Merge branch 'x86/paravirt' into x86/entry

Merge in the recent paravirt changes to resolve conflicts caused
by objtool annotations.

Conflicts:
	arch/x86/xen/xen-asm.S

Signed-off-by: Ingo Molnar <mingo@kernel.org>

152 files changed, 2266 insertions, 931 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 2d991da2cead..d1ed4f8df2b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -26,6 +26,7 @@
 #include <linux/sched/task.h>
 
 #include "amdgpu_object.h"
+#include "amdgpu_gem.h"
 #include "amdgpu_vm.h"
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_dma_buf.h"
@@ -1152,7 +1153,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	struct sg_table *sg = NULL;
 	uint64_t user_addr = 0;
 	struct amdgpu_bo *bo;
-	struct amdgpu_bo_param bp;
+	struct drm_gem_object *gobj;
 	u32 domain, alloc_domain;
 	u64 alloc_flags;
 	int ret;
@@ -1220,19 +1221,14 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	pr_debug("\tcreate BO VA 0x%llx size 0x%llx domain %s\n",
 			va, size, domain_string(alloc_domain));
 
-	memset(&bp, 0, sizeof(bp));
-	bp.size = size;
-	bp.byte_align = 1;
-	bp.domain = alloc_domain;
-	bp.flags = alloc_flags;
-	bp.type = bo_type;
-	bp.resv = NULL;
-	ret = amdgpu_bo_create(adev, &bp, &bo);
+	ret = amdgpu_gem_object_create(adev, size, 1, alloc_domain, alloc_flags,
+				       bo_type, NULL, &gobj);
 	if (ret) {
 		pr_debug("Failed to create BO on domain %s. ret %d\n",
-				domain_string(alloc_domain), ret);
+			 domain_string(alloc_domain), ret);
 		goto err_bo_create;
 	}
+	bo = gem_to_amdgpu_bo(gobj);
 	if (bo_type == ttm_bo_type_sg) {
 		bo->tbo.sg = sg;
 		bo->tbo.ttm->sg = sg;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 306077884a67..6107ac91db25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -112,6 +112,7 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
 union igp_info {
 	struct atom_integrated_system_info_v1_11 v11;
 	struct atom_integrated_system_info_v1_12 v12;
+	struct atom_integrated_system_info_v2_1 v21;
 };
 
 union umc_info {
@@ -209,24 +210,42 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 		if (adev->flags & AMD_IS_APU) {
 			igp_info = (union igp_info *)
 				(mode_info->atom_context->bios + data_offset);
-			switch (crev) {
-			case 11:
-				mem_channel_number = igp_info->v11.umachannelnumber;
-				/* channel width is 64 */
-				if (vram_width)
-					*vram_width = mem_channel_number * 64;
-				mem_type = igp_info->v11.memorytype;
-				if (vram_type)
-					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+			switch (frev) {
+			case 1:
+				switch (crev) {
+				case 11:
+				case 12:
+					mem_channel_number = igp_info->v11.umachannelnumber;
+					if (!mem_channel_number)
+						mem_channel_number = 1;
+					/* channel width is 64 */
+					if (vram_width)
+						*vram_width = mem_channel_number * 64;
+					mem_type = igp_info->v11.memorytype;
+					if (vram_type)
+						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+					break;
+				default:
+					return -EINVAL;
+				}
 				break;
-			case 12:
-				mem_channel_number = igp_info->v12.umachannelnumber;
-				/* channel width is 64 */
-				if (vram_width)
-					*vram_width = mem_channel_number * 64;
-				mem_type = igp_info->v12.memorytype;
-				if (vram_type)
-					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+			case 2:
+				switch (crev) {
+				case 1:
+				case 2:
+					mem_channel_number = igp_info->v21.umachannelnumber;
+					if (!mem_channel_number)
+						mem_channel_number = 1;
+					/* channel width is 64 */
+					if (vram_width)
+						*vram_width = mem_channel_number * 64;
+					mem_type = igp_info->v21.memorytype;
+					if (vram_type)
+						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+					break;
+				default:
+					return -EINVAL;
+				}
 				break;
 			default:
 				return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b69c34074d8d..cab1ebaf6d62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -81,7 +81,6 @@ MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vangogh_gpu_info.bin");
-MODULE_FIRMWARE("amdgpu/green_sardine_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
@@ -3034,7 +3033,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 #endif
 	default:
 		if (amdgpu_dc > 0)
-			DRM_INFO("Display Core has been requested via kernel parameter "
+			DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
 					 "but isn't supported by ASIC, ignoring\n");
 		return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index f764803c53a4..48cb33e5b382 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -926,8 +926,10 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 				       struct drm_file *file_priv,
 				       const struct drm_mode_fb_cmd2 *mode_cmd)
 {
-	struct drm_gem_object *obj;
 	struct amdgpu_framebuffer *amdgpu_fb;
+	struct drm_gem_object *obj;
+	struct amdgpu_bo *bo;
+	uint32_t domains;
 	int ret;
 
 	obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[0]);
@@ -938,7 +940,9 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev,
 	}
 
 	/* Handle is imported dma-buf, so cannot be migrated to VRAM for scanout */
-	if (obj->import_attach) {
+	bo = gem_to_amdgpu_bo(obj);
+	domains = amdgpu_display_supported_domains(drm_to_adev(dev), bo->flags);
+	if (obj->import_attach && !(domains & AMDGPU_GEM_DOMAIN_GTT)) {
 		drm_dbg_kms(dev, "Cannot create framebuffer from imported dma_buf\n");
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 72efd579ec5e..7169fb5e3d9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1085,6 +1085,8 @@ static const struct pci_device_id pciidlist[] = {
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+	{0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+	{0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
 
 	/* Navi12 */
 	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index d0a1fee1f5f6..174a73eb23f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -269,8 +269,8 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 		resv = vm->root.base.bo->tbo.base.resv;
 	}
 
-retry:
 	initial_domain = (u32)(0xffffffff & args->in.domains);
+retry:
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     initial_domain,
 				     flags, ttm_bo_type_device, resv, &gobj);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 25ec4d57333f..b4c8e5d5c763 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -897,7 +897,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		return -EINVAL;
 
 	/* A shared bo cannot be migrated to VRAM */
-	if (bo->prime_shared_count) {
+	if (bo->prime_shared_count || bo->tbo.base.import_attach) {
 		if (domain & AMDGPU_GEM_DOMAIN_GTT)
 			domain = AMDGPU_GEM_DOMAIN_GTT;
 		else
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ba1086784525..d86b42a36560 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -99,6 +99,14 @@
 #define mmGCR_GENERAL_CNTL_Sienna_Cichlid			0x1580
 #define mmGCR_GENERAL_CNTL_Sienna_Cichlid_BASE_IDX	0
 
+#define mmCGTS_TCC_DISABLE_Vangogh                0x5006
+#define mmCGTS_TCC_DISABLE_Vangogh_BASE_IDX       1
+#define mmCGTS_USER_TCC_DISABLE_Vangogh                0x5007
+#define mmCGTS_USER_TCC_DISABLE_Vangogh_BASE_IDX       1
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh                0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh_BASE_IDX       1
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh                0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh_BASE_IDX       1
 #define mmSPI_CONFIG_CNTL_1_Vangogh		 0x2441
 #define mmSPI_CONFIG_CNTL_1_Vangogh_BASE_IDX	 1
 #define mmVGT_TF_MEMORY_BASE_HI_Vangogh          0x2261
@@ -115,6 +123,8 @@
 #define mmVGT_ESGS_RING_SIZE_Vangogh_BASE_IDX    1
 #define mmSPI_CONFIG_CNTL_Vangogh                0x2440
 #define mmSPI_CONFIG_CNTL_Vangogh_BASE_IDX       1
+#define mmGCR_GENERAL_CNTL_Vangogh               0x1580
+#define mmGCR_GENERAL_CNTL_Vangogh_BASE_IDX      0
 
 #define mmCP_HYP_PFP_UCODE_ADDR			0x5814
 #define mmCP_HYP_PFP_UCODE_ADDR_BASE_IDX	1
@@ -160,6 +170,9 @@
 #define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid          0x15db
 #define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid_BASE_IDX	0
 
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid              0x2030
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid_BASE_IDX     0
+
 MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
 MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
 MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3237,7 +3250,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_EXCEPTION_CONTROL, 0x7fff0f1f, 0x00b80000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000142),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210),
@@ -3324,6 +3337,7 @@ static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
 static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
 static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
 static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev);
 
 static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
 {
@@ -4926,8 +4940,18 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
 {
 	/* TCCs are global (not instanced). */
-	uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
-			       RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+	uint32_t tcc_disable;
+
+	switch (adev->asic_type) {
+	case CHIP_VANGOGH:
+		tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE_Vangogh) |
+				RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE_Vangogh);
+		break;
+	default:
+		tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
+				RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+		break;
+	}
 
 	adev->gfx.config.tcc_disabled_mask =
 		REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) |
@@ -7192,6 +7216,9 @@ static int gfx_v10_0_hw_init(void *handle)
 	if (adev->asic_type == CHIP_SIENNA_CICHLID)
 		gfx_v10_3_program_pbb_mode(adev);
 
+	if (adev->asic_type >= CHIP_SIENNA_CICHLID)
+		gfx_v10_3_set_power_brake_sequence(adev);
+
 	return r;
 }
 
@@ -7377,8 +7404,16 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 
 	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
-		((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+	switch (adev->asic_type) {
+	case CHIP_VANGOGH:
+		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
+			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+		break;
+	default:
+		clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
+			((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+		break;
+	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
 	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
@@ -9169,6 +9204,31 @@ static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev)
+{
+	WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX,
+		     (0x1 << GRBM_GFX_INDEX__SA_BROADCAST_WRITES__SHIFT) |
+		     (0x1 << GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES__SHIFT) |
+		     (0x1 << GRBM_GFX_INDEX__SE_BROADCAST_WRITES__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL);
+	WREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA,
+		     (0x1 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_STEP_INTERVAL__SHIFT) |
+		     (0x12 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_BEGIN_STEP__SHIFT) |
+		     (0x13 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_END_STEP__SHIFT) |
+		     (0xf << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_THROTTLE_PATTERN_BIT_NUMS__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmGC_THROTTLE_CTRL_Sienna_Cichlid,
+		     (0x1 << GC_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT) |
+		     (0x1 << GC_THROTTLE_CTRL__PATTERN_MODE__SHIFT) |
+		     (0x5 << GC_THROTTLE_CTRL__RELEASE_STEP_INTERVAL__SHIFT));
+
+	WREG32_SOC15(GC, 0, mmDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL);
+
+	WREG32_SOC15(GC, 0, mmDIDT_IND_DATA,
+		     (0x1 << DIDT_SQ_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT));
+}
+
 const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_GFX,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index 07104a1de308..1961745e89c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -491,12 +491,11 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 {
 	uint32_t def, data, def1, data1;
 
-	def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
+	def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL);
 	def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) {
-		data |= MM_ATC_L2_MISC_CG__ENABLE_MASK;
-
+		data &= ~MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK;
 		data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
 		           DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK |
 		           DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK |
@@ -505,8 +504,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		           DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK);
 
 	} else {
-		data &= ~MM_ATC_L2_MISC_CG__ENABLE_MASK;
-
+		data |= MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK;
 		data1 |= (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
 			  DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK |
 			  DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK |
@@ -516,7 +514,7 @@ mmhub_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 	}
 
 	if (def != data)
-		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
+		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data);
 	if (def1 != data1)
 		WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2, data1);
 }
@@ -525,17 +523,44 @@ static void
 mmhub_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev,
 					   bool enable)
 {
-	uint32_t def, data;
-
-	def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
-
-	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS))
-		data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
-	else
-		data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
+	uint32_t def, data, def1, data1, def2, data2;
+
+	def  = data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL);
+	def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL);
+	def2 = data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL);
+
+	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) {
+		data &= ~MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK;
+		data1 &= !(DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK);
+		data2 &= !(DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK);
+	} else {
+		data |= MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK;
+		data1 |= (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+			DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK);
+		data2 |= (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+			DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK);
+	}
 
 	if (def != data)
-		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
+		WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL, data);
+	if (def1 != data1)
+		WREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL, data1);
+	if (def2 != data2)
+		WREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL, data2);
 }
 
 static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev,
@@ -554,26 +579,39 @@ static int mmhub_v2_3_set_clockgating(struct amdgpu_device *adev,
 
 static void mmhub_v2_3_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
-	int data, data1;
+	int data, data1, data2, data3;
 
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	data  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
-	data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+	data = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2);
+	data1  = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_CGTT_CLK_CTRL);
+	data2 = RREG32_SOC15(MMHUB, 0, mmDAGB0_WR_CGTT_CLK_CTRL);
+	data3 = RREG32_SOC15(MMHUB, 0, mmDAGB0_RD_CGTT_CLK_CTRL);
 
 	/* AMD_CG_SUPPORT_MC_MGCG */
-	if ((data & MM_ATC_L2_MISC_CG__ENABLE_MASK) &&
-	    !(data1 & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
+	if (!(data & (DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK |
 		       DAGB0_CNTL_MISC2__DISABLE_WRRET_CG_MASK |
 		       DAGB0_CNTL_MISC2__DISABLE_RDREQ_CG_MASK |
 		       DAGB0_CNTL_MISC2__DISABLE_RDRET_CG_MASK |
 		       DAGB0_CNTL_MISC2__DISABLE_TLBWR_CG_MASK |
-		       DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK)))
-		*flags |= AMD_CG_SUPPORT_MC_MGCG;
+		       DAGB0_CNTL_MISC2__DISABLE_TLBRD_CG_MASK))
+		&& !(data1 & MM_ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK)) {
+			*flags |= AMD_CG_SUPPORT_MC_MGCG;
+	}
 
 	/* AMD_CG_SUPPORT_MC_LS */
-	if (data & MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
+	if (!(data1 & MM_ATC_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK)
+		&& !(data2 & (DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+				DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+				DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+				DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+				DAGB0_WR_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK))
+		&& !(data3 & (DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_MASK |
+				DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_WRITE_MASK |
+				DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_READ_MASK |
+				DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_RETURN_MASK |
+				DAGB0_RD_CGTT_CLK_CTRL__LS_OVERRIDE_REGISTER_MASK)))
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index d65a5339d354..3ba7bdfde65d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -47,7 +47,7 @@ enum psp_gfx_crtl_cmd_id
     GFX_CTRL_CMD_ID_DISABLE_INT     = 0x00060000,   /* disable PSP-to-Gfx interrupt */
     GFX_CTRL_CMD_ID_MODE1_RST       = 0x00070000,   /* trigger the Mode 1 reset */
     GFX_CTRL_CMD_ID_GBR_IH_SET      = 0x00080000,   /* set Gbr IH_RB_CNTL registers */
-    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x000A0000,   /* send interrupt to psp for updating write pointer of vf */
+    GFX_CTRL_CMD_ID_CONSUME_CMD     = 0x00090000,   /* send interrupt to psp for updating write pointer of vf */
     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING = 0x000C0000, /* destroy GPCOM ring */
 
     GFX_CTRL_CMD_ID_MAX             = 0x000F0000,   /* max command ID */
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8a23636ecc27..0b3516c4eefb 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1239,7 +1239,8 @@ static int soc15_common_early_init(void *handle)
 		break;
 	case CHIP_RENOIR:
 		adev->asic_funcs = &soc15_asic_funcs;
-		if (adev->pdev->device == 0x1636)
+		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;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 8cac497c2c45..a5640a6138cf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1040,11 +1040,14 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
 				(struct crat_subtype_iolink *)sub_type_hdr);
 		if (ret < 0)
 			return ret;
-		crat_table->length += (sub_type_hdr->length * entries);
-		crat_table->total_entries += entries;
 
-		sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
-				sub_type_hdr->length * entries);
+		if (entries) {
+			crat_table->length += (sub_type_hdr->length * entries);
+			crat_table->total_entries += entries;
+
+			sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+					sub_type_hdr->length * entries);
+		}
 #else
 		pr_info("IO link not available for non x86 platforms\n");
 #endif
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 146486071d01..961abf1cf040 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -939,41 +939,6 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 }
 #endif
 
-#ifdef CONFIG_DEBUG_FS
-static int create_crtc_crc_properties(struct amdgpu_display_manager *dm)
-{
-	dm->crc_win_x_start_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_X_START", 0, U16_MAX);
-	if (!dm->crc_win_x_start_property)
-		return -ENOMEM;
-
-	dm->crc_win_y_start_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_Y_START", 0, U16_MAX);
-	if (!dm->crc_win_y_start_property)
-		return -ENOMEM;
-
-	dm->crc_win_x_end_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_X_END", 0, U16_MAX);
-	if (!dm->crc_win_x_end_property)
-		return -ENOMEM;
-
-	dm->crc_win_y_end_property =
-		drm_property_create_range(adev_to_drm(dm->adev),
-					  DRM_MODE_PROP_ATOMIC,
-					  "AMD_CRC_WIN_Y_END", 0, U16_MAX);
-	if (!dm->crc_win_y_end_property)
-		return -ENOMEM;
-
-	return 0;
-}
-#endif
-
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -1121,10 +1086,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		dc_init_callbacks(adev->dm.dc, &init_params);
 	}
 #endif
-#ifdef CONFIG_DEBUG_FS
-	if (create_crtc_crc_properties(&adev->dm))
-		DRM_ERROR("amdgpu: failed to create crc property.\n");
-#endif
 	if (amdgpu_dm_initialize_drm_device(adev)) {
 		DRM_ERROR(
 		"amdgpu: failed to initialize sw for display support.\n");
@@ -1872,8 +1833,8 @@ static void emulated_link_detect(struct dc_link *link)
 	link->type = dc_connection_none;
 	prev_sink = link->local_sink;
 
-	if (prev_sink != NULL)
-		dc_sink_retain(prev_sink);
+	if (prev_sink)
+		dc_sink_release(prev_sink);
 
 	switch (link->connector_signal) {
 	case SIGNAL_TYPE_HDMI_TYPE_A: {
@@ -1973,7 +1934,7 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
 		dc_commit_updates_for_stream(
 			dm->dc, bundle->surface_updates,
 			dc_state->stream_status->plane_count,
-			dc_state->streams[k], &bundle->stream_update, dc_state);
+			dc_state->streams[k], &bundle->stream_update);
 	}
 
 cleanup:
@@ -2004,8 +1965,7 @@ static void dm_set_dpms_off(struct dc_link *link)
 
 	stream_update.stream = stream_state;
 	dc_commit_updates_for_stream(stream_state->ctx->dc, NULL, 0,
-				     stream_state, &stream_update,
-				     stream_state->ctx->dc->current_state);
+				     stream_state, &stream_update);
 	mutex_unlock(&adev->dm.dc_lock);
 }
 
@@ -2369,8 +2329,10 @@ void amdgpu_dm_update_connector_after_detect(
 		 * TODO: check if we still need the S3 mode update workaround.
 		 * If yes, put it here.
 		 */
-		if (aconnector->dc_sink)
+		if (aconnector->dc_sink) {
 			amdgpu_dm_update_freesync_caps(connector, NULL);
+			dc_sink_release(aconnector->dc_sink);
+		}
 
 		aconnector->dc_sink = sink;
 		dc_sink_retain(aconnector->dc_sink);
@@ -2386,8 +2348,6 @@ void amdgpu_dm_update_connector_after_detect(
 
 			drm_connector_update_edid_property(connector,
 							   aconnector->edid);
-			drm_add_edid_modes(connector, aconnector->edid);
-
 			if (aconnector->dc_link->aux_mode)
 				drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux,
 						    aconnector->edid);
@@ -5333,64 +5293,12 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc)
 	state->crc_src = cur->crc_src;
 	state->cm_has_degamma = cur->cm_has_degamma;
 	state->cm_is_degamma_srgb = cur->cm_is_degamma_srgb;
-#ifdef CONFIG_DEBUG_FS
-	state->crc_window = cur->crc_window;
-#endif
+
 	/* TODO Duplicate dc_stream after objects are stream object is flattened */
 
 	return &state->base;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static int amdgpu_dm_crtc_atomic_set_property(struct drm_crtc *crtc,
-					    struct drm_crtc_state *crtc_state,
-					    struct drm_property *property,
-					    uint64_t val)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct dm_crtc_state *dm_new_state =
-		to_dm_crtc_state(crtc_state);
-
-	if (property == adev->dm.crc_win_x_start_property)
-		dm_new_state->crc_window.x_start = val;
-	else if (property == adev->dm.crc_win_y_start_property)
-		dm_new_state->crc_window.y_start = val;
-	else if (property == adev->dm.crc_win_x_end_property)
-		dm_new_state->crc_window.x_end = val;
-	else if (property == adev->dm.crc_win_y_end_property)
-		dm_new_state->crc_window.y_end = val;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-
-static int amdgpu_dm_crtc_atomic_get_property(struct drm_crtc *crtc,
-					    const struct drm_crtc_state *state,
-					    struct drm_property *property,
-					    uint64_t *val)
-{
-	struct drm_device *dev = crtc->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct dm_crtc_state *dm_state =
-		to_dm_crtc_state(state);
-
-	if (property == adev->dm.crc_win_x_start_property)
-		*val = dm_state->crc_window.x_start;
-	else if (property == adev->dm.crc_win_y_start_property)
-		*val = dm_state->crc_window.y_start;
-	else if (property == adev->dm.crc_win_x_end_property)
-		*val = dm_state->crc_window.x_end;
-	else if (property == adev->dm.crc_win_y_end_property)
-		*val = dm_state->crc_window.y_end;
-	else
-		return -EINVAL;
-
-	return 0;
-}
-#endif
-
 static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 {
 	enum dc_irq_source irq_source;
@@ -5457,10 +5365,6 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = {
 	.enable_vblank = dm_enable_vblank,
 	.disable_vblank = dm_disable_vblank,
 	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-#ifdef CONFIG_DEBUG_FS
-	.atomic_set_property = amdgpu_dm_crtc_atomic_set_property,
-	.atomic_get_property = amdgpu_dm_crtc_atomic_get_property,
-#endif
 };
 
 static enum drm_connector_status
@@ -6662,25 +6566,6 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void attach_crtc_crc_properties(struct amdgpu_display_manager *dm,
-				struct amdgpu_crtc *acrtc)
-{
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_x_start_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_y_start_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_x_end_property,
-				   0);
-	drm_object_attach_property(&acrtc->base.base,
-				   dm->crc_win_y_end_property,
-				   0);
-}
-#endif
-
 static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 			       struct drm_plane *plane,
 			       uint32_t crtc_index)
@@ -6728,9 +6613,7 @@ static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
 	drm_crtc_enable_color_mgmt(&acrtc->base, MAX_COLOR_LUT_ENTRIES,
 				   true, MAX_COLOR_LUT_ENTRIES);
 	drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
-#ifdef CONFIG_DEBUG_FS
-	attach_crtc_crc_properties(dm, acrtc);
-#endif
+
 	return 0;
 
 fail:
@@ -7665,7 +7548,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_crtc *pcrtc,
 				    bool wait_for_vblank)
 {
-	uint32_t i;
+	int i;
 	uint64_t timestamp_ns;
 	struct drm_plane *plane;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
@@ -7706,7 +7589,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		amdgpu_dm_commit_cursors(state);
 
 	/* update planes when needed */
-	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
+	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
 		struct drm_crtc *crtc = new_plane_state->crtc;
 		struct drm_crtc_state *new_crtc_state;
 		struct drm_framebuffer *fb = new_plane_state->fb;
@@ -7929,8 +7812,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 						     bundle->surface_updates,
 						     planes_count,
 						     acrtc_state->stream,
-						     &bundle->stream_update,
-						     dc_state);
+						     &bundle->stream_update);
 
 		/**
 		 * Enable or disable the interrupts on the backend.
@@ -8266,13 +8148,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
 		struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state);
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
-		struct dc_surface_update dummy_updates[MAX_SURFACES];
+		struct dc_surface_update surface_updates[MAX_SURFACES];
 		struct dc_stream_update stream_update;
 		struct dc_info_packet hdr_packet;
 		struct dc_stream_status *status = NULL;
 		bool abm_changed, hdr_changed, scaling_changed;
 
-		memset(&dummy_updates, 0, sizeof(dummy_updates));
+		memset(&surface_updates, 0, sizeof(surface_updates));
 		memset(&stream_update, 0, sizeof(stream_update));
 
 		if (acrtc) {
@@ -8329,16 +8211,15 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		for (j = 0; j < status->plane_count; j++)
-			dummy_updates[j].surface = status->plane_states[0];
+			surface_updates[j].surface = status->plane_states[j];
 
 
 		mutex_lock(&dm->dc_lock);
 		dc_commit_updates_for_stream(dm->dc,
-						     dummy_updates,
+						surface_updates,
 						     status->plane_count,
 						     dm_new_crtc_state->stream,
-						     &stream_update,
-						     dc_state);
+						     &stream_update);
 		mutex_unlock(&dm->dc_lock);
 	}
 
@@ -8367,7 +8248,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	 */
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
-		bool configure_crc = false;
 
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 
@@ -8377,27 +8257,20 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			dc_stream_retain(dm_new_crtc_state->stream);
 			acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
 			manage_dm_interrupts(adev, acrtc, true);
-		}
-		if (IS_ENABLED(CONFIG_DEBUG_FS) && new_crtc_state->active &&
-			amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
+
+#ifdef CONFIG_DEBUG_FS
 			/**
 			 * Frontend may have changed so reapply the CRC capture
 			 * settings for the stream.
 			 */
 			dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
-			dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
 
-			if (amdgpu_dm_crc_window_is_default(dm_new_crtc_state)) {
-				if (!old_crtc_state->active || drm_atomic_crtc_needs_modeset(new_crtc_state))
-					configure_crc = true;
-			} else {
-				if (amdgpu_dm_crc_window_changed(dm_new_crtc_state, dm_old_crtc_state))
-					configure_crc = true;
-			}
-
-			if (configure_crc)
+			if (amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
 				amdgpu_dm_crtc_configure_crc_source(
-					crtc, dm_new_crtc_state, dm_new_crtc_state->crc_src);
+					crtc, dm_new_crtc_state,
+					dm_new_crtc_state->crc_src);
+			}
+#endif
 		}
 	}
 
@@ -8483,14 +8356,14 @@ static int dm_force_atomic_commit(struct drm_connector *connector)
 
 	ret = PTR_ERR_OR_ZERO(conn_state);
 	if (ret)
-		goto err;
+		goto out;
 
 	/* Attach crtc to drm_atomic_state*/
 	crtc_state = drm_atomic_get_crtc_state(state, &disconnected_acrtc->base);
 
 	ret = PTR_ERR_OR_ZERO(crtc_state);
 	if (ret)
-		goto err;
+		goto out;
 
 	/* force a restore */
 	crtc_state->mode_changed = true;
@@ -8500,17 +8373,15 @@ static int dm_force_atomic_commit(struct drm_connector *connector)
 
 	ret = PTR_ERR_OR_ZERO(plane_state);
 	if (ret)
-		goto err;
-
+		goto out;
 
 	/* Call commit internally with the state we just constructed */
 	ret = drm_atomic_commit(state);
-	if (!ret)
-		return 0;
 
-err:
-	DRM_ERROR("Restoring old state failed with %i\n", ret);
+out:
 	drm_atomic_state_put(state);
+	if (ret)
+		DRM_ERROR("Restoring old state failed with %i\n", ret);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 2ee6edb3df93..1182dafcef02 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -336,32 +336,6 @@ struct amdgpu_display_manager {
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
 
-#ifdef CONFIG_DEBUG_FS
-	/**
-	 * @crc_win_x_start_property:
-	 *
-	 * X start of the crc calculation window
-	 */
-	struct drm_property *crc_win_x_start_property;
-	/**
-	 * @crc_win_y_start_property:
-	 *
-	 * Y start of the crc calculation window
-	 */
-	struct drm_property *crc_win_y_start_property;
-	/**
-	 * @crc_win_x_end_property:
-	 *
-	 * X end of the crc calculation window
-	 */
-	struct drm_property *crc_win_x_end_property;
-	/**
-	 * @crc_win_y_end_property:
-	 *
-	 * Y end of the crc calculation window
-	 */
-	struct drm_property *crc_win_y_end_property;
-#endif
 	/**
 	 * @mst_encoders:
 	 *
@@ -448,15 +422,6 @@ struct dm_plane_state {
 	struct dc_plane_state *dc_state;
 };
 
-#ifdef CONFIG_DEBUG_FS
-struct crc_rec {
-	uint16_t x_start;
-	uint16_t y_start;
-	uint16_t x_end;
-	uint16_t y_end;
-	};
-#endif
-
 struct dm_crtc_state {
 	struct drm_crtc_state base;
 	struct dc_stream_state *stream;
@@ -479,9 +444,6 @@ struct dm_crtc_state {
 	struct dc_info_packet vrr_infopacket;
 
 	int abm_level;
-#ifdef CONFIG_DEBUG_FS
-	struct crc_rec crc_window;
-#endif
 };
 
 #define to_dm_crtc_state(x) container_of(x, struct dm_crtc_state, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index 7b886a779a8c..66cb8730586b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -81,41 +81,6 @@ const char *const *amdgpu_dm_crtc_get_crc_sources(struct drm_crtc *crtc,
 	return pipe_crc_sources;
 }
 
-static void amdgpu_dm_set_crc_window_default(struct dm_crtc_state *dm_crtc_state)
-{
-	dm_crtc_state->crc_window.x_start = 0;
-	dm_crtc_state->crc_window.y_start = 0;
-	dm_crtc_state->crc_window.x_end = 0;
-	dm_crtc_state->crc_window.y_end = 0;
-}
-
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state)
-{
-	bool ret = true;
-
-	if ((dm_crtc_state->crc_window.x_start != 0) ||
-		(dm_crtc_state->crc_window.y_start != 0) ||
-		(dm_crtc_state->crc_window.x_end != 0) ||
-		(dm_crtc_state->crc_window.y_end != 0))
-		ret = false;
-
-	return ret;
-}
-
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
-					struct dm_crtc_state *dm_old_crtc_state)
-{
-	bool ret = false;
-
-	if ((dm_new_crtc_state->crc_window.x_start != dm_old_crtc_state->crc_window.x_start) ||
-		(dm_new_crtc_state->crc_window.y_start != dm_old_crtc_state->crc_window.y_start) ||
-		(dm_new_crtc_state->crc_window.x_end != dm_old_crtc_state->crc_window.x_end) ||
-		(dm_new_crtc_state->crc_window.y_end != dm_old_crtc_state->crc_window.y_end))
-		ret = true;
-
-	return ret;
-}
-
 int
 amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
 				 size_t *values_cnt)
@@ -140,7 +105,6 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 	struct dc_stream_state *stream_state = dm_crtc_state->stream;
 	bool enable = amdgpu_dm_is_valid_crc_source(source);
 	int ret = 0;
-	struct crc_params *crc_window = NULL, tmp_window;
 
 	/* Configuration will be deferred to stream enable. */
 	if (!stream_state)
@@ -150,24 +114,8 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 
 	/* Enable CRTC CRC generation if necessary. */
 	if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) {
-		if (!enable)
-			amdgpu_dm_set_crc_window_default(dm_crtc_state);
-
-		if (!amdgpu_dm_crc_window_is_default(dm_crtc_state)) {
-			crc_window = &tmp_window;
-
-			tmp_window.windowa_x_start = dm_crtc_state->crc_window.x_start;
-			tmp_window.windowa_y_start = dm_crtc_state->crc_window.y_start;
-			tmp_window.windowa_x_end = dm_crtc_state->crc_window.x_end;
-			tmp_window.windowa_y_end = dm_crtc_state->crc_window.y_end;
-			tmp_window.windowb_x_start = dm_crtc_state->crc_window.x_start;
-			tmp_window.windowb_y_start = dm_crtc_state->crc_window.y_start;
-			tmp_window.windowb_x_end = dm_crtc_state->crc_window.x_end;
-			tmp_window.windowb_y_end = dm_crtc_state->crc_window.y_end;
-		}
-
 		if (!dc_stream_configure_crc(stream_state->ctx->dc,
-					     stream_state, crc_window, enable, enable)) {
+					     stream_state, NULL, enable, enable)) {
 			ret = -EINVAL;
 			goto unlock;
 		}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
index eba2f1d35d07..f7d731797d3f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
@@ -46,13 +46,10 @@ static inline bool amdgpu_dm_is_valid_crc_source(enum amdgpu_dm_pipe_crc_source
 }
 
 /* amdgpu_dm_crc.c */
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state);
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
-					struct dm_crtc_state *dm_old_crtc_state);
+#ifdef CONFIG_DEBUG_FS
 int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 					struct dm_crtc_state *dm_crtc_state,
 					enum amdgpu_dm_pipe_crc_source source);
-#ifdef CONFIG_DEBUG_FS
 int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name);
 int amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc,
 				     const char *src_name,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 8ab0b9060d2b..f2d8cf34be46 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -833,6 +833,9 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 		if (computed_streams[i])
 			continue;
 
+		if (dcn20_remove_stream_from_ctx(stream->ctx->dc, dc_state, stream) != DC_OK)
+			return false;
+
 		mutex_lock(&aconnector->mst_mgr.lock);
 		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) {
 			mutex_unlock(&aconnector->mst_mgr.lock);
@@ -850,7 +853,8 @@ bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 		stream = dc_state->streams[i];
 
 		if (stream->timing.flags.DSC == 1)
-			dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream);
+			if (dc_stream_add_dsc_to_resource(stream->ctx->dc, dc_state, stream) != DC_OK)
+				return false;
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index 5b466f440d67..ab98c259ef69 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -251,6 +251,7 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 	bool force_reset = false;
 	bool update_uclk = false;
+	bool p_state_change_support;
 
 	if (dc->work_arounds.skip_clock_update || !clk_mgr->smu_present)
 		return;
@@ -291,8 +292,9 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base,
 		clk_mgr_base->clks.socclk_khz = new_clocks->socclk_khz;
 
 	clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support;
-	if (should_update_pstate_support(safe_to_lower, new_clocks->p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
-		clk_mgr_base->clks.p_state_change_support = new_clocks->p_state_change_support;
+	p_state_change_support = new_clocks->p_state_change_support || (display_count == 0);
+	if (should_update_pstate_support(safe_to_lower, p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
+		clk_mgr_base->clks.p_state_change_support = p_state_change_support;
 
 		/* to disable P-State switching, set UCLK min = max */
 		if (!clk_mgr_base->clks.p_state_change_support)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 58eb0d69873a..6cf1a5a2a5ec 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2679,8 +2679,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
 		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update,
-		struct dc_state *state)
+		struct dc_stream_update *stream_update)
 {
 	const struct dc_stream_status *stream_status;
 	enum surface_update_type update_type;
@@ -2699,6 +2698,12 @@ void dc_commit_updates_for_stream(struct dc *dc,
 
 
 	if (update_type >= UPDATE_TYPE_FULL) {
+		struct dc_plane_state *new_planes[MAX_SURFACES];
+
+		memset(new_planes, 0, sizeof(new_planes));
+
+		for (i = 0; i < surface_count; i++)
+			new_planes[i] = srf_updates[i].surface;
 
 		/* initialize scratch memory for building context */
 		context = dc_create_state(dc);
@@ -2707,15 +2712,21 @@ void dc_commit_updates_for_stream(struct dc *dc,
 			return;
 		}
 
-		dc_resource_state_copy_construct(state, context);
+		dc_resource_state_copy_construct(
+				dc->current_state, context);
 
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-			struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+		/*remove old surfaces from context */
+		if (!dc_rem_all_planes_for_stream(dc, stream, context)) {
+			DC_ERROR("Failed to remove streams for new validate context!\n");
+			return;
+		}
 
-			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
-				new_pipe->plane_state->force_full_update = true;
+		/* add surface to context */
+		if (!dc_add_all_planes_for_stream(dc, stream, new_planes, surface_count, context)) {
+			DC_ERROR("Failed to add streams for new validate context!\n");
+			return;
 		}
+
 	}
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 2fc12239b22c..1e4794e2825c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -892,13 +892,13 @@ static uint32_t translate_training_aux_read_interval(uint32_t dpcd_aux_read_inte
 
 	switch (dpcd_aux_read_interval) {
 	case 0x01:
-		aux_rd_interval_us = 400;
+		aux_rd_interval_us = 4000;
 		break;
 	case 0x02:
-		aux_rd_interval_us = 4000;
+		aux_rd_interval_us = 8000;
 		break;
 	case 0x03:
-		aux_rd_interval_us = 8000;
+		aux_rd_interval_us = 12000;
 		break;
 	case 0x04:
 		aux_rd_interval_us = 16000;
@@ -2399,6 +2399,9 @@ static bool decide_dp_link_settings(struct dc_link *link, struct dc_link_setting
 			initial_link_setting;
 	uint32_t link_bw;
 
+	if (req_bw > dc_link_bandwidth_kbps(link, &link->verified_link_cap))
+		return false;
+
 	/* search for the minimum link setting that:
 	 * 1. is supported according to the link training result
 	 * 2. could support the b/w requested by the timing
@@ -3045,14 +3048,14 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link)
+					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
 				core_link_disable_stream(pipe_ctx);
 		}
 
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe_ctx && pipe_ctx->stream && !pipe_ctx->stream->dpms_off &&
-					pipe_ctx->stream->link == link)
+					pipe_ctx->stream->link == link && !pipe_ctx->prev_odm_pipe)
 				core_link_enable_stream(link->dc->current_state, pipe_ctx);
 		}
 
@@ -3992,7 +3995,7 @@ bool dc_link_dp_set_test_pattern(
 	unsigned int cust_pattern_size)
 {
 	struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
-	struct pipe_ctx *pipe_ctx = &pipes[0];
+	struct pipe_ctx *pipe_ctx = NULL;
 	unsigned int lane;
 	unsigned int i;
 	unsigned char link_qual_pattern[LANE_COUNT_DP_MAX] = {0};
@@ -4002,12 +4005,18 @@ bool dc_link_dp_set_test_pattern(
 	memset(&training_pattern, 0, sizeof(training_pattern));
 
 	for (i = 0; i < MAX_PIPES; i++) {
+		if (pipes[i].stream == NULL)
+			continue;
+
 		if (pipes[i].stream->link == link && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe) {
 			pipe_ctx = &pipes[i];
 			break;
 		}
 	}
 
+	if (pipe_ctx == NULL)
+		return false;
+
 	/* Reset CRTC Test Pattern if it is currently running and request is VideoMode */
 	if (link->test_pattern_enabled && test_pattern ==
 			DP_TEST_PATTERN_VIDEO_MODE) {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index b7910976b81a..e243c01b9672 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -283,8 +283,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
 		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update,
-		struct dc_state *state);
+		struct dc_stream_update *stream_update);
 /*
  * Log the current stream state.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index cfc130e2d6fd..017b67b830e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -647,8 +647,13 @@ static void power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->funcs.dpp_pg_control(hws, plane_id, true);
-		hws->funcs.hubp_pg_control(hws, plane_id, true);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, plane_id, true);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, plane_id, true);
+
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
@@ -1082,8 +1087,13 @@ void dcn10_plane_atomic_power_down(struct dc *dc,
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->funcs.dpp_pg_control(hws, dpp->inst, false);
-		hws->funcs.hubp_pg_control(hws, hubp->inst, false);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, dpp->inst, false);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, hubp->inst, false);
+
 		dpp->funcs->dpp_reset(dpp);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 100ce0e28fd5..b096011acb49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -470,7 +470,7 @@ void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock)
 unsigned int mpc1_get_mpc_out_mux(struct mpc *mpc, int opp_id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
-	uint32_t val = 0;
+	uint32_t val = 0xf;
 
 	if (opp_id < MAX_OPP && REG(MUX[opp_id]))
 		REG_GET(MUX[opp_id], MPC_OUT_MUX, &val);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 36745193c391..90e912fef2b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -608,8 +608,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.disable_pplib_clock_request = false,
 		.disable_pplib_wm_range = false,
 		.pplib_wm_report_mode = WM_REPORT_DEFAULT,
-		.pipe_split_policy = MPC_SPLIT_DYNAMIC,
-		.force_single_disp_pipe_split = true,
+		.pipe_split_policy = MPC_SPLIT_AVOID,
+		.force_single_disp_pipe_split = false,
 		.disable_dcc = DCC_ENABLE,
 		.voltage_align_fclk = true,
 		.disable_stereo_support = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index cb822df21b7c..480d928cb1ca 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1062,8 +1062,13 @@ static void dcn20_power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		dcn20_dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true);
-		dcn20_hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true);
+
+		if (hws->funcs.dpp_pg_control)
+			hws->funcs.dpp_pg_control(hws, pipe_ctx->plane_res.dpp->inst, true);
+
+		if (hws->funcs.hubp_pg_control)
+			hws->funcs.hubp_pg_control(hws, pipe_ctx->plane_res.hubp->inst, true);
+
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index e04ecf0fc0db..5ed18cac57e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2517,8 +2517,7 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		 * if this primary pipe has a bottom pipe in prev. state
 		 * and if the bottom pipe is still available (which it should be),
 		 * pick that pipe as secondary
-		 * Same logic applies for ODM pipes. Since mpo is not allowed with odm
-		 * check in else case.
+		 * Same logic applies for ODM pipes
 		 */
 		if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe) {
 			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].bottom_pipe->pipe_idx;
@@ -2526,7 +2525,9 @@ struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 				secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
 				secondary_pipe->pipe_idx = preferred_pipe_idx;
 			}
-		} else if (dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) {
+		}
+		if (secondary_pipe == NULL &&
+				dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe) {
 			preferred_pipe_idx = dc->current_state->res_ctx.pipe_ctx[primary_pipe->pipe_idx].next_odm_pipe->pipe_idx;
 			if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) {
 				secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index 1c88d2edd381..674376428916 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -296,7 +296,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 	.num_banks = 8,
 	.num_chans = 4,
 	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 23.84,
+	.dram_clock_change_latency_us = 11.72,
 	.return_bus_width_bytes = 64,
 	.dispclk_dppclk_vco_speed_mhz = 3600,
 	.xfc_bus_transport_time_us = 4,
@@ -906,6 +906,8 @@ enum dcn20_clk_src_array_id {
 	DCN20_CLK_SRC_PLL0,
 	DCN20_CLK_SRC_PLL1,
 	DCN20_CLK_SRC_PLL2,
+	DCN20_CLK_SRC_PLL3,
+	DCN20_CLK_SRC_PLL4,
 	DCN20_CLK_SRC_TOTAL_DCN21
 };
 
@@ -2030,6 +2032,14 @@ static bool dcn21_resource_construct(
 			dcn21_clock_source_create(ctx, ctx->dc_bios,
 				CLOCK_SOURCE_COMBO_PHY_PLL2,
 				&clk_src_regs[2], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL3] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL3,
+				&clk_src_regs[3], false);
+	pool->base.clock_sources[DCN20_CLK_SRC_PLL4] =
+			dcn21_clock_source_create(ctx, ctx->dc_bios,
+				CLOCK_SOURCE_COMBO_PHY_PLL4,
+				&clk_src_regs[4], false);
 
 	pool->base.clk_src_count = DCN20_CLK_SRC_TOTAL_DCN21;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
index c20331eb62e0..dfd77b3cc84d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile
@@ -32,8 +32,8 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \
 
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse
-CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -45,6 +45,8 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mhard-float
+CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
index 3ca7d911d25c..09264716d1dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/Makefile
@@ -14,7 +14,7 @@ DCN301 = dcn301_init.o dcn301_resource.o dcn301_dccg.o \
 		dcn301_dio_link_encoder.o dcn301_hwseq.o dcn301_panel_cntl.o dcn301_hubbub.o
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -25,6 +25,7 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn301/dcn301_resource.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
index 4825c5c1c6ed..35f5bf08ae96 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
@@ -1731,6 +1731,7 @@ static struct resource_funcs dcn301_res_pool_funcs = {
 	.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
+	.add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource,
 	.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
 	.populate_dml_writeback_from_context = dcn30_populate_dml_writeback_from_context,
 	.set_mcif_arb_params = dcn30_set_mcif_arb_params,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
index 8d4924b7dc22..101620a8867a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/Makefile
@@ -13,7 +13,7 @@
 DCN3_02 = dcn302_init.o dcn302_hwseq.o dcn302_resource.o
 
 ifdef CONFIG_X86
-CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -mhard-float -msse
+CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o := -msse
 endif
 
 ifdef CONFIG_PPC64
@@ -24,6 +24,7 @@ ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
 IS_OLD_GCC = 1
 endif
+CFLAGS_$(AMDDALPATH)/dc/dcn302/dcn302_resource.o += -mhard-float
 endif
 
 ifdef CONFIG_X86
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 860e72a51534..80170f9721ce 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -2635,14 +2635,15 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 	}
 
 	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
-			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 &&
-			mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 
 		for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
-			if (mode_lib->vba.DRAMClockChangeWatermark >
-			dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
-				mode_lib->vba.MinTTUVBlank[k] += 25;
+			if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+				if (mode_lib->vba.DRAMClockChangeWatermark >
+				dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+					mode_lib->vba.MinTTUVBlank[k] += 25;
+			}
 		}
 
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 4bdbcce7092d..0d797fa9f5cc 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -553,6 +553,7 @@ struct pptable_funcs {
 					     *clock_req);
 	uint32_t (*get_fan_control_mode)(struct smu_context *smu);
 	int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
+	int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed);
 	int (*set_fan_speed_rpm)(struct smu_context *smu, uint32_t speed);
 	int (*set_xgmi_pstate)(struct smu_context *smu, uint32_t pstate);
 	int (*gfx_off_control)(struct smu_context *smu, bool enable);
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index 13de692a4213..5d0b29653ffa 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -203,6 +203,9 @@ int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode);
 
+int
+smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
+
 int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 				       uint32_t speed);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 8b867a6d52b5..e84c737e3967 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2151,19 +2151,14 @@ int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed)
 int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 {
 	int ret = 0;
-	uint32_t rpm;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->set_fan_speed_rpm) {
-		if (speed > 100)
-			speed = 100;
-		rpm = speed * smu->fan_max_rpm / 100;
-		ret = smu->ppt_funcs->set_fan_speed_rpm(smu, rpm);
-	}
+	if (smu->ppt_funcs->set_fan_speed_percent)
+		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
 
 	mutex_unlock(&smu->mutex);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index cd7b411457ff..16db0b506b0d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -2326,6 +2326,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 51e83123f72a..cd7efa923195 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -2456,6 +2456,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 12b36eb0ff6a..d68d3dfee51d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -2802,6 +2802,7 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = {
 	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
 	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
 	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
 	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
 	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
 	.gfx_off_control = smu_v11_0_gfx_off_control,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index b279dbbbce6b..5aeb5f5a0447 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1174,6 +1174,35 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode)
 }
 
 int
+smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
+{
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
+
+	if (speed > 100)
+		speed = 100;
+
+	if (smu_v11_0_auto_fan_control(smu, 0))
+		return -EINVAL;
+
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	if (!duty100)
+		return -EINVAL;
+
+	tmp64 = (uint64_t)speed * duty100;
+	do_div(tmp64, 100);
+	duty = (uint32_t)tmp64;
+
+	WREG32_SOC15(THM, 0, mmCG_FDO_CTRL0,
+		     REG_SET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL0),
+				   CG_FDO_CTRL0, FDO_STATIC_DUTY, duty));
+
+	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
+}
+
+int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode)
 {
@@ -1181,7 +1210,7 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
-		ret = smu_v11_0_set_fan_speed_rpm(smu, smu->fan_max_rpm);
+		ret = smu_v11_0_set_fan_speed_percent(smu, 100);
 		break;
 	case AMD_FAN_CTRL_MANUAL:
 		ret = smu_v11_0_auto_fan_control(smu, 0);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 5c1482d4ca43..92ad2cdbae10 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -591,14 +591,17 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_socket_power = metrics.CurrentSocketPower;
 	gpu_metrics->average_cpu_power = metrics.Power[0];
 	gpu_metrics->average_soc_power = metrics.Power[1];
+	gpu_metrics->average_gfx_power = metrics.Power[2];
 	memcpy(&gpu_metrics->average_core_power[0],
 		&metrics.CorePower[0],
 		sizeof(uint16_t) * 8);
 
 	gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency;
 	gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency;
+	gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency;
 	gpu_metrics->average_fclk_frequency = metrics.MemclkFrequency;
 	gpu_metrics->average_vclk_frequency = metrics.VclkFrequency;
+	gpu_metrics->average_dclk_frequency = metrics.DclkFrequency;
 
 	memcpy(&gpu_metrics->current_coreclk[0],
 		&metrics.CoreFrequency[0],
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index f743685a20e8..9a9697038016 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -1121,7 +1121,7 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu,
 static int renoir_gfx_state_change_set(struct smu_context *smu, uint32_t state)
 {
 
-	return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GpuChangeState, state, NULL);
+	return 0;
 }
 
 static const struct pptable_funcs renoir_ppt_funcs = {
diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
index 0c98d27f84ac..fee27952ec6d 100644
--- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
+++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c
@@ -14,6 +14,7 @@
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 
 #include <sound/hdmi-codec.h>
 
@@ -36,6 +37,7 @@ struct lt9611uxc {
 	struct mutex ocm_lock;
 
 	struct wait_queue_head wq;
+	struct work_struct work;
 
 	struct device_node *dsi0_node;
 	struct device_node *dsi1_node;
@@ -52,6 +54,8 @@ struct lt9611uxc {
 
 	bool hpd_supported;
 	bool edid_read;
+	/* can be accessed from different threads, so protect this with ocm_lock */
+	bool hdmi_connected;
 	uint8_t fw_version;
 };
 
@@ -143,21 +147,41 @@ static irqreturn_t lt9611uxc_irq_thread_handler(int irq, void *dev_id)
 	if (irq_status)
 		regmap_write(lt9611uxc->regmap, 0xb022, 0);
 
-	lt9611uxc_unlock(lt9611uxc);
-
-	if (irq_status & BIT(0))
+	if (irq_status & BIT(0)) {
 		lt9611uxc->edid_read = !!(hpd_status & BIT(0));
+		wake_up_all(&lt9611uxc->wq);
+	}
 
 	if (irq_status & BIT(1)) {
-		if (lt9611uxc->connector.dev)
-			drm_kms_helper_hotplug_event(lt9611uxc->connector.dev);
-		else
-			drm_bridge_hpd_notify(&lt9611uxc->bridge, !!(hpd_status & BIT(1)));
+		lt9611uxc->hdmi_connected = hpd_status & BIT(1);
+		schedule_work(&lt9611uxc->work);
 	}
 
+	lt9611uxc_unlock(lt9611uxc);
+
 	return IRQ_HANDLED;
 }
 
+static void lt9611uxc_hpd_work(struct work_struct *work)
+{
+	struct lt9611uxc *lt9611uxc = container_of(work, struct lt9611uxc, work);
+	bool connected;
+
+	if (lt9611uxc->connector.dev)
+		drm_kms_helper_hotplug_event(lt9611uxc->connector.dev);
+	else {
+
+		mutex_lock(&lt9611uxc->ocm_lock);
+		connected = lt9611uxc->hdmi_connected;
+		mutex_unlock(&lt9611uxc->ocm_lock);
+
+		drm_bridge_hpd_notify(&lt9611uxc->bridge,
+				      connected ?
+				      connector_status_connected :
+				      connector_status_disconnected);
+	}
+}
+
 static void lt9611uxc_reset(struct lt9611uxc *lt9611uxc)
 {
 	gpiod_set_value_cansleep(lt9611uxc->reset_gpio, 1);
@@ -445,18 +469,21 @@ static enum drm_connector_status lt9611uxc_bridge_detect(struct drm_bridge *brid
 	struct lt9611uxc *lt9611uxc = bridge_to_lt9611uxc(bridge);
 	unsigned int reg_val = 0;
 	int ret;
-	int connected = 1;
+	bool connected = true;
+
+	lt9611uxc_lock(lt9611uxc);
 
 	if (lt9611uxc->hpd_supported) {
-		lt9611uxc_lock(lt9611uxc);
 		ret = regmap_read(lt9611uxc->regmap, 0xb023, &reg_val);
-		lt9611uxc_unlock(lt9611uxc);
 
 		if (ret)
 			dev_err(lt9611uxc->dev, "failed to read hpd status: %d\n", ret);
 		else
 			connected  = reg_val & BIT(1);
 	}
+	lt9611uxc->hdmi_connected = connected;
+
+	lt9611uxc_unlock(lt9611uxc);
 
 	return connected ?  connector_status_connected :
 				connector_status_disconnected;
@@ -465,7 +492,7 @@ static enum drm_connector_status lt9611uxc_bridge_detect(struct drm_bridge *brid
 static int lt9611uxc_wait_for_edid(struct lt9611uxc *lt9611uxc)
 {
 	return wait_event_interruptible_timeout(lt9611uxc->wq, lt9611uxc->edid_read,
-			msecs_to_jiffies(100));
+			msecs_to_jiffies(500));
 }
 
 static int lt9611uxc_get_edid_block(void *data, u8 *buf, unsigned int block, size_t len)
@@ -503,7 +530,10 @@ static struct edid *lt9611uxc_bridge_get_edid(struct drm_bridge *bridge,
 	ret = lt9611uxc_wait_for_edid(lt9611uxc);
 	if (ret < 0) {
 		dev_err(lt9611uxc->dev, "wait for EDID failed: %d\n", ret);
-		return ERR_PTR(ret);
+		return NULL;
+	} else if (ret == 0) {
+		dev_err(lt9611uxc->dev, "wait for EDID timeout\n");
+		return NULL;
 	}
 
 	return drm_do_get_edid(connector, lt9611uxc_get_edid_block, lt9611uxc);
@@ -926,6 +956,8 @@ retry:
 	lt9611uxc->fw_version = ret;
 
 	init_waitqueue_head(&lt9611uxc->wq);
+	INIT_WORK(&lt9611uxc->work, lt9611uxc_hpd_work);
+
 	ret = devm_request_threaded_irq(dev, client->irq, NULL,
 					lt9611uxc_irq_thread_handler,
 					IRQF_ONESHOT, "lt9611uxc", lt9611uxc);
@@ -962,6 +994,7 @@ static int lt9611uxc_remove(struct i2c_client *client)
 	struct lt9611uxc *lt9611uxc = i2c_get_clientdata(client);
 
 	disable_irq(client->irq);
+	flush_scheduled_work();
 	lt9611uxc_audio_exit(lt9611uxc);
 	drm_bridge_remove(&lt9611uxc->bridge);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index ba1507036f26..4a8cbec832bc 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -3021,7 +3021,7 @@ int drm_atomic_helper_set_config(struct drm_mode_set *set,
 
 	ret = handle_conflicting_encoders(state, true);
 	if (ret)
-		return ret;
+		goto fail;
 
 	ret = drm_atomic_commit(state);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 0401b2f47500..8781deefeae3 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -3629,14 +3629,26 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr,
 	return 0;
 }
 
-static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8  dp_link_count)
+/**
+ * drm_dp_get_vc_payload_bw - get the VC payload BW for an MST link
+ * @link_rate: link rate in 10kbits/s units
+ * @link_lane_count: lane count
+ *
+ * Calculate the total bandwidth of a MultiStream Transport link. The returned
+ * value is in units of PBNs/(timeslots/1 MTP). This value can be used to
+ * convert the number of PBNs required for a given stream to the number of
+ * timeslots this stream requires in each MTP.
+ */
+int drm_dp_get_vc_payload_bw(int link_rate, int link_lane_count)
 {
-	if (dp_link_bw == 0 || dp_link_count == 0)
-		DRM_DEBUG_KMS("invalid link bandwidth in DPCD: %x (link count: %d)\n",
-			      dp_link_bw, dp_link_count);
+	if (link_rate == 0 || link_lane_count == 0)
+		DRM_DEBUG_KMS("invalid link rate/lane count: (%d / %d)\n",
+			      link_rate, link_lane_count);
 
-	return dp_link_bw * dp_link_count / 2;
+	/* See DP v2.0 2.6.4.2, VCPayload_Bandwidth_for_OneTimeSlotPer_MTP_Allocation */
+	return link_rate * link_lane_count / 54000;
 }
+EXPORT_SYMBOL(drm_dp_get_vc_payload_bw);
 
 /**
  * drm_dp_read_mst_cap() - check whether or not a sink supports MST
@@ -3692,7 +3704,7 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 			goto out_unlock;
 		}
 
-		mgr->pbn_div = drm_dp_get_vc_payload_bw(mgr->dpcd[1],
+		mgr->pbn_div = drm_dp_get_vc_payload_bw(drm_dp_bw_code_to_link_rate(mgr->dpcd[1]),
 							mgr->dpcd[2] & DP_MAX_LANE_COUNT_MASK);
 		if (mgr->pbn_div == 0) {
 			ret = -EINVAL;
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 02ca22e90290..0b232a73c1b7 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -387,9 +387,16 @@ static int drm_gem_vram_kmap_locked(struct drm_gem_vram_object *gbo,
 	if (gbo->vmap_use_count > 0)
 		goto out;
 
-	ret = ttm_bo_vmap(&gbo->bo, &gbo->map);
-	if (ret)
-		return ret;
+	/*
+	 * VRAM helpers unmap the BO only on demand. So the previous
+	 * page mapping might still be around. Only vmap if the there's
+	 * no mapping present.
+	 */
+	if (dma_buf_map_is_null(&gbo->map)) {
+		ret = ttm_bo_vmap(&gbo->bo, &gbo->map);
+		if (ret)
+			return ret;
+	}
 
 out:
 	++gbo->vmap_use_count;
@@ -577,6 +584,7 @@ static void drm_gem_vram_bo_driver_move_notify(struct drm_gem_vram_object *gbo,
 		return;
 
 	ttm_bo_vunmap(bo, &gbo->map);
+	dma_buf_map_clear(&gbo->map); /* explicitly clear mapping for next vmap call */
 }
 
 static int drm_gem_vram_bo_driver_move(struct drm_gem_vram_object *gbo,
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index e6231947f987..a0cb746bcb0a 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -1163,7 +1163,14 @@ retry:
 	if (ret)
 		goto out;
 
-	if (old_fb->format != fb->format) {
+	/*
+	 * Only check the FOURCC format code, excluding modifiers. This is
+	 * enough for all legacy drivers. Atomic drivers have their own
+	 * checks in their ->atomic_check implementation, which will
+	 * return -EINVAL if any hw or driver constraint is violated due
+	 * to modifier changes.
+	 */
+	if (old_fb->format->format != fb->format->format) {
 		DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n");
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 6e74e6745eca..349146049849 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -388,19 +388,18 @@ int drm_syncobj_find_fence(struct drm_file *file_private,
 		return -ENOENT;
 
 	*fence = drm_syncobj_fence_get(syncobj);
-	drm_syncobj_put(syncobj);
 
 	if (*fence) {
 		ret = dma_fence_chain_find_seqno(fence, point);
 		if (!ret)
-			return 0;
+			goto out;
 		dma_fence_put(*fence);
 	} else {
 		ret = -EINVAL;
 	}
 
 	if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT))
-		return ret;
+		goto out;
 
 	memset(&wait, 0, sizeof(wait));
 	wait.task = current;
@@ -432,6 +431,9 @@ int drm_syncobj_find_fence(struct drm_file *file_private,
 	if (wait.node.next)
 		drm_syncobj_remove_wait(syncobj, &wait);
 
+out:
+	drm_syncobj_put(syncobj);
+
 	return ret;
 }
 EXPORT_SYMBOL(drm_syncobj_find_fence);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e5574e506a5c..6d9e81ea67f4 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -38,6 +38,7 @@ i915-y += i915_drv.o \
 	  i915_config.o \
 	  i915_irq.o \
 	  i915_getparam.o \
+	  i915_mitigations.o \
 	  i915_params.o \
 	  i915_pci.o \
 	  i915_scatterlist.o \
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index a9439b415603..b3533a32f8ba 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1616,10 +1616,6 @@ static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
 
 	get_dsi_io_power_domains(i915,
 				 enc_to_intel_dsi(encoder));
-
-	if (crtc_state->dsc.compression_enable)
-		intel_display_power_get(i915,
-					intel_dsc_power_domain(crtc_state));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 92940a0c5ef8..dc13d1814d95 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2754,13 +2754,15 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 	int n_entries, ln;
 	u32 val;
 
+	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
+		return;
+
 	ddi_translations = icl_get_mg_buf_trans(encoder, crtc_state, &n_entries);
-	/* The table does not have values for level 3 and level 9. */
-	if (level >= n_entries || level == 3 || level == 9) {
+	if (level >= n_entries) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "DDI translation not found for level %d. Using %d instead.",
-			    level, n_entries - 2);
-		level = n_entries - 2;
+			    level, n_entries - 1);
+		level = n_entries - 1;
 	}
 
 	/* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */
@@ -2891,6 +2893,9 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 	u32 val, dpcnt_mask, dpcnt_val;
 	int n_entries, ln;
 
+	if (enc_to_dig_port(encoder)->tc_mode == TC_PORT_TBT_ALT)
+		return;
+
 	ddi_translations = tgl_get_dkl_buf_trans(encoder, crtc_state, &n_entries);
 
 	if (level >= n_entries)
@@ -3532,6 +3537,23 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	intel_de_posting_read(dev_priv, dp_tp_ctl_reg(encoder, crtc_state));
 }
 
+static void intel_ddi_power_up_lanes(struct intel_encoder *encoder,
+				     const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	enum phy phy = intel_port_to_phy(i915, encoder->port);
+
+	if (intel_phy_is_combo(i915, phy)) {
+		bool lane_reversal =
+			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
+
+		intel_combo_phy_power_up_lanes(i915, phy, false,
+					       crtc_state->lane_count,
+					       lane_reversal);
+	}
+}
+
 static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state,
 				  struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
@@ -3621,14 +3643,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_atomic_state *state,
 	 * 7.f Combo PHY: Configure PORT_CL_DW10 Static Power Down to power up
 	 * the used lanes of the DDI.
 	 */
-	if (intel_phy_is_combo(dev_priv, phy)) {
-		bool lane_reversal =
-			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
-
-		intel_combo_phy_power_up_lanes(dev_priv, phy, false,
-					       crtc_state->lane_count,
-					       lane_reversal);
-	}
+	intel_ddi_power_up_lanes(encoder, crtc_state);
 
 	/*
 	 * 7.g Configure and enable DDI_BUF_CTL
@@ -3713,19 +3728,12 @@ static void hsw_ddi_pre_enable_dp(struct intel_atomic_state *state,
 	else
 		intel_prepare_dp_ddi_buffers(encoder, crtc_state);
 
-	if (intel_phy_is_combo(dev_priv, phy)) {
-		bool lane_reversal =
-			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
-
-		intel_combo_phy_power_up_lanes(dev_priv, phy, false,
-					       crtc_state->lane_count,
-					       lane_reversal);
-	}
+	intel_ddi_power_up_lanes(encoder, crtc_state);
 
 	intel_ddi_init_dp_buf_reg(encoder, crtc_state);
 	if (!is_mst)
 		intel_dp_set_power(intel_dp, DP_SET_POWER_D0);
-	intel_dp_configure_protocol_converter(intel_dp);
+	intel_dp_configure_protocol_converter(intel_dp, crtc_state);
 	intel_dp_sink_set_decompression_state(intel_dp, crtc_state,
 					      true);
 	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
@@ -4206,6 +4214,8 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state,
 		intel_de_write(dev_priv, reg, val);
 	}
 
+	intel_ddi_power_up_lanes(encoder, crtc_state);
+
 	/* In HDMI/DVI mode, the port width, and swing/emphasis values
 	 * are ignored so nothing special needs to be done besides
 	 * enabling the port.
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 53a00cf3fa32..61be6bed9162 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2309,7 +2309,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 		 */
 		ret = i915_vma_pin_fence(vma);
 		if (ret != 0 && INTEL_GEN(dev_priv) < 4) {
-			i915_gem_object_unpin_from_display_plane(vma);
+			i915_vma_unpin(vma);
 			vma = ERR_PTR(ret);
 			goto err;
 		}
@@ -2327,12 +2327,9 @@ err:
 
 void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags)
 {
-	i915_gem_object_lock(vma->obj, NULL);
 	if (flags & PLANE_HAS_FENCE)
 		i915_vma_unpin_fence(vma);
-	i915_gem_object_unpin_from_display_plane(vma);
-	i915_gem_object_unlock(vma->obj);
-
+	i915_vma_unpin(vma);
 	i915_vma_put(vma);
 }
 
@@ -4807,6 +4804,8 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	} else if (fb->format->is_yuv) {
 		plane_color_ctl |= PLANE_COLOR_INPUT_CSC_ENABLE;
+		if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	}
 
 	return plane_color_ctl;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 37f1a10fd021..8a26307c4896 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4014,7 +4014,8 @@ static void intel_dp_enable_port(struct intel_dp *intel_dp,
 	intel_de_posting_read(dev_priv, intel_dp->output_reg);
 }
 
-void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp)
+void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp,
+					   const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	u8 tmp;
@@ -4033,8 +4034,8 @@ void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp)
 		drm_dbg_kms(&i915->drm, "Failed to set protocol converter HDMI mode to %s\n",
 			    enableddisabled(intel_dp->has_hdmi_sink));
 
-	tmp = intel_dp->dfp.ycbcr_444_to_420 ?
-		DP_CONVERSION_TO_YCBCR420_ENABLE : 0;
+	tmp = crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444 &&
+		intel_dp->dfp.ycbcr_444_to_420 ? DP_CONVERSION_TO_YCBCR420_ENABLE : 0;
 
 	if (drm_dp_dpcd_writeb(&intel_dp->aux,
 			       DP_PROTOCOL_CONVERTER_CONTROL_1, tmp) != 1)
@@ -4088,7 +4089,7 @@ static void intel_enable_dp(struct intel_atomic_state *state,
 	}
 
 	intel_dp_set_power(intel_dp, DP_SET_POWER_D0);
-	intel_dp_configure_protocol_converter(intel_dp);
+	intel_dp_configure_protocol_converter(intel_dp, pipe_config);
 	intel_dp_start_link_train(intel_dp, pipe_config);
 	intel_dp_stop_link_train(intel_dp, pipe_config);
 
@@ -4636,24 +4637,6 @@ ivb_cpu_edp_set_signal_levels(struct intel_dp *intel_dp,
 	intel_de_posting_read(dev_priv, intel_dp->output_reg);
 }
 
-void intel_dp_set_signal_levels(struct intel_dp *intel_dp,
-				const struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	u8 train_set = intel_dp->train_set[0];
-
-	drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s\n",
-		    train_set & DP_TRAIN_VOLTAGE_SWING_MASK,
-		    train_set & DP_TRAIN_MAX_SWING_REACHED ? " (max)" : "");
-	drm_dbg_kms(&dev_priv->drm, "Using pre-emphasis level %d%s\n",
-		    (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) >>
-		    DP_TRAIN_PRE_EMPHASIS_SHIFT,
-		    train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ?
-		    " (max)" : "");
-
-	intel_dp->set_signal_levels(intel_dp, crtc_state);
-}
-
 void
 intel_dp_program_link_training_pattern(struct intel_dp *intel_dp,
 				       const struct intel_crtc_state *crtc_state,
@@ -5702,7 +5685,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp,
 
 	intel_dp_autotest_phy_ddi_disable(intel_dp, crtc_state);
 
-	intel_dp_set_signal_levels(intel_dp, crtc_state);
+	intel_dp_set_signal_levels(intel_dp, crtc_state, DP_PHY_DPRX);
 
 	intel_dp_phy_pattern_update(intel_dp, crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index b871a09b6901..6620f9efdcbb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -51,7 +51,8 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 int intel_dp_retrain_link(struct intel_encoder *encoder,
 			  struct drm_modeset_acquire_ctx *ctx);
 void intel_dp_set_power(struct intel_dp *intel_dp, u8 mode);
-void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp);
+void intel_dp_configure_protocol_converter(struct intel_dp *intel_dp,
+					   const struct intel_crtc_state *crtc_state);
 void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp,
 					   const struct intel_crtc_state *crtc_state,
 					   bool enable);
@@ -95,9 +96,6 @@ void
 intel_dp_program_link_training_pattern(struct intel_dp *intel_dp,
 				       const struct intel_crtc_state *crtc_state,
 				       u8 dp_train_pat);
-void
-intel_dp_set_signal_levels(struct intel_dp *intel_dp,
-			   const struct intel_crtc_state *crtc_state);
 void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 			   u8 *link_bw, u8 *rate_select);
 bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 91d3979902d0..d8c6d7054d11 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -334,6 +334,27 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 	return drm_dp_dpcd_write(&intel_dp->aux, reg, buf, len) == len;
 }
 
+void intel_dp_set_signal_levels(struct intel_dp *intel_dp,
+				const struct intel_crtc_state *crtc_state,
+				enum drm_dp_phy dp_phy)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	u8 train_set = intel_dp->train_set[0];
+	char phy_name[10];
+
+	drm_dbg_kms(&dev_priv->drm, "Using vswing level %d%s, pre-emphasis level %d%s, at %s\n",
+		    train_set & DP_TRAIN_VOLTAGE_SWING_MASK,
+		    train_set & DP_TRAIN_MAX_SWING_REACHED ? " (max)" : "",
+		    (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) >>
+		    DP_TRAIN_PRE_EMPHASIS_SHIFT,
+		    train_set & DP_TRAIN_MAX_PRE_EMPHASIS_REACHED ?
+		    " (max)" : "",
+		    intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)));
+
+	if (intel_dp_phy_is_downstream_of_source(intel_dp, dp_phy))
+		intel_dp->set_signal_levels(intel_dp, crtc_state);
+}
+
 static bool
 intel_dp_reset_link_train(struct intel_dp *intel_dp,
 			  const struct intel_crtc_state *crtc_state,
@@ -341,7 +362,7 @@ intel_dp_reset_link_train(struct intel_dp *intel_dp,
 			  u8 dp_train_pat)
 {
 	memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set));
-	intel_dp_set_signal_levels(intel_dp, crtc_state);
+	intel_dp_set_signal_levels(intel_dp, crtc_state, dp_phy);
 	return intel_dp_set_link_train(intel_dp, crtc_state, dp_phy, dp_train_pat);
 }
 
@@ -355,7 +376,7 @@ intel_dp_update_link_train(struct intel_dp *intel_dp,
 			    DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy);
 	int ret;
 
-	intel_dp_set_signal_levels(intel_dp, crtc_state);
+	intel_dp_set_signal_levels(intel_dp, crtc_state, dp_phy);
 
 	ret = drm_dp_dpcd_write(&intel_dp->aux, reg,
 				intel_dp->train_set, crtc_state->lane_count);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
index 86905aa24db7..6a1f76bd8c75 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
@@ -17,6 +17,9 @@ void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state,
 			       enum drm_dp_phy dp_phy,
 			       const u8 link_status[DP_LINK_STATUS_SIZE]);
+void intel_dp_set_signal_levels(struct intel_dp *intel_dp,
+				const struct intel_crtc_state *crtc_state,
+				enum drm_dp_phy dp_phy);
 void intel_dp_start_link_train(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state);
 void intel_dp_stop_link_train(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 27f04aed8764..3286b232be0b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -69,7 +69,9 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 
 		slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
 						      connector->port,
-						      crtc_state->pbn, 0);
+						      crtc_state->pbn,
+						      drm_dp_get_vc_payload_bw(crtc_state->port_clock,
+									       crtc_state->lane_count));
 		if (slots == -EDEADLK)
 			return slots;
 		if (slots >= 0)
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index b2a4bbcfdcd2..b9d8825e2bb1 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -2210,6 +2210,7 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state,
 	if (content_protection_type_changed) {
 		mutex_lock(&hdcp->mutex);
 		hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		drm_connector_get(&connector->base);
 		schedule_work(&hdcp->prop_work);
 		mutex_unlock(&hdcp->mutex);
 	}
@@ -2221,6 +2222,14 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state,
 		desired_and_not_enabled =
 			hdcp->value != DRM_MODE_CONTENT_PROTECTION_ENABLED;
 		mutex_unlock(&hdcp->mutex);
+		/*
+		 * If HDCP already ENABLED and CP property is DESIRED, schedule
+		 * prop_work to update correct CP property to user space.
+		 */
+		if (!desired_and_not_enabled && !content_protection_type_changed) {
+			drm_connector_get(&connector->base);
+			schedule_work(&hdcp->prop_work);
+		}
 	}
 
 	if (desired_and_not_enabled || content_protection_type_changed)
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 52b4f6193b4c..0095c8cac9b4 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -359,7 +359,7 @@ static void intel_overlay_release_old_vma(struct intel_overlay *overlay)
 	intel_frontbuffer_flip_complete(overlay->i915,
 					INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
 
-	i915_gem_object_unpin_from_display_plane(vma);
+	i915_vma_unpin(vma);
 	i915_vma_put(vma);
 }
 
@@ -860,7 +860,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	return 0;
 
 out_unpin:
-	i915_gem_object_unpin_from_display_plane(vma);
+	i915_vma_unpin(vma);
 out_pin_section:
 	atomic_dec(&dev_priv->gpu_error.pending_fb_pin);
 
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index 9f23bac0d792..d64fce1a17cb 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -1650,16 +1650,13 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
 		val = pch_get_backlight(connector);
 	else
 		val = lpt_get_backlight(connector);
-	val = intel_panel_compute_brightness(connector, val);
-	panel->backlight.level = clamp(val, panel->backlight.min,
-				       panel->backlight.max);
 
 	if (cpu_mode) {
 		drm_dbg_kms(&dev_priv->drm,
 			    "CPU backlight register was enabled, switching to PCH override\n");
 
 		/* Write converted CPU PWM value to PCH override register */
-		lpt_set_backlight(connector->base.state, panel->backlight.level);
+		lpt_set_backlight(connector->base.state, val);
 		intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
 			       pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
 
@@ -1667,6 +1664,10 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
 			       cpu_ctl2 & ~BLM_PWM_ENABLE);
 	}
 
+	val = intel_panel_compute_brightness(connector, val);
+	panel->backlight.level = clamp(val, panel->backlight.min,
+				       panel->backlight.max);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 019a2d6d807a..3da2544fa1c0 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -618,13 +618,19 @@ skl_program_scaler(struct intel_plane *plane,
 
 /* Preoffset values for YUV to RGB Conversion */
 #define PREOFF_YUV_TO_RGB_HI		0x1800
-#define PREOFF_YUV_TO_RGB_ME		0x1F00
+#define PREOFF_YUV_TO_RGB_ME		0x0000
 #define PREOFF_YUV_TO_RGB_LO		0x1800
 
 #define  ROFF(x)          (((x) & 0xffff) << 16)
 #define  GOFF(x)          (((x) & 0xffff) << 0)
 #define  BOFF(x)          (((x) & 0xffff) << 16)
 
+/*
+ * Programs the input color space conversion stage for ICL HDR planes.
+ * Note that it is assumed that this stage always happens after YUV
+ * range correction. Thus, the input to this stage is assumed to be
+ * in full-range YCbCr.
+ */
 static void
 icl_program_input_csc(struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
@@ -672,52 +678,7 @@ icl_program_input_csc(struct intel_plane *plane,
 			0x0, 0x7800, 0x7F10,
 		},
 	};
-
-	/* Matrix for Limited Range to Full Range Conversion */
-	static const u16 input_csc_matrix_lr[][9] = {
-		/*
-		 * BT.601 Limted range YCbCr -> full range RGB
-		 * The matrix required is :
-		 * [1.164384, 0.000, 1.596027,
-		 *  1.164384, -0.39175, -0.812813,
-		 *  1.164384, 2.017232, 0.0000]
-		 */
-		[DRM_COLOR_YCBCR_BT601] = {
-			0x7CC8, 0x7950, 0x0,
-			0x8D00, 0x7950, 0x9C88,
-			0x0, 0x7950, 0x6810,
-		},
-		/*
-		 * BT.709 Limited range YCbCr -> full range RGB
-		 * The matrix required is :
-		 * [1.164384, 0.000, 1.792741,
-		 *  1.164384, -0.213249, -0.532909,
-		 *  1.164384, 2.112402, 0.0000]
-		 */
-		[DRM_COLOR_YCBCR_BT709] = {
-			0x7E58, 0x7950, 0x0,
-			0x8888, 0x7950, 0xADA8,
-			0x0, 0x7950,  0x6870,
-		},
-		/*
-		 * BT.2020 Limited range YCbCr -> full range RGB
-		 * The matrix required is :
-		 * [1.164, 0.000, 1.678,
-		 *  1.164, -0.1873, -0.6504,
-		 *  1.164, 2.1417, 0.0000]
-		 */
-		[DRM_COLOR_YCBCR_BT2020] = {
-			0x7D70, 0x7950, 0x0,
-			0x8A68, 0x7950, 0xAC00,
-			0x0, 0x7950, 0x6890,
-		},
-	};
-	const u16 *csc;
-
-	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
-		csc = input_csc_matrix[plane_state->hw.color_encoding];
-	else
-		csc = input_csc_matrix_lr[plane_state->hw.color_encoding];
+	const u16 *csc = input_csc_matrix[plane_state->hw.color_encoding];
 
 	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0),
 			  ROFF(csc[0]) | GOFF(csc[1]));
@@ -734,14 +695,8 @@ icl_program_input_csc(struct intel_plane *plane,
 
 	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0),
 			  PREOFF_YUV_TO_RGB_HI);
-	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
-		intel_de_write_fw(dev_priv,
-				  PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
-				  0);
-	else
-		intel_de_write_fw(dev_priv,
-				  PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
-				  PREOFF_YUV_TO_RGB_ME);
+	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
+			  PREOFF_YUV_TO_RGB_ME);
 	intel_de_write_fw(dev_priv, PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 2),
 			  PREOFF_YUV_TO_RGB_LO);
 	intel_de_write_fw(dev_priv,
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index d52f9c177908..f94025ec603a 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -812,10 +812,20 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 		intel_dsi_prepare(encoder, pipe_config);
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
 
-	/* Deassert reset */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	/*
+	 * Give the panel time to power-on and then deassert its reset.
+	 * Depending on the VBT MIPI sequences version the deassert-seq
+	 * may contain the necessary delay, intel_dsi_msleep() will skip
+	 * the delay in that case. If there is no deassert-seq, then an
+	 * unconditional msleep is used to give the panel time to power-on.
+	 */
+	if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
+		intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+	} else {
+		msleep(intel_dsi->panel_on_delay);
+	}
 
 	if (IS_GEMINILAKE(dev_priv)) {
 		glk_cold_boot = glk_dsi_enable_io(encoder);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index fcce6909f201..3d435bfff764 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -387,48 +387,6 @@ err:
 	return vma;
 }
 
-static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
-{
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_vma *vma;
-
-	if (list_empty(&obj->vma.list))
-		return;
-
-	mutex_lock(&i915->ggtt.vm.mutex);
-	spin_lock(&obj->vma.lock);
-	for_each_ggtt_vma(vma, obj) {
-		if (!drm_mm_node_allocated(&vma->node))
-			continue;
-
-		GEM_BUG_ON(vma->vm != &i915->ggtt.vm);
-		list_move_tail(&vma->vm_link, &vma->vm->bound_list);
-	}
-	spin_unlock(&obj->vma.lock);
-	mutex_unlock(&i915->ggtt.vm.mutex);
-
-	if (i915_gem_object_is_shrinkable(obj)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&i915->mm.obj_lock, flags);
-
-		if (obj->mm.madv == I915_MADV_WILLNEED &&
-		    !atomic_read(&obj->mm.shrink_pin))
-			list_move_tail(&obj->mm.link, &i915->mm.shrink_list);
-
-		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
-	}
-}
-
-void
-i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
-{
-	/* Bump the LRU to try and avoid premature eviction whilst flipping  */
-	i915_gem_object_bump_inactive_ggtt(vma->obj);
-
-	i915_vma_unpin(vma);
-}
-
 /**
  * Moves a single object to the CPU read, and possibly write domain.
  * @obj: object to act on
@@ -569,9 +527,6 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	else
 		err = i915_gem_object_set_to_cpu_domain(obj, write_domain);
 
-	/* And bump the LRU for this access */
-	i915_gem_object_bump_inactive_ggtt(obj);
-
 	i915_gem_object_unlock(obj);
 
 	if (write_domain)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index be14486f63a7..4556afe18f16 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -486,7 +486,6 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
 				     const struct i915_ggtt_view *view,
 				     unsigned int flags);
-void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma);
 
 void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj);
 void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj);
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
index d93d85cd3027..e961ad6a3129 100644
--- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -7,8 +7,6 @@
 #include "i915_drv.h"
 #include "intel_gpu_commands.h"
 
-#define MAX_URB_ENTRIES 64
-#define STATE_SIZE (4 * 1024)
 #define GT3_INLINE_DATA_DELAYS 0x1E00
 #define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))
 
@@ -34,38 +32,59 @@ struct batch_chunk {
 };
 
 struct batch_vals {
-	u32 max_primitives;
-	u32 max_urb_entries;
-	u32 cmd_size;
-	u32 state_size;
+	u32 max_threads;
 	u32 state_start;
-	u32 batch_size;
+	u32 surface_start;
 	u32 surface_height;
 	u32 surface_width;
-	u32 scratch_size;
-	u32 max_size;
+	u32 size;
 };
 
+static inline int num_primitives(const struct batch_vals *bv)
+{
+	/*
+	 * We need to saturate the GPU with work in order to dispatch
+	 * a shader on every HW thread, and clear the thread-local registers.
+	 * In short, we have to dispatch work faster than the shaders can
+	 * run in order to fill the EU and occupy each HW thread.
+	 */
+	return bv->max_threads;
+}
+
 static void
 batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
 {
 	if (IS_HASWELL(i915)) {
-		bv->max_primitives = 280;
-		bv->max_urb_entries = MAX_URB_ENTRIES;
+		switch (INTEL_INFO(i915)->gt) {
+		default:
+		case 1:
+			bv->max_threads = 70;
+			break;
+		case 2:
+			bv->max_threads = 140;
+			break;
+		case 3:
+			bv->max_threads = 280;
+			break;
+		}
 		bv->surface_height = 16 * 16;
 		bv->surface_width = 32 * 2 * 16;
 	} else {
-		bv->max_primitives = 128;
-		bv->max_urb_entries = MAX_URB_ENTRIES / 2;
+		switch (INTEL_INFO(i915)->gt) {
+		default:
+		case 1: /* including vlv */
+			bv->max_threads = 36;
+			break;
+		case 2:
+			bv->max_threads = 128;
+			break;
+		}
 		bv->surface_height = 16 * 8;
 		bv->surface_width = 32 * 16;
 	}
-	bv->cmd_size = bv->max_primitives * 4096;
-	bv->state_size = STATE_SIZE;
-	bv->state_start = bv->cmd_size;
-	bv->batch_size = bv->cmd_size + bv->state_size;
-	bv->scratch_size = bv->surface_height * bv->surface_width;
-	bv->max_size = bv->batch_size + bv->scratch_size;
+	bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K);
+	bv->surface_start = bv->state_start + SZ_4K;
+	bv->size = bv->surface_start + bv->surface_height * bv->surface_width;
 }
 
 static void batch_init(struct batch_chunk *bc,
@@ -155,7 +174,8 @@ static u32
 gen7_fill_binding_table(struct batch_chunk *state,
 			const struct batch_vals *bv)
 {
-	u32 surface_start = gen7_fill_surface_state(state, bv->batch_size, bv);
+	u32 surface_start =
+		gen7_fill_surface_state(state, bv->surface_start, bv);
 	u32 *cs = batch_alloc_items(state, 32, 8);
 	u32 offset = batch_offset(state, cs);
 
@@ -214,9 +234,9 @@ static void
 gen7_emit_state_base_address(struct batch_chunk *batch,
 			     u32 surface_state_base)
 {
-	u32 *cs = batch_alloc_items(batch, 0, 12);
+	u32 *cs = batch_alloc_items(batch, 0, 10);
 
-	*cs++ = STATE_BASE_ADDRESS | (12 - 2);
+	*cs++ = STATE_BASE_ADDRESS | (10 - 2);
 	/* general */
 	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
 	/* surface */
@@ -233,8 +253,6 @@ gen7_emit_state_base_address(struct batch_chunk *batch,
 	*cs++ = BASE_ADDRESS_MODIFY;
 	*cs++ = 0;
 	*cs++ = BASE_ADDRESS_MODIFY;
-	*cs++ = 0;
-	*cs++ = 0;
 	batch_advance(batch, cs);
 }
 
@@ -244,8 +262,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
 		    u32 urb_size, u32 curbe_size,
 		    u32 mode)
 {
-	u32 urb_entries = bv->max_urb_entries;
-	u32 threads = bv->max_primitives - 1;
+	u32 threads = bv->max_threads - 1;
 	u32 *cs = batch_alloc_items(batch, 32, 8);
 
 	*cs++ = MEDIA_VFE_STATE | (8 - 2);
@@ -254,7 +271,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
 	*cs++ = 0;
 
 	/* number of threads & urb entries for GPGPU vs Media Mode */
-	*cs++ = threads << 16 | urb_entries << 8 | mode << 2;
+	*cs++ = threads << 16 | 1 << 8 | mode << 2;
 
 	*cs++ = 0;
 
@@ -293,17 +310,12 @@ gen7_emit_media_object(struct batch_chunk *batch,
 {
 	unsigned int x_offset = (media_object_index % 16) * 64;
 	unsigned int y_offset = (media_object_index / 16) * 16;
-	unsigned int inline_data_size;
-	unsigned int media_batch_size;
-	unsigned int i;
+	unsigned int pkt = 6 + 3;
 	u32 *cs;
 
-	inline_data_size = 112 * 8;
-	media_batch_size = inline_data_size + 6;
-
-	cs = batch_alloc_items(batch, 8, media_batch_size);
+	cs = batch_alloc_items(batch, 8, pkt);
 
-	*cs++ = MEDIA_OBJECT | (media_batch_size - 2);
+	*cs++ = MEDIA_OBJECT | (pkt - 2);
 
 	/* interface descriptor offset */
 	*cs++ = 0;
@@ -317,25 +329,44 @@ gen7_emit_media_object(struct batch_chunk *batch,
 	*cs++ = 0;
 
 	/* inline */
-	*cs++ = (y_offset << 16) | (x_offset);
+	*cs++ = y_offset << 16 | x_offset;
 	*cs++ = 0;
 	*cs++ = GT3_INLINE_DATA_DELAYS;
-	for (i = 3; i < inline_data_size; i++)
-		*cs++ = 0;
 
 	batch_advance(batch, cs);
 }
 
 static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
 {
-	u32 *cs = batch_alloc_items(batch, 0, 5);
+	u32 *cs = batch_alloc_items(batch, 0, 4);
 
-	*cs++ = GFX_OP_PIPE_CONTROL(5);
-	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE |
-		PIPE_CONTROL_GLOBAL_GTT_IVB;
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+		PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+		PIPE_CONTROL_DC_FLUSH_ENABLE |
+		PIPE_CONTROL_CS_STALL;
 	*cs++ = 0;
 	*cs++ = 0;
+
+	batch_advance(batch, cs);
+}
+
+static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch)
+{
+	u32 *cs = batch_alloc_items(batch, 0, 8);
+
+	/* ivb: Stall before STATE_CACHE_INVALIDATE */
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD |
+		PIPE_CONTROL_CS_STALL;
+	*cs++ = 0;
+	*cs++ = 0;
+
+	*cs++ = GFX_OP_PIPE_CONTROL(4);
+	*cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 	*cs++ = 0;
+	*cs++ = 0;
+
 	batch_advance(batch, cs);
 }
 
@@ -344,34 +375,46 @@ static void emit_batch(struct i915_vma * const vma,
 		       const struct batch_vals *bv)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	unsigned int desc_count = 64;
-	const u32 urb_size = 112;
+	const unsigned int desc_count = 1;
+	const unsigned int urb_size = 1;
 	struct batch_chunk cmds, state;
-	u32 interface_descriptor;
+	u32 descriptors;
 	unsigned int i;
 
-	batch_init(&cmds, vma, start, 0, bv->cmd_size);
-	batch_init(&state, vma, start, bv->state_start, bv->state_size);
-
-	interface_descriptor =
-		gen7_fill_interface_descriptor(&state, bv,
-					       IS_HASWELL(i915) ?
-					       &cb_kernel_hsw :
-					       &cb_kernel_ivb,
-					       desc_count);
+	batch_init(&cmds, vma, start, 0, bv->state_start);
+	batch_init(&state, vma, start, bv->state_start, SZ_4K);
+
+	descriptors = gen7_fill_interface_descriptor(&state, bv,
+						     IS_HASWELL(i915) ?
+						     &cb_kernel_hsw :
+						     &cb_kernel_ivb,
+						     desc_count);
+
+	/* Reset inherited context registers */
+	gen7_emit_pipeline_invalidate(&cmds);
+	batch_add(&cmds, MI_LOAD_REGISTER_IMM(2));
+	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_0_GEN7));
+	batch_add(&cmds, 0xffff0000);
+	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_1));
+	batch_add(&cmds, 0xffff0000 | PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
 	gen7_emit_pipeline_flush(&cmds);
+
+	/* Switch to the media pipeline and our base address */
+	gen7_emit_pipeline_invalidate(&cmds);
 	batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
 	batch_add(&cmds, MI_NOOP);
-	gen7_emit_state_base_address(&cmds, interface_descriptor);
+	gen7_emit_pipeline_invalidate(&cmds);
+
 	gen7_emit_pipeline_flush(&cmds);
+	gen7_emit_state_base_address(&cmds, descriptors);
+	gen7_emit_pipeline_invalidate(&cmds);
 
+	/* Set the clear-residual kernel state */
 	gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
+	gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);
 
-	gen7_emit_interface_descriptor_load(&cmds,
-					    interface_descriptor,
-					    desc_count);
-
-	for (i = 0; i < bv->max_primitives; i++)
+	/* Execute the kernel on all HW threads */
+	for (i = 0; i < num_primitives(bv); i++)
 		gen7_emit_media_object(&cmds, i);
 
 	batch_add(&cmds, MI_BATCH_BUFFER_END);
@@ -385,15 +428,15 @@ int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
 
 	batch_get_defaults(engine->i915, &bv);
 	if (!vma)
-		return bv.max_size;
+		return bv.size;
 
-	GEM_BUG_ON(vma->obj->base.size < bv.max_size);
+	GEM_BUG_ON(vma->obj->base.size < bv.size);
 
 	batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
-	emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
+	emit_batch(vma, memset(batch, 0, bv.size), &bv);
 
 	i915_gem_object_flush_map(vma->obj);
 	__i915_gem_object_release_map(vma->obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index a24cc1ff08a0..1d1757584f49 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -134,11 +134,6 @@ static bool remove_signaling_context(struct intel_breadcrumbs *b,
 	return true;
 }
 
-static inline bool __request_completed(const struct i915_request *rq)
-{
-	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno);
-}
-
 __maybe_unused static bool
 check_signal_order(struct intel_context *ce, struct i915_request *rq)
 {
@@ -192,18 +187,6 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 		intel_engine_add_retire(b->irq_engine, tl);
 }
 
-static bool __signal_request(struct i915_request *rq)
-{
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
-
-	if (!__dma_fence_signal(&rq->fence)) {
-		i915_request_put(rq);
-		return false;
-	}
-
-	return true;
-}
-
 static struct llist_node *
 slist_add(struct llist_node *node, struct llist_node *head)
 {
@@ -257,7 +240,7 @@ static void signal_irq_work(struct irq_work *work)
 		list_for_each_entry_rcu(rq, &ce->signals, signal_link) {
 			bool release;
 
-			if (!__request_completed(rq))
+			if (!__i915_request_is_complete(rq))
 				break;
 
 			if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL,
@@ -274,9 +257,11 @@ static void signal_irq_work(struct irq_work *work)
 			release = remove_signaling_context(b, ce);
 			spin_unlock(&ce->signal_lock);
 
-			if (__signal_request(rq))
+			if (__dma_fence_signal(&rq->fence))
 				/* We own signal_node now, xfer to local list */
 				signal = slist_add(&rq->signal_node, signal);
+			else
+				i915_request_put(rq);
 
 			if (release) {
 				add_retire(b, ce->timeline);
@@ -363,6 +348,17 @@ void intel_breadcrumbs_free(struct intel_breadcrumbs *b)
 	kfree(b);
 }
 
+static void irq_signal_request(struct i915_request *rq,
+			       struct intel_breadcrumbs *b)
+{
+	if (!__dma_fence_signal(&rq->fence))
+		return;
+
+	i915_request_get(rq);
+	if (llist_add(&rq->signal_node, &b->signaled_requests))
+		irq_work_queue(&b->irq_work);
+}
+
 static void insert_breadcrumb(struct i915_request *rq)
 {
 	struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
@@ -372,17 +368,13 @@ static void insert_breadcrumb(struct i915_request *rq)
 	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
 		return;
 
-	i915_request_get(rq);
-
 	/*
 	 * If the request is already completed, we can transfer it
 	 * straight onto a signaled list, and queue the irq worker for
 	 * its signal completion.
 	 */
-	if (__request_completed(rq)) {
-		if (__signal_request(rq) &&
-		    llist_add(&rq->signal_node, &b->signaled_requests))
-			irq_work_queue(&b->irq_work);
+	if (__i915_request_is_complete(rq)) {
+		irq_signal_request(rq, b);
 		return;
 	}
 
@@ -413,6 +405,8 @@ static void insert_breadcrumb(struct i915_request *rq)
 				break;
 		}
 	}
+
+	i915_request_get(rq);
 	list_add_rcu(&rq->signal_link, pos);
 	GEM_BUG_ON(!check_signal_order(ce, rq));
 	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags));
@@ -453,19 +447,25 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 
 void i915_request_cancel_breadcrumb(struct i915_request *rq)
 {
+	struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs;
 	struct intel_context *ce = rq->context;
 	bool release;
 
-	if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
+	spin_lock(&ce->signal_lock);
+	if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
+		spin_unlock(&ce->signal_lock);
 		return;
+	}
 
-	spin_lock(&ce->signal_lock);
 	list_del_rcu(&rq->signal_link);
-	release = remove_signaling_context(rq->engine->breadcrumbs, ce);
+	release = remove_signaling_context(b, ce);
 	spin_unlock(&ce->signal_lock);
 	if (release)
 		intel_context_put(ce);
 
+	if (__i915_request_is_complete(rq))
+		irq_signal_request(rq, b);
+
 	i915_request_put(rq);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index cf94525be2c1..db8c66dde655 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -526,16 +526,39 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 
 	mutex_init(&ggtt->error_mutex);
 	if (ggtt->mappable_end) {
-		/* Reserve a mappable slot for our lockless error capture */
-		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm,
-						  &ggtt->error_capture,
-						  PAGE_SIZE, 0,
-						  I915_COLOR_UNEVICTABLE,
-						  0, ggtt->mappable_end,
-						  DRM_MM_INSERT_LOW);
-		if (ret)
-			return ret;
+		/*
+		 * Reserve a mappable slot for our lockless error capture.
+		 *
+		 * We strongly prefer taking address 0x0 in order to protect
+		 * other critical buffers against accidental overwrites,
+		 * as writing to address 0 is a very common mistake.
+		 *
+		 * Since 0 may already be in use by the system (e.g. the BIOS
+		 * framebuffer), we let the reservation fail quietly and hope
+		 * 0 remains reserved always.
+		 *
+		 * If we fail to reserve 0, and then fail to find any space
+		 * for an error-capture, remain silent. We can afford not
+		 * to reserve an error_capture node as we have fallback
+		 * paths, and we trust that 0 will remain reserved. However,
+		 * the only likely reason for failure to insert is a driver
+		 * bug, which we expect to cause other failures...
+		 */
+		ggtt->error_capture.size = I915_GTT_PAGE_SIZE;
+		ggtt->error_capture.color = I915_COLOR_UNEVICTABLE;
+		if (drm_mm_reserve_node(&ggtt->vm.mm, &ggtt->error_capture))
+			drm_mm_insert_node_in_range(&ggtt->vm.mm,
+						    &ggtt->error_capture,
+						    ggtt->error_capture.size, 0,
+						    ggtt->error_capture.color,
+						    0, ggtt->mappable_end,
+						    DRM_MM_INSERT_LOW);
 	}
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_dbg(&ggtt->vm.i915->drm,
+			"Reserved GGTT:[%llx, %llx] for use by error capture\n",
+			ggtt->error_capture.start,
+			ggtt->error_capture.start + ggtt->error_capture.size);
 
 	/*
 	 * The upper portion of the GuC address space has a sizeable hole
@@ -548,9 +571,9 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 
 	/* Clear any non-preallocated blocks */
 	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
-		drm_dbg_kms(&ggtt->vm.i915->drm,
-			    "clearing unused GTT space: [%lx, %lx]\n",
-			    hole_start, hole_end);
+		drm_dbg(&ggtt->vm.i915->drm,
+			"clearing unused GTT space: [%lx, %lx]\n",
+			hole_start, hole_end);
 		ggtt->vm.clear_range(&ggtt->vm, hole_start,
 				     hole_end - hole_start);
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7614a3d24fca..26c7d0a50585 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3988,6 +3988,9 @@ err:
 static void lrc_destroy_wa_ctx(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0);
+
+	/* Called on error unwind, clear all flags to prevent further use */
+	memset(&engine->wa_ctx, 0, sizeof(engine->wa_ctx));
 }
 
 typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a41b43f445b8..ecf3a6118a6d 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -32,6 +32,7 @@
 #include "gen6_ppgtt.h"
 #include "gen7_renderclear.h"
 #include "i915_drv.h"
+#include "i915_mitigations.h"
 #include "intel_breadcrumbs.h"
 #include "intel_context.h"
 #include "intel_gt.h"
@@ -886,7 +887,8 @@ static int switch_context(struct i915_request *rq)
 	GEM_BUG_ON(HAS_EXECLISTS(engine->i915));
 
 	if (engine->wa_ctx.vma && ce != engine->kernel_context) {
-		if (engine->wa_ctx.vma->private != ce) {
+		if (engine->wa_ctx.vma->private != ce &&
+		    i915_mitigate_clear_residuals()) {
 			ret = clear_residuals(rq);
 			if (ret)
 				return ret;
@@ -1290,7 +1292,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
 
-	if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) {
+	if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) {
 		err = gen7_ctx_switch_bb_init(engine);
 		if (err)
 			goto err_ring_unpin;
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 7ea94d201fe6..8015964043eb 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -126,6 +126,10 @@ static void __rcu_cacheline_free(struct rcu_head *rcu)
 	struct intel_timeline_cacheline *cl =
 		container_of(rcu, typeof(*cl), rcu);
 
+	/* Must wait until after all *rq->hwsp are complete before removing */
+	i915_gem_object_unpin_map(cl->hwsp->vma->obj);
+	__idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS));
+
 	i915_active_fini(&cl->active);
 	kfree(cl);
 }
@@ -133,11 +137,6 @@ static void __rcu_cacheline_free(struct rcu_head *rcu)
 static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 {
 	GEM_BUG_ON(!i915_active_is_idle(&cl->active));
-
-	i915_gem_object_unpin_map(cl->hwsp->vma->obj);
-	i915_vma_put(cl->hwsp->vma);
-	__idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS));
-
 	call_rcu(&cl->rcu, __rcu_cacheline_free);
 }
 
@@ -179,7 +178,6 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline)
 		return ERR_CAST(vaddr);
 	}
 
-	i915_vma_get(hwsp->vma);
 	cl->hwsp = hwsp;
 	cl->vaddr = page_pack_bits(vaddr, cacheline);
 
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a15f87539657..62a5b0dd2003 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -217,6 +217,15 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				  DDI_BUF_CTL_ENABLE);
 			vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE;
 		}
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK);
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+			~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK);
+		/* No hpd_invert set in vgpu vbt, need to clear invert mask */
+		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK;
+		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK;
 
 		vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1));
 		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
@@ -273,6 +282,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |=
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
 		}
@@ -301,6 +312,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 		}
@@ -329,6 +342,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
 				 (PORT_B << TRANS_DDI_PORT_SHIFT) |
 				 TRANS_DDI_FUNC_ENABLE);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_ENABLE;
 			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 				GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
 		}
@@ -661,44 +676,62 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
 				PORTD_HOTPLUG_STATUS_MASK;
 		intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG);
 	} else if (IS_BROXTON(i915)) {
-		if (connected) {
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			if (connected) {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 					GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+			} else {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
 			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
-				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
-					SFUSE_STRAP_DDIB_DETECTED;
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTA_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTA_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			if (connected) {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
 					GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
-			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
 				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
-					SFUSE_STRAP_DDIC_DETECTED;
-				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
-					GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
-			}
-		} else {
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+					SFUSE_STRAP_DDIB_DETECTED;
+			} else {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
-					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
-			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
 					~SFUSE_STRAP_DDIB_DETECTED;
-				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
-					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
 			}
-			if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
-				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
-					~SFUSE_STRAP_DDIC_DETECTED;
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTB_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTB_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
+		}
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			if (connected) {
+				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+					GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+					SFUSE_STRAP_DDIC_DETECTED;
+			} else {
 				vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
 					~GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+				vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+					~SFUSE_STRAP_DDIC_DETECTED;
 			}
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+				GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+				~PORTC_HOTPLUG_STATUS_MASK;
+			vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+				PORTC_HOTPLUG_LONG_DETECT;
+			intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG);
 		}
-		vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
-			PORTB_HOTPLUG_STATUS_MASK;
-		intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index e49944fde333..cbe5931906e0 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -437,10 +437,9 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_sched_policy;
 
-	if (IS_BROADWELL(dev_priv))
+	if (IS_BROADWELL(dev_priv) || IS_BROXTON(dev_priv))
 		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
-	/* FixMe: Re-enable APL/BXT once vfio_edid enabled */
-	else if (!IS_BROXTON(dev_priv))
+	else
 		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
 	if (ret)
 		goto out_clean_sched_policy;
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 10a865f3dc09..9ed19b8bca60 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -631,24 +631,26 @@ static int flush_lazy_signals(struct i915_active *ref)
 
 int __i915_active_wait(struct i915_active *ref, int state)
 {
-	int err;
-
 	might_sleep();
 
-	if (!i915_active_acquire_if_busy(ref))
-		return 0;
-
 	/* Any fence added after the wait begins will not be auto-signaled */
-	err = flush_lazy_signals(ref);
-	i915_active_release(ref);
-	if (err)
-		return err;
+	if (i915_active_acquire_if_busy(ref)) {
+		int err;
 
-	if (!i915_active_is_idle(ref) &&
-	    ___wait_var_event(ref, i915_active_is_idle(ref),
-			      state, 0, 0, schedule()))
-		return -EINTR;
+		err = flush_lazy_signals(ref);
+		i915_active_release(ref);
+		if (err)
+			return err;
 
+		if (___wait_var_event(ref, i915_active_is_idle(ref),
+				      state, 0, 0, schedule()))
+			return -EINTR;
+	}
+
+	/*
+	 * After the wait is complete, the caller may free the active.
+	 * We have to flush any concurrent retirement before returning.
+	 */
 	flush_work(&ref->work);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 88ad754962af..99eb0d7bbc44 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1047,6 +1047,8 @@ static void intel_shutdown_encoders(struct drm_i915_private *dev_priv)
 
 void i915_driver_shutdown(struct drm_i915_private *i915)
 {
+	disable_rpm_wakeref_asserts(&i915->runtime_pm);
+
 	i915_gem_suspend(i915);
 
 	drm_kms_helper_poll_disable(&i915->drm);
@@ -1060,6 +1062,8 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
 
 	intel_suspend_encoders(i915);
 	intel_shutdown_encoders(i915);
+
+	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 }
 
 static bool suspend_to_idle(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 632c713227dc..c6964f82a1bb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1346,7 +1346,7 @@ intel_subplatform(const struct intel_runtime_info *info, enum intel_platform p)
 {
 	const unsigned int pi = __platform_mask_index(info, p);
 
-	return info->platform_mask[pi] & INTEL_SUBPLATFORM_BITS;
+	return info->platform_mask[pi] & ((1 << INTEL_SUBPLATFORM_BITS) - 1);
 }
 
 static __always_inline bool
diff --git a/drivers/gpu/drm/i915/i915_mitigations.c b/drivers/gpu/drm/i915/i915_mitigations.c
new file mode 100644
index 000000000000..84f12598d145
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "i915_drv.h"
+#include "i915_mitigations.h"
+
+static unsigned long mitigations __read_mostly = ~0UL;
+
+enum {
+	CLEAR_RESIDUALS = 0,
+};
+
+static const char * const names[] = {
+	[CLEAR_RESIDUALS] = "residuals",
+};
+
+bool i915_mitigate_clear_residuals(void)
+{
+	return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS);
+}
+
+static int mitigations_set(const char *val, const struct kernel_param *kp)
+{
+	unsigned long new = ~0UL;
+	char *str, *sep, *tok;
+	bool first = true;
+	int err = 0;
+
+	BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations));
+
+	str = kstrdup(val, GFP_KERNEL);
+	if (!str)
+		return -ENOMEM;
+
+	for (sep = str; (tok = strsep(&sep, ","));) {
+		bool enable = true;
+		int i;
+
+		/* Be tolerant of leading/trailing whitespace */
+		tok = strim(tok);
+
+		if (first) {
+			first = false;
+
+			if (!strcmp(tok, "auto"))
+				continue;
+
+			new = 0;
+			if (!strcmp(tok, "off"))
+				continue;
+		}
+
+		if (*tok == '!') {
+			enable = !enable;
+			tok++;
+		}
+
+		if (!strncmp(tok, "no", 2)) {
+			enable = !enable;
+			tok += 2;
+		}
+
+		if (*tok == '\0')
+			continue;
+
+		for (i = 0; i < ARRAY_SIZE(names); i++) {
+			if (!strcmp(tok, names[i])) {
+				if (enable)
+					new |= BIT(i);
+				else
+					new &= ~BIT(i);
+				break;
+			}
+		}
+		if (i == ARRAY_SIZE(names)) {
+			pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n",
+			       DRIVER_NAME, val, tok);
+			err = -EINVAL;
+			break;
+		}
+	}
+	kfree(str);
+	if (err)
+		return err;
+
+	WRITE_ONCE(mitigations, new);
+	return 0;
+}
+
+static int mitigations_get(char *buffer, const struct kernel_param *kp)
+{
+	unsigned long local = READ_ONCE(mitigations);
+	int count, i;
+	bool enable;
+
+	if (!local)
+		return scnprintf(buffer, PAGE_SIZE, "%s\n", "off");
+
+	if (local & BIT(BITS_PER_LONG - 1)) {
+		count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto");
+		enable = false;
+	} else {
+		enable = true;
+		count = 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(names); i++) {
+		if ((local & BIT(i)) != enable)
+			continue;
+
+		count += scnprintf(buffer + count, PAGE_SIZE - count,
+				   "%s%s,", enable ? "" : "!", names[i]);
+	}
+
+	buffer[count - 1] = '\n';
+	return count;
+}
+
+static const struct kernel_param_ops ops = {
+	.set = mitigations_set,
+	.get = mitigations_get,
+};
+
+module_param_cb_unsafe(mitigations, &ops, NULL, 0600);
+MODULE_PARM_DESC(mitigations,
+"Selectively enable security mitigations for all Intel® GPUs in the system.\n"
+"\n"
+"  auto -- enables all mitigations required for the platform [default]\n"
+"  off  -- disables all mitigations\n"
+"\n"
+"Individual mitigations can be enabled by passing a comma-separated string,\n"
+"e.g. mitigations=residuals to enable only clearing residuals or\n"
+"mitigations=auto,noresiduals to disable only the clear residual mitigation.\n"
+"Either '!' or 'no' may be used to switch from enabling the mitigation to\n"
+"disabling it.\n"
+"\n"
+"Active mitigations for Ivybridge, Baytrail, Haswell:\n"
+"  residuals -- clear all thread-local registers between contexts"
+);
diff --git a/drivers/gpu/drm/i915/i915_mitigations.h b/drivers/gpu/drm/i915/i915_mitigations.h
new file mode 100644
index 000000000000..1359d8135287
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_MITIGATIONS_H__
+#define __I915_MITIGATIONS_H__
+
+#include <linux/types.h>
+
+bool i915_mitigate_clear_residuals(void);
+
+#endif /* __I915_MITIGATIONS_H__ */
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d76685ce0399..9856479b56d8 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -184,13 +184,24 @@ static u64 get_rc6(struct intel_gt *gt)
 	return val;
 }
 
-static void park_rc6(struct drm_i915_private *i915)
+static void init_rc6(struct i915_pmu *pmu)
 {
-	struct i915_pmu *pmu = &i915->pmu;
+	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
+	intel_wakeref_t wakeref;
 
-	if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY))
+	with_intel_runtime_pm(i915->gt.uncore->rpm, wakeref) {
 		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
+		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur =
+					pmu->sample[__I915_SAMPLE_RC6].cur;
+		pmu->sleep_last = ktime_get();
+	}
+}
 
+static void park_rc6(struct drm_i915_private *i915)
+{
+	struct i915_pmu *pmu = &i915->pmu;
+
+	pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
 	pmu->sleep_last = ktime_get();
 }
 
@@ -201,6 +212,7 @@ static u64 get_rc6(struct intel_gt *gt)
 	return __get_rc6(gt);
 }
 
+static void init_rc6(struct i915_pmu *pmu) { }
 static void park_rc6(struct drm_i915_private *i915) {}
 
 #endif
@@ -612,10 +624,8 @@ static void i915_pmu_enable(struct perf_event *event)
 		container_of(event->pmu, typeof(*i915), pmu.base);
 	unsigned int bit = event_enabled_bit(event);
 	struct i915_pmu *pmu = &i915->pmu;
-	intel_wakeref_t wakeref;
 	unsigned long flags;
 
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	spin_lock_irqsave(&pmu->lock, flags);
 
 	/*
@@ -626,13 +636,6 @@ static void i915_pmu_enable(struct perf_event *event)
 	GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count));
 	GEM_BUG_ON(pmu->enable_count[bit] == ~0);
 
-	if (pmu->enable_count[bit] == 0 &&
-	    config_enabled_mask(I915_PMU_RC6_RESIDENCY) & BIT_ULL(bit)) {
-		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = 0;
-		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(&i915->gt);
-		pmu->sleep_last = ktime_get();
-	}
-
 	pmu->enable |= BIT_ULL(bit);
 	pmu->enable_count[bit]++;
 
@@ -673,8 +676,6 @@ static void i915_pmu_enable(struct perf_event *event)
 	 * an existing non-zero value.
 	 */
 	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event));
-
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
 static void i915_pmu_disable(struct perf_event *event)
@@ -1130,6 +1131,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
 	pmu->cpuhp.cpu = -1;
+	init_rc6(pmu);
 
 	if (!is_igp(i915)) {
 		pmu->name = kasprintf(GFP_KERNEL,
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 620b6fab2c5c..92adfee30c7c 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -434,7 +434,7 @@ static inline u32 hwsp_seqno(const struct i915_request *rq)
 
 static inline bool __i915_request_has_started(const struct i915_request *rq)
 {
-	return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno - 1);
+	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno - 1);
 }
 
 /**
@@ -465,11 +465,19 @@ static inline bool __i915_request_has_started(const struct i915_request *rq)
  */
 static inline bool i915_request_started(const struct i915_request *rq)
 {
+	bool result;
+
 	if (i915_request_signaled(rq))
 		return true;
 
-	/* Remember: started but may have since been preempted! */
-	return __i915_request_has_started(rq);
+	result = true;
+	rcu_read_lock(); /* the HWSP may be freed at runtime */
+	if (likely(!i915_request_signaled(rq)))
+		/* Remember: started but may have since been preempted! */
+		result = __i915_request_has_started(rq);
+	rcu_read_unlock();
+
+	return result;
 }
 
 /**
@@ -482,10 +490,16 @@ static inline bool i915_request_started(const struct i915_request *rq)
  */
 static inline bool i915_request_is_running(const struct i915_request *rq)
 {
+	bool result;
+
 	if (!i915_request_is_active(rq))
 		return false;
 
-	return __i915_request_has_started(rq);
+	rcu_read_lock();
+	result = __i915_request_has_started(rq) && i915_request_is_active(rq);
+	rcu_read_unlock();
+
+	return result;
 }
 
 /**
@@ -509,12 +523,25 @@ static inline bool i915_request_is_ready(const struct i915_request *rq)
 	return !list_empty(&rq->sched.link);
 }
 
+static inline bool __i915_request_is_complete(const struct i915_request *rq)
+{
+	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno);
+}
+
 static inline bool i915_request_completed(const struct i915_request *rq)
 {
+	bool result;
+
 	if (i915_request_signaled(rq))
 		return true;
 
-	return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno);
+	result = true;
+	rcu_read_lock(); /* the HWSP may be freed at runtime */
+	if (likely(!i915_request_signaled(rq)))
+		result = __i915_request_is_complete(rq);
+	rcu_read_unlock();
+
+	return result;
 }
 
 static inline void i915_request_mark_complete(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index c53a222e3dec..713770fb2b92 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1880,7 +1880,7 @@ static int igt_cs_tlb(void *arg)
 	vma = i915_vma_instance(out, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto out_put_batch;
+		goto out_put_out;
 	}
 
 	err = i915_vma_pin(vma, 0, 0,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/Kbuild b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
index 6fdddb266fb1..4488e1c061b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/Kbuild
+++ b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
@@ -37,6 +37,7 @@ nouveau-y += dispnv50/wimmc37b.o
 nouveau-y += dispnv50/wndw.o
 nouveau-y += dispnv50/wndwc37e.o
 nouveau-y += dispnv50/wndwc57e.o
+nouveau-y += dispnv50/wndwc67e.o
 
 nouveau-y += dispnv50/base.o
 nouveau-y += dispnv50/base507c.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base507c.c b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
index 302d4e6fc52f..788db043a342 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base507c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base507c.c
@@ -88,7 +88,11 @@ base507c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 			  NVVAL(NV507C, SET_CONVERSION, OFS, 0x64));
 	} else {
 		PUSH_MTHD(push, NV507C, SET_PROCESSING,
-			  NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE));
+			  NVDEF(NV507C, SET_PROCESSING, USE_GAIN_OFS, DISABLE),
+
+					SET_CONVERSION,
+			  NVVAL(NV507C, SET_CONVERSION, GAIN, 0) |
+			  NVVAL(NV507C, SET_CONVERSION, OFS, 0));
 	}
 
 	PUSH_MTHD(push, NV507C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base827c.c b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
index 18d34096f125..093d4ba6910e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base827c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base827c.c
@@ -49,7 +49,11 @@ base827c_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 			  NVVAL(NV827C, SET_CONVERSION, OFS, 0x64));
 	} else {
 		PUSH_MTHD(push, NV827C, SET_PROCESSING,
-			  NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE));
+			  NVDEF(NV827C, SET_PROCESSING, USE_GAIN_OFS, DISABLE),
+
+					SET_CONVERSION,
+			  NVVAL(NV827C, SET_CONVERSION, GAIN, 0) |
+			  NVVAL(NV827C, SET_CONVERSION, OFS, 0));
 	}
 
 	PUSH_MTHD(push, NV827C, SURFACE_SET_OFFSET(0, 0), asyw->image.offset[0] >> 8,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.c b/drivers/gpu/drm/nouveau/dispnv50/core.c
index 27ea3f34706d..abefc2343443 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.c
@@ -42,6 +42,7 @@ nv50_core_new(struct nouveau_drm *drm, struct nv50_core **pcore)
 		int version;
 		int (*new)(struct nouveau_drm *, s32, struct nv50_core **);
 	} cores[] = {
+		{ GA102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
 		{ TU102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
 		{ GV100_DISP_CORE_CHANNEL_DMA, 0, corec37d_new },
 		{ GP102_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs.c b/drivers/gpu/drm/nouveau/dispnv50/curs.c
index 121c24a18f11..31d8b2e4791d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/curs.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs.c
@@ -31,6 +31,7 @@ nv50_curs_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
 		int version;
 		int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
 	} curses[] = {
+		{ GA102_DISP_CURSOR, 0, cursc37a_new },
 		{ TU102_DISP_CURSOR, 0, cursc37a_new },
 		{ GV100_DISP_CURSOR, 0, cursc37a_new },
 		{ GK104_DISP_CURSOR, 0, curs907a_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 33fff388dd83..5f4f09a601d4 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -222,7 +222,7 @@ nv50_dmac_wait(struct nvif_push *push, u32 size)
 
 int
 nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
-		 const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+		 const s32 *oclass, u8 head, void *data, u32 size, s64 syncbuf,
 		 struct nv50_dmac *dmac)
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
@@ -271,7 +271,7 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 	if (ret)
 		return ret;
 
-	if (!syncbuf)
+	if (syncbuf < 0)
 		return 0;
 
 	ret = nvif_object_ctor(&dmac->base.user, "kmsSyncCtxDma", NV50_DISP_HANDLE_SYNCBUF,
@@ -2663,6 +2663,14 @@ nv50_display_create(struct drm_device *dev)
 	else
 		nouveau_display(dev)->format_modifiers = disp50xx_modifiers;
 
+	if (disp->disp->object.oclass >= GK104_DISP) {
+		dev->mode_config.cursor_width = 256;
+		dev->mode_config.cursor_height = 256;
+	} else {
+		dev->mode_config.cursor_width = 64;
+		dev->mode_config.cursor_height = 64;
+	}
+
 	/* create crtc objects to represent the hw heads */
 	if (disp->disp->object.oclass >= GV100_DISP)
 		crtcs = nvif_rd32(&device->object, 0x610060) & 0xff;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 92bddc083617..38dec11e7dda 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -95,7 +95,7 @@ struct nv50_outp_atom {
 
 int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 		     const s32 *oclass, u8 head, void *data, u32 size,
-		     u64 syncbuf, struct nv50_dmac *dmac);
+		     s64 syncbuf, struct nv50_dmac *dmac);
 void nv50_dmac_destroy(struct nv50_dmac *);
 
 /*
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
index a5d827403660..ea9f8667305e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head917d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
@@ -22,6 +22,7 @@
 #include "head.h"
 #include "core.h"
 
+#include "nvif/push.h"
 #include <nvif/push507c.h>
 
 #include <nvhw/class/cl917d.h>
@@ -73,6 +74,31 @@ head917d_base(struct nv50_head *head, struct nv50_head_atom *asyh)
 	return 0;
 }
 
+static int
+head917d_curs_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	struct nvif_push *push = nv50_disp(head->base.base.dev)->core->chan.push;
+	const int i = head->base.index;
+	int ret;
+
+	ret = PUSH_WAIT(push, 5);
+	if (ret)
+		return ret;
+
+	PUSH_MTHD(push, NV917D, HEAD_SET_CONTROL_CURSOR(i),
+		  NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, ENABLE, ENABLE) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, FORMAT, asyh->curs.format) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, SIZE, asyh->curs.layout) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_X, 0) |
+		  NVVAL(NV917D, HEAD_SET_CONTROL_CURSOR, HOT_SPOT_Y, 0) |
+		  NVDEF(NV917D, HEAD_SET_CONTROL_CURSOR, COMPOSITION, ALPHA_BLEND),
+
+				HEAD_SET_OFFSET_CURSOR(i), asyh->curs.offset >> 8);
+
+	PUSH_MTHD(push, NV917D, HEAD_SET_CONTEXT_DMA_CURSOR(i), asyh->curs.handle);
+	return 0;
+}
+
 int
 head917d_curs_layout(struct nv50_head *head, struct nv50_wndw_atom *asyw,
 		     struct nv50_head_atom *asyh)
@@ -101,7 +127,7 @@ head917d = {
 	.core_clr = head907d_core_clr,
 	.curs_layout = head917d_curs_layout,
 	.curs_format = head507d_curs_format,
-	.curs_set = head907d_curs_set,
+	.curs_set = head917d_curs_set,
 	.curs_clr = head907d_curs_clr,
 	.base = head917d_base,
 	.ovly = head907d_ovly,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimm.c b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
index a1ac153d5e98..566fbddfc8d7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimm.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
@@ -31,6 +31,7 @@ nv50_wimm_init(struct nouveau_drm *drm, struct nv50_wndw *wndw)
 		int version;
 		int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
 	} wimms[] = {
+		{ GA102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{ TU102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{ GV100_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
 		{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
index 685b70871324..b390029c69ec 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -76,7 +76,7 @@ wimmc37b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
 	int ret;
 
 	ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
-			       &oclass, 0, &args, sizeof(args), 0,
+			       &oclass, 0, &args, sizeof(args), -1,
 			       &wndw->wimm);
 	if (ret) {
 		NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 0356474ad6f6..271de3a63f21 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -702,6 +702,11 @@ nv50_wndw_init(struct nv50_wndw *wndw)
 	nvif_notify_get(&wndw->notify);
 }
 
+static const u64 nv50_cursor_format_modifiers[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
 int
 nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	       enum drm_plane_type type, const char *name, int index,
@@ -713,6 +718,7 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	struct nvif_mmu *mmu = &drm->client.mmu;
 	struct nv50_disp *disp = nv50_disp(dev);
 	struct nv50_wndw *wndw;
+	const u64 *format_modifiers;
 	int nformat;
 	int ret;
 
@@ -728,10 +734,13 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 
 	for (nformat = 0; format[nformat]; nformat++);
 
-	ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw,
-				       format, nformat,
-				       nouveau_display(dev)->format_modifiers,
-				       type, "%s-%d", name, index);
+	if (type == DRM_PLANE_TYPE_CURSOR)
+		format_modifiers = nv50_cursor_format_modifiers;
+	else
+		format_modifiers = nouveau_display(dev)->format_modifiers;
+
+	ret = drm_universal_plane_init(dev, &wndw->plane, heads, &nv50_wndw, format, nformat,
+				       format_modifiers, type, "%s-%d", name, index);
 	if (ret) {
 		kfree(*pwndw);
 		*pwndw = NULL;
@@ -784,6 +793,7 @@ nv50_wndw_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
 		int (*new)(struct nouveau_drm *, enum drm_plane_type,
 			   int, s32, struct nv50_wndw **);
 	} wndws[] = {
+		{ GA102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc67e_new },
 		{ TU102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc57e_new },
 		{ GV100_DISP_WINDOW_CHANNEL_DMA, 0, wndwc37e_new },
 		{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
index 3278e2880034..f4e0c5080034 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -129,6 +129,14 @@ int wndwc37e_update(struct nv50_wndw *, u32 *);
 
 int wndwc57e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
 		 struct nv50_wndw **);
+bool wndwc57e_ilut(struct nv50_wndw *, struct nv50_wndw_atom *, int);
+int wndwc57e_ilut_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_ilut_clr(struct nv50_wndw *);
+int wndwc57e_csc_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_csc_clr(struct nv50_wndw *);
+
+int wndwc67e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
+		 struct nv50_wndw **);
 
 int nv50_wndw_new(struct nouveau_drm *, enum drm_plane_type, int index,
 		  struct nv50_wndw **);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
index 429be0bb0222..abdd3bb658b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
@@ -80,7 +80,7 @@ wndwc57e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_csc_clr(struct nv50_wndw *wndw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -98,7 +98,7 @@ wndwc57e_csc_clr(struct nv50_wndw *wndw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -111,7 +111,7 @@ wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_ilut_clr(struct nv50_wndw *wndw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -124,7 +124,7 @@ wndwc57e_ilut_clr(struct nv50_wndw *wndw)
 	return 0;
 }
 
-static int
+int
 wndwc57e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 {
 	struct nvif_push *push = wndw->wndw.push;
@@ -179,7 +179,7 @@ wndwc57e_ilut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-static bool
+bool
 wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
 	if (size = size ? size : 1024, size != 256 && size != 1024)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
new file mode 100644
index 000000000000..7a370fa1df20
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wndw.h"
+#include "atom.h"
+
+#include <nvif/pushc37b.h>
+
+#include <nvhw/class/clc57e.h>
+
+static int
+wndwc67e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+	struct nvif_push *push = wndw->wndw.push;
+	int ret;
+
+	if ((ret = PUSH_WAIT(push, 17)))
+		return ret;
+
+	PUSH_MTHD(push, NVC57E, SET_PRESENT_CONTROL,
+		  NVVAL(NVC57E, SET_PRESENT_CONTROL, MIN_PRESENT_INTERVAL, asyw->image.interval) |
+		  NVVAL(NVC57E, SET_PRESENT_CONTROL, BEGIN_MODE, asyw->image.mode) |
+		  NVDEF(NVC57E, SET_PRESENT_CONTROL, TIMESTAMP_MODE, DISABLE));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE,
+		  NVVAL(NVC57E, SET_SIZE, WIDTH, asyw->image.w) |
+		  NVVAL(NVC57E, SET_SIZE, HEIGHT, asyw->image.h),
+
+				SET_STORAGE,
+		  NVVAL(NVC57E, SET_STORAGE, BLOCK_HEIGHT, asyw->image.blockh),
+
+				SET_PARAMS,
+		  NVVAL(NVC57E, SET_PARAMS, FORMAT, asyw->image.format) |
+		  NVDEF(NVC57E, SET_PARAMS, CLAMP_BEFORE_BLEND, DISABLE) |
+		  NVDEF(NVC57E, SET_PARAMS, SWAP_UV, DISABLE) |
+		  NVDEF(NVC57E, SET_PARAMS, FMT_ROUNDING_MODE, ROUND_TO_NEAREST),
+
+				SET_PLANAR_STORAGE(0),
+		  NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.blocks[0]) |
+		  NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.pitch[0] >> 6));
+
+	PUSH_MTHD(push, NVC57E, SET_CONTEXT_DMA_ISO(0), asyw->image.handle, 1);
+	PUSH_MTHD(push, NVC57E, SET_OFFSET(0), asyw->image.offset[0] >> 8);
+
+	PUSH_MTHD(push, NVC57E, SET_POINT_IN(0),
+		  NVVAL(NVC57E, SET_POINT_IN, X, asyw->state.src_x >> 16) |
+		  NVVAL(NVC57E, SET_POINT_IN, Y, asyw->state.src_y >> 16));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE_IN,
+		  NVVAL(NVC57E, SET_SIZE_IN, WIDTH, asyw->state.src_w >> 16) |
+		  NVVAL(NVC57E, SET_SIZE_IN, HEIGHT, asyw->state.src_h >> 16));
+
+	PUSH_MTHD(push, NVC57E, SET_SIZE_OUT,
+		  NVVAL(NVC57E, SET_SIZE_OUT, WIDTH, asyw->state.crtc_w) |
+		  NVVAL(NVC57E, SET_SIZE_OUT, HEIGHT, asyw->state.crtc_h));
+	return 0;
+}
+
+static const struct nv50_wndw_func
+wndwc67e = {
+	.acquire = wndwc37e_acquire,
+	.release = wndwc37e_release,
+	.sema_set = wndwc37e_sema_set,
+	.sema_clr = wndwc37e_sema_clr,
+	.ntfy_set = wndwc37e_ntfy_set,
+	.ntfy_clr = wndwc37e_ntfy_clr,
+	.ntfy_reset = corec37d_ntfy_init,
+	.ntfy_wait_begun = base507c_ntfy_wait_begun,
+	.ilut = wndwc57e_ilut,
+	.ilut_identity = true,
+	.ilut_size = 1024,
+	.xlut_set = wndwc57e_ilut_set,
+	.xlut_clr = wndwc57e_ilut_clr,
+	.csc = base907c_csc,
+	.csc_set = wndwc57e_csc_set,
+	.csc_clr = wndwc57e_csc_clr,
+	.image_set = wndwc67e_image_set,
+	.image_clr = wndwc37e_image_clr,
+	.blend_set = wndwc37e_blend_set,
+	.update = wndwc37e_update,
+};
+
+int
+wndwc67e_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+	     s32 oclass, struct nv50_wndw **pwndw)
+{
+	return wndwc37e_new_(&wndwc67e, drm, type, index, oclass, BIT(index >> 1), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
index 2a2612d6e1e0..fb223723a38a 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl917d.h
@@ -66,6 +66,10 @@
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_ALPHA_BLEND                  (0x00000000)
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_PREMULT_ALPHA_BLEND          (0x00000001)
 #define NV917D_HEAD_SET_CONTROL_CURSOR_COMPOSITION_XOR                          (0x00000002)
+#define NV917D_HEAD_SET_OFFSET_CURSOR(a)                                        (0x00000484 + (a)*0x00000300)
+#define NV917D_HEAD_SET_OFFSET_CURSOR_ORIGIN                                    31:0
+#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR(a)                                   (0x0000048C + (a)*0x00000300)
+#define NV917D_HEAD_SET_CONTEXT_DMA_CURSOR_HANDLE                               31:0
 #define NV917D_HEAD_SET_DITHER_CONTROL(a)                                       (0x000004A0 + (a)*0x00000300)
 #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE                                   0:0
 #define NV917D_HEAD_SET_DITHER_CONTROL_ENABLE_DISABLE                           (0x00000000)
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index cd9a2e687bb6..57d4f457a7d4 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -33,6 +33,7 @@ struct nv_device_info_v0 {
 #define NV_DEVICE_INFO_V0_PASCAL                                           0x0a
 #define NV_DEVICE_INFO_V0_VOLTA                                            0x0b
 #define NV_DEVICE_INFO_V0_TURING                                           0x0c
+#define NV_DEVICE_INFO_V0_AMPERE                                           0x0d
 	__u8  family;
 	__u8  pad06[2];
 	__u64 ram_size;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 2c79beb41126..ba2c28ea43d2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -88,6 +88,7 @@
 #define GP102_DISP                                    /* cl5070.h */ 0x00009870
 #define GV100_DISP                                    /* cl5070.h */ 0x0000c370
 #define TU102_DISP                                    /* cl5070.h */ 0x0000c570
+#define GA102_DISP                                    /* cl5070.h */ 0x0000c670
 
 #define GV100_DISP_CAPS                                              0x0000c373
 
@@ -103,6 +104,7 @@
 #define GK104_DISP_CURSOR                             /* cl507a.h */ 0x0000917a
 #define GV100_DISP_CURSOR                             /* cl507a.h */ 0x0000c37a
 #define TU102_DISP_CURSOR                             /* cl507a.h */ 0x0000c57a
+#define GA102_DISP_CURSOR                             /* cl507a.h */ 0x0000c67a
 
 #define NV50_DISP_OVERLAY                             /* cl507b.h */ 0x0000507b
 #define G82_DISP_OVERLAY                              /* cl507b.h */ 0x0000827b
@@ -112,6 +114,7 @@
 
 #define GV100_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c37b
 #define TU102_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c57b
+#define GA102_DISP_WINDOW_IMM_CHANNEL_DMA             /* clc37b.h */ 0x0000c67b
 
 #define NV50_DISP_BASE_CHANNEL_DMA                    /* cl507c.h */ 0x0000507c
 #define G82_DISP_BASE_CHANNEL_DMA                     /* cl507c.h */ 0x0000827c
@@ -135,6 +138,7 @@
 #define GP102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000987d
 #define GV100_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c37d
 #define TU102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c57d
+#define GA102_DISP_CORE_CHANNEL_DMA                   /* cl507d.h */ 0x0000c67d
 
 #define NV50_DISP_OVERLAY_CHANNEL_DMA                 /* cl507e.h */ 0x0000507e
 #define G82_DISP_OVERLAY_CHANNEL_DMA                  /* cl507e.h */ 0x0000827e
@@ -145,6 +149,7 @@
 
 #define GV100_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c37e
 #define TU102_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c57e
+#define GA102_DISP_WINDOW_CHANNEL_DMA                 /* clc37e.h */ 0x0000c67e
 
 #define NV50_TESLA                                                   0x00005097
 #define G82_TESLA                                                    0x00008297
diff --git a/drivers/gpu/drm/nouveau/include/nvif/push.h b/drivers/gpu/drm/nouveau/include/nvif/push.h
index 168d7694ede5..6d3a8a3d2087 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/push.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/push.h
@@ -123,131 +123,131 @@ PUSH_KICK(struct nvif_push *push)
 } while(0)
 #endif
 
-#define PUSH_1(X,f,ds,n,c,o,p,s,mA,dA) do {                            \
-	PUSH_##o##_HDR((p), s, mA, (c)+(n));                           \
-	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                   \
+#define PUSH_1(X,f,ds,n,o,p,s,mA,dA) do {                             \
+	PUSH_##o##_HDR((p), s, mA, (ds)+(n));                         \
+	PUSH_##f(X, (p), X##mA, 1, o, (dA), ds, "");                  \
 } while(0)
-#define PUSH_2(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");       \
-	PUSH_1(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_2(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (1?PUSH_##o##_INC), "mthd1");      \
+	PUSH_1(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_3(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");       \
-	PUSH_2(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_3(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd2");      \
+	PUSH_2(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_4(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");       \
-	PUSH_3(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_4(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd3");      \
+	PUSH_3(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_5(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");       \
-	PUSH_4(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_5(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd4");      \
+	PUSH_4(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_6(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");       \
-	PUSH_5(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_6(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd5");      \
+	PUSH_5(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_7(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");       \
-	PUSH_6(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_7(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd6");      \
+	PUSH_6(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_8(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");       \
-	PUSH_7(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_8(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd7");      \
+	PUSH_7(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_9(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                 \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");       \
-	PUSH_8(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_9(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                  \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd8");      \
+	PUSH_8(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
-#define PUSH_10(X,f,ds,n,c,o,p,s,mB,dB,mA,dA,a...) do {                \
-	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");       \
-	PUSH_9(X, DATA_, 1, ds, (c)+(n), o, (p), s, X##mA, (dA), ##a); \
-	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                   \
+#define PUSH_10(X,f,ds,n,o,p,s,mB,dB,mA,dA,a...) do {                 \
+	PUSH_ASSERT((mB) - (mA) == (0?PUSH_##o##_INC), "mthd9");      \
+	PUSH_9(X, DATA_, 1, (ds) + (n), o, (p), s, X##mA, (dA), ##a); \
+	PUSH_##f(X, (p), X##mB, 0, o, (dB), ds, "");                  \
 } while(0)
 
-#define PUSH_1D(X,o,p,s,mA,dA)                            \
-	PUSH_1(X, DATA_, 1, 1, 0, o, (p), s, X##mA, (dA))
-#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                      \
-	PUSH_2(X, DATA_, 1, 1, 0, o, (p), s, X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)                \
-	PUSH_3(X, DATA_, 1, 1, 0, o, (p), s, X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)          \
-	PUSH_4(X, DATA_, 1, 1, 0, o, (p), s, X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
-#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE)    \
-	PUSH_5(X, DATA_, 1, 1, 0, o, (p), s, X##mE, (dE), \
-					     X##mD, (dD), \
-					     X##mC, (dC), \
-					     X##mB, (dB), \
-					     X##mA, (dA))
+#define PUSH_1D(X,o,p,s,mA,dA)                         \
+	PUSH_1(X, DATA_, 1, 0, o, (p), s, X##mA, (dA))
+#define PUSH_2D(X,o,p,s,mA,dA,mB,dB)                   \
+	PUSH_2(X, DATA_, 1, 0, o, (p), s, X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_3D(X,o,p,s,mA,dA,mB,dB,mC,dC)             \
+	PUSH_3(X, DATA_, 1, 0, o, (p), s, X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_4D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD)       \
+	PUSH_4(X, DATA_, 1, 0, o, (p), s, X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
+#define PUSH_5D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE) \
+	PUSH_5(X, DATA_, 1, 0, o, (p), s, X##mE, (dE), \
+					  X##mD, (dD), \
+					  X##mC, (dC), \
+					  X##mB, (dB), \
+					  X##mA, (dA))
 #define PUSH_6D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF) \
-	PUSH_6(X, DATA_, 1, 1, 0, o, (p), s, X##mF, (dF),    \
-					     X##mE, (dE),    \
-					     X##mD, (dD),    \
-					     X##mC, (dC),    \
-					     X##mB, (dB),    \
-					     X##mA, (dA))
+	PUSH_6(X, DATA_, 1, 0, o, (p), s, X##mF, (dF),       \
+					  X##mE, (dE),       \
+					  X##mD, (dD),       \
+					  X##mC, (dC),       \
+					  X##mB, (dB),       \
+					  X##mA, (dA))
 #define PUSH_7D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG) \
-	PUSH_7(X, DATA_, 1, 1, 0, o, (p), s, X##mG, (dG),          \
-					     X##mF, (dF),          \
-					     X##mE, (dE),          \
-					     X##mD, (dD),          \
-					     X##mC, (dC),          \
-					     X##mB, (dB),          \
-					     X##mA, (dA))
+	PUSH_7(X, DATA_, 1, 0, o, (p), s, X##mG, (dG),             \
+					  X##mF, (dF),             \
+					  X##mE, (dE),             \
+					  X##mD, (dD),             \
+					  X##mC, (dC),             \
+					  X##mB, (dB),             \
+					  X##mA, (dA))
 #define PUSH_8D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH) \
-	PUSH_8(X, DATA_, 1, 1, 0, o, (p), s, X##mH, (dH),                \
-					     X##mG, (dG),                \
-					     X##mF, (dF),                \
-					     X##mE, (dE),                \
-					     X##mD, (dD),                \
-					     X##mC, (dC),                \
-					     X##mB, (dB),                \
-					     X##mA, (dA))
+	PUSH_8(X, DATA_, 1, 0, o, (p), s, X##mH, (dH),                   \
+					  X##mG, (dG),                   \
+					  X##mF, (dF),                   \
+					  X##mE, (dE),                   \
+					  X##mD, (dD),                   \
+					  X##mC, (dC),                   \
+					  X##mB, (dB),                   \
+					  X##mA, (dA))
 #define PUSH_9D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI) \
-	PUSH_9(X, DATA_, 1, 1, 0, o, (p), s, X##mI, (dI),                      \
-					     X##mH, (dH),                      \
-					     X##mG, (dG),                      \
-					     X##mF, (dF),                      \
-					     X##mE, (dE),                      \
-					     X##mD, (dD),                      \
-					     X##mC, (dC),                      \
-					     X##mB, (dB),                      \
-					     X##mA, (dA))
+	PUSH_9(X, DATA_, 1, 0, o, (p), s, X##mI, (dI),                         \
+					  X##mH, (dH),                         \
+					  X##mG, (dG),                         \
+					  X##mF, (dF),                         \
+					  X##mE, (dE),                         \
+					  X##mD, (dD),                         \
+					  X##mC, (dC),                         \
+					  X##mB, (dB),                         \
+					  X##mA, (dA))
 #define PUSH_10D(X,o,p,s,mA,dA,mB,dB,mC,dC,mD,dD,mE,dE,mF,dF,mG,dG,mH,dH,mI,dI,mJ,dJ) \
-	PUSH_10(X, DATA_, 1, 1, 0, o, (p), s, X##mJ, (dJ),                            \
-					      X##mI, (dI),                            \
-					      X##mH, (dH),                            \
-					      X##mG, (dG),                            \
-					      X##mF, (dF),                            \
-					      X##mE, (dE),                            \
-					      X##mD, (dD),                            \
-					      X##mC, (dC),                            \
-					      X##mB, (dB),                            \
-					      X##mA, (dA))
+	PUSH_10(X, DATA_, 1, 0, o, (p), s, X##mJ, (dJ),                               \
+					   X##mI, (dI),                               \
+					   X##mH, (dH),                               \
+					   X##mG, (dG),                               \
+					   X##mF, (dF),                               \
+					   X##mE, (dE),                               \
+					   X##mD, (dD),                               \
+					   X##mC, (dC),                               \
+					   X##mB, (dB),                               \
+					   X##mA, (dA))
 
-#define PUSH_1P(X,o,p,s,mA,dp,ds)                           \
-	PUSH_1(X, DATAp, ds, ds, 0, o, (p), s, X##mA, (dp))
-#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                     \
-	PUSH_2(X, DATAp, ds, ds, 0, o, (p), s, X##mB, (dp), \
-					       X##mA, (dA))
-#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)               \
-	PUSH_3(X, DATAp, ds, ds, 0, o, (p), s, X##mC, (dp), \
-					       X##mB, (dB), \
-					       X##mA, (dA))
+#define PUSH_1P(X,o,p,s,mA,dp,ds)                       \
+	PUSH_1(X, DATAp, ds, 0, o, (p), s, X##mA, (dp))
+#define PUSH_2P(X,o,p,s,mA,dA,mB,dp,ds)                 \
+	PUSH_2(X, DATAp, ds, 0, o, (p), s, X##mB, (dp), \
+					   X##mA, (dA))
+#define PUSH_3P(X,o,p,s,mA,dA,mB,dB,mC,dp,ds)           \
+	PUSH_3(X, DATAp, ds, 0, o, (p), s, X##mC, (dp), \
+					   X##mB, (dB), \
+					   X##mA, (dA))
 
 #define PUSH_(A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,IMPL,...) IMPL
 #define PUSH(A...) PUSH_(A, PUSH_10P, PUSH_10D,          \
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 5c007ce62fc3..c920939a1467 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -120,6 +120,7 @@ struct nvkm_device {
 		GP100    = 0x130,
 		GV100    = 0x140,
 		TU100    = 0x160,
+		GA100    = 0x170,
 	} card_type;
 	u32 chipset;
 	u8  chiprev;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
index 5a96c942d912..0f6fa6631a19 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
@@ -37,4 +37,5 @@ int gp100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gp102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int gv100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 int tu102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int ga102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
index 1a39e52e09e3..50cc7c05eac4 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
@@ -32,4 +32,5 @@ int gm107_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gm200_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int gv100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 int tu102_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
+int ga100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 34b56b10218a..2ecd52aec1d1 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -86,6 +86,8 @@ int gp100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gp10b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 int gv100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
 
 #include <subdev/bios.h>
 #include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
index eaacf8d80527..cdcce5ece6ff 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
@@ -37,4 +37,5 @@ int nv50_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int g94_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int gf119_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 int gk104_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
+int ga102_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
index 81b977319640..640f649ce497 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
@@ -92,6 +92,7 @@ int g94_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gf117_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gf119_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gk104_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
+int gk110_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 int gm200_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
 
 static inline int
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
index 6641fe4c252c..e45ca4583967 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
@@ -32,4 +32,5 @@ int gk20a_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gp100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int gp10b_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 int tu102_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
+int ga100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index c7a94c94dbf3..72f35a2babcb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -256,6 +256,7 @@ nouveau_backlight_init(struct drm_connector *connector)
 	case NV_DEVICE_INFO_V0_PASCAL:
 	case NV_DEVICE_INFO_V0_VOLTA:
 	case NV_DEVICE_INFO_V0_TURING:
+	case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed
 		ret = nv50_backlight_init(nv_encoder, &props, &ops);
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index c85b1af06b7b..7ea367a5444d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -547,7 +547,7 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 {
 	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct ttm_tt *ttm_dma = (struct ttm_tt *)nvbo->bo.ttm;
-	int i;
+	int i, j;
 
 	if (!ttm_dma)
 		return;
@@ -556,10 +556,21 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo)
 	if (nvbo->force_coherent)
 		return;
 
-	for (i = 0; i < ttm_dma->num_pages; i++)
+	for (i = 0; i < ttm_dma->num_pages; ++i) {
+		struct page *p = ttm_dma->pages[i];
+		size_t num_pages = 1;
+
+		for (j = i + 1; j < ttm_dma->num_pages; ++j) {
+			if (++p != ttm_dma->pages[j])
+				break;
+
+			++num_pages;
+		}
 		dma_sync_single_for_device(drm->dev->dev,
 					   ttm_dma->dma_address[i],
-					   PAGE_SIZE, DMA_TO_DEVICE);
+					   num_pages * PAGE_SIZE, DMA_TO_DEVICE);
+		i += num_pages;
+	}
 }
 
 void
@@ -567,7 +578,7 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 {
 	struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev);
 	struct ttm_tt *ttm_dma = (struct ttm_tt *)nvbo->bo.ttm;
-	int i;
+	int i, j;
 
 	if (!ttm_dma)
 		return;
@@ -576,9 +587,21 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo)
 	if (nvbo->force_coherent)
 		return;
 
-	for (i = 0; i < ttm_dma->num_pages; i++)
+	for (i = 0; i < ttm_dma->num_pages; ++i) {
+		struct page *p = ttm_dma->pages[i];
+		size_t num_pages = 1;
+
+		for (j = i + 1; j < ttm_dma->num_pages; ++j) {
+			if (++p != ttm_dma->pages[j])
+				break;
+
+			++num_pages;
+		}
+
 		dma_sync_single_for_cpu(drm->dev->dev, ttm_dma->dma_address[i],
-					PAGE_SIZE, DMA_FROM_DEVICE);
+					num_pages * PAGE_SIZE, DMA_FROM_DEVICE);
+		i += num_pages;
+	}
 }
 
 void nouveau_bo_add_io_reserve_lru(struct ttm_buffer_object *bo)
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 4f69e4c3dafd..1c3f890377d2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -315,6 +315,10 @@ nouveau_svmm_init(struct drm_device *dev, void *data,
 	struct drm_nouveau_svm_init *args = data;
 	int ret;
 
+	/* We need to fail if svm is disabled */
+	if (!cli->drm->svm)
+		return -ENOSYS;
+
 	/* Allocate tracking for SVM-enabled VMM. */
 	if (!(svmm = kzalloc(sizeof(*svmm), GFP_KERNEL)))
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/nouveau/nvif/disp.c b/drivers/gpu/drm/nouveau/nvif/disp.c
index 8d0d30e08f57..529cb60d5efb 100644
--- a/drivers/gpu/drm/nouveau/nvif/disp.c
+++ b/drivers/gpu/drm/nouveau/nvif/disp.c
@@ -35,6 +35,7 @@ nvif_disp_ctor(struct nvif_device *device, const char *name, s32 oclass,
 	       struct nvif_disp *disp)
 {
 	static const struct nvif_mclass disps[] = {
+		{ GA102_DISP, -1 },
 		{ TU102_DISP, -1 },
 		{ GV100_DISP, -1 },
 		{ GP102_DISP, -1 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 7851bec5f0e5..cdcc851e06f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -1815,7 +1815,7 @@ nvf0_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1853,7 +1853,7 @@ nvf1_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1891,7 +1891,7 @@ nv106_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1929,7 +1929,7 @@ nv108_chipset = {
 	.fb = gk110_fb_new,
 	.fuse = gf100_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -1967,7 +1967,7 @@ nv117_chipset = {
 	.fb = gm107_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -2003,7 +2003,7 @@ nv118_chipset = {
 	.fb = gm107_fb_new,
 	.fuse = gm107_fuse_new,
 	.gpio = gk104_gpio_new,
-	.i2c = gk104_i2c_new,
+	.i2c = gk110_i2c_new,
 	.ibus = gk104_ibus_new,
 	.iccsense = gf100_iccsense_new,
 	.imem = nv50_instmem_new,
@@ -2652,6 +2652,61 @@ nv168_chipset = {
 	.sec2 = tu102_sec2_new,
 };
 
+static const struct nvkm_device_chip
+nv170_chipset = {
+	.name = "GA100",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga100_fb_new,
+	.gpio = gk104_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+};
+
+static const struct nvkm_device_chip
+nv172_chipset = {
+	.name = "GA102",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga102_fb_new,
+	.gpio = ga102_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.disp = ga102_disp_new,
+	.dma = gv100_dma_new,
+};
+
+static const struct nvkm_device_chip
+nv174_chipset = {
+	.name = "GA104",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.devinit = ga100_devinit_new,
+	.fb = ga102_fb_new,
+	.gpio = ga102_gpio_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.mc = ga100_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.timer = gk20a_timer_new,
+	.disp = ga102_disp_new,
+	.dma = gv100_dma_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -3063,6 +3118,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 			case 0x130: device->card_type = GP100; break;
 			case 0x140: device->card_type = GV100; break;
 			case 0x160: device->card_type = TU100; break;
+			case 0x170: device->card_type = GA100; break;
 			default:
 				break;
 			}
@@ -3160,10 +3216,23 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x166: device->chip = &nv166_chipset; break;
 		case 0x167: device->chip = &nv167_chipset; break;
 		case 0x168: device->chip = &nv168_chipset; break;
+		case 0x172: device->chip = &nv172_chipset; break;
+		case 0x174: device->chip = &nv174_chipset; break;
 		default:
-			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
-			ret = -ENODEV;
-			goto done;
+			if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
+				switch (device->chipset) {
+				case 0x170: device->chip = &nv170_chipset; break;
+				default:
+					break;
+				}
+			}
+
+			if (!device->chip) {
+				nvdev_error(device, "unknown chipset (%08x)\n", boot0);
+				ret = -ENODEV;
+				goto done;
+			}
+			break;
 		}
 
 		nvdev_info(device, "NVIDIA %s (%08x)\n",
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 03c6d9aef075..147894798786 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -176,6 +176,7 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
 	case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
 	case GV100: args->v0.family = NV_DEVICE_INFO_V0_VOLTA; break;
 	case TU100: args->v0.family = NV_DEVICE_INFO_V0_TURING; break;
+	case GA100: args->v0.family = NV_DEVICE_INFO_V0_AMPERE; break;
 	default:
 		args->v0.family = 0;
 		break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index cf075311cdd2..b03f043efe26 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -17,6 +17,7 @@ nvkm-y += nvkm/engine/disp/gp100.o
 nvkm-y += nvkm/engine/disp/gp102.o
 nvkm-y += nvkm/engine/disp/gv100.o
 nvkm-y += nvkm/engine/disp/tu102.o
+nvkm-y += nvkm/engine/disp/ga102.o
 nvkm-y += nvkm/engine/disp/vga.o
 
 nvkm-y += nvkm/engine/disp/head.o
@@ -42,6 +43,7 @@ nvkm-y += nvkm/engine/disp/sorgm200.o
 nvkm-y += nvkm/engine/disp/sorgp100.o
 nvkm-y += nvkm/engine/disp/sorgv100.o
 nvkm-y += nvkm/engine/disp/sortu102.o
+nvkm-y += nvkm/engine/disp/sorga102.o
 
 nvkm-y += nvkm/engine/disp/outp.o
 nvkm-y += nvkm/engine/disp/dp.o
@@ -75,6 +77,7 @@ nvkm-y += nvkm/engine/disp/rootgp100.o
 nvkm-y += nvkm/engine/disp/rootgp102.o
 nvkm-y += nvkm/engine/disp/rootgv100.o
 nvkm-y += nvkm/engine/disp/roottu102.o
+nvkm-y += nvkm/engine/disp/rootga102.o
 
 nvkm-y += nvkm/engine/disp/capsgv100.o
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 3800aeb507d0..55fbfe28c6dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -33,6 +33,12 @@
 
 #include <nvif/event.h>
 
+/* IED scripts are no longer used by UEFI/RM from Ampere, but have been updated for
+ * the x86 option ROM.  However, the relevant VBIOS table versions weren't modified,
+ * so we're unable to detect this in a nice way.
+ */
+#define AMPERE_IED_HACK(disp) ((disp)->engine.subdev.device->card_type >= GA100)
+
 struct lt_state {
 	struct nvkm_dp *dp;
 	u8  stat[6];
@@ -238,6 +244,19 @@ nvkm_dp_train_links(struct nvkm_dp *dp)
 		dp->dpcd[DPCD_RC02] &= ~DPCD_RC02_TPS3_SUPPORTED;
 	lt.pc2 = dp->dpcd[DPCD_RC02] & DPCD_RC02_TPS3_SUPPORTED;
 
+	if (AMPERE_IED_HACK(disp) && (lnkcmp = lt.dp->info.script[0])) {
+		/* Execute BeforeLinkTraining script from DP Info table. */
+		while (ior->dp.bw < nvbios_rd08(bios, lnkcmp))
+			lnkcmp += 3;
+		lnkcmp = nvbios_rd16(bios, lnkcmp + 1);
+
+		nvbios_init(&dp->outp.disp->engine.subdev, lnkcmp,
+			init.outp = &dp->outp.info;
+			init.or   = ior->id;
+			init.link = ior->asy.link;
+		);
+	}
+
 	/* Set desired link configuration on the source. */
 	if ((lnkcmp = lt.dp->info.lnkcmp)) {
 		if (dp->version < 0x30) {
@@ -316,12 +335,14 @@ nvkm_dp_train_init(struct nvkm_dp *dp)
 		);
 	}
 
-	/* Execute BeforeLinkTraining script from DP Info table. */
-	nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
-		init.outp = &dp->outp.info;
-		init.or   = dp->outp.ior->id;
-		init.link = dp->outp.ior->asy.link;
-	);
+	if (!AMPERE_IED_HACK(dp->outp.disp)) {
+		/* Execute BeforeLinkTraining script from DP Info table. */
+		nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
+			init.outp = &dp->outp.info;
+			init.or   = dp->outp.ior->id;
+			init.link = dp->outp.ior->asy.link;
+		);
+	}
 }
 
 static const struct dp_rates {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
new file mode 100644
index 000000000000..aa2e5645fe36
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+#include "head.h"
+#include "ior.h"
+#include "channv50.h"
+#include "rootnv50.h"
+
+static const struct nv50_disp_func
+ga102_disp = {
+	.init = tu102_disp_init,
+	.fini = gv100_disp_fini,
+	.intr = gv100_disp_intr,
+	.uevent = &gv100_disp_chan_uevent,
+	.super = gv100_disp_super,
+	.root = &ga102_disp_root_oclass,
+	.wndw = { .cnt = gv100_disp_wndw_cnt },
+	.head = { .cnt = gv100_head_cnt, .new = gv100_head_new },
+	.sor = { .cnt = gv100_sor_cnt, .new = ga102_sor_new },
+	.ramht_size = 0x2000,
+};
+
+int
+ga102_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+	return nv50_disp_new_(&ga102_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
index 09f3038eff26..9f0bb7c6b010 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
@@ -150,6 +150,8 @@ void gv100_sor_dp_audio(struct nvkm_ior *, int, bool);
 void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32);
 void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8);
 
+void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16);
+
 void g84_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gt215_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
 void gf119_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
@@ -207,4 +209,6 @@ int gv100_sor_cnt(struct nvkm_disp *, unsigned long *);
 int gv100_sor_new(struct nvkm_disp *, int);
 
 int tu102_sor_new(struct nvkm_disp *, int);
+
+int ga102_sor_new(struct nvkm_disp *, int);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
index a677161c7f3a..db31b37752a2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
@@ -86,6 +86,8 @@ void gv100_disp_intr(struct nv50_disp *);
 void gv100_disp_super(struct work_struct *);
 int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *);
 
+int tu102_disp_init(struct nv50_disp *);
+
 void nv50_disp_dptmds_war_2(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_dptmds_war_3(struct nv50_disp *, struct dcb_output *);
 void nv50_disp_update_sppll1(struct nv50_disp *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
new file mode 100644
index 000000000000..9af07c3cf9fc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "rootnv50.h"
+#include "channv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+ga102_disp_root = {
+	.user = {
+		{{-1,-1,GV100_DISP_CAPS                }, gv100_disp_caps_new },
+		{{0,0,GA102_DISP_CURSOR                }, gv100_disp_curs_new },
+		{{0,0,GA102_DISP_WINDOW_IMM_CHANNEL_DMA}, gv100_disp_wimm_new },
+		{{0,0,GA102_DISP_CORE_CHANNEL_DMA      }, gv100_disp_core_new },
+		{{0,0,GA102_DISP_WINDOW_CHANNEL_DMA    }, gv100_disp_wndw_new },
+		{}
+	},
+};
+
+static int
+ga102_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+		    void *data, u32 size, struct nvkm_object **pobject)
+{
+	return nv50_disp_root_new_(&ga102_disp_root, disp, oclass, data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+ga102_disp_root_oclass = {
+	.base.oclass = GA102_DISP,
+	.base.minver = -1,
+	.base.maxver = -1,
+	.ctor = ga102_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
index 7070f5408d92..27bb170d0293 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
@@ -41,4 +41,5 @@ extern const struct nvkm_disp_oclass gp100_disp_root_oclass;
 extern const struct nvkm_disp_oclass gp102_disp_root_oclass;
 extern const struct nvkm_disp_oclass gv100_disp_root_oclass;
 extern const struct nvkm_disp_oclass tu102_disp_root_oclass;
+extern const struct nvkm_disp_oclass ga102_disp_root_oclass;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
new file mode 100644
index 000000000000..033827de9116
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ior.h"
+
+#include <subdev/timer.h>
+
+static int
+ga102_sor_dp_links(struct nvkm_ior *sor, struct nvkm_i2c_aux *aux)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	const u32 soff = nv50_ior_base(sor);
+	const u32 loff = nv50_sor_link(sor);
+	u32 dpctrl = 0x00000000;
+	u32 clksor = 0x00000000;
+
+	switch (sor->dp.bw) {
+	case 0x06: clksor |= 0x00000000; break;
+	case 0x0a: clksor |= 0x00040000; break;
+	case 0x14: clksor |= 0x00080000; break;
+	case 0x1e: clksor |= 0x000c0000; break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	dpctrl |= ((1 << sor->dp.nr) - 1) << 16;
+	if (sor->dp.mst)
+		dpctrl |= 0x40000000;
+	if (sor->dp.ef)
+		dpctrl |= 0x00004000;
+
+	nvkm_mask(device, 0x612300 + soff, 0x007c0000, clksor);
+
+	/*XXX*/
+	nvkm_msec(device, 40, NVKM_DELAY);
+	nvkm_mask(device, 0x612300 + soff, 0x00030000, 0x00010000);
+	nvkm_mask(device, 0x61c10c + loff, 0x00000003, 0x00000001);
+
+	nvkm_mask(device, 0x61c10c + loff, 0x401f4000, dpctrl);
+	return 0;
+}
+
+static void
+ga102_sor_clock(struct nvkm_ior *sor)
+{
+	struct nvkm_device *device = sor->disp->engine.subdev.device;
+	u32 div2 = 0;
+	if (sor->asy.proto == TMDS) {
+		if (sor->tmds.high_speed)
+			div2 = 1;
+	}
+	nvkm_wr32(device, 0x00ec08 + (sor->id * 0x10), 0x00000000);
+	nvkm_wr32(device, 0x00ec04 + (sor->id * 0x10), div2);
+}
+
+static const struct nvkm_ior_func
+ga102_sor_hda = {
+	.route = {
+		.get = gm200_sor_route_get,
+		.set = gm200_sor_route_set,
+	},
+	.state = gv100_sor_state,
+	.power = nv50_sor_power,
+	.clock = ga102_sor_clock,
+	.hdmi = {
+		.ctrl = gv100_hdmi_ctrl,
+		.scdc = gm200_hdmi_scdc,
+	},
+	.dp = {
+		.lanes = { 0, 1, 2, 3 },
+		.links = ga102_sor_dp_links,
+		.power = g94_sor_dp_power,
+		.pattern = gm107_sor_dp_pattern,
+		.drive = gm200_sor_dp_drive,
+		.vcpi = tu102_sor_dp_vcpi,
+		.audio = gv100_sor_dp_audio,
+		.audio_sym = gv100_sor_dp_audio_sym,
+		.watermark = gv100_sor_dp_watermark,
+	},
+	.hda = {
+		.hpd = gf119_hda_hpd,
+		.eld = gf119_hda_eld,
+		.device_entry = gv100_hda_device_entry,
+	},
+};
+
+static const struct nvkm_ior_func
+ga102_sor = {
+	.route = {
+		.get = gm200_sor_route_get,
+		.set = gm200_sor_route_set,
+	},
+	.state = gv100_sor_state,
+	.power = nv50_sor_power,
+	.clock = ga102_sor_clock,
+	.hdmi = {
+		.ctrl = gv100_hdmi_ctrl,
+		.scdc = gm200_hdmi_scdc,
+	},
+	.dp = {
+		.lanes = { 0, 1, 2, 3 },
+		.links = ga102_sor_dp_links,
+		.power = g94_sor_dp_power,
+		.pattern = gm107_sor_dp_pattern,
+		.drive = gm200_sor_dp_drive,
+		.vcpi = tu102_sor_dp_vcpi,
+		.audio = gv100_sor_dp_audio,
+		.audio_sym = gv100_sor_dp_audio_sym,
+		.watermark = gv100_sor_dp_watermark,
+	},
+};
+
+int
+ga102_sor_new(struct nvkm_disp *disp, int id)
+{
+	struct nvkm_device *device = disp->engine.subdev.device;
+	u32 hda = nvkm_rd32(device, 0x08a15c);
+	if (hda & BIT(id))
+		return nvkm_ior_new_(&ga102_sor_hda, disp, SOR, id);
+	return nvkm_ior_new_(&ga102_sor, disp, SOR, id);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
index 59865a934c4b..0cf9e8752d25 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
@@ -23,7 +23,7 @@
 
 #include <subdev/timer.h>
 
-static void
+void
 tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head,
 		  u8 slot, u8 slot_nr, u16 pbn, u16 aligned)
 {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
index 883ae4151ff8..4c85d1d4fbd4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
@@ -28,7 +28,7 @@
 #include <core/gpuobj.h>
 #include <subdev/timer.h>
 
-static int
+int
 tu102_disp_init(struct nv50_disp *disp)
 {
 	struct nvkm_device *device = disp->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 7deb81b6dbac..4b571cc6bc70 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -75,7 +75,7 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd)
 	nvkm_debug(subdev, "%08x: type %02x, %d bytes\n",
 		   image.base, image.type, image.size);
 
-	if (!shadow_fetch(bios, mthd, image.size)) {
+	if (!shadow_fetch(bios, mthd, image.base + image.size)) {
 		nvkm_debug(subdev, "%08x: fetch failed\n", image.base);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
index 3634cd0630b8..023ddc7c5399 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
@@ -64,6 +64,9 @@ pramin_init(struct nvkm_bios *bios, const char *name)
 		return NULL;
 
 	/* we can't get the bios image pointer without PDISP */
+	if (device->card_type >= GA100)
+		addr = device->chipset == 0x170; /*XXX: find the fuse reg for this */
+	else
 	if (device->card_type >= GM100)
 		addr = nvkm_rd32(device, 0x021c04);
 	else
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
index b3429371ed82..d1abb64841da 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
@@ -15,3 +15,4 @@ nvkm-y += nvkm/subdev/devinit/gm107.o
 nvkm-y += nvkm/subdev/devinit/gm200.o
 nvkm-y += nvkm/subdev/devinit/gv100.o
 nvkm-y += nvkm/subdev/devinit/tu102.o
+nvkm-y += nvkm/subdev/devinit/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
new file mode 100644
index 000000000000..636a92128f6c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/clk/pll.h>
+
+static int
+ga100_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
+{
+	struct nvkm_subdev *subdev = &init->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvbios_pll info;
+	int head = type - PLL_VPLL0;
+	int N, fN, M, P;
+	int ret;
+
+	ret = nvbios_pll_parse(device->bios, type, &info);
+	if (ret)
+		return ret;
+
+	ret = gt215_pll_calc(subdev, &info, freq, &N, &fN, &M, &P);
+	if (ret < 0)
+		return ret;
+
+	switch (info.type) {
+	case PLL_VPLL0:
+	case PLL_VPLL1:
+	case PLL_VPLL2:
+	case PLL_VPLL3:
+		nvkm_wr32(device, 0x00ef00 + (head * 0x40), 0x02080004);
+		nvkm_wr32(device, 0x00ef18 + (head * 0x40), (N << 16) | fN);
+		nvkm_wr32(device, 0x00ef04 + (head * 0x40), (P << 16) | M);
+		nvkm_wr32(device, 0x00e9c0 + (head * 0x04), 0x00000001);
+		break;
+	default:
+		nvkm_warn(subdev, "%08x/%dKhz unimplemented\n", type, freq);
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct nvkm_devinit_func
+ga100_devinit = {
+	.init = nv50_devinit_init,
+	.post = tu102_devinit_post,
+	.pll_set = ga100_devinit_pll_set,
+};
+
+int
+ga100_devinit_new(struct nvkm_device *device, int index, struct nvkm_devinit **pinit)
+{
+	return nv50_devinit_new_(&ga100_devinit, device, index, pinit);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
index 94723352137a..05961e624264 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
@@ -19,4 +19,5 @@ void nvkm_devinit_ctor(const struct nvkm_devinit_func *, struct nvkm_device *,
 		       int index, struct nvkm_devinit *);
 
 int nv04_devinit_post(struct nvkm_devinit *, bool);
+int tu102_devinit_post(struct nvkm_devinit *, bool);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
index 397670e72fff..9a469bf482f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
@@ -65,7 +65,7 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
 	return ret;
 }
 
-static int
+int
 tu102_devinit_post(struct nvkm_devinit *base, bool post)
 {
 	struct nv50_devinit *init = nv50_devinit(base);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 43a42159a3d0..5d0bab8ecb43 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -32,6 +32,8 @@ nvkm-y += nvkm/subdev/fb/gp100.o
 nvkm-y += nvkm/subdev/fb/gp102.o
 nvkm-y += nvkm/subdev/fb/gp10b.o
 nvkm-y += nvkm/subdev/fb/gv100.o
+nvkm-y += nvkm/subdev/fb/ga100.o
+nvkm-y += nvkm/subdev/fb/ga102.o
 
 nvkm-y += nvkm/subdev/fb/ram.o
 nvkm-y += nvkm/subdev/fb/ramnv04.o
@@ -52,6 +54,7 @@ nvkm-y += nvkm/subdev/fb/ramgk104.o
 nvkm-y += nvkm/subdev/fb/ramgm107.o
 nvkm-y += nvkm/subdev/fb/ramgm200.o
 nvkm-y += nvkm/subdev/fb/ramgp100.o
+nvkm-y += nvkm/subdev/fb/ramga102.o
 nvkm-y += nvkm/subdev/fb/sddr2.o
 nvkm-y += nvkm/subdev/fb/sddr3.o
 nvkm-y += nvkm/subdev/fb/gddr3.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
new file mode 100644
index 000000000000..bf82686851cd
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga100_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gv100_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = gp100_ram_new,
+	.default_bigpage = 16,
+};
+
+int
+ga100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gp102_fb_new_(&ga100_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
new file mode 100644
index 000000000000..bcecf84a6e67
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga102_fb = {
+	.dtor = gf100_fb_dtor,
+	.oneinit = gf100_fb_oneinit,
+	.init = gp100_fb_init,
+	.init_page = gv100_fb_init_page,
+	.init_unkn = gp100_fb_init_unkn,
+	.ram_new = ga102_ram_new,
+	.default_bigpage = 16,
+};
+
+int
+ga102_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+	return gp102_fb_new_(&ga102_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 10ff5d053f7e..feda86a5fba8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -22,7 +22,7 @@
 #include "gf100.h"
 #include "ram.h"
 
-static int
+int
 gv100_fb_init_page(struct nvkm_fb *fb)
 {
 	return (fb->page == 16) ? 0 : -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 5be9c563350d..66932ac10d15 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -82,4 +82,6 @@ int gp102_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *, int,
 		  struct nvkm_fb **);
 bool gp102_fb_vpr_scrub_required(struct nvkm_fb *);
 int gp102_fb_vpr_scrub(struct nvkm_fb *);
+
+int gv100_fb_init_page(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
index d723a9b4e3c4..ea7d66f3dd82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
@@ -70,4 +70,5 @@ int gk104_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gm107_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gm200_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 int gp100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
+int ga102_ram_new(struct nvkm_fb *, struct nvkm_ram **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
new file mode 100644
index 000000000000..298c136cefe0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ram.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/init.h>
+#include <subdev/bios/rammap.h>
+
+static const struct nvkm_ram_func
+ga102_ram = {
+};
+
+int
+ga102_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	enum nvkm_ram_type type = nvkm_fb_bios_memtype(device->bios);
+	u32 size = nvkm_rd32(device, 0x1183a4);
+
+	return nvkm_ram_new_(&ga102_ram, fb, type, (u64)size << 20, pram);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
index b2ad5922a1c2..efbbaa080de5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
@@ -5,3 +5,4 @@ nvkm-y += nvkm/subdev/gpio/nv50.o
 nvkm-y += nvkm/subdev/gpio/g94.o
 nvkm-y += nvkm/subdev/gpio/gf119.o
 nvkm-y += nvkm/subdev/gpio/gk104.o
+nvkm-y += nvkm/subdev/gpio/ga102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
new file mode 100644
index 000000000000..62c791baf400
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga102_gpio_reset(struct nvkm_gpio *gpio, u8 match)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	struct nvkm_bios *bios = device->bios;
+	u8 ver, len;
+	u16 entry;
+	int ent = -1;
+
+	while ((entry = dcb_gpio_entry(bios, 0, ++ent, &ver, &len))) {
+		u32 data = nvbios_rd32(bios, entry);
+		u8  line =   (data & 0x0000003f);
+		u8  defs = !!(data & 0x00000080);
+		u8  func =   (data & 0x0000ff00) >> 8;
+		u8  unk0 =   (data & 0x00ff0000) >> 16;
+		u8  unk1 =   (data & 0x1f000000) >> 24;
+
+		if ( func  == DCB_GPIO_UNUSED ||
+		    (match != DCB_GPIO_UNUSED && match != func))
+			continue;
+
+		nvkm_gpio_set(gpio, 0, func, line, defs);
+
+		nvkm_mask(device, 0x021200 + (line * 4), 0xff, unk0);
+		if (unk1--)
+			nvkm_mask(device, 0x00d740 + (unk1 * 4), 0xff, line);
+	}
+}
+
+static int
+ga102_gpio_drive(struct nvkm_gpio *gpio, int line, int dir, int out)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 data = ((dir ^ 1) << 13) | (out << 12);
+	nvkm_mask(device, 0x021200 + (line * 4), 0x00003000, data);
+	nvkm_mask(device, 0x00d604, 0x00000001, 0x00000001); /* update? */
+	return 0;
+}
+
+static int
+ga102_gpio_sense(struct nvkm_gpio *gpio, int line)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	return !!(nvkm_rd32(device, 0x021200 + (line * 4)) & 0x00004000);
+}
+
+static void
+ga102_gpio_intr_stat(struct nvkm_gpio *gpio, u32 *hi, u32 *lo)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 intr0 = nvkm_rd32(device, 0x021640);
+	u32 intr1 = nvkm_rd32(device, 0x02164c);
+	u32 stat0 = nvkm_rd32(device, 0x021648) & intr0;
+	u32 stat1 = nvkm_rd32(device, 0x021654) & intr1;
+	*lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+	*hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+	nvkm_wr32(device, 0x021640, intr0);
+	nvkm_wr32(device, 0x02164c, intr1);
+}
+
+static void
+ga102_gpio_intr_mask(struct nvkm_gpio *gpio, u32 type, u32 mask, u32 data)
+{
+	struct nvkm_device *device = gpio->subdev.device;
+	u32 inte0 = nvkm_rd32(device, 0x021648);
+	u32 inte1 = nvkm_rd32(device, 0x021654);
+	if (type & NVKM_GPIO_LO)
+		inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+	mask >>= 16;
+	data >>= 16;
+	if (type & NVKM_GPIO_LO)
+		inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte1 = (inte1 & ~mask) | data;
+	nvkm_wr32(device, 0x021648, inte0);
+	nvkm_wr32(device, 0x021654, inte1);
+}
+
+static const struct nvkm_gpio_func
+ga102_gpio = {
+	.lines = 32,
+	.intr_stat = ga102_gpio_intr_stat,
+	.intr_mask = ga102_gpio_intr_mask,
+	.drive = ga102_gpio_drive,
+	.sense = ga102_gpio_sense,
+	.reset = ga102_gpio_reset,
+};
+
+int
+ga102_gpio_new(struct nvkm_device *device, int index, struct nvkm_gpio **pgpio)
+{
+	return nvkm_gpio_new_(&ga102_gpio, device, index, pgpio);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
index 723d0284caef..819703913a00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
@@ -7,6 +7,7 @@ nvkm-y += nvkm/subdev/i2c/g94.o
 nvkm-y += nvkm/subdev/i2c/gf117.o
 nvkm-y += nvkm/subdev/i2c/gf119.o
 nvkm-y += nvkm/subdev/i2c/gk104.o
+nvkm-y += nvkm/subdev/i2c/gk110.o
 nvkm-y += nvkm/subdev/i2c/gm200.o
 
 nvkm-y += nvkm/subdev/i2c/pad.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
index 30b48896965e..f920eabf8628 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
@@ -3,6 +3,13 @@
 #define __NVKM_I2C_AUX_H__
 #include "pad.h"
 
+static inline void
+nvkm_i2c_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	if (i2c->func->aux_autodpcd)
+		i2c->func->aux_autodpcd(i2c, aux, false);
+}
+
 struct nvkm_i2c_aux_func {
 	bool address_only;
 	int  (*xfer)(struct nvkm_i2c_aux *, bool retry, u8 type,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index db7769cb33eb..47068f6f9c55 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -77,7 +77,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		 u8 type, u32 addr, u8 *data, u8 *size)
 {
 	struct g94_i2c_aux *aux = g94_i2c_aux(obj);
-	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+	struct nvkm_i2c *i2c = aux->base.pad->i2c;
+	struct nvkm_device *device = i2c->subdev.device;
 	const u32 base = aux->ch * 0x50;
 	u32 ctrl, stat, timeout, retries = 0;
 	u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		goto out;
 	}
 
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
 	if (!(type & 1)) {
 		memcpy(xbuf, data, *size);
 		for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 			if (!timeout--) {
 				AUX_ERR(&aux->base, "timeout %08x", ctrl);
 				ret = -EIO;
-				goto out;
+				goto out_err;
 			}
 		} while (ctrl & 0x00010000);
 		ret = 0;
@@ -154,7 +157,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		memcpy(data, xbuf, *size);
 		*size = stat & 0x0000001f;
 	}
-
+out_err:
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
 out:
 	g94_i2c_aux_fini(aux);
 	return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index edb6148cbca0..8bd1d442e465 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -33,7 +33,7 @@ static void
 gm200_i2c_aux_fini(struct gm200_i2c_aux *aux)
 {
 	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00310000, 0x00000000);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00710000, 0x00000000);
 }
 
 static int
@@ -54,10 +54,10 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
 			AUX_ERR(&aux->base, "begin idle timeout %08x", ctrl);
 			return -EBUSY;
 		}
-	} while (ctrl & 0x03010000);
+	} while (ctrl & 0x07010000);
 
 	/* set some magic, and wait up to 1ms for it to appear */
-	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00300000, ureq);
+	nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00700000, ureq);
 	timeout = 1000;
 	do {
 		ctrl = nvkm_rd32(device, 0x00d954 + (aux->ch * 0x50));
@@ -67,7 +67,7 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
 			gm200_i2c_aux_fini(aux);
 			return -EBUSY;
 		}
-	} while ((ctrl & 0x03000000) != urep);
+	} while ((ctrl & 0x07000000) != urep);
 
 	return 0;
 }
@@ -77,7 +77,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		   u8 type, u32 addr, u8 *data, u8 *size)
 {
 	struct gm200_i2c_aux *aux = gm200_i2c_aux(obj);
-	struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+	struct nvkm_i2c *i2c = aux->base.pad->i2c;
+	struct nvkm_device *device = i2c->subdev.device;
 	const u32 base = aux->ch * 0x50;
 	u32 ctrl, stat, timeout, retries = 0;
 	u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		goto out;
 	}
 
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
 	if (!(type & 1)) {
 		memcpy(xbuf, data, *size);
 		for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 			if (!timeout--) {
 				AUX_ERR(&aux->base, "timeout %08x", ctrl);
 				ret = -EIO;
-				goto out;
+				goto out_err;
 			}
 		} while (ctrl & 0x00010000);
 		ret = 0;
@@ -155,6 +158,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
 		*size = stat & 0x0000001f;
 	}
 
+out_err:
+	nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
 out:
 	gm200_i2c_aux_fini(aux);
 	return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
new file mode 100644
index 000000000000..8e3bfa1af52a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include "pad.h"
+
+static void
+gk110_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	nvkm_mask(i2c->subdev.device, 0x00e4f8 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
+static const struct nvkm_i2c_func
+gk110_i2c = {
+	.pad_x_new = gf119_i2c_pad_x_new,
+	.pad_s_new = gf119_i2c_pad_s_new,
+	.aux = 4,
+	.aux_stat = gk104_aux_stat,
+	.aux_mask = gk104_aux_mask,
+	.aux_autodpcd = gk110_aux_autodpcd,
+};
+
+int
+gk110_i2c_new(struct nvkm_device *device, int index, struct nvkm_i2c **pi2c)
+{
+	return nvkm_i2c_new_(&gk110_i2c, device, index, pi2c);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
index a23c5f315221..7b2375bff8a9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
@@ -24,6 +24,12 @@
 #include "priv.h"
 #include "pad.h"
 
+static void
+gm200_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+	nvkm_mask(i2c->subdev.device, 0x00d968 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
 static const struct nvkm_i2c_func
 gm200_i2c = {
 	.pad_x_new = gf119_i2c_pad_x_new,
@@ -31,6 +37,7 @@ gm200_i2c = {
 	.aux = 8,
 	.aux_stat = gk104_aux_stat,
 	.aux_mask = gk104_aux_mask,
+	.aux_autodpcd = gm200_aux_autodpcd,
 };
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
index 461016814f4f..44b7bb7d4777 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_I2C_PAD_H__
 #define __NVKM_I2C_PAD_H__
-#include <subdev/i2c.h>
+#include "priv.h"
 
 struct nvkm_i2c_pad {
 	const struct nvkm_i2c_pad_func *func;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
index bd86bc298ebe..e35f6036fcfc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
@@ -23,6 +23,10 @@ struct nvkm_i2c_func {
 	/* mask on/off interrupt types for a given set of auxch
 	 */
 	void (*aux_mask)(struct nvkm_i2c *, u32, u32, u32);
+
+	/* enable/disable HW-initiated DPCD reads
+	 */
+	void (*aux_autodpcd)(struct nvkm_i2c *, int aux, bool enable);
 };
 
 void g94_aux_stat(struct nvkm_i2c *, u32 *, u32 *, u32 *, u32 *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
index 2340040942c9..1115376bc85f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0400));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@ gf100_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0400));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@ gf100_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0400));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0400));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0400), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@ gf100_ibus_intr(struct nvkm_subdev *ibus)
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x121c4c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x121c4c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
index f3915f85838e..22e487b493ad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "priv.h"
+#include <subdev/timer.h>
 
 static void
 gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0800));
 	nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x122128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -42,7 +42,6 @@ gk104_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0800));
 	nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x124128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 static void
@@ -53,7 +52,6 @@ gk104_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
 	u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0800));
 	u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0800));
 	nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
-	nvkm_mask(device, 0x128128 + (i * 0x0800), 0x00000200, 0x00000000);
 }
 
 void
@@ -90,6 +88,12 @@ gk104_ibus_intr(struct nvkm_subdev *ibus)
 			intr1 &= ~stat;
 		}
 	}
+
+	nvkm_mask(device, 0x12004c, 0x0000003f, 0x00000002);
+	nvkm_msec(device, 2000,
+		if (!(nvkm_rd32(device, 0x12004c) & 0x0000003f))
+			break;
+	);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
index 2585ef07532a..ac2b34e9ac6a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
@@ -14,3 +14,4 @@ nvkm-y += nvkm/subdev/mc/gk20a.o
 nvkm-y += nvkm/subdev/mc/gp100.o
 nvkm-y += nvkm/subdev/mc/gp10b.o
 nvkm-y += nvkm/subdev/mc/tu102.o
+nvkm-y += nvkm/subdev/mc/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
new file mode 100644
index 000000000000..967eb3af11eb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga100_mc_intr_unarm(struct nvkm_mc *mc)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81610, 0x00000004);
+}
+
+static void
+ga100_mc_intr_rearm(struct nvkm_mc *mc)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81608, 0x00000004);
+}
+
+static void
+ga100_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 intr)
+{
+	nvkm_wr32(mc->subdev.device, 0xb81210,          mask & intr );
+	nvkm_wr32(mc->subdev.device, 0xb81410, mask & ~(mask & intr));
+}
+
+static u32
+ga100_mc_intr_stat(struct nvkm_mc *mc)
+{
+	u32 intr_top = nvkm_rd32(mc->subdev.device, 0xb81600), intr = 0x00000000;
+	if (intr_top & 0x00000004)
+		intr = nvkm_mask(mc->subdev.device, 0xb81010, 0x00000000, 0x00000000);
+	return intr;
+}
+
+static void
+ga100_mc_init(struct nvkm_mc *mc)
+{
+	nv50_mc_init(mc);
+	nvkm_wr32(mc->subdev.device, 0xb81210, 0xffffffff);
+}
+
+static const struct nvkm_mc_func
+ga100_mc = {
+	.init = ga100_mc_init,
+	.intr = gp100_mc_intr,
+	.intr_unarm = ga100_mc_intr_unarm,
+	.intr_rearm = ga100_mc_intr_rearm,
+	.intr_mask = ga100_mc_intr_mask,
+	.intr_stat = ga100_mc_intr_stat,
+	.reset = gk104_mc_reset,
+};
+
+int
+ga100_mc_new(struct nvkm_device *device, int index, struct nvkm_mc **pmc)
+{
+	return nvkm_mc_new_(&ga100_mc, device, index, pmc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
index de91e9a26172..6d5212ae2fd5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
@@ -316,9 +316,9 @@ nvkm_mmu_vram(struct nvkm_mmu *mmu)
 {
 	struct nvkm_device *device = mmu->subdev.device;
 	struct nvkm_mm *mm = &device->fb->ram->vram;
-	const u32 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
-	const u32 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
-	const u32 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
+	const u64 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
+	const u64 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
+	const u64 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
 	u8 type = NVKM_MEM_KIND * !!mmu->func->kind;
 	u8 heap = NVKM_MEM_VRAM;
 	int heapM, heapN, heapU;
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index a00b7ab9c14c..74bf1c84b637 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -66,7 +66,7 @@ static struct ttm_pool_type global_uncached[MAX_ORDER];
 static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
 static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
 
-static spinlock_t shrinker_lock;
+static struct mutex shrinker_lock;
 static struct list_head shrinker_list;
 static struct shrinker mm_shrinker;
 
@@ -79,12 +79,13 @@ static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
 	struct page *p;
 	void *vaddr;
 
-	if (order) {
-		gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY |
+	/* Don't set the __GFP_COMP flag for higher order allocations.
+	 * Mapping pages directly into an userspace process and calling
+	 * put_page() on a TTM allocated page is illegal.
+	 */
+	if (order)
+		gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN |
 			__GFP_KSWAPD_RECLAIM;
-		gfp_flags &= ~__GFP_MOVABLE;
-		gfp_flags &= ~__GFP_COMP;
-	}
 
 	if (!pool->use_dma_alloc) {
 		p = alloc_pages(gfp_flags, order);
@@ -190,7 +191,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order,
 		size_t size = (1ULL << order) * PAGE_SIZE;
 
 		addr = dma_map_page(pool->dev, p, 0, size, DMA_BIDIRECTIONAL);
-		if (dma_mapping_error(pool->dev, **dma_addr))
+		if (dma_mapping_error(pool->dev, addr))
 			return -EFAULT;
 	}
 
@@ -249,9 +250,9 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
 	spin_lock_init(&pt->lock);
 	INIT_LIST_HEAD(&pt->pages);
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	list_add_tail(&pt->shrinker_list, &shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 }
 
 /* Remove a pool_type from the global shrinker list and free all pages */
@@ -259,9 +260,9 @@ static void ttm_pool_type_fini(struct ttm_pool_type *pt)
 {
 	struct page *p, *tmp;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	list_del(&pt->shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	list_for_each_entry_safe(p, tmp, &pt->pages, lru)
 		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
@@ -302,7 +303,7 @@ static unsigned int ttm_pool_shrink(void)
 	unsigned int num_freed;
 	struct page *p;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 	pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
 
 	p = ttm_pool_type_take(pt);
@@ -314,7 +315,7 @@ static unsigned int ttm_pool_shrink(void)
 	}
 
 	list_move_tail(&pt->shrinker_list, &shrinker_list);
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	return num_freed;
 }
@@ -564,7 +565,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 {
 	unsigned int i;
 
-	spin_lock(&shrinker_lock);
+	mutex_lock(&shrinker_lock);
 
 	seq_puts(m, "\t ");
 	for (i = 0; i < MAX_ORDER; ++i)
@@ -600,7 +601,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
 	seq_printf(m, "\ntotal\t: %8lu of %8lu\n",
 		   atomic_long_read(&allocated_pages), page_pool_size);
 
-	spin_unlock(&shrinker_lock);
+	mutex_unlock(&shrinker_lock);
 
 	return 0;
 }
@@ -644,7 +645,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	if (!page_pool_size)
 		page_pool_size = num_pages;
 
-	spin_lock_init(&shrinker_lock);
+	mutex_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
 	for (i = 0; i < MAX_ORDER; ++i) {
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 555106220578..98cab0bbe92d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1267,6 +1267,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 	card->dai_link = dai_link;
 	card->num_links = 1;
 	card->name = vc4_hdmi->variant->card_name;
+	card->driver_name = "vc4-hdmi";
 	card->dev = dev;
 	card->owner = THIS_MODULE;
 
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index cccd341e5d67..3b722252d1fb 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -620,11 +620,11 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	 * for now we just allocate globally.
 	 */
 	if (!hvs->hvs5)
-		/* 96kB */
-		drm_mm_init(&hvs->lbm_mm, 0, 96 * 1024);
+		/* 48k words of 2x12-bit pixels */
+		drm_mm_init(&hvs->lbm_mm, 0, 48 * 1024);
 	else
-		/* 70k words */
-		drm_mm_init(&hvs->lbm_mm, 0, 70 * 2 * 1024);
+		/* 60k words of 4x12-bit pixels */
+		drm_mm_init(&hvs->lbm_mm, 0, 60 * 1024);
 
 	/* Upload filter kernels.  We only have the one for now, so we
 	 * keep it around for the lifetime of the driver.
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 6b39cc2ca18d..5612cab55227 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -437,6 +437,7 @@ static void vc4_write_ppf(struct vc4_plane_state *vc4_state, u32 src, u32 dst)
 static u32 vc4_lbm_size(struct drm_plane_state *state)
 {
 	struct vc4_plane_state *vc4_state = to_vc4_plane_state(state);
+	struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev);
 	u32 pix_per_line;
 	u32 lbm;
 
@@ -472,7 +473,11 @@ static u32 vc4_lbm_size(struct drm_plane_state *state)
 		lbm = pix_per_line * 16;
 	}
 
-	lbm = roundup(lbm, 32);
+	/* Align it to 64 or 128 (hvs5) bytes */
+	lbm = roundup(lbm, vc4->hvs->hvs5 ? 128 : 64);
+
+	/* Each "word" of the LBM memory contains 2 or 4 (hvs5) pixels */
+	lbm /= vc4->hvs->hvs5 ? 4 : 2;
 
 	return lbm;
 }
@@ -912,9 +917,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		if (!vc4_state->is_unity) {
 			vc4_dlist_write(vc4_state,
 					VC4_SET_FIELD(vc4_state->crtc_w,
-						      SCALER_POS1_SCL_WIDTH) |
+						      SCALER5_POS1_SCL_WIDTH) |
 					VC4_SET_FIELD(vc4_state->crtc_h,
-						      SCALER_POS1_SCL_HEIGHT));
+						      SCALER5_POS1_SCL_HEIGHT));
 		}
 
 		/* Position Word 2: Source Image Size */