Merge tag 'drm-next-2023-11-07' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "Geert pointed out I missed the renesas reworks in my main pull, so
  this pull contains the renesas next work for atomic conversion and DT
  support.

  It also contains a bunch of amdgpu and some small ssd13xx fixes.

  renesas:
   - atomic conversion
   - DT support

  ssd13xx:
   - dt binding fix for ssd132x
   - Initialize ssd130x crtc_state to NULL.

  amdgpu:
   - Fix RAS support check
   - RAS fixes
   - MES fixes
   - SMU13 fixes
   - Contiguous memory allocation fix
   - BACO fixes
   - GPU reset fixes
   - Min power limit fixes
   - GFX11 fixes
   - USB4/TB hotplug fixes
   - ARM regression fix
   - GFX9.4.3 fixes
   - KASAN/KCSAN stack size check fixes
   - SR-IOV fixes
   - SMU14 fixes
   - PSP13 fixes
   - Display blend fixes
   - Flexible array size fixes

  amdkfd:
   - GPUVM fix

  radeon:
   - Flexible array size fixes"

* tag 'drm-next-2023-11-07' of git://anongit.freedesktop.org/drm/drm: (83 commits)
  drm/amd/display: Enable fast update on blendTF change
  drm/amd/display: Fix blend LUT programming
  drm/amd/display: Program plane color setting correctly
  drm/amdgpu: Query and report boot status
  drm/amdgpu: Add psp v13 function to query boot status
  drm/amd/swsmu: remove fw version check in sw_init.
  drm/amd/swsmu: update smu v14_0_0 driver if and metrics table
  drm/amdgpu: Add C2PMSG_109/126 reg field shift/masks
  drm/amdgpu: Optimize the asic type fix code
  drm/amdgpu: fix GRBM read timeout when do mes_self_test
  drm/amdgpu: check recovery status of xgmi hive in ras_reset_error_count
  drm/amd/pm: only check sriov vf flag once when creating hwmon sysfs
  drm/amdgpu: Attach eviction fence on alloc
  drm/amdkfd: Improve amdgpu_vm_handle_moved
  drm/amd/display: Increase frame warning limit with KASAN or KCSAN in dml2
  drm/amd/display: Avoid NULL dereference of timing generator
  drm/amdkfd: Update cache info for GFX 9.4.3
  drm/amdkfd: Populate cache info for GFX 9.4.3
  drm/amdgpu: don't put MQDs in VRAM on ARM | ARM64
  drm/amdgpu/smu13: drop compute workload workaround
  ...

22 files changed, 328 insertions, 92 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 91820838b63b..8b4ca2576a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -363,9 +363,6 @@ struct amdgpu_ip_block_version {
 	const struct amd_ip_funcs *funcs;
 };
 
-#define HW_REV(_Major, _Minor, _Rev) \
-	((((uint32_t) (_Major)) << 16) | ((uint32_t) (_Minor) << 8) | ((uint32_t) (_Rev)))
-
 struct amdgpu_ip_block {
 	struct amdgpu_ip_block_status status;
 	const struct amdgpu_ip_block_version *version;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 1eccad4ce243..41fbc4fd0fac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -425,6 +425,32 @@ validate_fail:
 	return ret;
 }
 
+static int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo,
+					       uint32_t domain,
+					       struct dma_fence *fence)
+{
+	int ret = amdgpu_bo_reserve(bo, false);
+
+	if (ret)
+		return ret;
+
+	ret = amdgpu_amdkfd_bo_validate(bo, domain, true);
+	if (ret)
+		goto unreserve_out;
+
+	ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
+	if (ret)
+		goto unreserve_out;
+
+	dma_resv_add_fence(bo->tbo.base.resv, fence,
+			   DMA_RESV_USAGE_BOOKKEEP);
+
+unreserve_out:
+	amdgpu_bo_unreserve(bo);
+
+	return ret;
+}
+
 static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo)
 {
 	return amdgpu_amdkfd_bo_validate(bo, bo->allowed_domains, false);
@@ -1784,6 +1810,15 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		}
 		bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 		bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
+	} else {
+		mutex_lock(&avm->process_info->lock);
+		if (avm->process_info->eviction_fence &&
+		    !dma_fence_is_signaled(&avm->process_info->eviction_fence->base))
+			ret = amdgpu_amdkfd_bo_validate_and_fence(bo, domain,
+				&avm->process_info->eviction_fence->base);
+		mutex_unlock(&avm->process_info->lock);
+		if (ret)
+			goto err_validate_bo;
 	}
 
 	if (offset)
@@ -1793,6 +1828,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 
 allocate_init_user_pages_failed:
 err_pin_bo:
+err_validate_bo:
 	remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info);
 	drm_vma_node_revoke(&gobj->vma_node, drm_priv);
 err_node_allow:
@@ -1866,10 +1902,6 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	if (unlikely(ret))
 		return ret;
 
-	/* The eviction fence should be removed by the last unmap.
-	 * TODO: Log an error condition if the bo still has the eviction fence
-	 * attached
-	 */
 	amdgpu_amdkfd_remove_eviction_fence(mem->bo,
 					process_info->eviction_fence);
 	pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,
@@ -1998,19 +2030,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 	if (unlikely(ret))
 		goto out_unreserve;
 
-	if (mem->mapped_to_gpu_memory == 0 &&
-	    !amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) {
-		/* Validate BO only once. The eviction fence gets added to BO
-		 * the first time it is mapped. Validate will wait for all
-		 * background evictions to complete.
-		 */
-		ret = amdgpu_amdkfd_bo_validate(bo, domain, true);
-		if (ret) {
-			pr_debug("Validate failed\n");
-			goto out_unreserve;
-		}
-	}
-
 	list_for_each_entry(entry, &mem->attachments, list) {
 		if (entry->bo_va->base.vm != avm || entry->is_mapped)
 			continue;
@@ -2037,10 +2056,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
 			 mem->mapped_to_gpu_memory);
 	}
 
-	if (!amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && !bo->tbo.pin_count)
-		dma_resv_add_fence(bo->tbo.base.resv,
-				   &avm->process_info->eviction_fence->base,
-				   DMA_RESV_USAGE_BOOKKEEP);
 	ret = unreserve_bo_and_vms(&ctx, false, false);
 
 	goto out;
@@ -2074,7 +2089,6 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 		struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv)
 {
 	struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
-	struct amdkfd_process_info *process_info = avm->process_info;
 	unsigned long bo_size = mem->bo->tbo.base.size;
 	struct kfd_mem_attachment *entry;
 	struct bo_vm_reservation_context ctx;
@@ -2115,15 +2129,6 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
 			 mem->mapped_to_gpu_memory);
 	}
 
-	/* If BO is unmapped from all VMs, unfence it. It can be evicted if
-	 * required.
-	 */
-	if (mem->mapped_to_gpu_memory == 0 &&
-	    !amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm) &&
-	    !mem->bo->tbo.pin_count)
-		amdgpu_amdkfd_remove_eviction_fence(mem->bo,
-						process_info->eviction_fence);
-
 unreserve_out:
 	unreserve_bo_and_vms(&ctx, false, false);
 out:
@@ -2351,8 +2356,20 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev,
 	amdgpu_sync_create(&(*mem)->sync);
 	(*mem)->is_imported = true;
 
+	mutex_lock(&avm->process_info->lock);
+	if (avm->process_info->eviction_fence &&
+	    !dma_fence_is_signaled(&avm->process_info->eviction_fence->base))
+		ret = amdgpu_amdkfd_bo_validate_and_fence(bo, (*mem)->domain,
+				&avm->process_info->eviction_fence->base);
+	mutex_unlock(&avm->process_info->lock);
+	if (ret)
+		goto err_remove_mem;
+
 	return 0;
 
+err_remove_mem:
+	remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info);
+	drm_vma_node_revoke(&obj->vma_node, drm_priv);
 err_free_mem:
 	kfree(*mem);
 err_put_obj:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
index 5bbb23e102ba..618e469e3622 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c
@@ -29,6 +29,7 @@
 #include "amdgpu.h"
 #include "atom.h"
 
+#include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/acpi.h>
@@ -287,6 +288,10 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev)
 	if (adev->flags & AMD_IS_APU)
 		return false;
 
+	/* ATRM is for on-platform devices only */
+	if (dev_is_removable(&adev->pdev->dev))
+		return false;
+
 	while ((pdev = pci_get_base_class(PCI_BASE_CLASS_DISPLAY, pdev))) {
 		if ((pdev->class != PCI_CLASS_DISPLAY_VGA << 8) &&
 		    (pdev->class != PCI_CLASS_DISPLAY_OTHER << 8))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index e210fe5c22a0..86f88512eb7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1117,6 +1117,11 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			return r;
 	}
 
+	/* FIXME: In theory this loop shouldn't be needed any more when
+	 * amdgpu_vm_handle_moved handles all moved BOs that are reserved
+	 * with p->ticket. But removing it caused test regressions, so I'm
+	 * leaving it here for now.
+	 */
 	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 		bo_va = e->bo_va;
 		if (bo_va == NULL)
@@ -1131,7 +1136,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 			return r;
 	}
 
-	r = amdgpu_vm_handle_moved(adev, vm);
+	r = amdgpu_vm_handle_moved(adev, vm, &p->exec.ticket);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d5f78179b2b6..fd8cd8e2d3f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -41,6 +41,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/amdgpu_drm.h>
+#include <linux/device.h>
 #include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 #include <linux/efi.h>
@@ -1073,6 +1074,8 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev)
 	    amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0)) {
 		amdgpu_psp_wait_for_bootloader(adev);
 		ret = amdgpu_atomfirmware_asic_init(adev, true);
+		/* TODO: check the return val and stop device initialization if boot fails */
+		amdgpu_psp_query_boot_status(adev);
 		return ret;
 	} else {
 		return amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -2223,7 +2226,6 @@ out:
  */
 static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = adev_to_drm(adev);
 	struct pci_dev *parent;
 	int i, r;
 	bool total;
@@ -2294,7 +2296,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	    (amdgpu_is_atpx_hybrid() ||
 	     amdgpu_has_atpx_dgpu_power_cntl()) &&
 	    ((adev->flags & AMD_IS_APU) == 0) &&
-	    !pci_is_thunderbolt_attached(to_pci_dev(dev->dev)))
+	    !dev_is_removable(&adev->pdev->dev))
 		adev->flags |= AMD_IS_PX;
 
 	if (!(adev->flags & AMD_IS_APU)) {
@@ -3962,13 +3964,23 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
-			tmp = amdgpu_reset_method;
-			/* It should do a default reset when loading or reloading the driver,
-			 * regardless of the module parameter reset_method.
-			 */
-			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
-			r = amdgpu_asic_reset(adev);
-			amdgpu_reset_method = tmp;
+			switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) {
+			case IP_VERSION(13, 0, 0):
+			case IP_VERSION(13, 0, 7):
+			case IP_VERSION(13, 0, 10):
+				r = psp_gpu_reset(adev);
+				break;
+			default:
+				tmp = amdgpu_reset_method;
+				/* It should do a default reset when loading or reloading the driver,
+				 * regardless of the module parameter reset_method.
+				 */
+				amdgpu_reset_method = AMD_RESET_METHOD_NONE;
+				r = amdgpu_asic_reset(adev);
+				amdgpu_reset_method = tmp;
+				break;
+			}
+
 			if (r) {
 				dev_err(adev->dev, "asic reset on init failed\n");
 				goto failed;
@@ -4132,7 +4144,7 @@ fence_driver_init:
 
 	px = amdgpu_device_supports_px(ddev);
 
-	if (px || (!pci_is_thunderbolt_attached(adev->pdev) &&
+	if (px || (!dev_is_removable(&adev->pdev->dev) &&
 				apple_gmux_detect(NULL, NULL)))
 		vga_switcheroo_register_client(adev->pdev,
 					       &amdgpu_switcheroo_ops, px);
@@ -4282,7 +4294,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 
 	px = amdgpu_device_supports_px(adev_to_drm(adev));
 
-	if (px || (!pci_is_thunderbolt_attached(adev->pdev) &&
+	if (px || (!dev_is_removable(&adev->pdev->dev) &&
 				apple_gmux_detect(NULL, NULL)))
 		vga_switcheroo_unregister_client(adev->pdev);
 
@@ -5566,10 +5578,6 @@ skip_hw_reset:
 			drm_sched_start(&ring->sched, true);
 		}
 
-		if (adev->enable_mes &&
-		    amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(11, 0, 3))
-			amdgpu_mes_self_test(tmp_adev);
-
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index b6a53e8429b2..0431eafa86b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -99,6 +99,7 @@
 MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY);
 
 #define mmRCC_CONFIG_MEMSIZE	0xde3
+#define mmMP0_SMN_C2PMSG_33	0x16061
 #define mmMM_INDEX		0x0
 #define mmMM_INDEX_HI		0x6
 #define mmMM_DATA		0x1
@@ -239,8 +240,26 @@ static int amdgpu_discovery_read_binary_from_sysmem(struct amdgpu_device *adev,
 static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 						 uint8_t *binary)
 {
-	uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
-	int ret = 0;
+	uint64_t vram_size;
+	u32 msg;
+	int i, ret = 0;
+
+	/* It can take up to a second for IFWI init to complete on some dGPUs,
+	 * but generally it should be in the 60-100ms range.  Normally this starts
+	 * as soon as the device gets power so by the time the OS loads this has long
+	 * completed.  However, when a card is hotplugged via e.g., USB4, we need to
+	 * wait for this to complete.  Once the C2PMSG is updated, we can
+	 * continue.
+	 */
+	if (dev_is_removable(&adev->pdev->dev)) {
+		for (i = 0; i < 1000; i++) {
+			msg = RREG32(mmMP0_SMN_C2PMSG_33);
+			if (msg & 0x80000000)
+				break;
+			msleep(1);
+		}
+	}
+	vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
 
 	if (vram_size) {
 		uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET;
@@ -2449,6 +2468,9 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(4, 8, 0))
 		adev->gmc.xgmi.supported = true;
 
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3))
+		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 4, 0);
+
 	/* set NBIO version */
 	switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) {
 	case IP_VERSION(6, 1, 0):
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index b5e28fa3f414..e7e87a3b2601 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -409,7 +409,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach)
 		if (!r)
 			r = amdgpu_vm_clear_freed(adev, vm, NULL);
 		if (!r)
-			r = amdgpu_vm_handle_moved(adev, vm);
+			r = amdgpu_vm_handle_moved(adev, vm, ticket);
 
 		if (r && r != -EBUSY)
 			DRM_ERROR("Failed to invalidate VM page tables (%d))\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6cc6e3991410..3095a3a864af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2041,6 +2041,14 @@ static const struct pci_device_id pciidlist[] = {
 
 MODULE_DEVICE_TABLE(pci, pciidlist);
 
+static const struct amdgpu_asic_type_quirk asic_type_quirks[] = {
+	/* differentiate between P10 and P11 asics with the same DID */
+	{0x67FF, 0xE3, CHIP_POLARIS10},
+	{0x67FF, 0xE7, CHIP_POLARIS10},
+	{0x67FF, 0xF3, CHIP_POLARIS10},
+	{0x67FF, 0xF7, CHIP_POLARIS10},
+};
+
 static const struct drm_driver amdgpu_kms_driver;
 
 static void amdgpu_get_secondary_funcs(struct amdgpu_device *adev)
@@ -2083,6 +2091,22 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 	}
 }
 
+static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(asic_type_quirks); i++) {
+		if (pdev->device == asic_type_quirks[i].device &&
+			pdev->revision == asic_type_quirks[i].revision) {
+				flags &= ~AMD_ASIC_MASK;
+				flags |= asic_type_quirks[i].type;
+				break;
+			}
+	}
+
+	return flags;
+}
+
 static int amdgpu_pci_probe(struct pci_dev *pdev,
 			    const struct pci_device_id *ent)
 {
@@ -2110,15 +2134,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 			 "See modparam exp_hw_support\n");
 		return -ENODEV;
 	}
-	/* differentiate between P10 and P11 asics with the same DID */
-	if (pdev->device == 0x67FF &&
-	    (pdev->revision == 0xE3 ||
-	     pdev->revision == 0xE7 ||
-	     pdev->revision == 0xF3 ||
-	     pdev->revision == 0xF7)) {
-		flags &= ~AMD_ASIC_MASK;
-		flags |= CHIP_POLARIS10;
-	}
+
+	flags = amdgpu_fix_asic_type(pdev, flags);
 
 	/* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping,
 	 * however, SME requires an indirect IOMMU mapping because the encryption
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c92e0aba69e1..a2a29dcb2422 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -385,9 +385,11 @@ int amdgpu_gfx_mqd_sw_init(struct amdgpu_device *adev,
 	struct amdgpu_ring *ring = &kiq->ring;
 	u32 domain = AMDGPU_GEM_DOMAIN_GTT;
 
+#if !defined(CONFIG_ARM) && !defined(CONFIG_ARM64)
 	/* Only enable on gfx10 and 11 for now to avoid changing behavior on older chips */
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 0, 0))
 		domain |= AMDGPU_GEM_DOMAIN_VRAM;
+#endif
 
 	/* create MQD for KIQ */
 	if (!adev->enable_mes_kiq && !ring->mqd_obj) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 59f10b353b3a..9ddbf1494326 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -557,8 +557,20 @@ static void amdgpu_mes_queue_init_mqd(struct amdgpu_device *adev,
 	mqd_prop.hqd_queue_priority = p->hqd_queue_priority;
 	mqd_prop.hqd_active = false;
 
+	if (p->queue_type == AMDGPU_RING_TYPE_GFX ||
+	    p->queue_type == AMDGPU_RING_TYPE_COMPUTE) {
+		mutex_lock(&adev->srbm_mutex);
+		amdgpu_gfx_select_me_pipe_q(adev, p->ring->me, p->ring->pipe, 0, 0, 0);
+	}
+
 	mqd_mgr->init_mqd(adev, q->mqd_cpu_ptr, &mqd_prop);
 
+	if (p->queue_type == AMDGPU_RING_TYPE_GFX ||
+	    p->queue_type == AMDGPU_RING_TYPE_COMPUTE) {
+		amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
+	}
+
 	amdgpu_bo_unreserve(q->mqd_obj);
 }
 
@@ -994,9 +1006,13 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id,
 	switch (queue_type) {
 	case AMDGPU_RING_TYPE_GFX:
 		ring->funcs = adev->gfx.gfx_ring[0].funcs;
+		ring->me = adev->gfx.gfx_ring[0].me;
+		ring->pipe = adev->gfx.gfx_ring[0].pipe;
 		break;
 	case AMDGPU_RING_TYPE_COMPUTE:
 		ring->funcs = adev->gfx.compute_ring[0].funcs;
+		ring->me = adev->gfx.compute_ring[0].me;
+		ring->pipe = adev->gfx.compute_ring[0].pipe;
 		break;
 	case AMDGPU_RING_TYPE_SDMA:
 		ring->funcs = adev->sdma.instance[0].ring.funcs;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 648bd5e12830..32b701cc0376 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2120,6 +2120,21 @@ int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev)
 	return ret;
 }
 
+int amdgpu_psp_query_boot_status(struct amdgpu_device *adev)
+{
+	struct psp_context *psp = &adev->psp;
+	int ret = 0;
+
+	if (amdgpu_sriov_vf(adev) || (adev->flags & AMD_IS_APU))
+		return 0;
+
+	if (psp->funcs &&
+	    psp->funcs->query_boot_status)
+		ret = psp->funcs->query_boot_status(psp);
+
+	return ret;
+}
+
 static int psp_hw_start(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 7111dd32e66f..5d36ad3f48c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -134,6 +134,7 @@ struct psp_funcs {
 	int (*update_spirom)(struct psp_context *psp, uint64_t fw_pri_mc_addr);
 	int (*vbflash_stat)(struct psp_context *psp);
 	int (*fatal_error_recovery_quirk)(struct psp_context *psp);
+	int (*query_boot_status)(struct psp_context *psp);
 };
 
 struct ta_funcs {
@@ -537,4 +538,6 @@ int is_psp_fw_valid(struct psp_bin_desc bin);
 
 int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev);
 
+int amdgpu_psp_query_boot_status(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 303fbb6a48b6..b7fe5951b166 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
 	struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0);
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs;
+	struct amdgpu_hive_info *hive;
+	int hive_ras_recovery = 0;
 
 	if (!block_obj || !block_obj->hw_ops) {
 		dev_dbg_once(adev->dev, "%s doesn't config RAS function\n",
@@ -1229,15 +1231,22 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev,
 		return -EOPNOTSUPP;
 	}
 
-	/* skip ras error reset in gpu reset */
-	if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) &&
-	    mca_funcs && mca_funcs->mca_set_debug_mode)
-		return -EOPNOTSUPP;
-
 	if (!amdgpu_ras_is_supported(adev, block) ||
 	    !amdgpu_ras_get_mca_debug_mode(adev))
 		return -EOPNOTSUPP;
 
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		hive_ras_recovery = atomic_read(&hive->ras_recovery);
+		amdgpu_put_xgmi_hive(hive);
+	}
+
+	/* skip ras error reset in gpu reset */
+	if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) ||
+	    hive_ras_recovery) &&
+	    mca_funcs && mca_funcs->mca_set_debug_mode)
+		return -EOPNOTSUPP;
+
 	if (block_obj->hw_ops->reset_ras_error_count)
 		block_obj->hw_ops->reset_ras_error_count(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index f74347cc087a..d65e21914d8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -166,8 +166,12 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 			}
 		}
 
-		if (reset)
+		if (reset) {
+			/* use mode-2 reset for poison consumption */
+			if (!entry)
+				con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
 			amdgpu_ras_reset_gpu(adev);
+		}
 	}
 
 	kfree(err_data->err_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 3cd5977c0709..904252456d25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1373,6 +1373,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
+ * @ticket: optional reservation ticket used to reserve the VM
  *
  * Make sure all BOs which are moved are updated in the PTs.
  *
@@ -1382,11 +1383,12 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
  * PTs have to be reserved!
  */
 int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
-			   struct amdgpu_vm *vm)
+			   struct amdgpu_vm *vm,
+			   struct ww_acquire_ctx *ticket)
 {
 	struct amdgpu_bo_va *bo_va;
 	struct dma_resv *resv;
-	bool clear;
+	bool clear, unlock;
 	int r;
 
 	spin_lock(&vm->status_lock);
@@ -1409,17 +1411,24 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		spin_unlock(&vm->status_lock);
 
 		/* Try to reserve the BO to avoid clearing its ptes */
-		if (!adev->debug_vm && dma_resv_trylock(resv))
+		if (!adev->debug_vm && dma_resv_trylock(resv)) {
 			clear = false;
+			unlock = true;
+		/* The caller is already holding the reservation lock */
+		} else if (ticket && dma_resv_locking_ctx(resv) == ticket) {
+			clear = false;
+			unlock = false;
 		/* Somebody else is using the BO right now */
-		else
+		} else {
 			clear = true;
+			unlock = false;
+		}
 
 		r = amdgpu_vm_bo_update(adev, bo_va, clear);
 		if (r)
 			return r;
 
-		if (!clear)
+		if (unlock)
 			dma_resv_unlock(resv);
 		spin_lock(&vm->status_lock);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 9c7b5d33b56e..2cd86d2bf73f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -443,7 +443,8 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
 			  struct dma_fence **fence);
 int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
-			   struct amdgpu_vm *vm);
+			   struct amdgpu_vm *vm,
+			   struct ww_acquire_ctx *ticket);
 void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 			    struct amdgpu_vm *vm, struct amdgpu_bo *bo);
 int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 18f58efc9dc7..08916538a615 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -77,7 +77,16 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
 	return true;
 }
 
+static inline u64 amdgpu_vram_mgr_blocks_size(struct list_head *head)
+{
+	struct drm_buddy_block *block;
+	u64 size = 0;
 
+	list_for_each_entry(block, head, link)
+		size += amdgpu_vram_mgr_block_size(block);
+
+	return size;
+}
 
 /**
  * DOC: mem_info_vram_total
@@ -516,6 +525,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	mutex_unlock(&mgr->lock);
 
 	vres->base.start = 0;
+	size = max_t(u64, amdgpu_vram_mgr_blocks_size(&vres->blocks),
+		     vres->base.size);
 	list_for_each_entry(block, &vres->blocks, link) {
 		unsigned long start;
 
@@ -523,8 +534,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			amdgpu_vram_mgr_block_size(block);
 		start >>= PAGE_SHIFT;
 
-		if (start > PFN_UP(vres->base.size))
-			start -= PFN_UP(vres->base.size);
+		if (start > PFN_UP(size))
+			start -= PFN_UP(size);
 		else
 			start = 0;
 		vres->base.start = max(vres->base.start, start);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d9ccacd06fba..c8a3bf01743f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3498,6 +3498,8 @@ static void gfx_v10_0_ring_invalidate_tlbs(struct amdgpu_ring *ring,
 static void gfx_v10_0_update_spm_vmid_internal(struct amdgpu_device *adev,
 					       unsigned int vmid);
 
+static int gfx_v10_0_set_powergating_state(void *handle,
+					  enum amd_powergating_state state);
 static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
@@ -6465,11 +6467,18 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 		nv_grbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 		if (adev->gfx.me.mqd_backup[mqd_idx])
-			memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else {
+		mutex_lock(&adev->srbm_mutex);
+		nv_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
+		if (ring->doorbell_index == adev->doorbell_index.gfx_ring0 << 1)
+			gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+
+		nv_grbm_select(adev, 0, 0, 0, 0);
+		mutex_unlock(&adev->srbm_mutex);
 		/* restore mqd with the backup copy */
 		if (adev->gfx.me.mqd_backup[mqd_idx])
-			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
 		*ring->wptr_cpu_addr = 0;
@@ -6743,7 +6752,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring)
 	if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.kiq[0].mqd_backup)
-			memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
 
 		/* reset ring buffer */
 		ring->wptr = 0;
@@ -6766,7 +6775,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring)
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.kiq[0].mqd_backup)
-			memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
 	}
 
 	return 0;
@@ -6787,11 +6796,11 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring)
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
-			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else {
 		/* restore MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
-			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset ring buffer */
 		ring->wptr = 0;
 		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
@@ -7172,6 +7181,13 @@ static int gfx_v10_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
+	/* WA added for Vangogh asic fixing the SMU suspend failure
+	 * It needs to set power gating again during gfxoff control
+	 * otherwise the gfxoff disallowing will be failed to set.
+	 */
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(10, 3, 1))
+		gfx_v10_0_set_powergating_state(handle, AMD_PG_STATE_UNGATE);
+
 	if (!adev->no_hw_access) {
 		if (amdgpu_async_gfx_ring) {
 			if (amdgpu_gfx_disable_kgq(adev, 0))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index fd22943685f7..0c6133cc5e57 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -155,6 +155,7 @@ static void gfx11_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue
 {
 	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
 	amdgpu_ring_write(kiq_ring, PACKET3_SET_RESOURCES_VMID_MASK(0) |
+			  PACKET3_SET_RESOURCES_UNMAP_LATENTY(0xa) | /* unmap_latency: 0xa (~ 1s) */
 			  PACKET3_SET_RESOURCES_QUEUE_TYPE(0));	/* vmid_mask:0 queue_type:0 (KIQ) */
 	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
 	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
@@ -3714,11 +3715,11 @@ static int gfx_v11_0_gfx_init_queue(struct amdgpu_ring *ring)
 		soc21_grbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
 		if (adev->gfx.me.mqd_backup[mqd_idx])
-			memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else {
 		/* restore mqd with the backup copy */
 		if (adev->gfx.me.mqd_backup[mqd_idx])
-			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
 		*ring->wptr_cpu_addr = 0;
@@ -4007,7 +4008,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring)
 	if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */
 		/* reset MQD to a clean status */
 		if (adev->gfx.kiq[0].mqd_backup)
-			memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd));
 
 		/* reset ring buffer */
 		ring->wptr = 0;
@@ -4030,7 +4031,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring)
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.kiq[0].mqd_backup)
-			memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd));
 	}
 
 	return 0;
@@ -4051,11 +4052,11 @@ static int gfx_v11_0_kcq_init_queue(struct amdgpu_ring *ring)
 		mutex_unlock(&adev->srbm_mutex);
 
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
-			memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
+			memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else {
 		/* restore MQD to a clean status */
 		if (adev->gfx.mec.mqd_backup[mqd_idx])
-			memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
+			memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset ring buffer */
 		ring->wptr = 0;
 		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index e523627cfe25..df218d5ca775 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -28,6 +28,7 @@
 #include "nbio/nbio_2_3_offset.h"
 #include "nbio/nbio_2_3_sh_mask.h"
 #include <uapi/linux/kfd_ioctl.h>
+#include <linux/device.h>
 #include <linux/pci.h>
 
 #define smnPCIE_CONFIG_CNTL	0x11180044
@@ -361,7 +362,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
 
 		data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT;
 
-		if (pci_is_thunderbolt_attached(adev->pdev))
+		if (dev_is_removable(&adev->pdev->dev))
 			data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT  << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
 		else
 			data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
@@ -480,7 +481,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
 	data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT;
-	if (pci_is_thunderbolt_attached(adev->pdev))
+	if (dev_is_removable(&adev->pdev->dev))
 		data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT  << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
 	else
 		data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 4142e2fcd866..3cf4684d0d3f 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -759,6 +759,83 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp)
 	return 0;
 }
 
+
+static void psp_v13_0_boot_error_reporting(struct amdgpu_device *adev,
+					   uint32_t inst,
+					   uint32_t boot_error)
+{
+	uint32_t socket_id;
+	uint32_t aid_id;
+	uint32_t hbm_id;
+	uint32_t reg_data;
+
+	socket_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, SOCKET_ID);
+	aid_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, AID_ID);
+	hbm_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, HBM_ID);
+
+	reg_data = RREG32_SOC15(MP0, inst, regMP0_SMN_C2PMSG_109);
+	dev_info(adev->dev, "socket: %d, aid: %d, firmware boot failed, fw status is 0x%x\n",
+		 socket_id, aid_id, reg_data);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_MEM_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, memory training failed\n",
+			 socket_id, aid_id, hbm_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_FW_LOAD))
+		dev_info(adev->dev, "socket: %d, aid: %d, firmware load failed at boot time\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_WAFL_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, wafl link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_XGMI_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, xgmi link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_CP_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, usr cp link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_DP_LINK_TRAINING))
+		dev_info(adev->dev, "socket: %d, aid: %d, usr dp link training failed\n",
+			 socket_id, aid_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_MEM_TEST))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm memory test failed\n",
+			 socket_id, aid_id, hbm_id);
+
+	if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_BIST_TEST))
+		dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm bist test failed\n",
+			 socket_id, aid_id, hbm_id);
+}
+
+static int psp_v13_0_query_boot_status(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+	int inst_mask = adev->aid_mask;
+	uint32_t reg_data;
+	uint32_t i;
+	int ret = 0;
+
+	if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6))
+		return 0;
+
+	if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007)
+		return 0;
+
+	for_each_inst(i, inst_mask) {
+		reg_data = RREG32_SOC15(MP0, i, regMP0_SMN_C2PMSG_126);
+		if (!REG_GET_FIELD(reg_data, MP0_SMN_C2PMSG_126, BOOT_STATUS)) {
+			psp_v13_0_boot_error_reporting(adev, i, reg_data);
+			ret = -EINVAL;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 static const struct psp_funcs psp_v13_0_funcs = {
 	.init_microcode = psp_v13_0_init_microcode,
 	.wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state,
@@ -781,6 +858,7 @@ static const struct psp_funcs psp_v13_0_funcs = {
 	.update_spirom = psp_v13_0_update_spirom,
 	.vbflash_stat = psp_v13_0_vbflash_status,
 	.fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk,
+	.query_boot_status = psp_v13_0_query_boot_status,
 };
 
 void psp_v13_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index 743d2f68b090..770b4b4e3138 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -91,8 +91,7 @@ static void umc_v12_0_reset_error_count(struct amdgpu_device *adev)
 static bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status)
 {
 	return ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
-		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
-		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
+		(REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 ||
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 ||
 		REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1));
 }