Merge tag 'drm-next-2021-07-08-1' of git://anongit.freedesktop.org/drm/drm

f5596657 · Linus Torvalds <[email protected]> · 2021-07-08 12:28:15 -07:00

Pull drm fixes from Dave Airlie:
 "Some fixes for rc1 that came in the past weeks, mainly a bunch of
  amdgpu fixes, some i915 and the rest are misc around the place. I'm
  sending this a bit early so some more stuff may show up, but I'll
  probably take tomorrow off.

  dma-buf:
   - doc fixes

  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
   - TTM fixes

  amdkfd:
   - SVM fixes

  radeon:
   - Fix missing drm_gem_object_put in error path
   - NULL ptr deref fix

  i915:
   - display DP VSC fix
   - DG1 display fix
   - IRQ fixes
   - IRQ demidlayering

  gma500:
   - bo leaks in error paths fixed"

* tag 'drm-next-2021-07-08-1' of git://anongit.freedesktop.org/drm/drm: (52 commits)
  drm/i915: Drop all references to DRM IRQ midlayer
  drm/i915: Use the correct IRQ during resume
  drm/i915/display/dg1: Correctly map DPLLs during state readout
  drm/i915/display: Do not zero past infoframes.vsc
  drm/amdgpu: Conditionally reset SDMA RAS error counts
  drm/amdkfd: Maintain svm_bo reference in page->zone_device_data
  drm/amdkfd: add invalid pages debug at vram migration
  drm/amdkfd: skip migration for pages already in VRAM
  drm/amdkfd: skip invalid pages during migrations
  drm/amdkfd: classify and map mixed svm range pages in GPU
  drm/amdkfd: use hmm range fault to get both domain pfns
  drm/amdgpu: get owner ref in validate and map
  drm/amdkfd: set owner ref to svm range prefault
  drm/amdkfd: add owner ref param to get hmm pages
  drm/amdkfd: device pgmap owner at the svm migrate init
  drm/amdkfd: inc counter on child ranges with xnack off
  drm/amd/display: Extend DMUB diagnostic logging to DCN3.1
  drm/amdgpu: Update NV SIMD-per-CU to 2
  drm/amdgpu: add new dimgrey cavefish DID
  drm/amd/pm: skip PrepareMp1ForUnload message in s0ix
  ...

Commit: f55966571d5eb2876a11e48e798b4592fa1ffbb7
Parents: 8c1bfd74 · 21c355b0

Merge commit. Changes below are compared with the first parent: 8c1bfd74.

Changes

53 files changed · +1048 −504

File	Status	Add	Del	Content
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c	modified	+37	−0	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c	modified	+2	−0	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c	modified	+1	−0	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c	modified	+2	−1	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h	modified	+1	−1	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h	modified	+2	−0	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c	modified	+3	−6	View file
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c	modified	+5	−0	View file
drivers/gpu/drm/amd/amdgpu/athub_v2_0.c	modified	+9	−3	View file
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c	modified	+204	−62	View file
drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c	modified	+48	−37	View file
drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c	modified	+8	−2	View file
drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c	modified	+49	−2	View file
drivers/gpu/drm/amd/amdgpu/nv.c	modified	+36	−1	View file
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c	modified	+7	−4	View file
drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c	modified	+4	−1	View file
drivers/gpu/drm/amd/amdgpu/soc15.c	modified	+1	−9	View file
drivers/gpu/drm/amd/amdkfd/kfd_migrate.c	modified	+65	−35	View file
drivers/gpu/drm/amd/amdkfd/kfd_priv.h	modified	+9	−0	View file
drivers/gpu/drm/amd/amdkfd/kfd_process.c	modified	+161	−111	View file
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c	modified	+1	−0	View file
drivers/gpu/drm/amd/amdkfd/kfd_svm.c	modified	+157	−79	View file
drivers/gpu/drm/amd/amdkfd/kfd_svm.h	modified	+17	−2	View file
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c	modified	+4	−9	View file
drivers/gpu/drm/amd/display/dc/dc.h	modified	+1	−0	View file
drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c	modified	+27	−4	View file
drivers/gpu/drm/amd/display/dc/dcn31/Makefile	modified	+2	−0	View file
drivers/gpu/drm/amd/display/dc/dml/Makefile	modified	+6	−2	View file
drivers/gpu/drm/amd/display/dc/irq/irq_service.c	modified	+2	−2	View file
drivers/gpu/drm/amd/display/dc/irq_types.h	modified	+1	−1	View file
drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c	modified	+60	−0	View file
drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h	modified	+14	−2	View file
drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c	modified	+2	−3	View file
drivers/gpu/drm/amd/include/amd_shared.h	modified	+6	−4	View file
drivers/gpu/drm/amd/include/navi10_enum.h	modified	+1	−1	View file
drivers/gpu/drm/amd/pm/amdgpu_pm.c	modified	+21	−74	View file
drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c	modified	+6	−2	View file
drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c	modified	+2	−1	View file
drivers/gpu/drm/gma500/framebuffer.c	modified	+6	−1	View file
drivers/gpu/drm/i915/display/intel_ddi.c	modified	+16	−3	View file
drivers/gpu/drm/i915/display/intel_dp.c	modified	+1	−1	View file
drivers/gpu/drm/i915/gt/intel_engine_cs.c	modified	+1	−1	View file
drivers/gpu/drm/i915/gt/intel_ring_submission.c	modified	+5	−2	View file
drivers/gpu/drm/i915/i915_drv.c	modified	+0	−1	View file
drivers/gpu/drm/i915/i915_irq.c	modified	+5	−5	View file
drivers/gpu/drm/i915/i915_irq.h	modified	+1	−0	View file
drivers/gpu/drm/i915/i915_reg.h	modified	+0	−3	View file
drivers/gpu/drm/radeon/radeon_display.c	modified	+1	−0	View file
drivers/gpu/drm/radeon/radeon_drv.c	modified	+4	−4	View file
drivers/gpu/drm/radeon/radeon_object.c	modified	+12	−17	View file
drivers/gpu/drm/radeon/radeon_object.h	modified	+1	−1	View file
drivers/gpu/drm/radeon/radeon_ttm.c	modified	+10	−3	View file
include/linux/dma-resv.h	modified	+1	−1	View file

Only the first 600 diff lines are shown. Download the complete patch.

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 130a9ad..d303e88 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;

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6f30c52..71beb0d 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 */

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 0174f78..d0b8d41 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) {

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index d6c54c7..4b153da 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;

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h
index 7f7d37a..14a3c18 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)

drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 25ee535..45295dc 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 {

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index cdfc20b..3a55f08 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;
@@ -695,7 +691,7 @@ 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,
-				       true);
+				       true, NULL);
 out_unlock:
 	mmap_read_unlock(mm);
 	mmput(mm);
@@ -923,7 +919,8 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev,
 	    bo_mem->mem_type == AMDGPU_PL_OA)
 		return -EINVAL;
 
-	if (!amdgpu_gtt_mgr_has_gart_addr(bo_mem)) {
+	if (bo_mem->mem_type != TTM_PL_TT ||
+	    !amdgpu_gtt_mgr_has_gart_addr(bo_mem)) {
 		gtt->offset = AMDGPU_BO_INVALID_OFFSET;
 		return 0;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 436ec24..2fd77c3 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;

drivers/gpu/drm/amd/amdgpu/athub_v2_0.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c
index 5b90efd..3ac505d 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;

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

View file

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 2d56b60..f5e9c02 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);