, bridge);
+ of_node_put(node);
+
+ if (!ret)
+ return 0;
+ }
}
- /*
- * of_graph_get_remote_node() produces a noisy error message if port
- * node isn't found and the absence of the port is a legit case here,
- * so at first we silently check whether graph presents in the
- * device-tree node.
- */
- if (!of_graph_is_present(np))
- return -ENODEV;
-
- remote = of_graph_get_remote_node(np, port, endpoint);
-
-of_find_panel_or_bridge:
- if (!remote)
- return -ENODEV;
+ /* Otherwise check for any child node other than port/ports. */
+ for_each_available_child_of_node(np, node) {
+ if (of_node_name_eq(node, "port") ||
+ of_node_name_eq(node, "ports"))
+ continue;
- if (panel) {
- *panel = of_drm_find_panel(remote);
- if (!IS_ERR(*panel))
- ret = 0;
- else
- *panel = NULL;
- }
-
- /* No panel found yet, check for a bridge next. */
- if (bridge) {
- if (ret) {
- *bridge = of_drm_find_bridge(remote);
- if (*bridge)
- ret = 0;
- } else {
- *bridge = NULL;
- }
+ ret = find_panel_or_bridge(node, panel, bridge);
+ of_node_put(node);
+ /* Stop at the first found occurrence. */
+ if (!ret)
+ return 0;
}
- of_node_put(remote);
- return ret;
+ return -EPROBE_DEFER;
}
EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge);
diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c
index 87428fb23d9ffa5e53d8b20a76c3d71402265a77..a2277a0d6d06fb55f129531b1e7dd660e269113f 100644
--- a/drivers/gpu/drm/imx/dw_hdmi-imx.c
+++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c
@@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev)
struct device_node *np = pdev->dev.of_node;
const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np);
struct imx_hdmi *hdmi;
+ int ret;
hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL);
if (!hdmi)
@@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev)
hdmi->bridge = of_drm_find_bridge(np);
if (!hdmi->bridge) {
dev_err(hdmi->dev, "Unable to find bridge\n");
+ dw_hdmi_remove(hdmi->hdmi);
return -ENODEV;
}
- return component_add(&pdev->dev, &dw_hdmi_imx_ops);
+ ret = component_add(&pdev->dev, &dw_hdmi_imx_ops);
+ if (ret)
+ dw_hdmi_remove(hdmi->hdmi);
+
+ return ret;
}
static int dw_hdmi_imx_remove(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index e5078d03020d90e84b2ca6acbc877ae52234d4ac..fb0e951248f685ed0ace2f601c1fba6478db342f 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -572,6 +572,8 @@ static int imx_ldb_panel_ddc(struct device *dev,
edidp = of_get_property(child, "edid", &edid_len);
if (edidp) {
channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL);
+ if (!channel->edid)
+ return -ENOMEM;
} else if (!channel->panel) {
/* fallback to display-timings node */
ret = of_get_drm_display_mode(child,
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 06cb1a59b9bcd6fd38f573abfdbca904f9a69cc2..63ba2ad84679183af60a635ea3f014f2f47d0bba 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
ret = of_get_drm_display_mode(np, &imxpd->mode,
&imxpd->bus_flags,
OF_USE_NATIVE_MODE);
- if (ret)
+ if (ret) {
+ drm_mode_destroy(connector->dev, mode);
return ret;
+ }
drm_mode_copy(mode, &imxpd->mode);
mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
index e1772211b0a4b1567456e0eea30f5db88155f739..612310d5d4812eb056d6a9097acb64beb09c7cdc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
@@ -216,6 +216,7 @@ gm20b_pmu = {
.intr = gt215_pmu_intr,
.recv = gm20b_pmu_recv,
.initmsg = gm20b_pmu_initmsg,
+ .reset = gf100_pmu_reset,
};
#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
index 6bf7fc1bd1e3b1deb1808286b748eaef39b301f5..1a6f9c3af5ecde69df97d5892d3cd9dc926ae857 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
@@ -23,7 +23,7 @@
*/
#include "priv.h"
-static void
+void
gp102_pmu_reset(struct nvkm_pmu *pmu)
{
struct nvkm_device *device = pmu->subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
index ba1583bb618b2ef8379dcf5cfa99b0ccfdbd264e..94cfb1791af6ea50665b5a1a4a84b406538b096e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -83,6 +83,7 @@ gp10b_pmu = {
.intr = gt215_pmu_intr,
.recv = gm20b_pmu_recv,
.initmsg = gm20b_pmu_initmsg,
+ .reset = gp102_pmu_reset,
};
#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
index bcaade758ff728bd528fafb262fb608f0b08a09a..21abf31f44420247efd4ffb0c95ab3a988cab7f5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
@@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32);
bool gf100_pmu_enabled(struct nvkm_pmu *);
void gf100_pmu_reset(struct nvkm_pmu *);
+void gp102_pmu_reset(struct nvkm_pmu *pmu);
void gk110_pmu_pgob(struct nvkm_pmu *, bool);
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
index a07ef26234e57ccf71b5bc000b15772cc1601d15..6826f4d4826a4b12520c813da4540f47f2296efd 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c
@@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc,
int ret;
vcc = devm_regulator_get_optional(dev, "vcc");
- if (IS_ERR(vcc))
+ if (IS_ERR(vcc)) {
dev_err(dev, "get optional vcc failed\n");
+ vcc = NULL;
+ }
dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver,
struct mipi_dbi_dev, drm);
diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c
index 666223c6bec4d52da44b38d3a0263f19bae2f4a6..0a34e0ab4fe60e7d4caad5d9c0272c3b4a391d05 100644
--- a/drivers/gpu/ipu-v3/ipu-di.c
+++ b/drivers/gpu/ipu-v3/ipu-di.c
@@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di,
error = rate / (sig->mode.pixelclock / 1000);
- dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n",
- rate, div, (signed)(error - 1000) / 10, error % 10);
+ dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n",
+ rate, div, error < 1000 ? '-' : '+',
+ abs(error - 1000) / 10, abs(error - 1000) % 10);
/* Allow a 1% error */
if (error < 1010 && error >= 990) {
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 34d6bb1bf82eed3717eb78a3997e95408e2eb4bd..a6bb0e4382167e121c49bfeb0445197eab5ecea4 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -1579,7 +1579,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a,
* If it's not a platform device, at least print a warning. A
* fix would add code to remove the device from the system.
*/
- if (dev_is_platform(device)) {
+ if (!device) {
+ /* TODO: Represent each OF framebuffer as its own
+ * device in the device hierarchy. For now, offb
+ * doesn't have such a device, so unregister the
+ * framebuffer as before without warning.
+ */
+ do_unregister_framebuffer(registered_fb[i]);
+ } else if (dev_is_platform(device)) {
registered_fb[i]->forced_out = true;
platform_device_unregister(to_platform_device(device));
} else {
diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h
index fec374f69e125506a507e92ec9486e53c79c0de2..ec7f25def39290cfb331f0350f431cd8afd249b6 100644
--- a/include/linux/dma-fence-array.h
+++ b/include/linux/dma-fence-array.h
@@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence)
return container_of(fence, struct dma_fence_array, base);
}
+/**
+ * dma_fence_array_for_each - iterate over all fences in array
+ * @fence: current fence
+ * @index: index into the array
+ * @head: potential dma_fence_array object
+ *
+ * Test if @array is a dma_fence_array object and if yes iterate over all fences
+ * in the array. If not just iterate over the fence in @array itself.
+ *
+ * For a deep dive iterator see dma_fence_unwrap_for_each().
+ */
+#define dma_fence_array_for_each(fence, index, head) \
+ for (index = 0, fence = dma_fence_array_first(head); fence; \
+ ++(index), fence = dma_fence_array_next(head, index))
+
struct dma_fence_array *dma_fence_array_create(int num_fences,
struct dma_fence **fences,
u64 context, unsigned seqno,
@@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences,
bool dma_fence_match_context(struct dma_fence *fence, u64 context);
+struct dma_fence *dma_fence_array_first(struct dma_fence *head);
+struct dma_fence *dma_fence_array_next(struct dma_fence *head,
+ unsigned int index);
+
#endif /* __LINUX_DMA_FENCE_ARRAY_H */
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
index 10d51bcdf7b7946a675203d0e37110454e9256c4..4bdf0b96da28312c8e33755ad6ffa1befdd022ae 100644
--- a/include/linux/dma-fence-chain.h
+++ b/include/linux/dma-fence-chain.h
@@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain)
*
* Iterate over all fences in the chain. We keep a reference to the current
* fence while inside the loop which must be dropped when breaking out.
+ *
+ * For a deep dive iterator see dma_fence_unwrap_for_each().
*/
#define dma_fence_chain_for_each(iter, head) \
for (iter = dma_fence_get(head); iter; \
diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h
new file mode 100644
index 0000000000000000000000000000000000000000..77e335a1bcac8ce5b3998099e17570e117ba4540
--- /dev/null
+++ b/include/linux/dma-fence-unwrap.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * fence-chain: chain fences together in a timeline
+ *
+ * Copyright (C) 2022 Advanced Micro Devices, Inc.
+ * Authors:
+ * Christian König <christian.koenig@amd.com>
+ */
+
+#ifndef __LINUX_DMA_FENCE_UNWRAP_H
+#define __LINUX_DMA_FENCE_UNWRAP_H
+
+#include <linux/dma-fence-chain.h>
+#include <linux/dma-fence-array.h>
+
+/**
+ * struct dma_fence_unwrap - cursor into the container structure
+ *
+ * Should be used with dma_fence_unwrap_for_each() iterator macro.
+ */
+struct dma_fence_unwrap {
+ /**
+ * @chain: potential dma_fence_chain, but can be other fence as well
+ */
+ struct dma_fence *chain;
+ /**
+ * @array: potential dma_fence_array, but can be other fence as well
+ */
+ struct dma_fence *array;
+ /**
+ * @index: last returned index if @array is really a dma_fence_array
+ */
+ unsigned int index;
+};
+
+/* Internal helper to start new array iteration, don't use directly */
+static inline struct dma_fence *
+__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor)
+{
+ cursor->array = dma_fence_chain_contained(cursor->chain);
+ cursor->index = 0;
+ return dma_fence_array_first(cursor->array);
+}
+
+/**
+ * dma_fence_unwrap_first - return the first fence from fence containers
+ * @head: the entrypoint into the containers
+ * @cursor: current position inside the containers
+ *
+ * Unwraps potential dma_fence_chain/dma_fence_array containers and return the
+ * first fence.
+ */
+static inline struct dma_fence *
+dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor)
+{
+ cursor->chain = dma_fence_get(head);
+ return __dma_fence_unwrap_array(cursor);
+}
+
+/**
+ * dma_fence_unwrap_next - return the next fence from a fence containers
+ * @cursor: current position inside the containers
+ *
+ * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return
+ * the next fence from them.
+ */
+static inline struct dma_fence *
+dma_fence_unwrap_next(struct dma_fence_unwrap *cursor)
+{
+ struct dma_fence *tmp;
+
+ ++cursor->index;
+ tmp = dma_fence_array_next(cursor->array, cursor->index);
+ if (tmp)
+ return tmp;
+
+ cursor->chain = dma_fence_chain_walk(cursor->chain);
+ return __dma_fence_unwrap_array(cursor);
+}
+
+/**
+ * dma_fence_unwrap_for_each - iterate over all fences in containers
+ * @fence: current fence
+ * @cursor: current position inside the containers
+ * @head: starting point for the iterator
+ *
+ * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all
+ * potential fences in them. If @head is just a normal fence only that one is
+ * returned.
+ */
+#define dma_fence_unwrap_for_each(fence, cursor, head) \
+ for (fence = dma_fence_unwrap_first(head, cursor); fence; \
+ fence = dma_fence_unwrap_next(cursor))
+
+#endif