Merge tag 'amd-drm-next-5.14-2021-07-01' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-07-01:

amdgpu:
- Misc Navi fixes
- Powergating fix
- Yellow Carp updates
- Beige Goby updates
- S0ix fix
- Revert overlay validation fix
- GPU reset fix for DC
- PPC64 fix
- Add new dimgrey cavefish DID
- RAS fix

amdkfd:
- SVM fixes

radeon:
- Fix missing drm_gem_object_put in error path

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210701042241.25449-1-alexander.deucher@amd.com

40 files changed, 987 insertions, 464 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 130a9adf09ef..d303e88e3c23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1369,6 +1369,38 @@ def_value:
 	adev->pm.smu_prv_buffer_size = 0;
 }
 
+static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev)
+{
+	if (!(adev->flags & AMD_IS_APU) ||
+	    adev->asic_type < CHIP_RAVEN)
+		return 0;
+
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+		if (adev->pdev->device == 0x15dd)
+			adev->apu_flags |= AMD_APU_IS_RAVEN;
+		if (adev->pdev->device == 0x15d8)
+			adev->apu_flags |= AMD_APU_IS_PICASSO;
+		break;
+	case CHIP_RENOIR:
+		if ((adev->pdev->device == 0x1636) ||
+		    (adev->pdev->device == 0x164c))
+			adev->apu_flags |= AMD_APU_IS_RENOIR;
+		else
+			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
+		break;
+	case CHIP_VANGOGH:
+		adev->apu_flags |= AMD_APU_IS_VANGOGH;
+		break;
+	case CHIP_YELLOW_CARP:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_device_check_arguments - validate module params
  *
@@ -3386,6 +3418,10 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->psp.mutex);
 	mutex_init(&adev->notifier_lock);
 
+	r = amdgpu_device_init_apu_flags(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_check_arguments(adev);
 	if (r)
 		return r;
@@ -4304,6 +4340,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_SIENNA_CICHLID:
 		case CHIP_NAVY_FLOUNDER:
 		case CHIP_DIMGREY_CAVEFISH:
+		case CHIP_BEIGE_GOBY:
 		case CHIP_VANGOGH:
 		case CHIP_ALDEBARAN:
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6f30c525caac..71beb0db0125 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -160,6 +160,7 @@ int amdgpu_smu_pptable_id = -1;
  *     highest. That helps saving some idle power.
  * DISABLE_FRACTIONAL_PWM (bit 2) disabled by default
  * PSR (bit 3) disabled by default
+ * EDP NO POWER SEQUENCING (bit 4) disabled by default
  */
 uint amdgpu_dc_feature_mask = 2;
 uint amdgpu_dc_debug_mask;
@@ -1198,6 +1199,7 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x73E0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73E3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73FF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 
 	/* Aldebaran */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 0174f7817ce2..d0b8d415b63b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -562,6 +562,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
 	case CHIP_VANGOGH:
+	case CHIP_YELLOW_CARP:
 		/* Don't enable it by default yet.
 		 */
 		if (amdgpu_tmz < 1) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index d6c54c7f7679..4b153daf283d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -160,7 +160,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct mm_struct *mm, struct page **pages,
 			       uint64_t start, uint64_t npages,
 			       struct hmm_range **phmm_range, bool readonly,
-			       bool mmap_locked)
+			       bool mmap_locked, void *owner)
 {
 	struct hmm_range *hmm_range;
 	unsigned long timeout;
@@ -185,6 +185,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 	hmm_range->hmm_pfns = pfns;
 	hmm_range->start = start;
 	hmm_range->end = start + npages * PAGE_SIZE;
+	hmm_range->dev_private_owner = owner;
 
 	/* Assuming 512MB takes maxmium 1 second to fault page address */
 	timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index 7f7d37a457c3..14a3c1864085 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
@@ -34,7 +34,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       struct mm_struct *mm, struct page **pages,
 			       uint64_t start, uint64_t npages,
 			       struct hmm_range **phmm_range, bool readonly,
-			       bool mmap_locked);
+			       bool mmap_locked, void *owner);
 int amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range);
 
 #if defined(CONFIG_HMM_MIRROR)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 25ee53545837..45295dce5c3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -93,6 +93,8 @@ struct amdgpu_nbio_funcs {
 	void (*enable_aspm)(struct amdgpu_device *adev,
 			    bool enable);
 	void (*program_aspm)(struct amdgpu_device *adev);
+	void (*apply_lc_spc_mode_wa)(struct amdgpu_device *adev);
+	void (*apply_l1_link_width_reconfig_wa)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_nbio {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6a214a4dfe04..2e9ad6e0dfbb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -590,10 +590,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev,
 
 		mem->bus.offset += adev->gmc.aper_base;
 		mem->bus.is_iomem = true;
-		if (adev->gmc.xgmi.connected_to_cpu)
-			mem->bus.caching = ttm_cached;
-		else
-			mem->bus.caching = ttm_write_combined;
 		break;
 	default:
 		return -EINVAL;
@@ -696,7 +692,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	readonly = amdgpu_ttm_tt_is_readonly(ttm);
 	r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start,
 				       ttm->num_pages, &gtt->range, readonly,
-				       false);
+				       false, NULL);
 out_putmm:
 	mmput(mm);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 436ec246a7da..2fd77c36a1ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -463,6 +463,11 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	if (i == 1)
 		node->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
 
+	if (adev->gmc.xgmi.connected_to_cpu)
+		node->base.bus.caching = ttm_cached;
+	else
+		node->base.bus.caching = ttm_write_combined;
+
 	atomic64_add(vis_usage, &mgr->vis_usage);
 	*res = &node->base;
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
index 5b90efd6f6d0..3ac505d954c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
@@ -36,9 +36,12 @@ athub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+		return;
+
 	def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+	if (enable)
 		data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK;
 	else
 		data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK;
@@ -53,10 +56,13 @@ athub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
+	if (!((adev->cg_flags & AMD_CG_SUPPORT_MC_LS) &&
+	       (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS)))
+		return;
+
 	def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) &&
-	    (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))
+	if (enable)
 		data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
 	else
 		data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2d56b60bc058..f5e9c022960b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -5086,47 +5086,44 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 		4 + /* RMI */
 		1); /* SQG */
 
-	if (adev->asic_type == CHIP_NAVI10 ||
-	    adev->asic_type == CHIP_NAVI14 ||
-	    adev->asic_type == CHIP_NAVI12) {
-		mutex_lock(&adev->grbm_idx_mutex);
-		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
-			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
-				gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
-				wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev);
-				/*
-				 * Set corresponding TCP bits for the inactive WGPs in
-				 * GCRD_SA_TARGETS_DISABLE
-				 */
-				gcrd_targets_disable_tcp = 0;
-				/* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */
-				utcl_invreq_disable = 0;
-
-				for (k = 0; k < max_wgp_per_sh; k++) {
-					if (!(wgp_active_bitmap & (1 << k))) {
-						gcrd_targets_disable_tcp |= 3 << (2 * k);
-						utcl_invreq_disable |= (3 << (2 * k)) |
-							(3 << (2 * (max_wgp_per_sh + k)));
-					}
+	mutex_lock(&adev->grbm_idx_mutex);
+	for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
+		for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+			gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
+			wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev);
+			/*
+			 * Set corresponding TCP bits for the inactive WGPs in
+			 * GCRD_SA_TARGETS_DISABLE
+			 */
+			gcrd_targets_disable_tcp = 0;
+			/* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */
+			utcl_invreq_disable = 0;
+
+			for (k = 0; k < max_wgp_per_sh; k++) {
+				if (!(wgp_active_bitmap & (1 << k))) {
+					gcrd_targets_disable_tcp |= 3 << (2 * k);
+					gcrd_targets_disable_tcp |= 1 << (k + (max_wgp_per_sh * 2));
+					utcl_invreq_disable |= (3 << (2 * k)) |
+						(3 << (2 * (max_wgp_per_sh + k)));
 				}
-
-				tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE);
-				/* only override TCP & SQC bits */
-				tmp &= 0xffffffff << (4 * max_wgp_per_sh);
-				tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask);
-				WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp);
-
-				tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE);
-				/* only override TCP bits */
-				tmp &= 0xffffffff << (2 * max_wgp_per_sh);
-				tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask);
-				WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp);
 			}
-		}
 
-		gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-		mutex_unlock(&adev->grbm_idx_mutex);
+			tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE);
+			/* only override TCP & SQC bits */
+			tmp &= (0xffffffffU << (4 * max_wgp_per_sh));
+			tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask);
+			WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp);
+
+			tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE);
+			/* only override TCP & SQC bits */
+			tmp &= (0xffffffffU << (3 * max_wgp_per_sh));
+			tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask);
+			WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp);
+		}
 	}
+
+	gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	mutex_unlock(&adev->grbm_idx_mutex);
 }
 
 static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
@@ -7404,7 +7401,10 @@ static int gfx_v10_0_hw_init(void *handle)
 	 * init golden registers and rlc resume may override some registers,
 	 * reconfig them here
 	 */
-	gfx_v10_0_tcp_harvest(adev);
+	if (adev->asic_type == CHIP_NAVI10 ||
+	    adev->asic_type == CHIP_NAVI14 ||
+	    adev->asic_type == CHIP_NAVI12)
+		gfx_v10_0_tcp_harvest(adev);
 
 	r = gfx_v10_0_cp_resume(adev);
 	if (r)
@@ -7777,6 +7777,9 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t data, def;
 
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS)))
+		return;
+
 	/* It is disabled by HW by default */
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 0 - Disable some blocks' MGCG */
@@ -7791,6 +7794,7 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 			  RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 
 		if (def != data)
@@ -7813,13 +7817,15 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade
 					WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data);
 			}
 		}
-	} else {
+	} else if (!enable || !(adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 1 - MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
-			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
+			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK |
+			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK |
+			 RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK);
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -7845,22 +7851,34 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t data, def;
 
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS)))
+		return;
+
 	/* Enable 3D CGCG/CGLS */
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)) {
+	if (enable) {
 		/* write cmd to clear cgcg/cgls ov */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
+
 		/* unset CGCG override */
-		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK;
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK;
+
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
+
 		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
-		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
-			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+		data = 0;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+				RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
 				RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK;
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data);
 
@@ -7873,9 +7891,14 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev,
 	} else {
 		/* Disable CGCG/CGLS */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
+
 		/* disable cgcg, cgls should be disabled */
-		data &= ~(RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK |
-			  RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK);
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)
+			data &= ~RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
+			data &= ~RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK;
+
 		/* disable cgcg and cgls in FSM */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data);
@@ -7887,25 +7910,35 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) {
+	if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS)))
+		return;
+
+	if (enable) {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
+
 		/* unset CGCG override */
-		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK;
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK;
-		else
-			data |= RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK;
+
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
 		/* enable cgcg FSM(0x0000363F) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
-		data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
-			RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+		data = 0;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+				RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
 				RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK;
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data);
 
@@ -7917,8 +7950,14 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade
 			WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_CNTL, data);
 	} else {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
+
 		/* reset CGCG/CGLS bits */
-		data &= ~(RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK | RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK);
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)
+			data &= ~RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
+
+		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
+			data &= ~RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK;
+
 		/* disable cgcg and cgls in FSM */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data);
@@ -7930,7 +7969,10 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t def, data;
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG)) {
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG))
+		return;
+
+	if (enable) {
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
 		/* unset FGCG override */
 		data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK;
@@ -7961,6 +8003,97 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev,
 	}
 }
 
+static void gfx_v10_0_apply_medium_grain_clock_gating_workaround(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+	uint32_t reg_idx = 0;
+	uint32_t i;
+
+	const uint32_t tcp_ctrl_regs[] = {
+		mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP12_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP12_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP12_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP12_CU1_TCP_CTRL_REG
+	};
+
+	const uint32_t tcp_ctrl_regs_nv12[] = {
+		mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG,
+		mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG,
+	};
+
+	const uint32_t sm_ctlr_regs[] = {
+		mmCGTS_SA0_QUAD0_SM_CTRL_REG,
+		mmCGTS_SA0_QUAD1_SM_CTRL_REG,
+		mmCGTS_SA1_QUAD0_SM_CTRL_REG,
+		mmCGTS_SA1_QUAD1_SM_CTRL_REG
+	};
+
+	if (adev->asic_type == CHIP_NAVI12) {
+		for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs_nv12); i++) {
+			reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+				  tcp_ctrl_regs_nv12[i];
+			reg_data = RREG32(reg_idx);
+			reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+			WREG32(reg_idx, reg_data);
+		}
+	} else {
+		for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs); i++) {
+			reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] +
+				  tcp_ctrl_regs[i];
+			reg_data = RREG32(reg_idx);
+			reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK;
+			WREG32(reg_idx, reg_data);
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(sm_ctlr_regs); i++) {
+		reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_QUAD0_SM_CTRL_REG_BASE_IDX] +
+			  sm_ctlr_regs[i];
+		reg_data = RREG32(reg_idx);
+		reg_data &= ~CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE_MASK;
+		reg_data |= 2 << CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE__SHIFT;
+		WREG32(reg_idx, reg_data);
+	}
+}
+
 static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 					    bool enable)
 {
@@ -7977,6 +8110,10 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  CGCG + CGLS === */
 		gfx_v10_0_update_coarse_grain_clock_gating(adev, enable);
+
+		if ((adev->asic_type >= CHIP_NAVI10) &&
+		     (adev->asic_type <= CHIP_NAVI12))
+			gfx_v10_0_apply_medium_grain_clock_gating_workaround(adev);
 	} else {
 		/* CGCG/CGLS should be disabled before MGCG/MGLS
 		 * ===  CGCG + CGLS ===
@@ -9324,17 +9461,22 @@ static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(struct amdgpu_device *
 
 static u32 gfx_v10_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev)
 {
-	u32 data, wgp_bitmask;
-	data = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG);
-	data |= RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG);
+	u32 disabled_mask =
+		~amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1);
+	u32 efuse_setting = 0;
+	u32 vbios_setting = 0;
+
+	efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG);
+	efuse_setting &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
+	efuse_setting >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
 
-	data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
-	data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
+	vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG);
+	vbios_setting &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK;
+	vbios_setting >>= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT;
 
-	wgp_bitmask =
-		amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1);
+	disabled_mask |= efuse_setting | vbios_setting;
 
-	return (~data) & wgp_bitmask;
+	return (~disabled_mask);
 }
 
 static u32 gfx_v10_0_get_cu_active_bitmap_per_sh(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
index 7a15e669b68d..5793977953cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c
@@ -90,45 +90,56 @@ static void hdp_v5_0_update_mem_power_gating(struct amdgpu_device *adev,
 					 RC_MEM_POWER_SD_EN, 0);
 	WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
 
-	/* only one clock gating mode (LS/DS/SD) can be enabled */
-	if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_LS_EN, enable);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_LS_EN, enable);
-	} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_DS_EN, enable);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_DS_EN, enable);
-	} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_SD_EN, enable);
-		/* RC should not use shut down mode, fallback to ds */
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
-						 HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_DS_EN, enable);
-	}
-
-	/* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to
-	 * be set for SRAM LS/DS/SD */
-	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
-			      AMD_CG_SUPPORT_HDP_SD)) {
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
-						 IPH_MEM_POWER_CTRL_EN, 1);
-		hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
-						 RC_MEM_POWER_CTRL_EN, 1);
+	/* Already disabled above. The actions below are for "enabled" only */
+	if (enable) {
+		/* only one clock gating mode (LS/DS/SD) can be enabled */
+		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_LS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_LS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_DS_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_DS_EN, 1);
+		} else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+							 HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_SD_EN, 1);
+			/* RC should not use shut down mode, fallback to ds  or ls if allowed */
+			if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS)
+				hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+								 HDP_MEM_POWER_CTRL,
+								 RC_MEM_POWER_DS_EN, 1);
+			else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS)
+				hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl,
+								 HDP_MEM_POWER_CTRL,
+								 RC_MEM_POWER_LS_EN, 1);
+		}
+
+		/* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to
+		 * be set for SRAM LS/DS/SD */
+		if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS |
+				      AMD_CG_SUPPORT_HDP_SD)) {
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 IPH_MEM_POWER_CTRL_EN, 1);
+			hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL,
+							 RC_MEM_POWER_CTRL_EN, 1);
+			WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
+		}
 	}
 
-	WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl);
-
-	/* restore IPH & RC clock override after clock/power mode changing */
-	WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl1);
+	/* disable IPH & RC clock override after clock/power mode changing */
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     IPH_MEM_CLK_SOFT_OVERRIDE, 0);
+	hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL,
+				     RC_MEM_CLK_SOFT_OVERRIDE, 0);
+	WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl);
 }
 
 static void hdp_v5_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index f7e93bbc4e15..7ded6b2f058e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -568,6 +568,9 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 {
 	uint32_t def, data, def1, data1;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG))
+		return;
+
 	switch (adev->asic_type) {
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
@@ -582,7 +585,7 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
 		break;
 	}
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) {
+	if (enable) {
 		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
 
 		data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
@@ -627,6 +630,9 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
+		return;
+
 	switch (adev->asic_type) {
 	case CHIP_SIENNA_CICHLID:
 	case CHIP_NAVY_FLOUNDER:
@@ -639,7 +645,7 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
 		break;
 	}
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
+	if (enable)
 		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
 	else
 		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index 05ddec7ba7e2..7b79eeaa88aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -51,6 +51,8 @@
 #define mmBIF_MMSCH1_DOORBELL_RANGE		0x01d8
 #define mmBIF_MMSCH1_DOORBELL_RANGE_BASE_IDX	2
 
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
 static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
@@ -218,8 +220,11 @@ static void nbio_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *ade
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG))
+		return;
+
 	def = data = RREG32_PCIE(smnCPM_CONTROL);
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG)) {
+	if (enable) {
 		data |= (CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK |
 			 CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK |
 			 CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK |
@@ -244,8 +249,11 @@ static void nbio_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev
 {
 	uint32_t def, data;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS))
+		return;
+
 	def = data = RREG32_PCIE(smnPCIE_CNTL2);
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) {
+	if (enable) {
 		data |= (PCIE_CNTL2__SLV_MEM_LS_EN_MASK |
 			 PCIE_CNTL2__MST_MEM_LS_EN_MASK |
 			 PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK);
@@ -463,6 +471,43 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 		WREG32_PCIE(smnPCIE_LC_CNTL3, data);
 }
 
+static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+	uint32_t link_width = 0;
+
+	if (!((adev->asic_type >= CHIP_NAVI10) &&
+	     (adev->asic_type <= CHIP_NAVI12)))
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	link_width = (reg_data & PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+		>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+
+	/*
+	 * Program PCIE_LC_CNTL6.LC_SPC_MODE_8GT to 0x2 (4 symbols per clock data)
+	 * if link_width is 0x3 (x4)
+	 */
+	if (0x3 == link_width) {
+		reg_data = RREG32_PCIE(smnPCIE_LC_CNTL6);
+		reg_data &= ~PCIE_LC_CNTL6__LC_SPC_MODE_8GT_MASK;
+		reg_data |= (0x2 << PCIE_LC_CNTL6__LC_SPC_MODE_8GT__SHIFT);
+		WREG32_PCIE(smnPCIE_LC_CNTL6, reg_data);
+	}
+}
+
+static void nbio_v2_3_apply_l1_link_width_reconfig_wa(struct amdgpu_device *adev)
+{
+	uint32_t reg_data = 0;
+
+	if (adev->asic_type != CHIP_NAVI10)
+		return;
+
+	reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL);
+	reg_data |= PCIE_LC_LINK_WIDTH_CNTL__LC_L1_RECONFIG_EN_MASK;
+	WREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL, reg_data);
+}
+
 const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset,
@@ -484,4 +529,6 @@ const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.remap_hdp_registers = nbio_v2_3_remap_hdp_registers,
 	.enable_aspm = nbio_v2_3_enable_aspm,
 	.program_aspm =  nbio_v2_3_program_aspm,
+	.apply_lc_spc_mode_wa = nbio_v2_3_apply_lc_spc_mode_wa,
+	.apply_l1_link_width_reconfig_wa = nbio_v2_3_apply_l1_link_width_reconfig_wa,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 455d0425787c..94a2c0742ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -64,6 +64,13 @@
 #include "smuio_v11_0.h"
 #include "smuio_v11_0_6.h"
 
+#define codec_info_build(type, width, height, level) \
+			 .codec_type = type,\
+			 .max_width = width,\
+			 .max_height = height,\
+			 .max_pixels_per_frame = height * width,\
+			 .max_level = level,
+
 static const struct amd_ip_funcs nv_common_ip_funcs;
 
 /* Navi */
@@ -309,6 +316,23 @@ static struct amdgpu_video_codecs sriov_sc_video_codecs_decode =
 	.codec_array = sriov_sc_video_codecs_decode_array,
 };
 
+/* Beige Goby*/
+static const struct amdgpu_video_codec_info bg_video_codecs_decode_array[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+};
+
+static const struct amdgpu_video_codecs bg_video_codecs_decode = {
+	.codec_count = ARRAY_SIZE(bg_video_codecs_decode_array),
+	.codec_array = bg_video_codecs_decode_array,
+};
+
+static const struct amdgpu_video_codecs bg_video_codecs_encode = {
+	.codec_count = 0,
+	.codec_array = NULL,
+};
+
 static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
@@ -335,6 +359,12 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 		else
 			*codecs = &sc_video_codecs_decode;
 		return 0;
+	case CHIP_BEIGE_GOBY:
+		if (encode)
+			*codecs = &bg_video_codecs_encode;
+		else
+			*codecs = &bg_video_codecs_decode;
+		return 0;
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
@@ -1275,7 +1305,6 @@ static int nv_common_early_init(void *handle)
 		break;
 
 	case CHIP_VANGOGH:
-		adev->apu_flags |= AMD_APU_IS_VANGOGH;
 		adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 			AMD_CG_SUPPORT_GFX_MGLS |
 			AMD_CG_SUPPORT_GFX_CP_LS |
@@ -1411,6 +1440,12 @@ static int nv_common_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (adev->nbio.funcs->apply_lc_spc_mode_wa)
+		adev->nbio.funcs->apply_lc_spc_mode_wa(adev);
+
+	if (adev->nbio.funcs->apply_l1_link_width_reconfig_wa)
+		adev->nbio.funcs->apply_l1_link_width_reconfig_wa(adev);
+
 	/* enable pcie gen2/3 link */
 	nv_pcie_gen3_enable(adev);
 	/* enable aspm */
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ae5464e2535a..8931000dcd41 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -144,7 +144,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
-	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
@@ -288,7 +288,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_POWER_CNTL, 0x003fff07, 0x40000051),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
-	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe)
 };
 
@@ -1896,8 +1896,11 @@ static int sdma_v4_0_late_init(void *handle)
 
 	sdma_v4_0_setup_ulv(adev);
 
-	if (adev->sdma.funcs && adev->sdma.funcs->reset_ras_error_count)
-		adev->sdma.funcs->reset_ras_error_count(adev);
+	if (!amdgpu_persistent_edc_harvesting_supported(adev)) {
+		if (adev->sdma.funcs &&
+		    adev->sdma.funcs->reset_ras_error_count)
+			adev->sdma.funcs->reset_ras_error_count(adev);
+	}
 
 	if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init)
 		return adev->sdma.funcs->ras_late_init(adev, &ih_info);
diff --git a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
index e9c474c217ec..b6f1322f908c 100644
--- a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c
@@ -43,9 +43,12 @@ static void smuio_v11_0_update_rom_clock_gating(struct amdgpu_device *adev, bool
 	if (adev->flags & AMD_IS_APU)
 		return;
 
+	if (!(adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG))
+		return;
+
 	def = data = RREG32_SOC15(SMUIO, 0, mmCGTT_ROM_CLK_CTRL0);
 
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG))
+	if (enable)
 		data &= ~(CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK |
 			CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE1_MASK);
 	else
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index de85577c9cfd..b02436401d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1360,10 +1360,7 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RAVEN:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if (adev->pdev->device == 0x15dd)
-			adev->apu_flags |= AMD_APU_IS_RAVEN;
-		if (adev->pdev->device == 0x15d8)
-			adev->apu_flags |= AMD_APU_IS_PICASSO;
+
 		if (adev->rev_id >= 0x8)
 			adev->apu_flags |= AMD_APU_IS_RAVEN2;
 
@@ -1455,11 +1452,6 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if ((adev->pdev->device == 0x1636) ||
-		    (adev->pdev->device == 0x164c))
-			adev->apu_flags |= AMD_APU_IS_RENOIR;
-		else
-			adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
 
 		if (adev->apu_flags & AMD_APU_IS_RENOIR)
 			adev->external_rev_id = adev->rev_id + 0x91;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 2660f03e63a7..dab290a4d19d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -218,7 +218,8 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn)
 	struct page *page;
 
 	page = pfn_to_page(pfn);
-	page->zone_device_data = prange;
+	svm_range_bo_ref(prange->svm_bo);
+	page->zone_device_data = prange->svm_bo;
 	get_page(page);
 	lock_page(page);
 }
@@ -293,15 +294,13 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	for (i = j = 0; i < npages; i++) {
 		struct page *spage;
 
-		dst[i] = cursor.start + (j << PAGE_SHIFT);
-		migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
-		svm_migrate_get_vram_page(prange, migrate->dst[i]);
-
-		migrate->dst[i] = migrate_pfn(migrate->dst[i]);
-		migrate->dst[i] |= MIGRATE_PFN_LOCKED;
-
-		if (migrate->src[i] & MIGRATE_PFN_VALID) {
-			spage = migrate_pfn_to_page(migrate->src[i]);
+		spage = migrate_pfn_to_page(migrate->src[i]);
+		if (spage && !is_zone_device_page(spage)) {
+			dst[i] = cursor.start + (j << PAGE_SHIFT);
+			migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]);
+			svm_migrate_get_vram_page(prange, migrate->dst[i]);
+			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
+			migrate->dst[i] |= MIGRATE_PFN_LOCKED;
 			src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE,
 					      DMA_TO_DEVICE);
 			r = dma_mapping_error(dev, src[i]);
@@ -355,6 +354,20 @@ out_free_vram_pages:
 		}
 	}
 
+#ifdef DEBUG_FORCE_MIXED_DOMAINS
+	for (i = 0, j = 0; i < npages; i += 4, j++) {
+		if (j & 1)
+			continue;
+		svm_migrate_put_vram_page(adev, dst[i]);
+		migrate->dst[i] = 0;
+		svm_migrate_put_vram_page(adev, dst[i + 1]);
+		migrate->dst[i + 1] = 0;
+		svm_migrate_put_vram_page(adev, dst[i + 2]);
+		migrate->dst[i + 2] = 0;
+		svm_migrate_put_vram_page(adev, dst[i + 3]);
+		migrate->dst[i + 3] = 0;
+	}
+#endif
 out:
 	return r;
 }
@@ -365,20 +378,20 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			uint64_t end)
 {
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
+	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
 	struct migrate_vma migrate;
 	dma_addr_t *scratch;
 	size_t size;
 	void *buf;
 	int r = -ENOMEM;
-	int retry = 0;
 
 	memset(&migrate, 0, sizeof(migrate));
 	migrate.vma = vma;
 	migrate.start = start;
 	migrate.end = end;
 	migrate.flags = MIGRATE_VMA_SELECT_SYSTEM;
-	migrate.pgmap_owner = adev;
+	migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev);
 
 	size = 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t);
 	size *= npages;
@@ -390,7 +403,6 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.dst = migrate.src + npages;
 	scratch = (dma_addr_t *)(migrate.dst + npages);
 
-retry:
 	r = migrate_vma_setup(&migrate);
 	if (r) {
 		pr_debug("failed %d prepare migrate svms 0x%p [0x%lx 0x%lx]\n",
@@ -398,17 +410,9 @@ retry:
 		goto out_free;
 	}
 	if (migrate.cpages != npages) {
-		pr_debug("collect 0x%lx/0x%llx pages, retry\n", migrate.cpages,
+		pr_debug("Partial migration. 0x%lx/0x%llx pages can be migrated\n",
+			 migrate.cpages,
 			 npages);
-		migrate_vma_finalize(&migrate);
-		if (retry++ >= 3) {
-			r = -ENOMEM;
-			pr_debug("failed %d migrate svms 0x%p [0x%lx 0x%lx]\n",
-				 r, prange->svms, prange->start, prange->last);
-			goto out_free;
-		}
-
-		goto retry;
 	}
 
 	if (migrate.cpages) {
@@ -425,6 +429,12 @@ retry:
 out_free:
 	kvfree(buf);
 out:
+	if (!r) {
+		pdd = svm_range_get_pdd_by_adev(prange, adev);
+		if (pdd)
+			WRITE_ONCE(pdd->page_in, pdd->page_in + migrate.cpages);
+	}
+
 	return r;
 }
 
@@ -464,7 +474,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 		 prange->start, prange->last, best_loc);
 
 	/* FIXME: workaround for page locking bug with invalid pages */
-	svm_range_prefault(prange, mm);
+	svm_range_prefault(prange, mm, SVM_ADEV_PGMAP_OWNER(adev));
 
 	start = prange->start << PAGE_SHIFT;
 	end = (prange->last + 1) << PAGE_SHIFT;
@@ -493,15 +503,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 
 static void svm_migrate_page_free(struct page *page)
 {
-	/* Keep this function to avoid warning */
+	struct svm_range_bo *svm_bo = page->zone_device_data;
+
+	if (svm_bo) {
+		pr_debug("svm_bo ref left: %d\n", kref_read(&svm_bo->kref));
+		svm_range_bo_unref(svm_bo);
+	}
 }
 
 static int
 svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 			struct migrate_vma *migrate, struct dma_fence **mfence,
-			dma_addr_t *scratch)
+			dma_addr_t *scratch, uint64_t npages)
 {
-	uint64_t npages = migrate->cpages;
 	struct device *dev = adev->dev;
 	uint64_t *src;
 	dma_addr_t *dst;
@@ -518,15 +532,23 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
 
-	for (i = 0, j = 0; i < npages; i++, j++, addr += PAGE_SIZE) {
+	for (i = 0, j = 0; i < npages; i++, addr += PAGE_SIZE) {
 		struct page *spage;
 
 		spage = migrate_pfn_to_page(migrate->src[i]);
-		if (!spage) {
-			pr_debug("failed get spage svms 0x%p [0x%lx 0x%lx]\n",
+		if (!spage || !is_zone_device_page(spage)) {
+			pr_debug("invalid page. Could be in CPU already svms 0x%p [0x%lx 0x%lx]\n",
 				 prange->svms, prange->start, prange->last);
-			r = -ENOMEM;
-			goto out_oom;
+			if (j) {
+				r = svm_migrate_copy_memory_gart(adev, dst + i - j,
+								 src + i - j, j,
+								 FROM_VRAM_TO_RAM,
+								 mfence);
+				if (r)
+					goto out_oom;
+				j = 0;
+			}
+			continue;
 		}
 		src[i] = svm_migrate_addr(adev, spage);
 		if (i > 0 && src[i] != src[i - 1] + PAGE_SIZE) {
@@ -559,6 +581,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 		migrate->dst[i] = migrate_pfn(page_to_pfn(dpage));
 		migrate->dst[i] |= MIGRATE_PFN_LOCKED;
+		j++;
 	}
 
 	r = svm_migrate_copy_memory_gart(adev, dst + i - j, src + i - j, j,
@@ -581,6 +604,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 		       struct vm_area_struct *vma, uint64_t start, uint64_t end)
 {
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
+	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
 	struct migrate_vma migrate;
 	dma_addr_t *scratch;
@@ -593,7 +617,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.start = start;
 	migrate.end = end;
 	migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
-	migrate.pgmap_owner = adev;
+	migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev);
 
 	size = 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t);
 	size *= npages;
@@ -616,7 +640,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	if (migrate.cpages) {
 		r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence,
-					    scratch);
+					    scratch, npages);
 		migrate_vma_pages(&migrate);
 		svm_migrate_copy_done(adev, mfence);
 		migrate_vma_finalize(&migrate);
@@ -630,6 +654,12 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 out_free:
 	kvfree(buf);
 out:
+	if (!r) {
+		pdd = svm_range_get_pdd_by_adev(prange, adev);
+		if (pdd)
+			WRITE_ONCE(pdd->page_out,
+				   pdd->page_out + migrate.cpages);
+	}
 	return r;
 }
 
@@ -859,7 +889,7 @@ int svm_migrate_init(struct amdgpu_device *adev)
 	pgmap->range.start = res->start;
 	pgmap->range.end = res->end;
 	pgmap->ops = &svm_migrate_pgmap_ops;
-	pgmap->owner = adev;
+	pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev);
 	pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6dc22fa1e555..3426743ed228 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -730,6 +730,15 @@ struct kfd_process_device {
 	 *  number of CU's a device has along with number of other competing processes
 	 */
 	struct attribute attr_cu_occupancy;
+
+	/* sysfs counters for GPU retry fault and page migration tracking */
+	struct kobject *kobj_counters;
+	struct attribute attr_faults;
+	struct attribute attr_page_in;
+	struct attribute attr_page_out;
+	uint64_t faults;
+	uint64_t page_in;
+	uint64_t page_out;
 };
 
 #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 09b98a83f670..21ec8a18cad2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -416,6 +416,29 @@ static ssize_t kfd_procfs_stats_show(struct kobject *kobj,
 	return 0;
 }
 
+static ssize_t kfd_sysfs_counters_show(struct kobject *kobj,
+				       struct attribute *attr, char *buf)
+{
+	struct kfd_process_device *pdd;
+
+	if (!strcmp(attr->name, "faults")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_faults);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->faults));
+	}
+	if (!strcmp(attr->name, "page_in")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_page_in);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_in));
+	}
+	if (!strcmp(attr->name, "page_out")) {
+		pdd = container_of(attr, struct kfd_process_device,
+				   attr_page_out);
+		return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_out));
+	}
+	return 0;
+}
+
 static struct attribute attr_queue_size = {
 	.name = "size",
 	.mode = KFD_SYSFS_FILE_MODE
@@ -451,13 +474,18 @@ static const struct sysfs_ops procfs_stats_ops = {
 	.show = kfd_procfs_stats_show,
 };
 
-static struct attribute *procfs_stats_attrs[] = {
-	NULL
-};
-
 static struct kobj_type procfs_stats_type = {
 	.sysfs_ops = &procfs_stats_ops,
-	.default_attrs = procfs_stats_attrs,
+	.release = kfd_procfs_kobj_release,
+};
+
+static const struct sysfs_ops sysfs_counters_ops = {
+	.show = kfd_sysfs_counters_show,
+};
+
+static struct kobj_type sysfs_counters_type = {
+	.sysfs_ops = &sysfs_counters_ops,
+	.release = kfd_procfs_kobj_release,
 };
 
 int kfd_procfs_add_queue(struct queue *q)
@@ -484,34 +512,31 @@ int kfd_procfs_add_queue(struct queue *q)
 	return 0;
 }
 
-static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr,
+static void kfd_sysfs_create_file(struct kobject *kobj, struct attribute *attr,
 				 char *name)
 {
-	int ret = 0;
+	int ret;
 
-	if (!p || !attr || !name)
-		return -EINVAL;
+	if (!kobj || !attr || !name)
+		return;
 
 	attr->name = name;
 	attr->mode = KFD_SYSFS_FILE_MODE;
 	sysfs_attr_init(attr);
 
-	ret = sysfs_create_file(p->kobj, attr);
-
-	return ret;
+	ret = sysfs_create_file(kobj, attr);
+	if (ret)
+		pr_warn("Create sysfs %s/%s failed %d", kobj->name, name, ret);
 }
 
-static int kfd_procfs_add_sysfs_stats(struct kfd_process *p)
+static void kfd_procfs_add_sysfs_stats(struct kfd_process *p)
 {
-	int ret = 0;
+	int ret;
 	int i;
 	char stats_dir_filename[MAX_SYSFS_FILENAME_LEN];
 
-	if (!p)
-		return -EINVAL;
-
-	if (!p->kobj)
-		return -EFAULT;
+	if (!p || !p->kobj)
+		return;
 
 	/*
 	 * Create sysfs files for each GPU:
@@ -521,63 +546,87 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p)
 	 */
 	for (i = 0; i < p->n_pdds; i++) {
 		struct kfd_process_device *pdd = p->pdds[i];
-		struct kobject *kobj_stats;
 
 		snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN,
 				"stats_%u", pdd->dev->id);
-		kobj_stats = kfd_alloc_struct(kobj_stats);
-		if (!kobj_stats)
-			return -ENOMEM;
+		pdd->kobj_stats = kfd_alloc_struct(pdd->kobj_stats);
+		if (!pdd->kobj_stats)
+			return;
 
-		ret = kobject_init_and_add(kobj_stats,
-						&procfs_stats_type,
-						p->kobj,
-						stats_dir_filename);
+		ret = kobject_init_and_add(pdd->kobj_stats,
+					   &procfs_stats_type,
+					   p->kobj,
+					   stats_dir_filename);
 
 		if (ret) {
 			pr_warn("Creating KFD proc/stats_%s folder failed",
-					stats_dir_filename);
-			kobject_put(kobj_stats);
-			goto err;
+				stats_dir_filename);
+			kobject_put(pdd->kobj_stats);
+			pdd->kobj_stats = NULL;
+			return;
 		}
 
-		pdd->kobj_stats = kobj_stats;
-		pdd->attr_evict.name = "evicted_ms";
-		pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE;
-		sysfs_attr_init(&pdd->attr_evict);
-		ret = sysfs_create_file(kobj_stats, &pdd->attr_evict);
-		if (ret)
-			pr_warn("Creating eviction stats for gpuid %d failed",
-					(int)pdd->dev->id);
-
+		kfd_sysfs_create_file(pdd->kobj_stats, &pdd->attr_evict,
+				      "evicted_ms");
 		/* Add sysfs file to report compute unit occupancy */
-		if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) {
-			pdd->attr_cu_occupancy.name = "cu_occupancy";
-			pdd->attr_cu_occupancy.mode = KFD_SYSFS_FILE_MODE;
-			sysfs_attr_init(&pdd->attr_cu_occupancy);
-			ret = sysfs_create_file(kobj_stats,
-						&pdd->attr_cu_occupancy);
-			if (ret)
-				pr_warn("Creating %s failed for gpuid: %d",
-					pdd->attr_cu_occupancy.name,
-					(int)pdd->dev->id);
-		}
+		if (pdd->dev->kfd2kgd->get_cu_occupancy)
+			kfd_sysfs_create_file(pdd->kobj_stats,
+					      &pdd->attr_cu_occupancy,
+					      "cu_occupancy");
 	}
-err:
-	return ret;
 }
 
-
-static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
+static void kfd_procfs_add_sysfs_counters(struct kfd_process *p)
 {
 	int ret = 0;
 	int i;
+	char counters_dir_filename[MAX_SYSFS_FILENAME_LEN];
 
-	if (!p)
-		return -EINVAL;
+	if (!p || !p->kobj)
+		return;
 
-	if (!p->kobj)
-		return -EFAULT;
+	/*
+	 * Create sysfs files for each GPU which supports SVM
+	 * - proc/<pid>/counters_<gpuid>/
+	 * - proc/<pid>/counters_<gpuid>/faults
+	 * - proc/<pid>/counters_<gpuid>/page_in
+	 * - proc/<pid>/counters_<gpuid>/page_out
+	 */
+	for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) {
+		struct kfd_process_device *pdd = p->pdds[i];
+		struct kobject *kobj_counters;
+
+		snprintf(counters_dir_filename, MAX_SYSFS_FILENAME_LEN,
+			"counters_%u", pdd->dev->id);
+		kobj_counters = kfd_alloc_struct(kobj_counters);
+		if (!kobj_counters)
+			return;
+
+		ret = kobject_init_and_add(kobj_counters, &sysfs_counters_type,
+					   p->kobj, counters_dir_filename);
+		if (ret) {
+			pr_warn("Creating KFD proc/%s folder failed",
+				counters_dir_filename);
+			kobject_put(kobj_counters);
+			return;
+		}
+
+		pdd->kobj_counters = kobj_counters;
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_faults,
+				      "faults");
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_in,
+				      "page_in");
+		kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_out,
+				      "page_out");
+	}
+}
+
+static void kfd_procfs_add_sysfs_files(struct kfd_process *p)
+{
+	int i;
+
+	if (!p || !p->kobj)
+		return;
 
 	/*
 	 * Create sysfs files for each GPU:
@@ -589,20 +638,14 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p)
 
 		snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u",
 			 pdd->dev->id);
-		ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename);
-		if (ret)
-			pr_warn("Creating vram usage for gpu id %d failed",
-				(int)pdd->dev->id);
+		kfd_sysfs_create_file(p->kobj, &pdd->attr_vram,
+				      pdd->vram_filename);
 
 		snprintf(pdd->sdma_filename, MAX_SYSFS_FILENAME_LEN, "sdma_%u",
 			 pdd->dev->id);
-		ret = kfd_sysfs_create_file(p, &pdd->attr_sdma, pdd->sdma_filename);
-		if (ret)
-			pr_warn("Creating sdma usage for gpu id %d failed",
-				(int)pdd->dev->id);
+		kfd_sysfs_create_file(p->kobj, &pdd->attr_sdma,
+					    pdd->sdma_filename);
 	}
-
-	return ret;
 }
 
 void kfd_procfs_del_queue(struct queue *q)
@@ -800,28 +843,17 @@ struct kfd_process *kfd_create_process(struct file *filep)
 			goto out;
 		}
 
-		process->attr_pasid.name = "pasid";
-		process->attr_pasid.mode = KFD_SYSFS_FILE_MODE;
-		sysfs_attr_init(&process->attr_pasid);
-		ret = sysfs_create_file(process->kobj, &process->attr_pasid);
-		if (ret)
-			pr_warn("Creating pasid for pid %d failed",
-					(int)process->lead_thread->pid);
+		kfd_sysfs_create_file(process->kobj, &process->attr_pasid,
+				      "pasid");
 
 		process->kobj_queues = kobject_create_and_add("queues",
 							process->kobj);
 		if (!process->kobj_queues)
 			pr_warn("Creating KFD proc/queues folder failed");
 
-		ret = kfd_procfs_add_sysfs_stats(process);
-		if (ret)
-			pr_warn("Creating sysfs stats dir for pid %d failed",
-				(int)process->lead_thread->pid);
-
-		ret = kfd_procfs_add_sysfs_files(process);
-		if (ret)
-			pr_warn("Creating sysfs usage file for pid %d failed",
-				(int)process->lead_thread->pid);
+		kfd_procfs_add_sysfs_stats(process);
+		kfd_procfs_add_sysfs_files(process);
+		kfd_procfs_add_sysfs_counters(process);
 	}
 out:
 	if (!IS_ERR(process))
@@ -964,6 +996,50 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 	p->n_pdds = 0;
 }
 
+static void kfd_process_remove_sysfs(struct kfd_process *p)
+{
+	struct kfd_process_device *pdd;
+	int i;
+
+	if (!p->kobj)
+		return;
+
+	sysfs_remove_file(p->kobj, &p->attr_pasid);
+	kobject_del(p->kobj_queues);
+	kobject_put(p->kobj_queues);
+	p->kobj_queues = NULL;
+
+	for (i = 0; i < p->n_pdds; i++) {
+		pdd = p->pdds[i];
+
+		sysfs_remove_file(p->kobj, &pdd->attr_vram);
+		sysfs_remove_file(p->kobj, &pdd->attr_sdma);
+
+		sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict);
+		if (pdd->dev->kfd2kgd->get_cu_occupancy)
+			sysfs_remove_file(pdd->kobj_stats,
+					  &pdd->attr_cu_occupancy);
+		kobject_del(pdd->kobj_stats);
+		kobject_put(pdd->kobj_stats);
+		pdd->kobj_stats = NULL;
+	}
+
+	for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) {
+		pdd = p->pdds[i];
+
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_faults);
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_in);
+		sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_out);
+		kobject_del(pdd->kobj_counters);
+		kobject_put(pdd->kobj_counters);
+		pdd->kobj_counters = NULL;
+	}
+
+	kobject_del(p->kobj);
+	kobject_put(p->kobj);
+	p->kobj = NULL;
+}
+
 /* No process locking is needed in this function, because the process
  * is not findable any more. We must assume that no other thread is
  * using it any more, otherwise we couldn't safely free the process
@@ -973,33 +1049,7 @@ static void kfd_process_wq_release(struct work_struct *work)
 {
 	struct kfd_process *p = container_of(work, struct kfd_process,
 					     release_work);
-	int i;
-
-	/* Remove the procfs files */
-	if (p->kobj) {
-		sysfs_remove_file(p->kobj, &p->attr_pasid);
-		kobject_del(p->kobj_queues);
-		kobject_put(p->kobj_queues);
-		p->kobj_queues = NULL;
-
-		for (i = 0; i < p->n_pdds; i++) {
-			struct kfd_process_device *pdd = p->pdds[i];
-
-			sysfs_remove_file(p->kobj, &pdd->attr_vram);
-			sysfs_remove_file(p->kobj, &pdd->attr_sdma);
-			sysfs_remove_file(p->kobj, &pdd->attr_evict);
-			if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL)
-				sysfs_remove_file(p->kobj, &pdd->attr_cu_occupancy);
-			kobject_del(pdd->kobj_stats);
-			kobject_put(pdd->kobj_stats);
-			pdd->kobj_stats = NULL;
-		}
-
-		kobject_del(p->kobj);
-		kobject_put(p->kobj);
-		p->kobj = NULL;
-	}
-
+	kfd_process_remove_sysfs(p);
 	kfd_iommu_unbind_process(p);
 
 	kfd_process_free_outstanding_kfd_bos(p);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 95a6c36cea4c..243dd1efcdbf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -153,6 +153,7 @@ void pqm_uninit(struct process_queue_manager *pqm)
 		if (pqn->q && pqn->q->gws)
 			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
 				pqn->q->gws);
+		kfd_procfs_del_queue(pqn->q);
 		uninit_queue(pqn->q);
 		list_del(&pqn->process_queue_list);
 		kfree(pqn);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index dff1011dd7ee..9a71d8919bd6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -119,28 +119,40 @@ static void svm_range_remove_notifier(struct svm_range *prange)
 }
 
 static int
-svm_range_dma_map_dev(struct device *dev, dma_addr_t **dma_addr,
-		      unsigned long *hmm_pfns, uint64_t npages)
+svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange,
+		      unsigned long *hmm_pfns, uint32_t gpuidx)
 {
 	enum dma_data_direction dir = DMA_BIDIRECTIONAL;
-	dma_addr_t *addr = *dma_addr;
+	dma_addr_t *addr = prange->dma_addr[gpuidx];
+	struct device *dev = adev->dev;
 	struct page *page;
 	int i, r;
 
 	if (!addr) {
-		addr = kvmalloc_array(npages, sizeof(*addr),
+		addr = kvmalloc_array(prange->npages, sizeof(*addr),
 				      GFP_KERNEL | __GFP_ZERO);
 		if (!addr)
 			return -ENOMEM;
-		*dma_addr = addr;
+		prange->dma_addr[gpuidx] = addr;
 	}
 
-	for (i = 0; i < npages; i++) {
+	for (i = 0; i < prange->npages; i++) {
 		if (WARN_ONCE(addr[i] && !dma_mapping_error(dev, addr[i]),
 			      "leaking dma mapping\n"))
 			dma_unmap_page(dev, addr[i], PAGE_SIZE, dir);
 
 		page = hmm_pfn_to_page(hmm_pfns[i]);
+		if (is_zone_device_page(page)) {
+			struct amdgpu_device *bo_adev =
+					amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev);
+
+			addr[i] = (hmm_pfns[i] << PAGE_SHIFT) +
+				   bo_adev->vm_manager.vram_base_offset -
+				   bo_adev->kfd.dev->pgmap.range.start;
+			addr[i] |= SVM_RANGE_VRAM_DOMAIN;
+			pr_debug("vram address detected: 0x%llx\n", addr[i]);
+			continue;
+		}
 		addr[i] = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
 		r = dma_mapping_error(dev, addr[i]);
 		if (r) {
@@ -175,8 +187,7 @@ svm_range_dma_map(struct svm_range *prange, unsigned long *bitmap,
 		}
 		adev = (struct amdgpu_device *)pdd->dev->kgd;
 
-		r = svm_range_dma_map_dev(adev->dev, &prange->dma_addr[gpuidx],
-					  hmm_pfns, prange->npages);
+		r = svm_range_dma_map_dev(adev, prange, hmm_pfns, gpuidx);
 		if (r)
 			break;
 	}
@@ -301,14 +312,6 @@ static bool svm_bo_ref_unless_zero(struct svm_range_bo *svm_bo)
 	return true;
 }
 
-static struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
-{
-	if (svm_bo)
-		kref_get(&svm_bo->kref);
-
-	return svm_bo;
-}
-
 static void svm_range_bo_release(struct kref *kref)
 {
 	struct svm_range_bo *svm_bo;
@@ -347,7 +350,7 @@ static void svm_range_bo_release(struct kref *kref)
 	kfree(svm_bo);
 }
 
-static void svm_range_bo_unref(struct svm_range_bo *svm_bo)
+void svm_range_bo_unref(struct svm_range_bo *svm_bo)
 {
 	if (!svm_bo)
 		return;
@@ -564,6 +567,24 @@ svm_range_get_adev_by_id(struct svm_range *prange, uint32_t gpu_id)
 	return (struct amdgpu_device *)pdd->dev->kgd;
 }
 
+struct kfd_process_device *
+svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev)
+{
+	struct kfd_process *p;
+	int32_t gpu_idx, gpuid;
+	int r;
+
+	p = container_of(prange->svms, struct kfd_process, svms);
+
+	r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpu_idx);
+	if (r) {
+		pr_debug("failed to get device id by adev %p\n", adev);
+		return NULL;
+	}
+
+	return kfd_process_device_from_gpuidx(p, gpu_idx);
+}
+
 static int svm_range_bo_validate(void *param, struct amdgpu_bo *bo)
 {
 	struct ttm_operation_ctx ctx = { false, false };
@@ -1002,21 +1023,22 @@ svm_range_split_by_granularity(struct kfd_process *p, struct mm_struct *mm,
 }
 
 static uint64_t
-svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange)
+svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange,
+			int domain)
 {
 	struct amdgpu_device *bo_adev;
 	uint32_t flags = prange->flags;
 	uint32_t mapping_flags = 0;
 	uint64_t pte_flags;
-	bool snoop = !prange->ttm_res;
+	bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN);
 	bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT;
 
-	if (prange->svm_bo && prange->ttm_res)
+	if (domain == SVM_RANGE_VRAM_DOMAIN)
 		bo_adev = amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev);
 
 	switch (adev->asic_type) {
 	case CHIP_ARCTURUS:
-		if (prange->svm_bo && prange->ttm_res) {
+		if (domain == SVM_RANGE_VRAM_DOMAIN) {
 			if (bo_adev == adev) {
 				mapping_flags |= coherent ?
 					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW;
@@ -1032,7 +1054,7 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange)
 		}
 		break;
 	case CHIP_ALDEBARAN:
-		if (prange->svm_bo && prange->ttm_res) {
+		if (domain == SVM_RANGE_VRAM_DOMAIN) {
 			if (bo_adev == adev) {
 				mapping_flags |= coherent ?
 					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW;
@@ -1062,14 +1084,14 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange)
 		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
 
 	pte_flags = AMDGPU_PTE_VALID;
-	pte_flags |= prange->ttm_res ? 0 : AMDGPU_PTE_SYSTEM;
+	pte_flags |= (domain == SVM_RANGE_VRAM_DOMAIN) ? 0 : AMDGPU_PTE_SYSTEM;
 	pte_flags |= snoop ? AMDGPU_PTE_SNOOPED : 0;
 
 	pte_flags |= amdgpu_gem_va_map_flags(adev, mapping_flags);
 
 	pr_debug("svms 0x%p [0x%lx 0x%lx] vram %d PTE 0x%llx mapping 0x%x\n",
 		 prange->svms, prange->start, prange->last,
-		 prange->ttm_res ? 1:0, pte_flags, mapping_flags);
+		 (domain == SVM_RANGE_VRAM_DOMAIN) ? 1:0, pte_flags, mapping_flags);
 
 	return pte_flags;
 }
@@ -1140,31 +1162,41 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	struct amdgpu_bo_va bo_va;
 	bool table_freed = false;
 	uint64_t pte_flags;
+	unsigned long last_start;
+	int last_domain;
 	int r = 0;
+	int64_t i;
 
 	pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start,
 		 prange->last);
 
-	if (prange->svm_bo && prange->ttm_res) {
+	if (prange->svm_bo && prange->ttm_res)
 		bo_va.is_xgmi = amdgpu_xgmi_same_hive(adev, bo_adev);
-		prange->mapping.bo_va = &bo_va;
-	}
 
-	prange->mapping.start = prange->start;
-	prange->mapping.last = prange->last;
-	prange->mapping.offset = prange->ttm_res ? prange->offset : 0;
-	pte_flags = svm_range_get_pte_flags(adev, prange);
+	last_start = prange->start;
+	for (i = 0; i < prange->npages; i++) {
+		last_domain = dma_addr[i] & SVM_RANGE_VRAM_DOMAIN;
+		dma_addr[i] &= ~SVM_RANGE_VRAM_DOMAIN;
+		if ((prange->start + i) < prange->last &&
+		    last_domain == (dma_addr[i + 1] & SVM_RANGE_VRAM_DOMAIN))
+			continue;
 
-	r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
-					prange->mapping.start,
-					prange->mapping.last, pte_flags,
-					prange->mapping.offset,
-					prange->ttm_res,
-					dma_addr, &vm->last_update,
-					&table_freed);
-	if (r) {
-		pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start);
-		goto out;
+		pr_debug("Mapping range [0x%lx 0x%llx] on domain: %s\n",
+			 last_start, prange->start + i, last_domain ? "GPU" : "CPU");
+		pte_flags = svm_range_get_pte_flags(adev, prange, last_domain);
+		r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
+						last_start,
+						prange->start + i, pte_flags,
+						last_start - prange->start,
+						NULL,
+						dma_addr,
+						&vm->last_update,
+						&table_freed);
+		if (r) {
+			pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start);
+			goto out;
+		}
+		last_start = prange->start + i + 1;
 	}
 
 	r = amdgpu_vm_update_pdes(adev, vm, false);
@@ -1185,7 +1217,6 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 						p->pasid, TLB_FLUSH_LEGACY);
 	}
 out:
-	prange->mapping.bo_va = NULL;
 	return r;
 }
 
@@ -1319,6 +1350,17 @@ static void svm_range_unreserve_bos(struct svm_validate_context *ctx)
 	ttm_eu_backoff_reservation(&ctx->ticket, &ctx->validate_list);
 }
 
+static void *kfd_svm_page_owner(struct kfd_process *p, int32_t gpuidx)
+{
+	struct kfd_process_device *pdd;
+	struct amdgpu_device *adev;
+
+	pdd = kfd_process_device_from_gpuidx(p, gpuidx);
+	adev = (struct amdgpu_device *)pdd->dev->kgd;
+
+	return SVM_ADEV_PGMAP_OWNER(adev);
+}
+
 /*
  * Validation+GPU mapping with concurrent invalidation (MMU notifiers)
  *
@@ -1349,6 +1391,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 {
 	struct svm_validate_context ctx;
 	struct hmm_range *hmm_range;
+	struct kfd_process *p;
+	void *owner;
+	int32_t idx;
 	int r = 0;
 
 	ctx.process = container_of(prange->svms, struct kfd_process, svms);
@@ -1394,33 +1439,38 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 
 	svm_range_reserve_bos(&ctx);
 
-	if (!prange->actual_loc) {
-		r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
-					       prange->start << PAGE_SHIFT,
-					       prange->npages, &hmm_range,
-					       false, true);
-		if (r) {
-			pr_debug("failed %d to get svm range pages\n", r);
-			goto unreserve_out;
-		}
-
-		r = svm_range_dma_map(prange, ctx.bitmap,
-				      hmm_range->hmm_pfns);
-		if (r) {
-			pr_debug("failed %d to dma map range\n", r);
-			goto unreserve_out;
+	p = container_of(prange->svms, struct kfd_process, svms);
+	owner = kfd_svm_page_owner(p, find_first_bit(ctx.bitmap,
+						MAX_GPU_INSTANCE));
+	for_each_set_bit(idx, ctx.bitmap, MAX_GPU_INSTANCE) {
+		if (kfd_svm_page_owner(p, idx) != owner) {
+			owner = NULL;
+			break;
 		}
+	}
+	r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
+				       prange->start << PAGE_SHIFT,
+				       prange->npages, &hmm_range,
+				       false, true, owner);
+	if (r) {
+		pr_debug("failed %d to get svm range pages\n", r);
+		goto unreserve_out;
+	}
 
-		prange->validated_once = true;
+	r = svm_range_dma_map(prange, ctx.bitmap,
+			      hmm_range->hmm_pfns);
+	if (r) {
+		pr_debug("failed %d to dma map range\n", r);
+		goto unreserve_out;
 	}
 
+	prange->validated_once = true;
+
 	svm_range_lock(prange);
-	if (!prange->actual_loc) {
-		if (amdgpu_hmm_range_get_pages_done(hmm_range)) {
-			pr_debug("hmm update the range, need validate again\n");
-			r = -EAGAIN;
-			goto unlock_out;
-		}
+	if (amdgpu_hmm_range_get_pages_done(hmm_range)) {
+		pr_debug("hmm update the range, need validate again\n");
+		r = -EAGAIN;
+		goto unlock_out;
 	}
 	if (!list_empty(&prange->child_list)) {
 		pr_debug("range split by unmap in parallel, validate again\n");
@@ -1572,6 +1622,7 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
 		unsigned long start, unsigned long last)
 {
 	struct svm_range_list *svms = prange->svms;
+	struct svm_range *pchild;
 	struct kfd_process *p;
 	int r = 0;
 
@@ -1583,7 +1634,19 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
 	if (!p->xnack_enabled) {
 		int evicted_ranges;
 
-		atomic_inc(&prange->invalid);
+		list_for_each_entry(pchild, &prange->child_list, child_list) {
+			mutex_lock_nested(&pchild->lock, 1);
+			if (pchild->start <= last && pchild->last >= start) {
+				pr_debug("increment pchild invalid [0x%lx 0x%lx]\n",
+					 pchild->start, pchild->last);
+				atomic_inc(&pchild->invalid);
+			}
+			mutex_unlock(&pchild->lock);
+		}
+
+		if (prange->start <= last && prange->last >= start)
+			atomic_inc(&prange->invalid);
+
 		evicted_ranges = atomic_inc_return(&svms->evicted_ranges);
 		if (evicted_ranges != 1)
 			return r;
@@ -1600,7 +1663,6 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm,
 		schedule_delayed_work(&svms->restore_work,
 			msecs_to_jiffies(AMDGPU_SVM_RANGE_RESTORE_DELAY_MS));
 	} else {
-		struct svm_range *pchild;
 		unsigned long s, l;
 
 		pr_debug("invalidate unmap svms 0x%p [0x%lx 0x%lx] from GPUs\n",
@@ -2311,6 +2373,27 @@ static bool svm_range_skip_recover(struct svm_range *prange)
 	return false;
 }
 
+static void
+svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p,
+		      struct svm_range *prange, int32_t gpuidx)
+{
+	struct kfd_process_device *pdd;
+
+	if (gpuidx == MAX_GPU_INSTANCE)
+		/* fault is on different page of same range
+		 * or fault is skipped to recover later
+		 */
+		pdd = svm_range_get_pdd_by_adev(prange, adev);
+	else
+		/* fault recovered
+		 * or fault cannot recover because GPU no access on the range
+		 */
+		pdd = kfd_process_device_from_gpuidx(p, gpuidx);
+
+	if (pdd)
+		WRITE_ONCE(pdd->faults, pdd->faults + 1);
+}
+
 int
 svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 			uint64_t addr)
@@ -2320,7 +2403,8 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 	struct svm_range *prange;
 	struct kfd_process *p;
 	uint64_t timestamp;
-	int32_t best_loc, gpuidx;
+	int32_t best_loc;
+	int32_t gpuidx = MAX_GPU_INSTANCE;
 	bool write_locked = false;
 	int r = 0;
 
@@ -2440,6 +2524,9 @@ out_unlock_range:
 out_unlock_svms:
 	mutex_unlock(&svms->lock);
 	mmap_read_unlock(mm);
+
+	svm_range_count_fault(adev, p, prange, gpuidx);
+
 	mmput(mm);
 out:
 	kfd_unref_process(p);
@@ -2662,7 +2749,8 @@ out:
 /* FIXME: This is a workaround for page locking bug when some pages are
  * invalid during migration to VRAM
  */
-void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm)
+void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
+			void *owner)
 {
 	struct hmm_range *hmm_range;
 	int r;
@@ -2673,7 +2761,7 @@ void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm)
 	r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL,
 				       prange->start << PAGE_SHIFT,
 				       prange->npages, &hmm_range,
-				       false, true);
+				       false, true, owner);
 	if (!r) {
 		amdgpu_hmm_range_get_pages_done(hmm_range);
 		prange->validated_once = true;
@@ -2718,16 +2806,6 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 	    best_loc == prange->actual_loc)
 		return 0;
 
-	/*
-	 * Prefetch to GPU without host access flag, set actual_loc to gpu, then
-	 * validate on gpu and map to gpus will be handled afterwards.
-	 */
-	if (best_loc && !prange->actual_loc &&
-	    !(prange->flags & KFD_IOCTL_SVM_FLAG_HOST_ACCESS)) {
-		prange->actual_loc = best_loc;
-		return 0;
-	}
-
 	if (!best_loc) {
 		r = svm_migrate_vram_to_ram(prange, mm);
 		*migrated = !r;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 0c0fc399395e..3fc1fd8b4fbc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -35,6 +35,10 @@
 #include "amdgpu.h"
 #include "kfd_priv.h"
 
+#define SVM_RANGE_VRAM_DOMAIN (1UL << 0)
+#define SVM_ADEV_PGMAP_OWNER(adev)\
+			((adev)->hive ? (void *)(adev)->hive : (void *)(adev))
+
 struct svm_range_bo {
 	struct amdgpu_bo		*bo;
 	struct kref			kref;
@@ -110,7 +114,6 @@ struct svm_range {
 	struct list_head		update_list;
 	struct list_head		remove_list;
 	struct list_head		insert_list;
-	struct amdgpu_bo_va_mapping	mapping;
 	uint64_t			npages;
 	dma_addr_t			*dma_addr[MAX_GPU_INSTANCE];
 	struct ttm_resource		*ttm_res;
@@ -147,6 +150,14 @@ static inline void svm_range_unlock(struct svm_range *prange)
 	mutex_unlock(&prange->lock);
 }
 
+static inline struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
+{
+	if (svm_bo)
+		kref_get(&svm_bo->kref);
+
+	return svm_bo;
+}
+
 int svm_range_list_init(struct kfd_process *p);
 void svm_range_list_fini(struct kfd_process *p);
 int svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
@@ -173,13 +184,17 @@ void schedule_deferred_list_work(struct svm_range_list *svms);
 void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 			 unsigned long offset, unsigned long npages);
 void svm_range_free_dma_mappings(struct svm_range *prange);
-void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm);
+void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
+			void *owner);
+struct kfd_process_device *
+svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
 
 /* SVM API and HMM page migration work together, device memory type
  * is initialized to not 0 when page migration register device memory.
  */
 #define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0)
 
+void svm_range_bo_unref(struct svm_range_bo *svm_bo);
 #else
 
 struct kfd_process;
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 b5b5ccf0ed71..01e1062dc235 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1160,6 +1160,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_dc_feature_mask & DC_DISABLE_FRACTIONAL_PWM_MASK)
 		init_data.flags.disable_fractional_pwm = true;
 
+	if (amdgpu_dc_feature_mask & DC_EDP_NO_POWER_SEQUENCING)
+		init_data.flags.edp_no_power_sequencing = true;
+
 	init_data.flags.power_down_display_on_boot = true;
 
 	INIT_LIST_HEAD(&adev->dm.da_list);
@@ -10118,7 +10121,7 @@ static int validate_overlay(struct drm_atomic_state *state)
 	int i;
 	struct drm_plane *plane;
 	struct drm_plane_state *new_plane_state;
-	struct drm_plane_state *primary_state, *cursor_state, *overlay_state = NULL;
+	struct drm_plane_state *primary_state, *overlay_state = NULL;
 
 	/* Check if primary plane is contained inside overlay */
 	for_each_new_plane_in_state_reverse(state, plane, new_plane_state, i) {
@@ -10148,14 +10151,6 @@ static int validate_overlay(struct drm_atomic_state *state)
 	if (!primary_state->crtc)
 		return 0;
 
-	/* check if cursor plane is enabled */
-	cursor_state = drm_atomic_get_plane_state(state, overlay_state->crtc->cursor);
-	if (IS_ERR(cursor_state))
-		return PTR_ERR(cursor_state);
-
-	if (drm_atomic_plane_disabling(plane->state, cursor_state))
-		return 0;
-
 	/* Perform the bounds check to ensure the overlay plane covers the primary */
 	if (primary_state->crtc_x < overlay_state->crtc_x ||
 	    primary_state->crtc_y < overlay_state->crtc_y ||
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 5101a4f8f69f..45640f1c26c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -297,6 +297,7 @@ struct dc_config {
 	bool allow_seamless_boot_optimization;
 	bool power_down_display_on_boot;
 	bool edp_not_connected;
+	bool edp_no_power_sequencing;
 	bool force_enum_edp;
 	bool forced_clocks;
 	bool allow_lttpr_non_transparent_mode;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 2938caaa2299..62d595ded866 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1022,8 +1022,20 @@ void dce110_edp_backlight_control(
 	/* dc_service_sleep_in_milliseconds(50); */
 		/*edp 1.2*/
 	panel_instance = link->panel_cntl->inst;
-	if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON)
-		edp_receiver_ready_T7(link);
+
+	if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) {
+		if (!link->dc->config.edp_no_power_sequencing)
+		/*
+		 * Sometimes, DP receiver chip power-controlled externally by an
+		 * Embedded Controller could be treated and used as eDP,
+		 * if it drives mobile display. In this case,
+		 * we shouldn't be doing power-sequencing, hence we can skip
+		 * waiting for T7-ready.
+		 */
+			edp_receiver_ready_T7(link);
+		else
+			DC_LOG_DC("edp_receiver_ready_T7 skipped\n");
+	}
 
 	if (ctx->dc->ctx->dmub_srv &&
 			ctx->dc->debug.dmub_command_table) {
@@ -1048,8 +1060,19 @@ void dce110_edp_backlight_control(
 		dc_link_backlight_enable_aux(link, enable);
 
 	/*edp 1.2*/
-	if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_OFF)
-		edp_add_delay_for_T9(link);
+	if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_OFF) {
+		if (!link->dc->config.edp_no_power_sequencing)
+		/*
+		 * Sometimes, DP receiver chip power-controlled externally by an
+		 * Embedded Controller could be treated and used as eDP,
+		 * if it drives mobile display. In this case,
+		 * we shouldn't be doing power-sequencing, hence we can skip
+		 * waiting for T9-ready.
+		 */
+			edp_add_delay_for_T9(link);
+		else
+			DC_LOG_DC("edp_receiver_ready_T9 skipped\n");
+	}
 
 	if (!enable && link->dpcd_sink_ext_caps.bits.oled)
 		msleep(OLED_PRE_T11_DELAY);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/Makefile b/drivers/gpu/drm/amd/display/dc/dcn31/Makefile
index 5dcdc5a858fe..4bab97acb155 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/Makefile
@@ -28,6 +28,7 @@ endif
 CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -mhard-float
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -36,6 +37,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -msse2
 endif
+endif
 
 AMD_DAL_DCN31 = $(addprefix $(AMDDALPATH)/dc/dcn31/,$(DCN31))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index d34024fd798a..45862167e6ce 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -50,6 +50,10 @@ dml_ccflags += -msse2
 endif
 endif
 
+ifneq ($(CONFIG_FRAME_WARN),0)
+frame_warn_flag := -Wframe-larger-than=2048
+endif
+
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
 ifdef CONFIG_DRM_AMD_DC_DCN
@@ -60,9 +64,9 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) -Wframe-larger-than=2048
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
-CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) -Wframe-larger-than=2048
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags)
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 5f245bde54ff..a2a4fbeb83f8 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -119,7 +119,7 @@ bool dal_irq_service_set(
 
 	dal_irq_service_ack(irq_service, source);
 
-	if (info->funcs->set)
+	if (info->funcs && info->funcs->set)
 		return info->funcs->set(irq_service, info, enable);
 
 	dal_irq_service_set_generic(irq_service, info, enable);
@@ -153,7 +153,7 @@ bool dal_irq_service_ack(
 		return false;
 	}
 
-	if (info->funcs->ack)
+	if (info->funcs && info->funcs->ack)
 		return info->funcs->ack(irq_service, info);
 
 	dal_irq_service_ack_generic(irq_service, info);
diff --git a/drivers/gpu/drm/amd/display/dc/irq_types.h b/drivers/gpu/drm/amd/display/dc/irq_types.h
index 5f9346622301..1139b9eb9f6f 100644
--- a/drivers/gpu/drm/amd/display/dc/irq_types.h
+++ b/drivers/gpu/drm/amd/display/dc/irq_types.h
@@ -165,7 +165,7 @@ enum irq_type
 };
 
 #define DAL_VALID_IRQ_SRC_NUM(src) \
-	((src) <= DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID)
+	((src) < DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID)
 
 /* Number of Page Flip IRQ Sources. */
 #define DAL_PFLIP_IRQ_SRC_NUM \
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 8c886ece71f6..973de346410d 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -352,3 +352,63 @@ uint32_t dmub_dcn31_get_current_time(struct dmub_srv *dmub)
 {
 	return REG_READ(DMCUB_TIMER_CURRENT);
 }
+
+void dmub_dcn31_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data)
+{
+	uint32_t is_dmub_enabled, is_soft_reset, is_sec_reset;
+	uint32_t is_traceport_enabled, is_cw0_enabled, is_cw6_enabled;
+
+	if (!dmub || !diag_data)
+		return;
+
+	memset(diag_data, 0, sizeof(*diag_data));
+
+	diag_data->dmcub_version = dmub->fw_version;
+
+	diag_data->scratch[0] = REG_READ(DMCUB_SCRATCH0);
+	diag_data->scratch[1] = REG_READ(DMCUB_SCRATCH1);
+	diag_data->scratch[2] = REG_READ(DMCUB_SCRATCH2);
+	diag_data->scratch[3] = REG_READ(DMCUB_SCRATCH3);
+	diag_data->scratch[4] = REG_READ(DMCUB_SCRATCH4);
+	diag_data->scratch[5] = REG_READ(DMCUB_SCRATCH5);
+	diag_data->scratch[6] = REG_READ(DMCUB_SCRATCH6);
+	diag_data->scratch[7] = REG_READ(DMCUB_SCRATCH7);
+	diag_data->scratch[8] = REG_READ(DMCUB_SCRATCH8);
+	diag_data->scratch[9] = REG_READ(DMCUB_SCRATCH9);
+	diag_data->scratch[10] = REG_READ(DMCUB_SCRATCH10);
+	diag_data->scratch[11] = REG_READ(DMCUB_SCRATCH11);
+	diag_data->scratch[12] = REG_READ(DMCUB_SCRATCH12);
+	diag_data->scratch[13] = REG_READ(DMCUB_SCRATCH13);
+	diag_data->scratch[14] = REG_READ(DMCUB_SCRATCH14);
+	diag_data->scratch[15] = REG_READ(DMCUB_SCRATCH15);
+
+	diag_data->undefined_address_fault_addr = REG_READ(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR);
+	diag_data->inst_fetch_fault_addr = REG_READ(DMCUB_INST_FETCH_FAULT_ADDR);
+	diag_data->data_write_fault_addr = REG_READ(DMCUB_DATA_WRITE_FAULT_ADDR);
+
+	diag_data->inbox1_rptr = REG_READ(DMCUB_INBOX1_RPTR);
+	diag_data->inbox1_wptr = REG_READ(DMCUB_INBOX1_WPTR);
+	diag_data->inbox1_size = REG_READ(DMCUB_INBOX1_SIZE);
+
+	diag_data->inbox0_rptr = REG_READ(DMCUB_INBOX0_RPTR);
+	diag_data->inbox0_wptr = REG_READ(DMCUB_INBOX0_WPTR);
+	diag_data->inbox0_size = REG_READ(DMCUB_INBOX0_SIZE);
+
+	REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_dmub_enabled);
+	diag_data->is_dmcub_enabled = is_dmub_enabled;
+
+	REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &is_soft_reset);
+	diag_data->is_dmcub_soft_reset = is_soft_reset;
+
+	REG_GET(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS, &is_sec_reset);
+	diag_data->is_dmcub_secure_reset = is_sec_reset;
+
+	REG_GET(DMCUB_CNTL, DMCUB_TRACEPORT_EN, &is_traceport_enabled);
+	diag_data->is_traceport_en  = is_traceport_enabled;
+
+	REG_GET(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE, &is_cw0_enabled);
+	diag_data->is_cw0_enabled = is_cw0_enabled;
+
+	REG_GET(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE, &is_cw6_enabled);
+	diag_data->is_cw6_enabled = is_cw6_enabled;
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
index 2829c3e9a310..9456a6a2d518 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
@@ -36,6 +36,9 @@ struct dmub_srv;
 	DMUB_SR(DMCUB_CNTL) \
 	DMUB_SR(DMCUB_CNTL2) \
 	DMUB_SR(DMCUB_SEC_CNTL) \
+	DMUB_SR(DMCUB_INBOX0_SIZE) \
+	DMUB_SR(DMCUB_INBOX0_RPTR) \
+	DMUB_SR(DMCUB_INBOX0_WPTR) \
 	DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \
 	DMUB_SR(DMCUB_INBOX1_SIZE) \
 	DMUB_SR(DMCUB_INBOX1_RPTR) \
@@ -103,11 +106,15 @@ struct dmub_srv;
 	DMUB_SR(DMCUB_SCRATCH14) \
 	DMUB_SR(DMCUB_SCRATCH15) \
 	DMUB_SR(DMCUB_GPINT_DATAIN1) \
+	DMUB_SR(DMCUB_GPINT_DATAOUT) \
 	DMUB_SR(CC_DC_PIPE_DIS) \
 	DMUB_SR(MMHUBBUB_SOFT_RESET) \
 	DMUB_SR(DCN_VM_FB_LOCATION_BASE) \
 	DMUB_SR(DCN_VM_FB_OFFSET) \
-	DMUB_SR(DMCUB_TIMER_CURRENT)
+	DMUB_SR(DMCUB_TIMER_CURRENT) \
+	DMUB_SR(DMCUB_INST_FETCH_FAULT_ADDR) \
+	DMUB_SR(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR) \
+	DMUB_SR(DMCUB_DATA_WRITE_FAULT_ADDR)
 
 #define DMUB_DCN31_FIELDS() \
 	DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \
@@ -115,6 +122,7 @@ struct dmub_srv;
 	DMUB_SF(DMCUB_CNTL2, DMCUB_SOFT_RESET) \
 	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \
 	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \
+	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS) \
 	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \
 	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \
 	DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \
@@ -138,11 +146,13 @@ struct dmub_srv;
 	DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \
 	DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET) \
 	DMUB_SF(DCN_VM_FB_LOCATION_BASE, FB_BASE) \
-	DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET)
+	DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) \
+	DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR)
 
 struct dmub_srv_dcn31_reg_offset {
 #define DMUB_SR(reg) uint32_t reg;
 	DMUB_DCN31_REGS()
+	DMCUB_INTERNAL_REGS()
 #undef DMUB_SR
 };
 
@@ -227,4 +237,6 @@ void dmub_dcn31_set_outbox0_rptr(struct dmub_srv *dmub, uint32_t rptr_offset);
 
 uint32_t dmub_dcn31_get_current_time(struct dmub_srv *dmub);
 
+void dmub_dcn31_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data);
+
 #endif /* _DMUB_DCN31_H_ */
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 fd7e996ab1d7..2bdbd7406f56 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -208,6 +208,7 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
 		break;
 
 	case DMUB_ASIC_DCN31:
+		dmub->regs_dcn31 = &dmub_srv_dcn31_regs;
 		funcs->reset = dmub_dcn31_reset;
 		funcs->reset_release = dmub_dcn31_reset_release;
 		funcs->backdoor_load = dmub_dcn31_backdoor_load;
@@ -231,9 +232,7 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
 		funcs->get_outbox0_wptr = dmub_dcn31_get_outbox0_wptr;
 		funcs->set_outbox0_rptr = dmub_dcn31_set_outbox0_rptr;
 
-		if (asic == DMUB_ASIC_DCN31) {
-			dmub->regs_dcn31 = &dmub_srv_dcn31_regs;
-		}
+		funcs->get_diagnostic_data = dmub_dcn31_get_diagnostic_data;
 
 		funcs->get_current_time = dmub_dcn31_get_current_time;
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 332b0df53e52..ff1d3d4a6488 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -223,10 +223,12 @@ enum amd_harvest_ip_mask {
 };
 
 enum DC_FEATURE_MASK {
-	DC_FBC_MASK = 0x1,
-	DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2,
-	DC_DISABLE_FRACTIONAL_PWM_MASK = 0x4,
-	DC_PSR_MASK = 0x8,
+	//Default value can be found at "uint amdgpu_dc_feature_mask"
+	DC_FBC_MASK = (1 << 0), //0x1, disabled by default
+	DC_MULTI_MON_PP_MCLK_SWITCH_MASK = (1 << 1), //0x2, enabled by default
+	DC_DISABLE_FRACTIONAL_PWM_MASK = (1 << 2), //0x4, disabled by default
+	DC_PSR_MASK = (1 << 3), //0x8, disabled by default
+	DC_EDP_NO_POWER_SEQUENCING = (1 << 4), //0x10, disabled by default
 };
 
 enum DC_DEBUG_MASK {
diff --git a/drivers/gpu/drm/amd/include/navi10_enum.h b/drivers/gpu/drm/amd/include/navi10_enum.h
index d5ead9680c6e..84bcb96f76ea 100644
--- a/drivers/gpu/drm/amd/include/navi10_enum.h
+++ b/drivers/gpu/drm/amd/include/navi10_enum.h
@@ -430,7 +430,7 @@ ARRAY_2D_DEPTH                           = 0x00000001,
  */
 
 typedef enum ENUM_NUM_SIMD_PER_CU {
-NUM_SIMD_PER_CU                          = 0x00000004,
+NUM_SIMD_PER_CU                          = 0x00000002,
 } ENUM_NUM_SIMD_PER_CU;
 
 /*
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index a276ebad47e6..769f58d5ae1a 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2902,14 +2902,15 @@ static ssize_t amdgpu_hwmon_show_power_cap_min(struct device *dev,
 	return sprintf(buf, "%i\n", 0);
 }
 
-static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
-					 struct device_attribute *attr,
-					 char *buf)
+
+static ssize_t amdgpu_hwmon_show_power_cap_generic(struct device *dev,
+					struct device_attribute *attr,
+					char *buf,
+					enum pp_power_limit_level pp_limit_level)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
 	enum pp_power_type power_type = to_sensor_dev_attr(attr)->index;
-	enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_MAX;
 	uint32_t limit;
 	ssize_t size;
 	int r;
@@ -2919,17 +2920,17 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 	if (adev->in_suspend && !adev->in_runpm)
 		return -EPERM;
 
+	if ( !(pp_funcs && pp_funcs->get_power_limit))
+		return -ENODATA;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 		return r;
 	}
 
-	if (pp_funcs && pp_funcs->get_power_limit)
-		r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit,
-					      pp_limit_level, power_type);
-	else
-		r = -ENODATA;
+	r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit,
+				      pp_limit_level, power_type);
 
 	if (!r)
 		size = sysfs_emit(buf, "%u\n", limit * 1000000);
@@ -2942,85 +2943,31 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 	return size;
 }
 
-static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
+
+static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-	enum pp_power_type power_type = to_sensor_dev_attr(attr)->index;
-	enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_CURRENT;
-	uint32_t limit;
-	ssize_t size;
-	int r;
-
-	if (amdgpu_in_reset(adev))
-		return -EPERM;
-	if (adev->in_suspend && !adev->in_runpm)
-		return -EPERM;
-
-	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
-	if (r < 0) {
-		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-		return r;
-	}
-
-	if (pp_funcs && pp_funcs->get_power_limit)
-		r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit,
-					      pp_limit_level, power_type);
-	else
-		r = -ENODATA;
+	return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_MAX);
 
-	if (!r)
-		size = sysfs_emit(buf, "%u\n", limit * 1000000);
-	else
-		size = sysfs_emit(buf, "\n");
+}
 
-	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
+					 struct device_attribute *attr,
+					 char *buf)
+{
+	return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_CURRENT);
 
-	return size;
 }
 
 static ssize_t amdgpu_hwmon_show_power_cap_default(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-	enum pp_power_type power_type = to_sensor_dev_attr(attr)->index;
-	enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_DEFAULT;
-	uint32_t limit;
-	ssize_t size;
-	int r;
+	return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_DEFAULT);
 
-	if (amdgpu_in_reset(adev))
-		return -EPERM;
-	if (adev->in_suspend && !adev->in_runpm)
-		return -EPERM;
-
-	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
-	if (r < 0) {
-		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-		return r;
-	}
-
-	if (pp_funcs && pp_funcs->get_power_limit)
-		r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit,
-					      pp_limit_level, power_type);
-	else
-		r = -ENODATA;
-
-	if (!r)
-		size = sysfs_emit(buf, "%u\n", limit * 1000000);
-	else
-		size = sysfs_emit(buf, "\n");
-
-	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-
-	return size;
 }
+
 static ssize_t amdgpu_hwmon_show_power_label(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index cb375f1beebd..ebe672142808 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1453,10 +1453,14 @@ static int smu_hw_fini(void *handle)
 
 	if (smu->is_apu) {
 		smu_powergate_sdma(&adev->smu, true);
-		smu_dpm_set_vcn_enable(smu, false);
-		smu_dpm_set_jpeg_enable(smu, false);
 	}
 
+	smu_dpm_set_vcn_enable(smu, false);
+	smu_dpm_set_jpeg_enable(smu, false);
+
+	adev->vcn.cur_state = AMD_PG_STATE_GATE;
+	adev->jpeg.cur_state = AMD_PG_STATE_GATE;
+
 	if (!smu->pm_enabled)
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 7664334d8144..18a1ffdca227 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -189,10 +189,11 @@ err0_out:
 static int yellow_carp_system_features_control(struct smu_context *smu, bool en)
 {
 	struct smu_feature *feature = &smu->smu_feature;
+	struct amdgpu_device *adev = smu->adev;
 	uint32_t feature_mask[2];
 	int ret = 0;
 
-	if (!en)
+	if (!en && !adev->in_s0ix)
 		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
 
 	bitmap_zero(feature->enabled, feature->feature_num);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 406681317419..573154268d43 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1325,6 +1325,7 @@ radeon_user_framebuffer_create(struct drm_device *dev,
 	/* Handle is imported dma-buf, so cannot be migrated to VRAM for scanout */
 	if (obj->import_attach) {
 		DRM_DEBUG_KMS("Cannot create framebuffer from imported dma_buf\n");
+		drm_gem_object_put(obj);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 8cd135fa6dcd..5c23b77cb81a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -374,13 +374,13 @@ radeon_pci_shutdown(struct pci_dev *pdev)
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || defined(CONFIG_MACH_LOONGSON64)
 	/*
 	 * Some adapters need to be suspended before a
 	 * shutdown occurs in order to prevent an error
-	 * during kexec.
-	 * Make this power specific becauase it breaks
-	 * some non-power boards.
+	 * during kexec, shutdown or reboot.
+	 * Make this power and Loongson specific because
+	 * it breaks some other boards.
 	 */
 	radeon_suspend_kms(pci_get_drvdata(pdev), true, true, false);
 #endif