Merge tag 'amd-drm-next-6.13-2024-11-15' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.13-2024-11-15:

amdgpu:
- Parition fixes
- GFX 12 fixes
- SR-IOV fixes
- MES fixes
- RAS fixes
- GC queue handling fixes
- VCN fixes
- Add sysfs reset masks
- Better error messages for P2P failurs
- SMU fixes
- Documentation updates
- GFX11 enforce isolation updates
- Display HPD fixes
- PSR fixes
- Panel replay fixes
- DP MST fixes
- USB4 fixes
- Misc display fixes and cleanups
- VRAM handling fix for APUs
- NBIO fix

amdkfd:
- INIT_WORK fix
- Refcount fix
- KFD MES scheduling fixes

drm/fourcc:
- Add missing tiling mode

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241115165012.573465-1-alexander.deucher@amd.com

75 files changed, 1391 insertions, 243 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 7645e498faa4..d8bc6da50016 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -299,6 +299,12 @@ extern int amdgpu_wbrf;
 #define AMDGPU_RESET_VCE			(1 << 13)
 #define AMDGPU_RESET_VCE1			(1 << 14)
 
+/* reset mask */
+#define AMDGPU_RESET_TYPE_FULL (1 << 0) /* full adapter reset, mode1/mode2/BACO/etc. */
+#define AMDGPU_RESET_TYPE_SOFT_RESET (1 << 1) /* IP level soft reset */
+#define AMDGPU_RESET_TYPE_PER_QUEUE (1 << 2) /* per queue */
+#define AMDGPU_RESET_TYPE_PER_PIPE (1 << 3) /* per pipe */
+
 /* max cursor sizes (in pixels) */
 #define CIK_CURSOR_WIDTH 128
 #define CIK_CURSOR_HEIGHT 128
@@ -1464,6 +1470,8 @@ struct dma_fence *amdgpu_device_get_gang(struct amdgpu_device *adev);
 struct dma_fence *amdgpu_device_switch_gang(struct amdgpu_device *adev,
 					    struct dma_fence *gang);
 bool amdgpu_device_has_display_hardware(struct amdgpu_device *adev);
+ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring);
+ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index 2ca127173135..9d6345146495 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -158,7 +158,7 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 		return -EINVAL;
 	}
 
-	if (start + count >= max_count)
+	if (start + count > max_count)
 		return -EINVAL;
 
 	count = min_t(int, count, max_count);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 24343c312480..3afcd1e8aa54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -834,6 +834,9 @@ int amdgpu_amdkfd_unmap_hiq(struct amdgpu_device *adev, u32 doorbell_off,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	if (!kiq_ring->sched.ready || adev->job_hang)
+		return 0;
+
 	ring_funcs = kzalloc(sizeof(*ring_funcs), GFP_KERNEL);
 	if (!ring_funcs)
 		return -ENOMEM;
@@ -858,8 +861,14 @@ int amdgpu_amdkfd_unmap_hiq(struct amdgpu_device *adev, u32 doorbell_off,
 
 	kiq->pmf->kiq_unmap_queues(kiq_ring, ring, RESET_QUEUES, 0, 0);
 
-	if (kiq_ring->sched.ready && !adev->job_hang)
-		r = amdgpu_ring_test_helper(kiq_ring);
+	/* Submit unmap queue packet */
+	amdgpu_ring_commit(kiq_ring);
+	/*
+	 * Ring test will do a basic scratch register change check. Just run
+	 * this to ensure that unmap queues that is submitted before got
+	 * processed successfully before returning.
+	 */
+	r = amdgpu_ring_test_helper(kiq_ring);
 
 	spin_unlock(&kiq->ring_lock);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 0450eab6ade7..0171d240fcb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4236,7 +4236,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * for throttling interrupt) = 60 seconds.
 	 */
 	ratelimit_state_init(&adev->throttling_logging_rs, (60 - 1) * HZ, 1);
+	ratelimit_state_init(&adev->virt.ras_telemetry_rs, 5 * HZ, 1);
+
 	ratelimit_set_flags(&adev->throttling_logging_rs, RATELIMIT_MSG_ON_RELEASE);
+	ratelimit_set_flags(&adev->virt.ras_telemetry_rs, RATELIMIT_MSG_ON_RELEASE);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
@@ -5186,6 +5189,9 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4) ||
 	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(11, 0, 3))
 		amdgpu_ras_resume(adev);
+
+	amdgpu_virt_ras_telemetry_post_reset(adev);
+
 	return 0;
 }
 
@@ -6200,6 +6206,9 @@ bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 	bool p2p_access =
 		!adev->gmc.xgmi.connected_to_cpu &&
 		!(pci_p2pdma_distance(adev->pdev, peer_adev->dev, false) < 0);
+	if (!p2p_access)
+		dev_info(adev->dev, "PCIe P2P access from peer device %s is not supported by the chipset\n",
+			pci_name(peer_adev->pdev));
 
 	bool is_large_bar = adev->gmc.visible_vram_size &&
 		adev->gmc.real_vram_size == adev->gmc.visible_vram_size;
@@ -6715,3 +6724,47 @@ uint32_t amdgpu_device_wait_on_rreg(struct amdgpu_device *adev,
 	}
 	return ret;
 }
+
+ssize_t amdgpu_get_soft_full_reset_mask(struct amdgpu_ring *ring)
+{
+	ssize_t size = 0;
+
+	if (!ring || !ring->adev)
+		return size;
+
+	if (amdgpu_device_should_recover_gpu(ring->adev))
+		size |= AMDGPU_RESET_TYPE_FULL;
+
+	if (unlikely(!ring->adev->debug_disable_soft_recovery) &&
+	    !amdgpu_sriov_vf(ring->adev) && ring->funcs->soft_recovery)
+		size |= AMDGPU_RESET_TYPE_SOFT_RESET;
+
+	return size;
+}
+
+ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset)
+{
+	ssize_t size = 0;
+
+	if (supported_reset == 0) {
+		size += sysfs_emit_at(buf, size, "unsupported");
+		size += sysfs_emit_at(buf, size, "\n");
+		return size;
+
+	}
+
+	if (supported_reset & AMDGPU_RESET_TYPE_SOFT_RESET)
+		size += sysfs_emit_at(buf, size, "soft ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+		size += sysfs_emit_at(buf, size, "queue ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_PER_PIPE)
+		size += sysfs_emit_at(buf, size, "pipe ");
+
+	if (supported_reset & AMDGPU_RESET_TYPE_FULL)
+		size += sysfs_emit_at(buf, size, "full ");
+
+	size += sysfs_emit_at(buf, size, "\n");
+	return size;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 2f3f09dfb1fd..f57cc72c43cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -515,6 +515,9 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	if (!kiq_ring->sched.ready || adev->job_hang || amdgpu_in_reset(adev))
+		return 0;
+
 	spin_lock(&kiq->ring_lock);
 	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size *
 					adev->gfx.num_compute_rings)) {
@@ -528,20 +531,15 @@ int amdgpu_gfx_disable_kcq(struct amdgpu_device *adev, int xcc_id)
 					   &adev->gfx.compute_ring[j],
 					   RESET_QUEUES, 0, 0);
 	}
-
-	/**
-	 * This is workaround: only skip kiq_ring test
-	 * during ras recovery in suspend stage for gfx9.4.3
+	/* Submit unmap queue packet */
+	amdgpu_ring_commit(kiq_ring);
+	/*
+	 * Ring test will do a basic scratch register change check. Just run
+	 * this to ensure that unmap queues that is submitted before got
+	 * processed successfully before returning.
 	 */
-	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
-	    amdgpu_ras_in_recovery(adev)) {
-		spin_unlock(&kiq->ring_lock);
-		return 0;
-	}
+	r = amdgpu_ring_test_helper(kiq_ring);
 
-	if (kiq_ring->sched.ready && !adev->job_hang)
-		r = amdgpu_ring_test_helper(kiq_ring);
 	spin_unlock(&kiq->ring_lock);
 
 	return r;
@@ -569,8 +567,11 @@ int amdgpu_gfx_disable_kgq(struct amdgpu_device *adev, int xcc_id)
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
-	spin_lock(&kiq->ring_lock);
+	if (!adev->gfx.kiq[0].ring.sched.ready || adev->job_hang)
+		return 0;
+
 	if (amdgpu_gfx_is_master_xcc(adev, xcc_id)) {
+		spin_lock(&kiq->ring_lock);
 		if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size *
 						adev->gfx.num_gfx_rings)) {
 			spin_unlock(&kiq->ring_lock);
@@ -583,11 +584,17 @@ int amdgpu_gfx_disable_kgq(struct amdgpu_device *adev, int xcc_id)
 						   &adev->gfx.gfx_ring[j],
 						   PREEMPT_QUEUES, 0, 0);
 		}
-	}
+		/* Submit unmap queue packet */
+		amdgpu_ring_commit(kiq_ring);
 
-	if (adev->gfx.kiq[0].ring.sched.ready && !adev->job_hang)
+		/*
+		 * Ring test will do a basic scratch register change check.
+		 * Just run this to ensure that unmap queues that is submitted
+		 * before got processed successfully before returning.
+		 */
 		r = amdgpu_ring_test_helper(kiq_ring);
-	spin_unlock(&kiq->ring_lock);
+		spin_unlock(&kiq->ring_lock);
+	}
 
 	return r;
 }
@@ -692,7 +699,13 @@ int amdgpu_gfx_enable_kcq(struct amdgpu_device *adev, int xcc_id)
 		kiq->pmf->kiq_map_queues(kiq_ring,
 					 &adev->gfx.compute_ring[j]);
 	}
-
+	/* Submit map queue packet */
+	amdgpu_ring_commit(kiq_ring);
+	/*
+	 * Ring test will do a basic scratch register change check. Just run
+	 * this to ensure that map queues that is submitted before got
+	 * processed successfully before returning.
+	 */
 	r = amdgpu_ring_test_helper(kiq_ring);
 	spin_unlock(&kiq->ring_lock);
 	if (r)
@@ -743,7 +756,13 @@ int amdgpu_gfx_enable_kgq(struct amdgpu_device *adev, int xcc_id)
 						 &adev->gfx.gfx_ring[j]);
 		}
 	}
-
+	/* Submit map queue packet */
+	amdgpu_ring_commit(kiq_ring);
+	/*
+	 * Ring test will do a basic scratch register change check. Just run
+	 * this to ensure that map queues that is submitted before got
+	 * processed successfully before returning.
+	 */
 	r = amdgpu_ring_test_helper(kiq_ring);
 	spin_unlock(&kiq->ring_lock);
 	if (r)
@@ -885,6 +904,9 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 		if (r)
 			return r;
 
+		if (amdgpu_sriov_vf(adev))
+			return r;
+
 		if (adev->gfx.cp_ecc_error_irq.funcs) {
 			r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
 			if (r)
@@ -1576,9 +1598,11 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 		if (adev->enforce_isolation[i] && !partition_values[i]) {
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
+			amdgpu_mes_set_enforce_isolation(adev, i, false);
 		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
+			amdgpu_mes_set_enforce_isolation(adev, i, true);
 		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}
@@ -1588,6 +1612,32 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 	return count;
 }
 
+static ssize_t amdgpu_gfx_get_gfx_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->gfx.gfx_supported_reset);
+}
+
+static ssize_t amdgpu_gfx_get_compute_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->gfx.compute_supported_reset);
+}
+
 static DEVICE_ATTR(run_cleaner_shader, 0200,
 		   NULL, amdgpu_gfx_set_run_cleaner_shader);
 
@@ -1601,6 +1651,11 @@ static DEVICE_ATTR(current_compute_partition, 0644,
 
 static DEVICE_ATTR(available_compute_partition, 0444,
 		   amdgpu_gfx_get_available_compute_partition, NULL);
+static DEVICE_ATTR(gfx_reset_mask, 0444,
+		   amdgpu_gfx_get_gfx_reset_mask, NULL);
+
+static DEVICE_ATTR(compute_reset_mask, 0444,
+		   amdgpu_gfx_get_compute_reset_mask, NULL);
 
 static int amdgpu_gfx_sysfs_xcp_init(struct amdgpu_device *adev)
 {
@@ -1666,6 +1721,40 @@ static void amdgpu_gfx_sysfs_isolation_shader_fini(struct amdgpu_device *adev)
 		device_remove_file(adev->dev, &dev_attr_run_cleaner_shader);
 }
 
+static int amdgpu_gfx_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (!amdgpu_gpu_recovery)
+		return r;
+
+	if (adev->gfx.num_gfx_rings) {
+		r = device_create_file(adev->dev, &dev_attr_gfx_reset_mask);
+		if (r)
+			return r;
+	}
+
+	if (adev->gfx.num_compute_rings) {
+		r = device_create_file(adev->dev, &dev_attr_compute_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+static void amdgpu_gfx_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_gpu_recovery)
+		return;
+
+	if (adev->gfx.num_gfx_rings)
+		device_remove_file(adev->dev, &dev_attr_gfx_reset_mask);
+
+	if (adev->gfx.num_compute_rings)
+		device_remove_file(adev->dev, &dev_attr_compute_reset_mask);
+}
+
 int amdgpu_gfx_sysfs_init(struct amdgpu_device *adev)
 {
 	int r;
@@ -1680,6 +1769,10 @@ int amdgpu_gfx_sysfs_init(struct amdgpu_device *adev)
 	if (r)
 		dev_err(adev->dev, "failed to create isolation sysfs files");
 
+	r = amdgpu_gfx_sysfs_reset_mask_init(adev);
+	if (r)
+		dev_err(adev->dev, "failed to create reset mask sysfs files");
+
 	return r;
 }
 
@@ -1687,6 +1780,7 @@ void amdgpu_gfx_sysfs_fini(struct amdgpu_device *adev)
 {
 	amdgpu_gfx_sysfs_xcp_fini(adev);
 	amdgpu_gfx_sysfs_isolation_shader_fini(adev);
+	amdgpu_gfx_sysfs_reset_mask_fini(adev);
 }
 
 int amdgpu_gfx_cleaner_shader_sw_init(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index fd73e527f446..8b5bd63b5773 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -424,6 +424,8 @@ struct amdgpu_gfx {
 	/* reset mask */
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
+	uint32_t 			gfx_supported_reset;
+	uint32_t 			compute_supported_reset;
 
 	/* gfx off */
 	bool                            gfx_off_state;      /* true: enabled, false: disabled */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 95e2796919fc..04eb51674596 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -47,7 +47,7 @@ int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
 		adev->jpeg.indirect_sram = true;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
-		if (adev->jpeg.harvest_config & (1 << i))
+		if (adev->jpeg.harvest_config & (1U << i))
 			continue;
 
 		if (adev->jpeg.indirect_sram) {
@@ -73,7 +73,7 @@ int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
 	int i, j;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		if (adev->jpeg.harvest_config & (1 << i))
+		if (adev->jpeg.harvest_config & (1U << i))
 			continue;
 
 		amdgpu_bo_free_kernel(
@@ -110,7 +110,7 @@ static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
 	unsigned int i, j;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-		if (adev->jpeg.harvest_config & (1 << i))
+		if (adev->jpeg.harvest_config & (1U << i))
 			continue;
 
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j)
@@ -357,7 +357,7 @@ static int amdgpu_debugfs_jpeg_sched_mask_set(void *data, u64 val)
 	if (!adev)
 		return -ENODEV;
 
-	mask = (1 << (adev->jpeg.num_jpeg_inst * adev->jpeg.num_jpeg_rings)) - 1;
+	mask = (1ULL << (adev->jpeg.num_jpeg_inst * adev->jpeg.num_jpeg_rings)) - 1;
 	if ((val & mask) == 0)
 		return -EINVAL;
 
@@ -388,7 +388,7 @@ static int amdgpu_debugfs_jpeg_sched_mask_get(void *data, u64 *val)
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
 			ring = &adev->jpeg.inst[i].ring_dec[j];
 			if (ring->sched.ready)
-				mask |= 1 << ((i * adev->jpeg.num_jpeg_rings) + j);
+				mask |= 1ULL << ((i * adev->jpeg.num_jpeg_rings) + j);
 		}
 	}
 	*val = mask;
@@ -415,3 +415,38 @@ void amdgpu_debugfs_jpeg_sched_mask_init(struct amdgpu_device *adev)
 			    &amdgpu_debugfs_jpeg_sched_mask_fops);
 #endif
 }
+
+static ssize_t amdgpu_get_jpeg_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->jpeg.supported_reset);
+}
+
+static DEVICE_ATTR(jpeg_reset_mask, 0444,
+		   amdgpu_get_jpeg_reset_mask, NULL);
+
+int amdgpu_jpeg_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->jpeg.num_jpeg_inst) {
+		r = device_create_file(adev->dev, &dev_attr_jpeg_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+void amdgpu_jpeg_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (adev->jpeg.num_jpeg_inst)
+		device_remove_file(adev->dev, &dev_attr_jpeg_reset_mask);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
index 819dc7a0af99..3eb4a4653fce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
@@ -128,6 +128,7 @@ struct amdgpu_jpeg {
 	uint16_t inst_mask;
 	uint8_t num_inst_per_aid;
 	bool	indirect_sram;
+	uint32_t supported_reset;
 };
 
 int amdgpu_jpeg_sw_init(struct amdgpu_device *adev);
@@ -150,5 +151,7 @@ int amdgpu_jpeg_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_jpeg_psp_update_sram(struct amdgpu_device *adev, int inst_idx,
 			       enum AMDGPU_UCODE_ID ucode_id);
 void amdgpu_debugfs_jpeg_sched_mask_init(struct amdgpu_device *adev);
+int amdgpu_jpeg_sysfs_reset_mask_init(struct amdgpu_device *adev);
+void amdgpu_jpeg_sysfs_reset_mask_fini(struct amdgpu_device *adev);
 
 #endif /*__AMDGPU_JPEG_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index b10383f83d73..59ec20b07a6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -104,7 +104,7 @@ static int amdgpu_mes_event_log_init(struct amdgpu_device *adev)
 		return 0;
 
 	r = amdgpu_bo_create_kernel(adev, adev->mes.event_log_size, PAGE_SIZE,
-				    AMDGPU_GEM_DOMAIN_GTT,
+				    AMDGPU_GEM_DOMAIN_VRAM,
 				    &adev->mes.event_log_gpu_obj,
 				    &adev->mes.event_log_gpu_addr,
 				    &adev->mes.event_log_cpu_addr);
@@ -192,17 +192,6 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 			(uint64_t *)&adev->wb.wb[adev->mes.query_status_fence_offs[i]];
 	}
 
-	r = amdgpu_device_wb_get(adev, &adev->mes.read_val_offs);
-	if (r) {
-		dev_err(adev->dev,
-			"(%d) read_val_offs alloc failed\n", r);
-		goto error;
-	}
-	adev->mes.read_val_gpu_addr =
-		adev->wb.gpu_addr + (adev->mes.read_val_offs * 4);
-	adev->mes.read_val_ptr =
-		(uint32_t *)&adev->wb.wb[adev->mes.read_val_offs];
-
 	r = amdgpu_mes_doorbell_init(adev);
 	if (r)
 		goto error;
@@ -223,8 +212,6 @@ error:
 			amdgpu_device_wb_free(adev,
 				      adev->mes.query_status_fence_offs[i]);
 	}
-	if (adev->mes.read_val_ptr)
-		amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
 
 	idr_destroy(&adev->mes.pasid_idr);
 	idr_destroy(&adev->mes.gang_id_idr);
@@ -249,8 +236,6 @@ void amdgpu_mes_fini(struct amdgpu_device *adev)
 			amdgpu_device_wb_free(adev,
 				      adev->mes.query_status_fence_offs[i]);
 	}
-	if (adev->mes.read_val_ptr)
-		amdgpu_device_wb_free(adev, adev->mes.read_val_offs);
 
 	amdgpu_mes_doorbell_free(adev);
 
@@ -921,10 +906,19 @@ uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
 	struct mes_misc_op_input op_input;
 	int r, val = 0;
+	uint32_t addr_offset = 0;
+	uint64_t read_val_gpu_addr;
+	uint32_t *read_val_ptr;
 
+	if (amdgpu_device_wb_get(adev, &addr_offset)) {
+		DRM_ERROR("critical bug! too many mes readers\n");
+		goto error;
+	}
+	read_val_gpu_addr = adev->wb.gpu_addr + (addr_offset * 4);
+	read_val_ptr = (uint32_t *)&adev->wb.wb[addr_offset];
 	op_input.op = MES_MISC_OP_READ_REG;
 	op_input.read_reg.reg_offset = reg;
-	op_input.read_reg.buffer_addr = adev->mes.read_val_gpu_addr;
+	op_input.read_reg.buffer_addr = read_val_gpu_addr;
 
 	if (!adev->mes.funcs->misc_op) {
 		DRM_ERROR("mes rreg is not supported!\n");
@@ -935,9 +929,11 @@ uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 	if (r)
 		DRM_ERROR("failed to read reg (0x%x)\n", reg);
 	else
-		val = *(adev->mes.read_val_ptr);
+		val = *(read_val_ptr);
 
 error:
+	if (addr_offset)
+		amdgpu_device_wb_free(adev, addr_offset);
 	return val;
 }
 
@@ -1682,6 +1678,29 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
 	return is_supported;
 }
 
+/* Fix me -- node_id is used to identify the correct MES instances in the future */
+int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable)
+{
+	struct mes_misc_op_input op_input = {0};
+	int r;
+
+	op_input.op = MES_MISC_OP_CHANGE_CONFIG;
+	op_input.change_config.option.limit_single_process = enable ? 1 : 0;
+
+	if (!adev->mes.funcs->misc_op) {
+		dev_err(adev->dev, "mes change config is not supported!\n");
+		r = -EINVAL;
+		goto error;
+	}
+
+	r = adev->mes.funcs->misc_op(&adev->mes, &op_input);
+	if (r)
+		dev_err(adev->dev, "failed to change_config.\n");
+
+error:
+	return r;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 0684e482a204..c6f93cbd6739 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -40,6 +40,7 @@
 #define AMDGPU_MES_VERSION_MASK		0x00000fff
 #define AMDGPU_MES_API_VERSION_MASK	0x00fff000
 #define AMDGPU_MES_FEAT_VERSION_MASK	0xff000000
+#define AMDGPU_MES_MSCRATCH_SIZE	0x8000
 
 enum amdgpu_mes_priority_level {
 	AMDGPU_MES_PRIORITY_LEVEL_LOW       = 0,
@@ -120,9 +121,6 @@ struct amdgpu_mes {
 	uint32_t			query_status_fence_offs[AMDGPU_MAX_MES_PIPES];
 	uint64_t			query_status_fence_gpu_addr[AMDGPU_MAX_MES_PIPES];
 	uint64_t			*query_status_fence_ptr[AMDGPU_MAX_MES_PIPES];
-	uint32_t                        read_val_offs;
-	uint64_t			read_val_gpu_addr;
-	uint32_t			*read_val_ptr;
 
 	uint32_t			saved_flags;
 
@@ -311,6 +309,7 @@ enum mes_misc_opcode {
 	MES_MISC_OP_WRM_REG_WAIT,
 	MES_MISC_OP_WRM_REG_WR_WAIT,
 	MES_MISC_OP_SET_SHADER_DEBUGGER,
+	MES_MISC_OP_CHANGE_CONFIG,
 };
 
 struct mes_misc_op_input {
@@ -349,6 +348,21 @@ struct mes_misc_op_input {
 			uint32_t tcp_watch_cntl[4];
 			uint32_t trap_en;
 		} set_shader_debugger;
+
+		struct {
+			union {
+				struct {
+					uint32_t limit_single_process : 1;
+					uint32_t enable_hws_logging_buffer : 1;
+					uint32_t reserved : 30;
+				};
+				uint32_t all;
+			} option;
+			struct {
+				uint32_t tdr_level;
+				uint32_t tdr_delay;
+			} tdr_config;
+		} change_config;
 	};
 };
 
@@ -519,4 +533,7 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes)
 }
 
 bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev);
+
+int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable);
+
 #endif /* __AMDGPU_MES_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index b5f65ef1efcd..6852d50caa89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -162,7 +162,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		 * When GTT is just an alternative to VRAM make sure that we
 		 * only use it as fallback and still try to fill up VRAM first.
 		 */
-		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
+		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
+		    !(adev->flags & AMD_IS_APU))
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b772299e1067..1bc95b0cdbb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1214,6 +1214,42 @@ static void amdgpu_ras_error_generate_report(struct amdgpu_device *adev,
 	}
 }
 
+static void amdgpu_ras_virt_error_generate_report(struct amdgpu_device *adev,
+						  struct ras_query_if *query_if,
+						  struct ras_err_data *err_data,
+						  struct ras_query_context *qctx)
+{
+	unsigned long new_ue, new_ce, new_de;
+	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &query_if->head);
+	const char *blk_name = get_ras_block_str(&query_if->head);
+	u64 event_id = qctx->evid.event_id;
+
+	new_ce = err_data->ce_count - obj->err_data.ce_count;
+	new_ue = err_data->ue_count - obj->err_data.ue_count;
+	new_de = err_data->de_count - obj->err_data.de_count;
+
+	if (new_ce) {
+		RAS_EVENT_LOG(adev, event_id, "%lu correctable hardware errors "
+			      "detected in %s block\n",
+			      new_ce,
+			      blk_name);
+	}
+
+	if (new_ue) {
+		RAS_EVENT_LOG(adev, event_id, "%lu uncorrectable hardware errors "
+			      "detected in %s block\n",
+			      new_ue,
+			      blk_name);
+	}
+
+	if (new_de) {
+		RAS_EVENT_LOG(adev, event_id, "%lu deferred hardware errors "
+			      "detected in %s block\n",
+			      new_de,
+			      blk_name);
+	}
+}
+
 static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, struct ras_err_data *err_data)
 {
 	struct ras_err_node *err_node;
@@ -1237,6 +1273,15 @@ static void amdgpu_rasmgr_error_data_statistic_update(struct ras_manager *obj, s
 	}
 }
 
+static void amdgpu_ras_mgr_virt_error_data_statistics_update(struct ras_manager *obj,
+							     struct ras_err_data *err_data)
+{
+	/* Host reports absolute counts */
+	obj->err_data.ue_count = err_data->ue_count;
+	obj->err_data.ce_count = err_data->ce_count;
+	obj->err_data.de_count = err_data->de_count;
+}
+
 static struct ras_manager *get_ras_manager(struct amdgpu_device *adev, enum amdgpu_ras_block blk)
 {
 	struct ras_common_if head;
@@ -1323,7 +1368,9 @@ static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev,
 	if (error_query_mode == AMDGPU_RAS_INVALID_ERROR_QUERY)
 		return -EINVAL;
 
-	if (error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY) {
+	if (error_query_mode == AMDGPU_RAS_VIRT_ERROR_COUNT_QUERY) {
+		return amdgpu_virt_req_ras_err_count(adev, blk, err_data);
+	} else if (error_query_mode == AMDGPU_RAS_DIRECT_ERROR_QUERY) {
 		if (info->head.block == AMDGPU_RAS_BLOCK__UMC) {
 			amdgpu_ras_get_ecc_info(adev, err_data);
 		} else {
@@ -1405,14 +1452,22 @@ static int amdgpu_ras_query_error_status_with_event(struct amdgpu_device *adev,
 	if (ret)
 		goto out_fini_err_data;
 
-	amdgpu_rasmgr_error_data_statistic_update(obj, &err_data);
+	if (error_query_mode != AMDGPU_RAS_VIRT_ERROR_COUNT_QUERY) {
+		amdgpu_rasmgr_error_data_statistic_update(obj, &err_data);
+		amdgpu_ras_error_generate_report(adev, info, &err_data, &qctx);
+	} else {
+		/* Host provides absolute error counts. First generate the report
+		 * using the previous VF internal count against new host count.
+		 * Then Update VF internal count.
+		 */
+		amdgpu_ras_virt_error_generate_report(adev, info, &err_data, &qctx);
+		amdgpu_ras_mgr_virt_error_data_statistics_update(obj, &err_data);
+	}
 
 	info->ue_count = obj->err_data.ue_count;
 	info->ce_count = obj->err_data.ce_count;
 	info->de_count = obj->err_data.de_count;
 
-	amdgpu_ras_error_generate_report(adev, info, &err_data, &qctx);
-
 out_fini_err_data:
 	amdgpu_ras_error_data_fini(&err_data);
 
@@ -3453,6 +3508,11 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 	if (!amdgpu_ras_asic_supported(adev))
 		return;
 
+	if (amdgpu_sriov_vf(adev)) {
+		if (amdgpu_virt_get_ras_capability(adev))
+			goto init_ras_enabled_flag;
+	}
+
 	/* query ras capability from psp */
 	if (amdgpu_psp_get_ras_capability(&adev->psp))
 		goto init_ras_enabled_flag;
@@ -3925,7 +3985,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	}
 
 	/* Guest side doesn't need init ras feature */
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_ras_telemetry_en(adev))
 		return 0;
 
 	list_for_each_entry_safe(node, tmp, &adev->ras_list, node) {
@@ -4392,11 +4452,14 @@ bool amdgpu_ras_get_error_query_mode(struct amdgpu_device *adev,
 		return false;
 	}
 
-	if ((smu_funcs && smu_funcs->set_debug_mode) || (mca_funcs && mca_funcs->mca_set_debug_mode))
+	if (amdgpu_sriov_vf(adev)) {
+		*error_query_mode = AMDGPU_RAS_VIRT_ERROR_COUNT_QUERY;
+	} else if ((smu_funcs && smu_funcs->set_debug_mode) || (mca_funcs && mca_funcs->mca_set_debug_mode)) {
 		*error_query_mode =
 			(con->is_aca_debug_mode) ? AMDGPU_RAS_DIRECT_ERROR_QUERY : AMDGPU_RAS_FIRMWARE_ERROR_QUERY;
-	else
+	} else {
 		*error_query_mode = AMDGPU_RAS_DIRECT_ERROR_QUERY;
+	}
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 871b2d6278e0..6db772ecfee4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -365,6 +365,7 @@ enum amdgpu_ras_error_query_mode {
 	AMDGPU_RAS_INVALID_ERROR_QUERY		= 0,
 	AMDGPU_RAS_DIRECT_ERROR_QUERY		= 1,
 	AMDGPU_RAS_FIRMWARE_ERROR_QUERY		= 2,
+	AMDGPU_RAS_VIRT_ERROR_COUNT_QUERY	= 3,
 };
 
 /* ras error status reisger fields */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 5868b4a32ea6..8c89b69edc20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -413,3 +413,44 @@ void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev)
 			    &amdgpu_debugfs_sdma_sched_mask_fops);
 #endif
 }
+
+static ssize_t amdgpu_get_sdma_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->sdma.supported_reset);
+}
+
+static DEVICE_ATTR(sdma_reset_mask, 0444,
+		   amdgpu_get_sdma_reset_mask, NULL);
+
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (!amdgpu_gpu_recovery)
+		return r;
+
+	if (adev->sdma.num_instances) {
+		r = device_create_file(adev->dev, &dev_attr_sdma_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (!amdgpu_gpu_recovery)
+		return;
+
+	if (adev->sdma.num_instances)
+		device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index a37fcd9bb981..2db58b5812a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -116,6 +116,7 @@ struct amdgpu_sdma {
 	struct ras_common_if	*ras_if;
 	struct amdgpu_sdma_ras	*ras;
 	uint32_t		*ip_dump;
+	uint32_t 		supported_reset;
 };
 
 /*
@@ -176,4 +177,6 @@ void amdgpu_sdma_destroy_inst_ctx(struct amdgpu_device *adev,
         bool duplicate);
 int amdgpu_sdma_ras_sw_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_sdma_sched_mask_init(struct amdgpu_device *adev);
+int amdgpu_sdma_sysfs_reset_mask_init(struct amdgpu_device *adev);
+void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index bb7b9b2eaac1..896f3609b0ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -318,6 +318,9 @@ int amdgpu_umc_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 	if (r)
 		return r;
 
+	if (amdgpu_sriov_vf(adev))
+		return r;
+
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index b6397d3229e1..c704e9803e11 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -523,6 +523,9 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev)
 
 		adev->unique_id =
 			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->uuid;
+		adev->virt.ras_en_caps.all = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->ras_en_caps.all;
+		adev->virt.ras_telemetry_en_caps.all =
+			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->ras_telemetry_en_caps.all;
 		break;
 	default:
 		dev_err(adev->dev, "invalid pf2vf version: 0x%x\n", pf2vf_info->version);
@@ -703,6 +706,8 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 			adev->virt.fw_reserve.p_vf2pf =
 				(struct amd_sriov_msg_vf2pf_info_header *)
 				(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
+			adev->virt.fw_reserve.ras_telemetry =
+				(adev->mman.fw_vram_usage_va + (AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB << 10));
 		} else if (adev->mman.drv_vram_usage_va) {
 			adev->virt.fw_reserve.p_pf2vf =
 				(struct amd_sriov_msg_pf2vf_info_header *)
@@ -710,6 +715,8 @@ void amdgpu_virt_exchange_data(struct amdgpu_device *adev)
 			adev->virt.fw_reserve.p_vf2pf =
 				(struct amd_sriov_msg_vf2pf_info_header *)
 				(adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_VF2PF_OFFSET_KB << 10));
+			adev->virt.fw_reserve.ras_telemetry =
+				(adev->mman.drv_vram_usage_va + (AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB << 10));
 		}
 
 		amdgpu_virt_read_pf2vf_data(adev);
@@ -1144,3 +1151,185 @@ bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev)
 
 	return xnack_mode;
 }
+
+bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	if (!amdgpu_sriov_ras_caps_en(adev))
+		return false;
+
+	if (adev->virt.ras_en_caps.bits.block_umc)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__UMC);
+	if (adev->virt.ras_en_caps.bits.block_sdma)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SDMA);
+	if (adev->virt.ras_en_caps.bits.block_gfx)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__GFX);
+	if (adev->virt.ras_en_caps.bits.block_mmhub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MMHUB);
+	if (adev->virt.ras_en_caps.bits.block_athub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__ATHUB);
+	if (adev->virt.ras_en_caps.bits.block_pcie_bif)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__PCIE_BIF);
+	if (adev->virt.ras_en_caps.bits.block_hdp)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__HDP);
+	if (adev->virt.ras_en_caps.bits.block_xgmi_wafl)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__XGMI_WAFL);
+	if (adev->virt.ras_en_caps.bits.block_df)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__DF);
+	if (adev->virt.ras_en_caps.bits.block_smn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SMN);
+	if (adev->virt.ras_en_caps.bits.block_sem)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SEM);
+	if (adev->virt.ras_en_caps.bits.block_mp0)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP0);
+	if (adev->virt.ras_en_caps.bits.block_mp1)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP1);
+	if (adev->virt.ras_en_caps.bits.block_fuse)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__FUSE);
+	if (adev->virt.ras_en_caps.bits.block_mca)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MCA);
+	if (adev->virt.ras_en_caps.bits.block_vcn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__VCN);
+	if (adev->virt.ras_en_caps.bits.block_jpeg)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__JPEG);
+	if (adev->virt.ras_en_caps.bits.block_ih)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__IH);
+	if (adev->virt.ras_en_caps.bits.block_mpio)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MPIO);
+
+	if (adev->virt.ras_en_caps.bits.poison_propogation_mode)
+		con->poison_supported = true; /* Poison is handled by host */
+
+	return true;
+}
+
+static inline enum amd_sriov_ras_telemetry_gpu_block
+amdgpu_ras_block_to_sriov(struct amdgpu_device *adev, enum amdgpu_ras_block block) {
+	switch (block) {
+	case AMDGPU_RAS_BLOCK__UMC:
+		return RAS_TELEMETRY_GPU_BLOCK_UMC;
+	case AMDGPU_RAS_BLOCK__SDMA:
+		return RAS_TELEMETRY_GPU_BLOCK_SDMA;
+	case AMDGPU_RAS_BLOCK__GFX:
+		return RAS_TELEMETRY_GPU_BLOCK_GFX;
+	case AMDGPU_RAS_BLOCK__MMHUB:
+		return RAS_TELEMETRY_GPU_BLOCK_MMHUB;
+	case AMDGPU_RAS_BLOCK__ATHUB:
+		return RAS_TELEMETRY_GPU_BLOCK_ATHUB;
+	case AMDGPU_RAS_BLOCK__PCIE_BIF:
+		return RAS_TELEMETRY_GPU_BLOCK_PCIE_BIF;
+	case AMDGPU_RAS_BLOCK__HDP:
+		return RAS_TELEMETRY_GPU_BLOCK_HDP;
+	case AMDGPU_RAS_BLOCK__XGMI_WAFL:
+		return RAS_TELEMETRY_GPU_BLOCK_XGMI_WAFL;
+	case AMDGPU_RAS_BLOCK__DF:
+		return RAS_TELEMETRY_GPU_BLOCK_DF;
+	case AMDGPU_RAS_BLOCK__SMN:
+		return RAS_TELEMETRY_GPU_BLOCK_SMN;
+	case AMDGPU_RAS_BLOCK__SEM:
+		return RAS_TELEMETRY_GPU_BLOCK_SEM;
+	case AMDGPU_RAS_BLOCK__MP0:
+		return RAS_TELEMETRY_GPU_BLOCK_MP0;
+	case AMDGPU_RAS_BLOCK__MP1:
+		return RAS_TELEMETRY_GPU_BLOCK_MP1;
+	case AMDGPU_RAS_BLOCK__FUSE:
+		return RAS_TELEMETRY_GPU_BLOCK_FUSE;
+	case AMDGPU_RAS_BLOCK__MCA:
+		return RAS_TELEMETRY_GPU_BLOCK_MCA;
+	case AMDGPU_RAS_BLOCK__VCN:
+		return RAS_TELEMETRY_GPU_BLOCK_VCN;
+	case AMDGPU_RAS_BLOCK__JPEG:
+		return RAS_TELEMETRY_GPU_BLOCK_JPEG;
+	case AMDGPU_RAS_BLOCK__IH:
+		return RAS_TELEMETRY_GPU_BLOCK_IH;
+	case AMDGPU_RAS_BLOCK__MPIO:
+		return RAS_TELEMETRY_GPU_BLOCK_MPIO;
+	default:
+		dev_err(adev->dev, "Unsupported SRIOV RAS telemetry block 0x%x\n", block);
+		return RAS_TELEMETRY_GPU_BLOCK_COUNT;
+	}
+}
+
+static int amdgpu_virt_cache_host_error_counts(struct amdgpu_device *adev,
+					       struct amdsriov_ras_telemetry *host_telemetry)
+{
+	struct amd_sriov_ras_telemetry_error_count *tmp = NULL;
+	uint32_t checksum, used_size;
+
+	checksum = host_telemetry->header.checksum;
+	used_size = host_telemetry->header.used_size;
+
+	if (used_size > (AMD_SRIOV_RAS_TELEMETRY_SIZE_KB << 10))
+		return 0;
+
+	tmp = kmalloc(used_size, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	memcpy(tmp, &host_telemetry->body.error_count, used_size);
+
+	if (checksum != amd_sriov_msg_checksum(tmp, used_size, 0, 0))
+		goto out;
+
+	memcpy(&adev->virt.count_cache, tmp,
+	       min(used_size, sizeof(adev->virt.count_cache)));
+out:
+	kfree(tmp);
+
+	return 0;
+}
+
+static int amdgpu_virt_req_ras_err_count_internal(struct amdgpu_device *adev, bool force_update)
+{
+	struct amdgpu_virt *virt = &adev->virt;
+
+	/* Host allows 15 ras telemetry requests per 60 seconds. Afterwhich, the Host
+	 * will ignore incoming guest messages. Ratelimit the guest messages to
+	 * prevent guest self DOS.
+	 */
+	if (__ratelimit(&adev->virt.ras_telemetry_rs) || force_update) {
+		if (!virt->ops->req_ras_err_count(adev))
+			amdgpu_virt_cache_host_error_counts(adev,
+				adev->virt.fw_reserve.ras_telemetry);
+	}
+
+	return 0;
+}
+
+/* Bypass ACA interface and query ECC counts directly from host */
+int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block,
+				  struct ras_err_data *err_data)
+{
+	enum amd_sriov_ras_telemetry_gpu_block sriov_block;
+
+	sriov_block = amdgpu_ras_block_to_sriov(adev, block);
+
+	if (sriov_block >= RAS_TELEMETRY_GPU_BLOCK_COUNT ||
+	    !amdgpu_sriov_ras_telemetry_block_en(adev, sriov_block))
+		return -EOPNOTSUPP;
+
+	/* Host Access may be lost during reset, just return last cached data. */
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_req_ras_err_count_internal(adev, false);
+		up_read(&adev->reset_domain->sem);
+	}
+
+	err_data->ue_count = adev->virt.count_cache.block[sriov_block].ue_count;
+	err_data->ce_count = adev->virt.count_cache.block[sriov_block].ce_count;
+	err_data->de_count = adev->virt.count_cache.block[sriov_block].de_count;
+
+	return 0;
+}
+
+int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev)
+{
+	unsigned long ue_count, ce_count;
+
+	if (amdgpu_sriov_ras_telemetry_en(adev)) {
+		amdgpu_virt_req_ras_err_count_internal(adev, true);
+		amdgpu_ras_query_error_count(adev, &ce_count, &ue_count, NULL);
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b650a2032c42..5381b8d596e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -95,6 +95,7 @@ struct amdgpu_virt_ops {
 	void (*ras_poison_handler)(struct amdgpu_device *adev,
 					enum amdgpu_ras_block block);
 	bool (*rcvd_ras_intr)(struct amdgpu_device *adev);
+	int (*req_ras_err_count)(struct amdgpu_device *adev);
 };
 
 /*
@@ -103,6 +104,7 @@ struct amdgpu_virt_ops {
 struct amdgpu_virt_fw_reserve {
 	struct amd_sriov_msg_pf2vf_info_header *p_pf2vf;
 	struct amd_sriov_msg_vf2pf_info_header *p_vf2pf;
+	void *ras_telemetry;
 	unsigned int checksum_key;
 };
 
@@ -136,6 +138,8 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_VCN_RB_DECOUPLE = (1 << 7),
 	/* MES info */
 	AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8),
+	AMDGIM_FEATURE_RAS_CAPS = (1 << 9),
+	AMDGIM_FEATURE_RAS_TELEMETRY = (1 << 10),
 };
 
 enum AMDGIM_REG_ACCESS_FLAG {
@@ -276,6 +280,12 @@ struct amdgpu_virt {
 	uint32_t autoload_ucode_id;
 
 	struct mutex rlcg_reg_lock;
+
+	union amd_sriov_ras_caps ras_en_caps;
+	union amd_sriov_ras_caps ras_telemetry_en_caps;
+
+	struct ratelimit_state ras_telemetry_rs;
+	struct amd_sriov_ras_telemetry_error_count count_cache;
 };
 
 struct amdgpu_video_codec_info;
@@ -320,6 +330,15 @@ struct amdgpu_video_codec_info;
 #define amdgpu_sriov_vf_mmio_access_protection(adev) \
 ((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT)
 
+#define amdgpu_sriov_ras_caps_en(adev) \
+((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CAPS)
+
+#define amdgpu_sriov_ras_telemetry_en(adev) \
+(((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_TELEMETRY) && (adev)->virt.fw_reserve.ras_telemetry)
+
+#define amdgpu_sriov_ras_telemetry_block_en(adev, sriov_blk) \
+(amdgpu_sriov_ras_telemetry_en((adev)) && (adev)->virt.ras_telemetry_en_caps.all & BIT(sriov_blk))
+
 static inline bool is_virtual_machine(void)
 {
 #if defined(CONFIG_X86)
@@ -383,4 +402,8 @@ bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
 					  u32 acc_flags, u32 hwip,
 					  bool write, u32 *rlcg_flag);
 u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id);
+bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev);
+int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block,
+				  struct ras_err_data *err_data);
+int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 46713a158d90..3e6f9dfb61bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -377,6 +377,13 @@ static int vpe_sw_init(struct amdgpu_ip_block *ip_block)
 	ret = vpe_init_microcode(vpe);
 	if (ret)
 		goto out;
+
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->vpe.supported_reset =
+		 amdgpu_get_soft_full_reset_mask(&adev->vpe.ring);
+	ret = amdgpu_vpe_sysfs_reset_mask_init(adev);
+	if (ret)
+		goto out;
 out:
 	return ret;
 }
@@ -389,6 +396,7 @@ static int vpe_sw_fini(struct amdgpu_ip_block *ip_block)
 	release_firmware(vpe->fw);
 	vpe->fw = NULL;
 
+	amdgpu_vpe_sysfs_reset_mask_fini(adev);
 	vpe_ring_fini(vpe);
 
 	amdgpu_bo_free_kernel(&adev->vpe.cmdbuf_obj,
@@ -865,6 +873,41 @@ static void vpe_ring_end_use(struct amdgpu_ring *ring)
 	schedule_delayed_work(&adev->vpe.idle_work, VPE_IDLE_TIMEOUT);
 }
 
+static ssize_t amdgpu_get_vpe_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->vpe.supported_reset);
+}
+
+static DEVICE_ATTR(vpe_reset_mask, 0444,
+		   amdgpu_get_vpe_reset_mask, NULL);
+
+int amdgpu_vpe_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->vpe.num_instances) {
+		r = device_create_file(adev->dev, &dev_attr_vpe_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+void amdgpu_vpe_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (adev->vpe.num_instances)
+		device_remove_file(adev->dev, &dev_attr_vpe_reset_mask);
+}
+
 static const struct amdgpu_ring_funcs vpe_ring_funcs = {
 	.type = AMDGPU_RING_TYPE_VPE,
 	.align_mask = 0xf,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.h
index 231d86d0953e..695da740a97e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.h
@@ -79,6 +79,7 @@ struct amdgpu_vpe {
 
 	uint32_t			num_instances;
 	bool				collaborate_mode;
+	uint32_t			supported_reset;
 };
 
 int amdgpu_vpe_psp_update_sram(struct amdgpu_device *adev);
@@ -86,6 +87,8 @@ int amdgpu_vpe_init_microcode(struct amdgpu_vpe *vpe);
 int amdgpu_vpe_ring_init(struct amdgpu_vpe *vpe);
 int amdgpu_vpe_ring_fini(struct amdgpu_vpe *vpe);
 int amdgpu_vpe_configure_dpm(struct amdgpu_vpe *vpe);
+void amdgpu_vpe_sysfs_reset_mask_fini(struct amdgpu_device *adev);
+int amdgpu_vpe_sysfs_reset_mask_init(struct amdgpu_device *adev);
 
 #define vpe_ring_init(vpe) ((vpe)->funcs->ring_init ? (vpe)->funcs->ring_init((vpe)) : 0)
 #define vpe_ring_start(vpe) ((vpe)->funcs->ring_start ? (vpe)->funcs->ring_start((vpe)) : 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index 83a16918ea76..e209b5e101df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -471,6 +471,16 @@ static const char *xcp_desc[] = {
 	[AMDGPU_CPX_PARTITION_MODE] = "CPX",
 };
 
+static const char *nps_desc[] = {
+	[UNKNOWN_MEMORY_PARTITION_MODE] = "UNKNOWN",
+	[AMDGPU_NPS1_PARTITION_MODE] = "NPS1",
+	[AMDGPU_NPS2_PARTITION_MODE] = "NPS2",
+	[AMDGPU_NPS3_PARTITION_MODE] = "NPS3",
+	[AMDGPU_NPS4_PARTITION_MODE] = "NPS4",
+	[AMDGPU_NPS6_PARTITION_MODE] = "NPS6",
+	[AMDGPU_NPS8_PARTITION_MODE] = "NPS8",
+};
+
 ATTRIBUTE_GROUPS(xcp_cfg_res_sysfs);
 
 #define to_xcp_attr(x) \
@@ -540,6 +550,26 @@ static ssize_t supported_xcp_configs_show(struct kobject *kobj,
 	return size;
 }
 
+static ssize_t supported_nps_configs_show(struct kobject *kobj,
+					  struct kobj_attribute *attr, char *buf)
+{
+	struct amdgpu_xcp_cfg *xcp_cfg = to_xcp_cfg(kobj);
+	int size = 0, mode;
+	char *sep = "";
+
+	if (!xcp_cfg || !xcp_cfg->compatible_nps_modes)
+		return sysfs_emit(buf, "Not supported\n");
+
+	for_each_inst(mode, xcp_cfg->compatible_nps_modes) {
+		size += sysfs_emit_at(buf, size, "%s%s", sep, nps_desc[mode]);
+		sep = ", ";
+	}
+
+	size += sysfs_emit_at(buf, size, "\n");
+
+	return size;
+}
+
 static ssize_t xcp_config_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *buf)
 {
@@ -596,6 +626,9 @@ static const struct kobj_type xcp_cfg_sysfs_ktype = {
 static struct kobj_attribute supp_part_sysfs_mode =
 	__ATTR_RO(supported_xcp_configs);
 
+static struct kobj_attribute supp_nps_sysfs_mode =
+	__ATTR_RO(supported_nps_configs);
+
 static const struct attribute *xcp_attrs[] = {
 	&supp_part_sysfs_mode.attr,
 	&xcp_cfg_sysfs_mode.attr,
@@ -625,13 +658,24 @@ void amdgpu_xcp_cfg_sysfs_init(struct amdgpu_device *adev)
 	if (r)
 		goto err1;
 
+	if (adev->gmc.supported_nps_modes != 0) {
+		r = sysfs_create_file(&xcp_cfg->kobj, &supp_nps_sysfs_mode.attr);
+		if (r) {
+			sysfs_remove_files(&xcp_cfg->kobj, xcp_attrs);
+			goto err1;
+		}
+	}
+
 	mode = (xcp_cfg->xcp_mgr->mode ==
 		AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE) ?
 		       AMDGPU_SPX_PARTITION_MODE :
 		       xcp_cfg->xcp_mgr->mode;
 	r = amdgpu_xcp_get_res_info(xcp_cfg->xcp_mgr, mode, xcp_cfg);
-	if (r)
+	if (r) {
+		sysfs_remove_file(&xcp_cfg->kobj, &supp_nps_sysfs_mode.attr);
+		sysfs_remove_files(&xcp_cfg->kobj, xcp_attrs);
 		goto err1;
+	}
 
 	xcp_cfg->mode = mode;
 	for (i = 0; i < xcp_cfg->num_res; i++) {
@@ -653,6 +697,7 @@ err:
 		kobject_put(&xcp_res->kobj);
 	}
 
+	sysfs_remove_file(&xcp_cfg->kobj, &supp_nps_sysfs_mode.attr);
 	sysfs_remove_files(&xcp_cfg->kobj, xcp_attrs);
 err1:
 	kobject_put(&xcp_cfg->kobj);
@@ -673,6 +718,7 @@ void amdgpu_xcp_cfg_sysfs_fini(struct amdgpu_device *adev)
 		kobject_put(&xcp_res->kobj);
 	}
 
+	sysfs_remove_file(&xcp_cfg->kobj, &supp_nps_sysfs_mode.attr);
 	sysfs_remove_files(&xcp_cfg->kobj, xcp_attrs);
 	kobject_put(&xcp_cfg->kobj);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
index 6e9eeaeb3de1..b4f9c2f4e92c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -28,17 +28,21 @@
 #define AMD_SRIOV_MSG_VBIOS_SIZE_KB	     64
 #define AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB AMD_SRIOV_MSG_VBIOS_SIZE_KB
 #define AMD_SRIOV_MSG_DATAEXCHANGE_SIZE_KB   4
-
+#define AMD_SRIOV_MSG_TMR_OFFSET_KB	     2048
+#define AMD_SRIOV_MSG_BAD_PAGE_SIZE_KB	     2
+#define AMD_SRIOV_RAS_TELEMETRY_SIZE_KB	     64
 /*
  * layout
- * 0           64KB        65KB        66KB
- * |   VBIOS   |   PF2VF   |   VF2PF   |   Bad Page   | ...
- * |   64KB    |   1KB     |   1KB     |
+ * 0           64KB        65KB        66KB           68KB                   132KB
+ * |   VBIOS   |   PF2VF   |   VF2PF   |   Bad Page   | RAS Telemetry Region | ...
+ * |   64KB    |   1KB     |   1KB     |   2KB        | 64KB                 | ...
  */
+
 #define AMD_SRIOV_MSG_SIZE_KB                   1
 #define AMD_SRIOV_MSG_PF2VF_OFFSET_KB           AMD_SRIOV_MSG_DATAEXCHANGE_OFFSET_KB
 #define AMD_SRIOV_MSG_VF2PF_OFFSET_KB           (AMD_SRIOV_MSG_PF2VF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
 #define AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB        (AMD_SRIOV_MSG_VF2PF_OFFSET_KB + AMD_SRIOV_MSG_SIZE_KB)
+#define AMD_SRIOV_MSG_RAS_TELEMETRY_OFFSET_KB   (AMD_SRIOV_MSG_BAD_PAGE_OFFSET_KB + AMD_SRIOV_MSG_BAD_PAGE_SIZE_KB)
 
 /*
  * PF2VF history log:
@@ -86,30 +90,59 @@ enum amd_sriov_ucode_engine_id {
 
 union amd_sriov_msg_feature_flags {
 	struct {
-		uint32_t error_log_collect : 1;
-		uint32_t host_load_ucodes  : 1;
-		uint32_t host_flr_vramlost : 1;
-		uint32_t mm_bw_management  : 1;
-		uint32_t pp_one_vf_mode    : 1;
-		uint32_t reg_indirect_acc  : 1;
-		uint32_t av1_support       : 1;
-		uint32_t vcn_rb_decouple   : 1;
-		uint32_t mes_info_enable   : 1;
-		uint32_t reserved          : 23;
+		uint32_t error_log_collect	: 1;
+		uint32_t host_load_ucodes	: 1;
+		uint32_t host_flr_vramlost	: 1;
+		uint32_t mm_bw_management	: 1;
+		uint32_t pp_one_vf_mode		: 1;
+		uint32_t reg_indirect_acc	: 1;
+		uint32_t av1_support		: 1;
+		uint32_t vcn_rb_decouple 	: 1;
+		uint32_t mes_info_dump_enable	: 1;
+		uint32_t ras_caps		: 1;
+		uint32_t ras_telemetry		: 1;
+		uint32_t reserved		: 21;
 	} flags;
 	uint32_t all;
 };
 
 union amd_sriov_reg_access_flags {
 	struct {
-		uint32_t vf_reg_access_ih 	 : 1;
-		uint32_t vf_reg_access_mmhub : 1;
-		uint32_t vf_reg_access_gc 	 : 1;
-		uint32_t reserved	         : 29;
+		uint32_t vf_reg_access_ih	: 1;
+		uint32_t vf_reg_access_mmhub	: 1;
+		uint32_t vf_reg_access_gc	: 1;
+		uint32_t reserved		: 29;
 	} flags;
 	uint32_t all;
 };
 
+union amd_sriov_ras_caps {
+	struct {
+		uint64_t block_umc			: 1;
+		uint64_t block_sdma			: 1;
+		uint64_t block_gfx			: 1;
+		uint64_t block_mmhub			: 1;
+		uint64_t block_athub			: 1;
+		uint64_t block_pcie_bif			: 1;
+		uint64_t block_hdp			: 1;
+		uint64_t block_xgmi_wafl		: 1;
+		uint64_t block_df			: 1;
+		uint64_t block_smn			: 1;
+		uint64_t block_sem			: 1;
+		uint64_t block_mp0			: 1;
+		uint64_t block_mp1			: 1;
+		uint64_t block_fuse			: 1;
+		uint64_t block_mca			: 1;
+		uint64_t block_vcn			: 1;
+		uint64_t block_jpeg			: 1;
+		uint64_t block_ih			: 1;
+		uint64_t block_mpio			: 1;
+		uint64_t poison_propogation_mode	: 1;
+		uint64_t reserved			: 44;
+	} bits;
+	uint64_t all;
+};
+
 union amd_sriov_msg_os_info {
 	struct {
 		uint32_t windows  : 1;
@@ -158,7 +191,7 @@ struct amd_sriov_msg_pf2vf_info_header {
 	uint32_t reserved[2];
 };
 
-#define AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE (49)
+#define AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE (55)
 struct amd_sriov_msg_pf2vf_info {
 	/* header contains size and version */
 	struct amd_sriov_msg_pf2vf_info_header header;
@@ -211,6 +244,12 @@ struct amd_sriov_msg_pf2vf_info {
 	uint32_t pcie_atomic_ops_support_flags;
 	/* Portion of GPU memory occupied by VF.  MAX value is 65535, but set to uint32_t to maintain alignment with reserved size */
 	uint32_t gpu_capacity;
+	/* vf bdf on host pci tree for debug only */
+	uint32_t bdf_on_host;
+	uint32_t more_bp;	//Reserved for future use.
+	union amd_sriov_ras_caps ras_en_caps;
+	union amd_sriov_ras_caps ras_telemetry_en_caps;
+
 	/* reserved */
 	uint32_t reserved[256 - AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE];
 } __packed;
@@ -283,8 +322,12 @@ enum amd_sriov_mailbox_request_message {
 	MB_REQ_MSG_REL_GPU_FINI_ACCESS,
 	MB_REQ_MSG_REQ_GPU_RESET_ACCESS,
 	MB_REQ_MSG_REQ_GPU_INIT_DATA,
+	MB_REQ_MSG_PSP_VF_CMD_RELAY,
 
 	MB_REQ_MSG_LOG_VF_ERROR = 200,
+	MB_REQ_MSG_READY_TO_RESET = 201,
+	MB_REQ_MSG_RAS_POISON = 202,
+	MB_REQ_RAS_ERROR_COUNT = 203,
 };
 
 /* mailbox message send from host to guest  */
@@ -297,10 +340,60 @@ enum amd_sriov_mailbox_response_message {
 	MB_RES_MSG_FAIL,
 	MB_RES_MSG_QUERY_ALIVE,
 	MB_RES_MSG_GPU_INIT_DATA_READY,
+	MB_RES_MSG_RAS_ERROR_COUNT_READY = 11,
 
 	MB_RES_MSG_TEXT_MESSAGE = 255
 };
 
+enum amd_sriov_ras_telemetry_gpu_block {
+	RAS_TELEMETRY_GPU_BLOCK_UMC		= 0,
+	RAS_TELEMETRY_GPU_BLOCK_SDMA		= 1,
+	RAS_TELEMETRY_GPU_BLOCK_GFX		= 2,
+	RAS_TELEMETRY_GPU_BLOCK_MMHUB		= 3,
+	RAS_TELEMETRY_GPU_BLOCK_ATHUB		= 4,
+	RAS_TELEMETRY_GPU_BLOCK_PCIE_BIF	= 5,
+	RAS_TELEMETRY_GPU_BLOCK_HDP		= 6,
+	RAS_TELEMETRY_GPU_BLOCK_XGMI_WAFL	= 7,
+	RAS_TELEMETRY_GPU_BLOCK_DF		= 8,
+	RAS_TELEMETRY_GPU_BLOCK_SMN		= 9,
+	RAS_TELEMETRY_GPU_BLOCK_SEM		= 10,
+	RAS_TELEMETRY_GPU_BLOCK_MP0		= 11,
+	RAS_TELEMETRY_GPU_BLOCK_MP1		= 12,
+	RAS_TELEMETRY_GPU_BLOCK_FUSE		= 13,
+	RAS_TELEMETRY_GPU_BLOCK_MCA		= 14,
+	RAS_TELEMETRY_GPU_BLOCK_VCN		= 15,
+	RAS_TELEMETRY_GPU_BLOCK_JPEG		= 16,
+	RAS_TELEMETRY_GPU_BLOCK_IH		= 17,
+	RAS_TELEMETRY_GPU_BLOCK_MPIO		= 18,
+	RAS_TELEMETRY_GPU_BLOCK_COUNT		= 19,
+};
+
+struct amd_sriov_ras_telemetry_header {
+	uint32_t checksum;
+	uint32_t used_size;
+	uint32_t reserved[2];
+};
+
+struct amd_sriov_ras_telemetry_error_count {
+	struct {
+		uint32_t ce_count;
+		uint32_t ue_count;
+		uint32_t de_count;
+		uint32_t ce_overflow_count;
+		uint32_t ue_overflow_count;
+		uint32_t de_overflow_count;
+		uint32_t reserved[6];
+	} block[RAS_TELEMETRY_GPU_BLOCK_COUNT];
+};
+
+struct amdsriov_ras_telemetry {
+	struct amd_sriov_ras_telemetry_header header;
+
+	union {
+		struct amd_sriov_ras_telemetry_error_count error_count;
+	} body;
+};
+
 /* version data stored in MAILBOX_MSGBUF_RCV_DW1 for future expansion */
 enum amd_sriov_gpu_init_data_version {
 	GPU_INIT_DATA_READY_V1 = 1,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d1a18ca584dd..24dce803a829 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4825,6 +4825,11 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
 			}
 		}
 	}
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
 
 	r = amdgpu_gfx_kiq_init(adev, GFX10_MEC_HPD_SIZE, 0);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 62e4c446793d..2ae058a224f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1580,6 +1580,8 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
 		adev->gfx.cleaner_shader_ptr = gfx_11_0_3_cleaner_shader_hex;
 		adev->gfx.cleaner_shader_size = sizeof(gfx_11_0_3_cleaner_shader_hex);
@@ -1691,6 +1693,24 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(11, 0, 0):
+	case IP_VERSION(11, 0, 2):
+	case IP_VERSION(11, 0, 3):
+		if ((adev->gfx.me_fw_version >= 2280) &&
+			    (adev->gfx.mec_fw_version >= 2410)) {
+				adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+				adev->gfx.gfx_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		}
+		break;
+	default:
+		break;
+	}
+
 	if (!adev->enable_mes_kiq) {
 		r = amdgpu_gfx_kiq_init(adev, GFX11_MEC_HPD_SIZE, 0);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 1b99f90cd193..fe7c48f2fb2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -1437,6 +1437,12 @@ static int gfx_v12_0_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	if (!adev->enable_mes_kiq) {
 		r = amdgpu_gfx_kiq_init(adev, GFX12_MEC_HPD_SIZE, 0);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 480c41ee947e..b7006c41e270 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4823,6 +4823,13 @@ static int gfx_v8_0_kcq_disable(struct amdgpu_device *adev)
 		amdgpu_ring_write(kiq_ring, 0);
 		amdgpu_ring_write(kiq_ring, 0);
 	}
+	/* Submit unmap queue packet */
+	amdgpu_ring_commit(kiq_ring);
+	/*
+	 * Ring test will do a basic scratch register change check. Just run
+	 * this to ensure that unmap queues that is submitted before got
+	 * processed successfully before returning.
+	 */
 	r = amdgpu_ring_test_helper(kiq_ring);
 	if (r)
 		DRM_ERROR("KCQ disable failed\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index a880dce16ae2..0b6f09f2cc9b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2374,6 +2374,12 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->gfx.gfx_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.gfx_ring[0]);
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+
 	r = amdgpu_gfx_kiq_init(adev, GFX9_MEC_HPD_SIZE, 0);
 	if (r) {
 		DRM_ERROR("Failed to init KIQ BOs!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 983088805c3a..e2b3dda57030 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -1157,6 +1157,19 @@ static int gfx_v9_4_3_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->gfx.compute_supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->gfx.compute_ring[0]);
+	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(9, 4, 3):
+	case IP_VERSION(9, 4, 4):
+		if (adev->gfx.mec_fw_version >= 155) {
+			adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+			adev->gfx.compute_supported_reset |= AMDGPU_RESET_TYPE_PER_PIPE;
+		}
+		break;
+	default:
+		break;
+	}
 	r = gfx_v9_4_3_gpu_early_init(adev);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f43ded8a0aab..50c5da3020cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1130,8 +1130,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 					 uint64_t *flags)
 {
 	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM;
-	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | AMDGPU_GEM_CREATE_EXT_COHERENT);
+	bool is_vram = bo->tbo.resource &&
+		bo->tbo.resource->mem_type == TTM_PL_VRAM;
+	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT |
+				     AMDGPU_GEM_CREATE_EXT_COHERENT);
 	bool ext_coherent = bo->flags & AMDGPU_GEM_CREATE_EXT_COHERENT;
 	bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED;
 	struct amdgpu_vm *vm = mapping->bo_va->base.vm;
@@ -1139,6 +1141,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 	bool snoop = false;
 	bool is_local;
 
+	dma_resv_assert_held(bo->tbo.base.resv);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 1):
 	case IP_VERSION(9, 4, 2):
@@ -1257,9 +1261,8 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
-	if (bo && bo->tbo.resource)
-		gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.bo,
-					     mapping, flags);
+	if ((*flags & AMDGPU_PTE_VALID) && bo)
+		gmc_v9_0_get_coherence_flags(adev, bo, mapping, flags);
 }
 
 static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index 89953c0f5f1f..193dfac5dc76 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -123,6 +123,12 @@ static int jpeg_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 	r = amdgpu_jpeg_ras_sw_init(adev);
 	if (r)
 		return r;
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->jpeg.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
 
 	return 0;
 }
@@ -143,6 +149,7 @@ static int jpeg_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 6917e4a8e96a..67b51bcbacd1 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -159,6 +159,13 @@ static int jpeg_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->jpeg.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -178,6 +185,7 @@ static int jpeg_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index f3cce523f3cb..b48e2412e6cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -153,6 +153,13 @@ static int jpeg_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->jpeg.inst[i].external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, i, regUVD_JPEG_PITCH);
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->jpeg.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -172,6 +179,7 @@ static int jpeg_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
index 06840d1dae79..686f9605239d 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
@@ -100,6 +100,12 @@ static int jpeg_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->jpeg.internal.jpeg_pitch[0] = regUVD_JPEG_PITCH_INTERNAL_OFFSET;
 	adev->jpeg.inst->external.jpeg_pitch[0] = SOC15_REG_OFFSET(JPEG, 0, regUVD_JPEG_PITCH);
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->jpeg.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->jpeg.inst[0].ring_dec[0]);
+	r = amdgpu_jpeg_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
 	return 0;
 }
 
@@ -119,6 +125,7 @@ static int jpeg_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_jpeg_sysfs_reset_mask_fini(adev);
 	r = amdgpu_jpeg_sw_fini(adev);
 
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 0e758ebf2372..9c905b9e9376 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -644,6 +644,18 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes,
 				sizeof(misc_pkt.set_shader_debugger.tcp_watch_cntl));
 		misc_pkt.set_shader_debugger.trap_en = input->set_shader_debugger.trap_en;
 		break;
+	case MES_MISC_OP_CHANGE_CONFIG:
+		if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) {
+			dev_err(mes->adev->dev, "MES FW versoin must be larger than 0x63 to support limit single process feature.\n");
+			return -EINVAL;
+		}
+		misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG;
+		misc_pkt.change_config.opcode =
+				MESAPI_MISC__CHANGE_CONFIG_OPTION_LIMIT_SINGLE_PROCESS;
+		misc_pkt.change_config.option.bits.limit_single_process =
+				input->change_config.option.limit_single_process;
+		break;
+
 	default:
 		DRM_ERROR("unsupported misc op (%d) \n", input->op);
 		return -EINVAL;
@@ -708,6 +720,9 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 					mes->event_log_gpu_addr;
 	}
 
+	if (enforce_isolation)
+		mes_set_hw_res_pkt.limit_single_process = 1;
+
 	return mes_v11_0_submit_pkt_and_poll_completion(mes,
 			&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
 			offsetof(union MESAPI_SET_HW_RESOURCES, api_status));
@@ -908,6 +923,16 @@ static void mes_v11_0_enable(struct amdgpu_device *adev, bool enable)
 	uint32_t pipe, data = 0;
 
 	if (enable) {
+		if (amdgpu_mes_log_enable) {
+			WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO,
+				lower_32_bits(adev->mes.event_log_gpu_addr + AMDGPU_MES_LOG_BUFFER_SIZE));
+			WREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI,
+				upper_32_bits(adev->mes.event_log_gpu_addr + AMDGPU_MES_LOG_BUFFER_SIZE));
+			dev_info(adev->dev, "Setup CP MES MSCRATCH address : 0x%x. 0x%x\n",
+				RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_HI),
+				RREG32_SOC15(GC, 0, regCP_MES_MSCRATCH_LO));
+		}
+
 		data = RREG32_SOC15(GC, 0, regCP_MES_CNTL);
 		data = REG_SET_FIELD(data, CP_MES_CNTL, MES_PIPE0_RESET, 1);
 		data = REG_SET_FIELD(data, CP_MES_CNTL,
@@ -1370,7 +1395,7 @@ static int mes_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	adev->mes.kiq_hw_init = &mes_v11_0_kiq_hw_init;
 	adev->mes.kiq_hw_fini = &mes_v11_0_kiq_hw_fini;
 
-	adev->mes.event_log_size = AMDGPU_MES_LOG_BUFFER_SIZE;
+	adev->mes.event_log_size = AMDGPU_MES_LOG_BUFFER_SIZE + AMDGPU_MES_MSCRATCH_SIZE;
 
 	r = amdgpu_mes_init(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 3daa8862e622..9ecc5d61e49b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -531,6 +531,14 @@ static int mes_v12_0_misc_op(struct amdgpu_mes *mes,
 				sizeof(misc_pkt.set_shader_debugger.tcp_watch_cntl));
 		misc_pkt.set_shader_debugger.trap_en = input->set_shader_debugger.trap_en;
 		break;
+	case MES_MISC_OP_CHANGE_CONFIG:
+		misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG;
+		misc_pkt.change_config.opcode =
+				MESAPI_MISC__CHANGE_CONFIG_OPTION_LIMIT_SINGLE_PROCESS;
+		misc_pkt.change_config.option.bits.limit_single_process =
+				input->change_config.option.limit_single_process;
+		break;
+
 	default:
 		DRM_ERROR("unsupported misc op (%d) \n", input->op);
 		return -EINVAL;
@@ -550,7 +558,7 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_1_pkt.header.type = MES_API_TYPE_SCHEDULER;
 	mes_set_hw_res_1_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC_1;
 	mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
-	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100;
+	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa;
 
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
 			&mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt),
@@ -624,6 +632,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr = mes->event_log_gpu_addr + pipe * AMDGPU_MES_LOG_BUFFER_SIZE;
 	}
 
+	if (enforce_isolation)
+		mes_set_hw_res_pkt.limit_single_process = 1;
+
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
 			&mes_set_hw_res_pkt, sizeof(mes_set_hw_res_pkt),
 			offsetof(union MESAPI_SET_HW_RESOURCES, api_status));
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index f47bd7ada4d7..4dcb72d1bdda 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -61,15 +61,18 @@ static enum idh_event xgpu_nv_mailbox_peek_msg(struct amdgpu_device *adev)
 static int xgpu_nv_mailbox_rcv_msg(struct amdgpu_device *adev,
 				   enum idh_event event)
 {
+	int r = 0;
 	u32 reg;
 
 	reg = RREG32_NO_KIQ(mmMAILBOX_MSGBUF_RCV_DW0);
-	if (reg != event)
+	if (reg == IDH_FAIL)
+		r = -EINVAL;
+	else if (reg != event)
 		return -ENOENT;
 
 	xgpu_nv_mailbox_send_ack(adev);
 
-	return 0;
+	return r;
 }
 
 static uint8_t xgpu_nv_peek_ack(struct amdgpu_device *adev)
@@ -178,6 +181,9 @@ send_request:
 		if (data1 != 0)
 			event = IDH_RAS_POISON_READY;
 		break;
+	case IDH_REQ_RAS_ERROR_COUNT:
+		event = IDH_RAS_ERROR_COUNT_READY;
+		break;
 	default:
 		break;
 	}
@@ -456,6 +462,11 @@ static bool xgpu_nv_rcvd_ras_intr(struct amdgpu_device *adev)
 	return (msg == IDH_RAS_ERROR_DETECTED || msg == 0xFFFFFFFF);
 }
 
+static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev)
+{
+	return xgpu_nv_send_access_requests(adev, IDH_REQ_RAS_ERROR_COUNT);
+}
+
 const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.req_full_gpu	= xgpu_nv_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_nv_release_full_gpu_access,
@@ -466,4 +477,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.trans_msg = xgpu_nv_mailbox_trans_msg,
 	.ras_poison_handler = xgpu_nv_ras_poison_handler,
 	.rcvd_ras_intr = xgpu_nv_rcvd_ras_intr,
+	.req_ras_err_count = xgpu_nv_req_ras_err_count,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
index 1d099ffb3a5a..9d61d76e1bf9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
@@ -40,6 +40,7 @@ enum idh_request {
 	IDH_LOG_VF_ERROR	= 200,
 	IDH_READY_TO_RESET 	= 201,
 	IDH_RAS_POISON	= 202,
+	IDH_REQ_RAS_ERROR_COUNT = 203,
 };
 
 enum idh_event {
@@ -54,6 +55,8 @@ enum idh_event {
 	IDH_RAS_POISON_READY,
 	IDH_PF_SOFT_FLR_NOTIFICATION,
 	IDH_RAS_ERROR_DETECTED,
+	IDH_RAS_ERROR_COUNT_READY = 11,
+
 	IDH_TEXT_MESSAGE = 255,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index fb37e354a9d5..1ac730328516 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -247,6 +247,12 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data);
 
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(7, 7, 0):
+		data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23);
+		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data);
+		break;
+	}
 }
 
 static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 6b72169be8f8..3bad565ded73 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -67,8 +67,8 @@ static const struct amd_ip_funcs nv_common_ip_funcs;
 
 /* Navi */
 static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_encode = {
@@ -94,8 +94,8 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = {
 
 /* Sienna Cichlid */
 static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs sc_video_codecs_encode = {
@@ -136,8 +136,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = {
 
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 9c7cea0890c9..a38553f38fdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1430,6 +1430,10 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+
 	if (amdgpu_sdma_ras_sw_init(adev)) {
 		dev_err(adev->dev, "fail to initialize sdma ras block\n");
 		return -EINVAL;
@@ -1442,6 +1446,10 @@ static int sdma_v4_4_2_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1456,6 +1464,7 @@ static int sdma_v4_4_2_sw_fini(struct amdgpu_ip_block *ip_block)
 			amdgpu_ring_fini(&adev->sdma.instance[i].page);
 	}
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 2) ||
 	    amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 5))
 		amdgpu_sdma_destroy_inst_ctx(adev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index d31c4860933f..fa9b40934957 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1452,6 +1452,19 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 5):
+		if (adev->sdma.instance[0].fw_version >= 35)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	/* Allocate memory for SDMA IP Dump buffer */
 	ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
 	if (ptr)
@@ -1459,6 +1472,10 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1470,6 +1487,7 @@ static int sdma_v5_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, false);
 
 	kfree(adev->sdma.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index ffa8c62ac101..ba5160399ab2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1357,6 +1357,24 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 2):
+	case IP_VERSION(5, 2, 3):
+	case IP_VERSION(5, 2, 4):
+		if (adev->sdma.instance[0].fw_version >= 76)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	case IP_VERSION(5, 2, 5):
+		if (adev->sdma.instance[0].fw_version >= 34)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	/* Allocate memory for SDMA IP Dump buffer */
 	ptr = kcalloc(adev->sdma.num_instances * reg_count, sizeof(uint32_t), GFP_KERNEL);
 	if (ptr)
@@ -1364,6 +1382,10 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1375,6 +1397,7 @@ static int sdma_v5_2_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, true);
 
 	kfree(adev->sdma.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 5635f2d84090..d46128b0ec92 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1350,6 +1350,19 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	adev->sdma.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->sdma.instance[0].ring);
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(6, 0, 0):
+	case IP_VERSION(6, 0, 2):
+	case IP_VERSION(6, 0, 3):
+		if (adev->sdma.instance[0].fw_version >= 21)
+			adev->sdma.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
 	if (amdgpu_sdma_ras_sw_init(adev)) {
 		dev_err(adev->dev, "Failed to initialize sdma ras block!\n");
 		return -EINVAL;
@@ -1362,6 +1375,10 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
+	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -1373,6 +1390,7 @@ static int sdma_v6_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	for (i = 0; i < adev->sdma.num_instances; i++)
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
 
+	amdgpu_sdma_sysfs_reset_mask_fini(adev);
 	amdgpu_sdma_destroy_inst_ctx(adev, true);
 
 	kfree(adev->sdma.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 533b4b2b432d..ede072758dab 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -90,8 +90,8 @@ static const struct amd_ip_funcs soc15_common_ip_funcs;
 /* Vega, Raven, Arcturus */
 static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_encode =
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 93fbb3354720..d6999835918f 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -49,13 +49,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
@@ -96,14 +96,14 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = {
 
 /* SRIOV SOC21, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index 3af10ef4b793..be96de92b2f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -48,7 +48,7 @@
 static const struct amd_ip_funcs soc24_common_ip_funcs;
 
 static const struct amdgpu_video_codec_info vcn_5_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 0d5c94bfc0ef..cf808a153fce 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -95,6 +95,13 @@ static void vcn_v4_0_3_unified_ring_set_wptr(struct amdgpu_ring *ring);
 static void vcn_v4_0_3_set_ras_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_enable_ras(struct amdgpu_device *adev,
 				  int inst_idx, bool indirect);
+
+static inline bool vcn_v4_0_3_normalizn_reqd(struct amdgpu_device *adev)
+{
+	return (amdgpu_sriov_vf(adev) ||
+		(amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)));
+}
+
 /**
  * vcn_v4_0_3_early_init - set function pointers
  *
@@ -1428,8 +1435,8 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
 static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 				uint32_t val, uint32_t mask)
 {
-	/* For VF, only local offsets should be used */
-	if (amdgpu_sriov_vf(ring->adev))
+	/* Use normalized offsets when required */
+	if (vcn_v4_0_3_normalizn_reqd(ring->adev))
 		reg = NORMALIZE_VCN_REG_OFFSET(reg);
 
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
@@ -1440,8 +1447,8 @@ static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t
 
 static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
 {
-	/* For VF, only local offsets should be used */
-	if (amdgpu_sriov_vf(ring->adev))
+	/* Use normalized offsets when required */
+	if (vcn_v4_0_3_normalizn_reqd(ring->adev))
 		reg = NORMALIZE_VCN_REG_OFFSET(reg);
 
 	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index b3fa54c0514e..a83505815d39 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -136,15 +136,15 @@ static const struct amdgpu_video_codec_info polaris_video_codecs_encode_array[]
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
 		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 0,
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
 		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
+		.max_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 0,
 	},
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 348925254bff..956198da7859 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -534,7 +534,8 @@ static void kfd_cwsr_init(struct kfd_dev *kfd)
 			kfd->cwsr_isa = cwsr_trap_gfx11_hex;
 			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx11_hex);
 		} else {
-			BUILD_BUG_ON(sizeof(cwsr_trap_gfx12_hex) > PAGE_SIZE);
+			BUILD_BUG_ON(sizeof(cwsr_trap_gfx12_hex)
+					     > KFD_CWSR_TMA_OFFSET);
 			kfd->cwsr_isa = cwsr_trap_gfx12_hex;
 			kfd->cwsr_isa_size = sizeof(cwsr_trap_gfx12_hex);
 		}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 38c19dc8311d..c79fe9069e22 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -202,6 +202,8 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	int r, queue_type;
 	uint64_t wptr_addr_off;
 
+	if (!dqm->sched_running || dqm->sched_halt)
+		return 0;
 	if (!down_read_trylock(&adev->reset_domain->sem))
 		return -EIO;
 
@@ -270,6 +272,8 @@ static int remove_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	int r;
 	struct mes_remove_queue_input queue_input;
 
+	if (!dqm->sched_running || dqm->sched_halt)
+		return 0;
 	if (!down_read_trylock(&adev->reset_domain->sem))
 		return -EIO;
 
@@ -292,7 +296,7 @@ static int remove_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	return r;
 }
 
-static int remove_all_queues_mes(struct device_queue_manager *dqm)
+static int remove_all_kfd_queues_mes(struct device_queue_manager *dqm)
 {
 	struct device_process_node *cur;
 	struct device *dev = dqm->dev->adev->dev;
@@ -319,6 +323,33 @@ static int remove_all_queues_mes(struct device_queue_manager *dqm)
 	return retval;
 }
 
+static int add_all_kfd_queues_mes(struct device_queue_manager *dqm)
+{
+	struct device_process_node *cur;
+	struct device *dev = dqm->dev->adev->dev;
+	struct qcm_process_device *qpd;
+	struct queue *q;
+	int retval = 0;
+
+	list_for_each_entry(cur, &dqm->queues, list) {
+		qpd = cur->qpd;
+		list_for_each_entry(q, &qpd->queues_list, list) {
+			if (!q->properties.is_active)
+				continue;
+			retval = add_queue_mes(dqm, q, qpd);
+			if (retval) {
+				dev_err(dev, "%s: Failed to add queue %d for dev %d",
+					__func__,
+					q->properties.queue_id,
+					dqm->dev->id);
+				return retval;
+			}
+		}
+	}
+
+	return retval;
+}
+
 static int suspend_all_queues_mes(struct device_queue_manager *dqm)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)dqm->dev->adev;
@@ -1742,7 +1773,7 @@ static int halt_cpsch(struct device_queue_manager *dqm)
 						 KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0,
 				USE_DEFAULT_GRACE_PERIOD, false);
 		else
-			ret = remove_all_queues_mes(dqm);
+			ret = remove_all_kfd_queues_mes(dqm);
 	}
 	dqm->sched_halt = true;
 	dqm_unlock(dqm);
@@ -1768,6 +1799,9 @@ static int unhalt_cpsch(struct device_queue_manager *dqm)
 		ret = execute_queues_cpsch(dqm,
 					   KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES,
 			0, USE_DEFAULT_GRACE_PERIOD);
+	else
+		ret = add_all_kfd_queues_mes(dqm);
+
 	dqm_unlock(dqm);
 
 	return ret;
@@ -1867,7 +1901,7 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 	if (!dqm->dev->kfd->shared_resources.enable_mes)
 		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD, false);
 	else
-		remove_all_queues_mes(dqm);
+		remove_all_kfd_queues_mes(dqm);
 
 	dqm->sched_running = false;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 6bab6fc6a35d..87cd52cf4ee9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -341,8 +341,8 @@ static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,
 							      attr_sdma);
 		struct kfd_sdma_activity_handler_workarea sdma_activity_work_handler;
 
-		INIT_WORK(&sdma_activity_work_handler.sdma_activity_work,
-					kfd_sdma_activity_worker);
+		INIT_WORK_ONSTACK(&sdma_activity_work_handler.sdma_activity_work,
+				  kfd_sdma_activity_worker);
 
 		sdma_activity_work_handler.pdd = pdd;
 		sdma_activity_work_handler.sdma_activity_counter = 0;
@@ -350,6 +350,7 @@ static ssize_t kfd_procfs_show(struct kobject *kobj, struct attribute *attr,
 		schedule_work(&sdma_activity_work_handler.sdma_activity_work);
 
 		flush_work(&sdma_activity_work_handler.sdma_activity_work);
+		destroy_work_on_stack(&sdma_activity_work_handler.sdma_activity_work);
 
 		return snprintf(buffer, PAGE_SIZE, "%llu\n",
 				(sdma_activity_work_handler.sdma_activity_counter)/
@@ -853,8 +854,10 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 		goto out;
 	}
 
-	/* A prior open of /dev/kfd could have already created the process. */
-	process = find_process(thread, false);
+	/* A prior open of /dev/kfd could have already created the process.
+	 * find_process will increase process kref in this case
+	 */
+	process = find_process(thread, true);
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
@@ -902,8 +905,6 @@ struct kfd_process *kfd_create_process(struct task_struct *thread)
 		init_waitqueue_head(&process->wait_irq_drain);
 	}
 out:
-	if (!IS_ERR(process))
-		kref_get(&process->ref);
 	mutex_unlock(&kfd_processes_mutex);
 	mmput(thread->mm);
 
@@ -1189,10 +1190,8 @@ static void kfd_process_ref_release(struct kref *ref)
 
 static struct mmu_notifier *kfd_process_alloc_notifier(struct mm_struct *mm)
 {
-	int idx = srcu_read_lock(&kfd_processes_srcu);
-	struct kfd_process *p = find_process_by_mm(mm);
-
-	srcu_read_unlock(&kfd_processes_srcu, idx);
+	/* This increments p->ref counter if kfd process p exists */
+	struct kfd_process *p = kfd_lookup_process_by_mm(mm);
 
 	return p ? &p->mmu_notifier : ERR_PTR(-ESRCH);
 }
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 16653e0573b1..f0a6816709ca 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1307,6 +1307,29 @@ static int dm_dmub_hw_init(struct amdgpu_device *adev)
 	DRM_INFO("DMUB hardware initialized: version=0x%08X\n",
 		 adev->dm.dmcub_fw_version);
 
+	/* Keeping sanity checks off if
+	 * DCN31 >= 4.0.59.0
+	 * DCN314 >= 8.0.16.0
+	 * Otherwise, turn on sanity checks
+	 */
+	switch (amdgpu_ip_version(adev, DCE_HWIP, 0)) {
+	case IP_VERSION(3, 1, 2):
+	case IP_VERSION(3, 1, 3):
+		if (adev->dm.dmcub_fw_version &&
+			adev->dm.dmcub_fw_version >= DMUB_FW_VERSION(4, 0, 0) &&
+			adev->dm.dmcub_fw_version < DMUB_FW_VERSION(4, 0, 59))
+				adev->dm.dc->debug.sanity_checks = true;
+		break;
+	case IP_VERSION(3, 1, 4):
+		if (adev->dm.dmcub_fw_version &&
+			adev->dm.dmcub_fw_version >= DMUB_FW_VERSION(4, 0, 0) &&
+			adev->dm.dmcub_fw_version < DMUB_FW_VERSION(8, 0, 16))
+				adev->dm.dc->debug.sanity_checks = true;
+		break;
+	default:
+		break;
+	}
+
 	return 0;
 }
 
@@ -6790,7 +6813,7 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
-		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
+		aconnector->sr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
 	}
 finish:
@@ -8894,6 +8917,56 @@ static void amdgpu_dm_update_cursor(struct drm_plane *plane,
 	}
 }
 
+static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach,
+					  const struct dm_crtc_state *acrtc_state,
+					  const u64 current_ts)
+{
+	struct psr_settings *psr = &acrtc_state->stream->link->psr_settings;
+	struct replay_settings *pr = &acrtc_state->stream->link->replay_settings;
+	struct amdgpu_dm_connector *aconn =
+		(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
+
+	if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+		if (pr->config.replay_supported && !pr->replay_feature_enabled)
+			amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
+		else if (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED &&
+			     !psr->psr_feature_enabled)
+			if (!aconn->disallow_edp_enter_psr)
+				amdgpu_dm_link_setup_psr(acrtc_state->stream);
+	}
+
+	/* Decrement skip count when SR is enabled and we're doing fast updates. */
+	if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
+	    (psr->psr_feature_enabled || pr->config.replay_supported)) {
+		if (aconn->sr_skip_count > 0)
+			aconn->sr_skip_count--;
+
+		/* Allow SR when skip count is 0. */
+		acrtc_attach->dm_irq_params.allow_sr_entry = !aconn->sr_skip_count;
+
+		/*
+		 * If sink supports PSR SU/Panel Replay, there is no need to rely on
+		 * a vblank event disable request to enable PSR/RP. PSR SU/RP
+		 * can be enabled immediately once OS demonstrates an
+		 * adequate number of fast atomic commits to notify KMD
+		 * of update events. See `vblank_control_worker()`.
+		 */
+		if (acrtc_attach->dm_irq_params.allow_sr_entry &&
+#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
+		    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
+#endif
+		    (current_ts - psr->psr_dirty_rects_change_timestamp_ns) > 500000000) {
+			if (pr->replay_feature_enabled && !pr->replay_allow_active)
+				amdgpu_dm_replay_enable(acrtc_state->stream, true);
+			if (psr->psr_version >= DC_PSR_VERSION_SU_1 &&
+			    !psr->psr_allow_active && !aconn->disallow_edp_enter_psr)
+				amdgpu_dm_psr_enable(acrtc_state->stream);
+		}
+	} else {
+		acrtc_attach->dm_irq_params.allow_sr_entry = false;
+	}
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_device *dev,
 				    struct amdgpu_display_manager *dm,
@@ -9047,7 +9120,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			 * during the PSR-SU was disabled.
 			 */
 			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
+			    acrtc_attach->dm_irq_params.allow_sr_entry &&
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
 #endif
@@ -9222,9 +9295,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->stream_update.abm_level = &acrtc_state->abm_level;
 
 		mutex_lock(&dm->dc_lock);
-		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
-				acrtc_state->stream->link->psr_settings.psr_allow_active)
-			amdgpu_dm_psr_disable(acrtc_state->stream);
+		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+			if (acrtc_state->stream->link->replay_settings.replay_allow_active)
+				amdgpu_dm_replay_disable(acrtc_state->stream);
+			if (acrtc_state->stream->link->psr_settings.psr_allow_active)
+				amdgpu_dm_psr_disable(acrtc_state->stream);
+		}
 		mutex_unlock(&dm->dc_lock);
 
 		/*
@@ -9265,57 +9341,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			dm_update_pflip_irq_state(drm_to_adev(dev),
 						  acrtc_attach);
 
-		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
-			if (acrtc_state->stream->link->replay_settings.config.replay_supported &&
-					!acrtc_state->stream->link->replay_settings.replay_feature_enabled) {
-				struct amdgpu_dm_connector *aconn =
-					(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-				amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
-			} else if (acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
-					!acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-
-				struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *)
-					acrtc_state->stream->dm_stream_context;
-
-				if (!aconn->disallow_edp_enter_psr)
-					amdgpu_dm_link_setup_psr(acrtc_state->stream);
-			}
-		}
-
-		/* Decrement skip count when PSR is enabled and we're doing fast updates. */
-		if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
-		    acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-			struct amdgpu_dm_connector *aconn =
-				(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-
-			if (aconn->psr_skip_count > 0)
-				aconn->psr_skip_count--;
-
-			/* Allow PSR when skip count is 0. */
-			acrtc_attach->dm_irq_params.allow_psr_entry = !aconn->psr_skip_count;
-
-			/*
-			 * If sink supports PSR SU, there is no need to rely on
-			 * a vblank event disable request to enable PSR. PSR SU
-			 * can be enabled immediately once OS demonstrates an
-			 * adequate number of fast atomic commits to notify KMD
-			 * of update events. See `vblank_control_worker()`.
-			 */
-			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
-#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
-			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
-#endif
-			    !acrtc_state->stream->link->psr_settings.psr_allow_active &&
-			    !aconn->disallow_edp_enter_psr &&
-			    (timestamp_ns -
-			    acrtc_state->stream->link->psr_settings.psr_dirty_rects_change_timestamp_ns) >
-			    500000000)
-				amdgpu_dm_psr_enable(acrtc_state->stream);
-		} else {
-			acrtc_attach->dm_irq_params.allow_psr_entry = false;
-		}
-
+		amdgpu_dm_enable_self_refresh(acrtc_attach, acrtc_state, timestamp_ns);
 		mutex_unlock(&dm->dc_lock);
 	}
 
@@ -12101,7 +12127,7 @@ static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 			break;
 	}
 
-	while (j < EDID_LENGTH) {
+	while (j < EDID_LENGTH - sizeof(struct amd_vsdb_block)) {
 		struct amd_vsdb_block *amd_vsdb = (struct amd_vsdb_block *)&edid_ext[j];
 		unsigned int ieeeId = (amd_vsdb->ieee_id[2] << 16) | (amd_vsdb->ieee_id[1] << 8) | (amd_vsdb->ieee_id[0]);
 
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 25e95775c45c..6464a8378387 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -727,7 +727,7 @@ struct amdgpu_dm_connector {
 	/* Cached display modes */
 	struct drm_display_mode freesync_vid_base;
 
-	int psr_skip_count;
+	int sr_skip_count;
 	bool disallow_edp_enter_psr;
 
 	/* Record progress status of mst*/
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 8b5bea799a24..64a041c2af05 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -265,11 +265,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	 * where the SU region is the full hactive*vactive region. See
 	 * fill_dc_dirty_rects().
 	 */
-	if (vblank_work->stream && vblank_work->stream->link) {
+	if (vblank_work->stream && vblank_work->stream->link && vblank_work->acrtc) {
 		amdgpu_dm_crtc_set_panel_sr_feature(
 			vblank_work, vblank_work->enable,
-			vblank_work->acrtc->dm_irq_params.allow_psr_entry ||
-			vblank_work->stream->link->replay_settings.replay_feature_enabled);
+			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
 	if (dm->active_vblank_irq_count == 0)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
index 5c9303241aeb..6a7ecc1e4602 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -33,7 +33,7 @@ struct dm_irq_params {
 	struct mod_vrr_params vrr_params;
 	struct dc_stream_state *stream;
 	int active_planes;
-	bool allow_psr_entry;
+	bool allow_sr_entry;
 	struct mod_freesync_config freesync_config;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index be8fbb04ad98..c9a6de110b74 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -3122,14 +3122,12 @@ static enum bp_result bios_parser_get_vram_info(
 		struct dc_vram_info *info)
 {
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
-	static enum bp_result result = BP_RESULT_BADBIOSTABLE;
+	enum bp_result result = BP_RESULT_BADBIOSTABLE;
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
 
 	// vram info moved to umc_info for DCN4x
-	if (dcb->ctx->dce_version >= DCN_VERSION_4_01 &&
-		dcb->ctx->dce_version < DCN_VERSION_MAX &&
-		info && DATA_TABLES(umc_info)) {
+	if (info && DATA_TABLES(umc_info)) {
 		header = GET_IMAGE(struct atom_common_table_header,
 					DATA_TABLES(umc_info));
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 2597e3fd562b..e006f816ff2f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -265,6 +265,9 @@ struct dc_state *dc_state_create_copy(struct dc_state *src_state)
 	dc_state_copy_internal(new_state, src_state);
 
 #ifdef CONFIG_DRM_AMD_DC_FP
+	new_state->bw_ctx.dml2 = NULL;
+	new_state->bw_ctx.dml2_dc_power_source = NULL;
+
 	if (src_state->bw_ctx.dml2 &&
 			!dml2_create_copy(&new_state->bw_ctx.dml2, src_state->bw_ctx.dml2)) {
 		dc_state_release(new_state);
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index ad9ce3d0bfcf..e143fab00a86 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.308"
+#define DC_VER "3.2.309"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 1fd030e3f4be..edf4df1d03b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -181,6 +181,7 @@ struct dc_panel_patch {
 	unsigned int disable_colorimetry;
 	uint8_t blankstream_before_otg_off;
 	bool oled_optimize_display_on;
+	unsigned int force_mst_blocked_discovery;
 };
 
 struct dc_edid_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c
index 05df502a54f2..88cf47a5ea75 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.c
@@ -46,7 +46,7 @@
 #include "clk_mgr.h"
 
 __printf(3, 4)
-unsigned int snprintf_count(char *pbuf, unsigned int bufsize, char *fmt, ...)
+unsigned int snprintf_count(char *pbuf, unsigned int bufsize, const char *fmt, ...)
 {
 	int ret_vsnprintf;
 	unsigned int chars_printed;
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 9405c47ee2a9..f81e5a4e1d6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -143,7 +143,7 @@ void generic_reg_wait(const struct dc_context *ctx,
 	unsigned int delay_between_poll_us, unsigned int time_out_num_tries,
 	const char *func_name, int line);
 
-unsigned int snprintf_count(char *pBuf, unsigned int bufSize, char *fmt, ...);
+unsigned int snprintf_count(char *pBuf, unsigned int bufSize, const char *fmt, ...);
 
 /* These macros need to be used with soc15 registers in order to retrieve
  * the actual offset.
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
index 5a09dd298e6f..92269f0e50ed 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
@@ -8,6 +8,7 @@
 #include "dml2_pmo_dcn4_fams2.h"
 
 static const double MIN_VACTIVE_MARGIN_PCT = 0.25; // We need more than non-zero margin because DET buffer granularity can alter vactive latency hiding
+static const double MIN_BLANK_STUTTER_FACTOR = 3.0;
 
 static const struct dml2_pmo_pstate_strategy base_strategy_list_1_display[] = {
 	// VActive Preferred
@@ -2140,6 +2141,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 	struct dml2_pmo_instance *pmo = in_out->instance;
 	bool stutter_period_meets_z8_eco = true;
 	bool z8_stutter_optimization_too_expensive = false;
+	bool stutter_optimization_too_expensive = false;
 	double line_time_us, vblank_nom_time_us;
 
 	unsigned int i;
@@ -2161,10 +2163,15 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		line_time_us = (double)in_out->base_display_config->display_config.stream_descriptors[i].timing.h_total / (in_out->base_display_config->display_config.stream_descriptors[i].timing.pixel_clock_khz * 1000) * 1000000;
 		vblank_nom_time_us = line_time_us * in_out->base_display_config->display_config.stream_descriptors[i].timing.vblank_nom;
 
-		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us) {
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
 			z8_stutter_optimization_too_expensive = true;
 			break;
 		}
+
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
+			stutter_optimization_too_expensive = true;
+			break;
+		}
 	}
 
 	pmo->scratch.pmo_dcn4.num_stutter_candidates = 0;
@@ -2180,7 +2187,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		pmo->scratch.pmo_dcn4.z8_vblank_optimizable = false;
 	}
 
-	if (pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
+	if (!stutter_optimization_too_expensive && pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
 		pmo->scratch.pmo_dcn4.optimal_vblank_reserved_time_for_stutter_us[pmo->scratch.pmo_dcn4.num_stutter_candidates] = (unsigned int)pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us;
 		pmo->scratch.pmo_dcn4.num_stutter_candidates++;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
index 036cb7e9b5bb..03ba01f4ace1 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c
@@ -519,15 +519,18 @@ static void dcn31_reset_back_end_for_pipe(
 
 	dc->hwss.set_abm_immediate_disable(pipe_ctx);
 
-	if ((!pipe_ctx->stream->dpms_off || pipe_ctx->stream->link->link_status.link_active)
-		&& pipe_ctx->stream->sink && pipe_ctx->stream->sink->edid_caps.panel_patch.blankstream_before_otg_off) {
+	link = pipe_ctx->stream->link;
+
+	if ((!pipe_ctx->stream->dpms_off || link->link_status.link_active) &&
+		(link->connector_signal == SIGNAL_TYPE_EDP))
 		dc->hwss.blank_stream(pipe_ctx);
-	}
 
 	pipe_ctx->stream_res.tg->funcs->set_dsc_config(
 			pipe_ctx->stream_res.tg,
 			OPTC_DSC_DISABLED, 0, 0);
+
 	pipe_ctx->stream_res.tg->funcs->disable_crtc(pipe_ctx->stream_res.tg);
+
 	pipe_ctx->stream_res.tg->funcs->enable_optc_clock(pipe_ctx->stream_res.tg, false);
 	if (pipe_ctx->stream_res.tg->funcs->set_odm_bypass)
 		pipe_ctx->stream_res.tg->funcs->set_odm_bypass(
@@ -539,7 +542,6 @@ static void dcn31_reset_back_end_for_pipe(
 		pipe_ctx->stream_res.tg->funcs->set_drr(
 				pipe_ctx->stream_res.tg, NULL);
 
-	link = pipe_ctx->stream->link;
 	/* DPMS may already disable or */
 	/* dpms_off status is incorrect due to fastboot
 	 * feature. When system resume from S4 with second
@@ -651,7 +653,8 @@ static void dmub_abm_set_backlight(struct dc_context *dc,
 	cmd.abm_set_backlight.header.sub_type = DMUB_CMD__ABM_SET_BACKLIGHT;
 	cmd.abm_set_backlight.abm_set_backlight_data.frame_ramp = backlight_level_params->frame_ramp;
 	cmd.abm_set_backlight.abm_set_backlight_data.backlight_user_level = backlight_level_params->backlight_pwm_u16_16;
-	cmd.abm_set_backlight.abm_set_backlight_data.backlight_control_type = backlight_level_params->control_type;
+	cmd.abm_set_backlight.abm_set_backlight_data.backlight_control_type =
+		(enum dmub_backlight_control_type) backlight_level_params->control_type;
 	cmd.abm_set_backlight.abm_set_backlight_data.min_luminance = backlight_level_params->min_luminance;
 	cmd.abm_set_backlight.abm_set_backlight_data.max_luminance = backlight_level_params->max_luminance;
 	cmd.abm_set_backlight.abm_set_backlight_data.min_backlight_pwm = backlight_level_params->min_backlight_pwm;
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index 72ef0c3a7ebd..9dabaf682171 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -1633,9 +1633,11 @@ static bool retrieve_link_cap(struct dc_link *link)
 	}
 
 	/* Read DP tunneling information. */
-	status = dpcd_get_tunneling_device_data(link);
-	if (status != DC_OK)
-		dm_error("%s: Read tunneling device data failed.\n", __func__);
+	if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) {
+		status = dpcd_get_tunneling_device_data(link);
+		if (status != DC_OK)
+			dm_error("%s: Read tunneling device data failed.\n", __func__);
+	}
 
 	dpcd_set_source_specific_data(link);
 	/* Sink may need to configure internals based on vendor, so allow some
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
index 96bf135b6f05..48abeaa88678 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
@@ -221,21 +221,11 @@ static void handle_hpd_irq_replay_sink(struct dc_link *link)
 		&replay_error_status.raw,
 		sizeof(replay_error_status.raw));
 
-	link->replay_settings.config.replay_error_status.bits.LINK_CRC_ERROR =
-		replay_error_status.bits.LINK_CRC_ERROR;
-	link->replay_settings.config.replay_error_status.bits.DESYNC_ERROR =
-		replay_configuration.bits.DESYNC_ERROR_STATUS;
-	link->replay_settings.config.replay_error_status.bits.STATE_TRANSITION_ERROR =
-		replay_configuration.bits.STATE_TRANSITION_ERROR_STATUS;
-
-	if (link->replay_settings.config.replay_error_status.bits.LINK_CRC_ERROR ||
-		link->replay_settings.config.replay_error_status.bits.DESYNC_ERROR ||
-		link->replay_settings.config.replay_error_status.bits.STATE_TRANSITION_ERROR) {
+	if (replay_error_status.bits.LINK_CRC_ERROR ||
+		replay_configuration.bits.DESYNC_ERROR_STATUS ||
+		replay_configuration.bits.STATE_TRANSITION_ERROR_STATUS) {
 		bool allow_active;
 
-		if (link->replay_settings.config.replay_error_status.bits.DESYNC_ERROR)
-			link->replay_settings.config.received_desync_error_hpd = 1;
-
 		if (link->replay_settings.config.force_disable_desync_error_check)
 			return;
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
index 4f1bd71b9ad9..770a380cc03d 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn10/dcn10_resource.c
@@ -559,17 +559,6 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.using_dml2 = false,
 };
 
-static const struct dc_debug_options debug_defaults_diags = {
-		.disable_dmcu = false,
-		.force_abm_enable = false,
-		.clock_trace = true,
-		.disable_stutter = true,
-		.disable_pplib_clock_request = true,
-		.disable_pplib_wm_range = true,
-		.underflow_assert_delay_us = 0xFFFFFFFF,
-		.enable_legacy_fast_update = true,
-};
-
 static void dcn10_dpp_destroy(struct dpp **dpp)
 {
 	kfree(TO_DCN10_DPP(*dpp));
@@ -1398,8 +1387,6 @@ static bool dcn10_resource_construct(
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
-	else
-		dc->debug = debug_defaults_diags;
 
 	/*************************************************
 	 *  Create resources                             *
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index f71a5b8286b2..c16cf1c8f7f9 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -868,7 +868,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.max_downscale_src_width = 4096,/*upto true 4K*/
 	.disable_pplib_wm_range = false,
 	.scl_reset_length10 = true,
-	.sanity_checks = true,
+	.sanity_checks = false,
 	.underflow_assert_delay_us = 0xFFFFFFFF,
 	.dwb_fi_phase = -1, // -1 = disable,
 	.dmub_command_table = true,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index 8aa10da68432..c0f48c78e968 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -888,7 +888,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.max_downscale_src_width = 4096,/*upto true 4k*/
 	.disable_pplib_wm_range = false,
 	.scl_reset_length10 = true,
-	.sanity_checks = true,
+	.sanity_checks = false,
 	.underflow_assert_delay_us = 0xFFFFFFFF,
 	.dwb_fi_phase = -1, // -1 = disable,
 	.dmub_command_table = true,
diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
index a29a9f131e04..614276200aa0 100644
--- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
+++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
@@ -910,6 +910,16 @@ static void spl_get_taps_non_adaptive_scaler(
 		spl_scratch->scl_data.taps.h_taps_c = in_taps->h_taps_c - 1;
 	else
 		spl_scratch->scl_data.taps.h_taps_c = in_taps->h_taps_c;
+
+	if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz))
+		spl_scratch->scl_data.taps.h_taps = 1;
+	if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert))
+		spl_scratch->scl_data.taps.v_taps = 1;
+	if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz_c))
+		spl_scratch->scl_data.taps.h_taps_c = 1;
+	if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert_c))
+		spl_scratch->scl_data.taps.v_taps_c = 1;
+
 }
 
 /* Calculate optimal number of taps */
@@ -936,10 +946,7 @@ static bool spl_get_optimal_number_of_taps(
 
 	/* Disable adaptive scaler and sharpener when integer scaling is enabled */
 	if (spl_in->scaling_quality.integer_scaling) {
-		spl_scratch->scl_data.taps.h_taps = 1;
-		spl_scratch->scl_data.taps.v_taps = 1;
-		spl_scratch->scl_data.taps.v_taps_c = 1;
-		spl_scratch->scl_data.taps.h_taps_c = 1;
+		spl_get_taps_non_adaptive_scaler(spl_scratch, in_taps);
 		*enable_easf_v = false;
 		*enable_easf_h = false;
 		*enable_isharp = false;
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index a9b90fa00b88..b800a507d1e0 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4427,6 +4427,24 @@ struct dmub_rb_cmd_abm_set_pipe {
 };
 
 /**
+ * Type of backlight control method to be used by ABM module
+ */
+enum dmub_backlight_control_type {
+	/**
+	 * PWM Backlight control
+	 */
+	DMU_BACKLIGHT_CONTROL_PWM = 0,
+	/**
+	 * VESA Aux-based backlight control
+	 */
+	DMU_BACKLIGHT_CONTROL_VESA_AUX = 1,
+	/**
+	 * AMD DPCD Aux-based backlight control
+	 */
+	DMU_BACKLIGHT_CONTROL_AMD_AUX = 2,
+};
+
+/**
  * Data passed from driver to FW in a DMUB_CMD__ABM_SET_BACKLIGHT command.
  */
 struct dmub_cmd_abm_set_backlight_data {
@@ -4453,17 +4471,22 @@ struct dmub_cmd_abm_set_backlight_data {
 	uint8_t panel_mask;
 
 	/**
+	 * AUX HW Instance.
+	 */
+	uint8_t aux_inst;
+
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad[1];
+
+	/**
 	 * Backlight control type.
 	 * Value 0 is PWM backlight control.
 	 * Value 1 is VAUX backlight control.
 	 * Value 2 is AMD DPCD AUX backlight control.
 	 */
-	uint8_t backlight_control_type;
-
-	/**
-	 * AUX HW instance.
-	 */
-	uint8_t aux_inst;
+	enum dmub_backlight_control_type backlight_control_type;
 
 	/**
 	 * Minimum luminance in nits.
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
index db16066bc893..a3f3ff5d49ac 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -497,6 +497,7 @@ enum dmub_status
 	const struct dmub_fw_meta_info *fw_info;
 	uint32_t fw_state_size = DMUB_FW_STATE_SIZE;
 	uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE;
+	uint32_t shared_state_size = DMUB_FW_HEADER_SHARED_STATE_SIZE;
 	uint32_t window_sizes[DMUB_WINDOW_TOTAL] = { 0 };
 
 	if (!dmub->sw_init)
@@ -514,6 +515,7 @@ enum dmub_status
 
 		fw_state_size = fw_info->fw_region_size;
 		trace_buffer_size = fw_info->trace_buffer_size;
+		shared_state_size = fw_info->shared_state_size;
 
 		/**
 		 * If DM didn't fill in a version, then fill it in based on
@@ -534,7 +536,7 @@ enum dmub_status
 	window_sizes[DMUB_WINDOW_5_TRACEBUFF] = trace_buffer_size;
 	window_sizes[DMUB_WINDOW_6_FW_STATE] = fw_state_size;
 	window_sizes[DMUB_WINDOW_7_SCRATCH_MEM] = DMUB_SCRATCH_MEM_SIZE;
-	window_sizes[DMUB_WINDOW_SHARED_STATE] = DMUB_FW_HEADER_SHARED_STATE_SIZE;
+	window_sizes[DMUB_WINDOW_SHARED_STATE] = max(DMUB_FW_HEADER_SHARED_STATE_SIZE, shared_state_size);
 
 	out->fb_size =
 		dmub_srv_calc_regions_for_memory_type(params, out, window_sizes, DMUB_WINDOW_MEMORY_TYPE_FB);
diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
index 21ceafce1f9b..eb46cb10c24d 100644
--- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
@@ -230,13 +230,23 @@ union MESAPI_SET_HW_RESOURCES {
 				uint32_t disable_add_queue_wptr_mc_addr : 1;
 				uint32_t enable_mes_event_int_logging : 1;
 				uint32_t enable_reg_active_poll : 1;
-				uint32_t reserved	: 21;
+				uint32_t use_disable_queue_in_legacy_uq_preemption : 1;
+				uint32_t send_write_data : 1;
+				uint32_t os_tdr_timeout_override : 1;
+				uint32_t use_rs64mem_for_proc_gang_ctx : 1;
+				uint32_t use_add_queue_unmap_flag_addr : 1;
+				uint32_t enable_mes_sch_stb_log : 1;
+				uint32_t limit_single_process : 1;
+				uint32_t is_strix_tmz_wa_enabled  :1;
+				uint32_t reserved : 13;
 			};
 			uint32_t	uint32_t_all;
 		};
 		uint32_t	oversubscription_timer;
 		uint64_t        doorbell_info;
 		uint64_t        event_intr_history_gpu_mc_ptr;
+		uint64_t	timestamp;
+		uint32_t	os_tdr_timeout_in_sec;
 	};
 
 	uint32_t	max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
@@ -563,6 +573,11 @@ enum MESAPI_MISC_OPCODE {
 	MESAPI_MISC__READ_REG,
 	MESAPI_MISC__WAIT_REG_MEM,
 	MESAPI_MISC__SET_SHADER_DEBUGGER,
+	MESAPI_MISC__NOTIFY_WORK_ON_UNMAPPED_QUEUE,
+	MESAPI_MISC__NOTIFY_TO_UNMAP_PROCESSES,
+	MESAPI_MISC__CHANGE_CONFIG,
+	MESAPI_MISC__LAUNCH_CLEANER_SHADER,
+
 	MESAPI_MISC__MAX,
 };
 
@@ -617,6 +632,31 @@ struct SET_SHADER_DEBUGGER {
 	uint32_t trap_en;
 };
 
+enum MESAPI_MISC__CHANGE_CONFIG_OPTION {
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_LIMIT_SINGLE_PROCESS = 0,
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_ENABLE_HWS_LOGGING_BUFFER = 1,
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_CHANGE_TDR_CONFIG    = 2,
+
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_MAX = 0x1F
+};
+
+struct CHANGE_CONFIG {
+	enum MESAPI_MISC__CHANGE_CONFIG_OPTION opcode;
+	union {
+		struct {
+			uint32_t limit_single_process : 1;
+			uint32_t enable_hws_logging_buffer : 1;
+			uint32_t reserved : 31;
+		} bits;
+		uint32_t all;
+	} option;
+
+	struct {
+		uint32_t tdr_level;
+		uint32_t tdr_delay;
+	} tdr_config;
+};
+
 union MESAPI__MISC {
 	struct {
 		union MES_API_HEADER	header;
@@ -631,6 +671,7 @@ union MESAPI__MISC {
 			struct          WAIT_REG_MEM wait_reg_mem;
 			struct		SET_SHADER_DEBUGGER set_shader_debugger;
 			enum MES_AMD_PRIORITY_LEVEL queue_sch_level;
+			struct		CHANGE_CONFIG change_config;
 
 			uint32_t	data[MISC_DATA_MAX_SIZE_IN_DWORDS];
 		};
diff --git a/drivers/gpu/drm/amd/include/mes_v12_api_def.h b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
index 101e2fe962c6..c9b2ca5cf75f 100644
--- a/drivers/gpu/drm/amd/include/mes_v12_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
@@ -643,6 +643,10 @@ enum MESAPI_MISC_OPCODE {
 	MESAPI_MISC__SET_SHADER_DEBUGGER,
 	MESAPI_MISC__NOTIFY_WORK_ON_UNMAPPED_QUEUE,
 	MESAPI_MISC__NOTIFY_TO_UNMAP_PROCESSES,
+	MESAPI_MISC__QUERY_HUNG_ENGINE_ID,
+	MESAPI_MISC__CHANGE_CONFIG,
+	MESAPI_MISC__LAUNCH_CLEANER_SHADER,
+	MESAPI_MISC__SETUP_MES_DBGEXT,
 
 	MESAPI_MISC__MAX,
 };
@@ -713,6 +717,31 @@ struct SET_GANG_SUBMIT {
 	uint32_t slave_gang_context_array_index;
 };
 
+enum MESAPI_MISC__CHANGE_CONFIG_OPTION {
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_LIMIT_SINGLE_PROCESS = 0,
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_ENABLE_HWS_LOGGING_BUFFER = 1,
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_CHANGE_TDR_CONFIG    = 2,
+
+	MESAPI_MISC__CHANGE_CONFIG_OPTION_MAX = 0x1F
+};
+
+struct CHANGE_CONFIG {
+	enum MESAPI_MISC__CHANGE_CONFIG_OPTION opcode;
+	union {
+		struct  {
+			uint32_t limit_single_process : 1;
+			uint32_t enable_hws_logging_buffer : 1;
+			uint32_t reserved : 30;
+		} bits;
+		uint32_t all;
+	} option;
+
+	struct {
+		uint32_t tdr_level;
+		uint32_t tdr_delay;
+	} tdr_config;
+};
+
 union MESAPI__MISC {
 	struct {
 		union MES_API_HEADER	header;
@@ -726,7 +755,7 @@ union MESAPI__MISC {
 			struct WAIT_REG_MEM wait_reg_mem;
 			struct SET_SHADER_DEBUGGER set_shader_debugger;
 			enum MES_AMD_PRIORITY_LEVEL queue_sch_level;
-
+			struct CHANGE_CONFIG change_config;
 			uint32_t data[MISC_DATA_MAX_SIZE_IN_DWORDS];
 		};
 		uint64_t		timestamp;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 7ebb675c5786..fa30a9e1f27a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -3041,6 +3041,16 @@ static int mmhub_err_codes[] = {
 	CODE_VML2, CODE_VML2_WALKER, CODE_MMCANE,
 };
 
+static int vcn_err_codes[] = {
+	CODE_VIDD, CODE_VIDV,
+};
+static int jpeg_err_codes[] = {
+	CODE_JPEG0S, CODE_JPEG0D, CODE_JPEG1S, CODE_JPEG1D,
+	CODE_JPEG2S, CODE_JPEG2D, CODE_JPEG3S, CODE_JPEG3D,
+	CODE_JPEG4S, CODE_JPEG4D, CODE_JPEG5S, CODE_JPEG5D,
+	CODE_JPEG6S, CODE_JPEG6D, CODE_JPEG7S, CODE_JPEG7D,
+};
+
 static const struct mca_ras_info mca_ras_table[] = {
 	{
 		.blkid = AMDGPU_RAS_BLOCK__UMC,
@@ -3069,6 +3079,20 @@ static const struct mca_ras_info mca_ras_table[] = {
 		.blkid = AMDGPU_RAS_BLOCK__XGMI_WAFL,
 		.ip = AMDGPU_MCA_IP_PCS_XGMI,
 		.get_err_count = mca_pcs_xgmi_mca_get_err_count,
+	}, {
+		.blkid = AMDGPU_RAS_BLOCK__VCN,
+		.ip = AMDGPU_MCA_IP_SMU,
+		.err_code_array = vcn_err_codes,
+		.err_code_count = ARRAY_SIZE(vcn_err_codes),
+		.get_err_count = mca_smu_mca_get_err_count,
+		.bank_is_valid = mca_smu_bank_is_valid,
+	}, {
+		.blkid = AMDGPU_RAS_BLOCK__JPEG,
+		.ip = AMDGPU_MCA_IP_SMU,
+		.err_code_array = jpeg_err_codes,
+		.err_code_count = ARRAY_SIZE(jpeg_err_codes),
+		.get_err_count = mca_smu_mca_get_err_count,
+		.bank_is_valid = mca_smu_bank_is_valid,
 	},
 };
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 8798ebfcea83..84f9b007b59f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -1132,7 +1132,7 @@ static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu,
 static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 					enum smu_clk_type clk_type, char *buf)
 {
-	int i, size = 0, ret = 0;
+	int i, idx, ret = 0, size = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t min, max;
 
@@ -1168,7 +1168,8 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 			break;
 
 		for (i = 0; i < count; i++) {
-			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value);
+			idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i;
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, idx, &value);
 			if (ret)
 				break;