Backmerge tag 'v5.14-rc3' into drm-next

Linux 5.14-rc3

Daniel said we should pull the nouveau fix from fixes in here, probably
a good plan.

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

42 files changed, 450 insertions, 788 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c0316eaba547..8ac6eb9f1fdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -619,6 +619,13 @@ struct amdgpu_video_codec_info {
 	u32 max_level;
 };
 
+#define codec_info_build(type, width, height, level) \
+			 .codec_type = type,\
+			 .max_width = width,\
+			 .max_height = height,\
+			 .max_pixels_per_frame = height * width,\
+			 .max_level = level,
+
 struct amdgpu_video_codecs {
 	const u32 codec_count;
 	const struct amdgpu_video_codec_info *codec_array;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index a959624d576b..2bd13fc2541a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1190,6 +1190,10 @@ static const struct pci_device_id pciidlist[] = {
 	/* Van Gogh */
 	{0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU},
 
+	/* Yellow Carp */
+	{0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+	{0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+
 	/* Navy_Flounder */
 	{0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 	{0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index a25160797b61..611fd10c3410 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -255,6 +255,15 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str
 	if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
 		return -EPERM;
 
+	/* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings
+	 * for debugger access to invisible VRAM. Should have used MAP_SHARED
+	 * instead. Clearing VM_MAYWRITE prevents the mapping from ever
+	 * becoming writable and makes is_cow_mapping(vm_flags) false.
+	 */
+	if (is_cow_mapping(vma->vm_flags) &&
+	    !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
+		vma->vm_flags &= ~VM_MAYWRITE;
+
 	return drm_gem_ttm_mmap(obj, vma);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f5e9c022960b..a64b2c706090 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3300,6 +3300,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000)
 };
@@ -3379,6 +3380,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1_Vangogh, 0xffffffff, 0x00070103),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQG_CONFIG, 0x000017ff, 0x00001000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00400000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
@@ -3445,6 +3447,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x01030000, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x03a00000, 0x00a00000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG,  0x00000020, 0x00000020)
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 94a2c0742ee5..94d029dbf30d 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -64,32 +64,13 @@
 #include "smuio_v11_0.h"
 #include "smuio_v11_0_6.h"
 
-#define codec_info_build(type, width, height, level) \
-			 .codec_type = type,\
-			 .max_width = width,\
-			 .max_height = height,\
-			 .max_pixels_per_frame = height * width,\
-			 .max_level = level,
-
 static const struct amd_ip_funcs nv_common_ip_funcs;
 
 /* Navi */
 static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_encode =
@@ -101,55 +82,13 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode =
 /* Navi1x */
 static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_decode =
@@ -161,62 +100,14 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode =
 /* Sienna Cichlid */
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs sc_video_codecs_decode =
@@ -228,80 +119,20 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode =
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 8192 * 4352,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codecs sriov_sc_video_codecs_encode =
@@ -333,6 +164,19 @@ static const struct amdgpu_video_codecs bg_video_codecs_encode = {
 	.codec_array = NULL,
 };
 
+/* Yellow Carp*/
+static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+};
+
+static const struct amdgpu_video_codecs yc_video_codecs_decode = {
+	.codec_count = ARRAY_SIZE(yc_video_codecs_decode_array),
+	.codec_array = yc_video_codecs_decode_array,
+};
+
 static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 				 const struct amdgpu_video_codecs **codecs)
 {
@@ -353,12 +197,17 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 	case CHIP_NAVY_FLOUNDER:
 	case CHIP_DIMGREY_CAVEFISH:
 	case CHIP_VANGOGH:
-	case CHIP_YELLOW_CARP:
 		if (encode)
 			*codecs = &nv_video_codecs_encode;
 		else
 			*codecs = &sc_video_codecs_decode;
 		return 0;
+	case CHIP_YELLOW_CARP:
+		if (encode)
+			*codecs = &nv_video_codecs_encode;
+		else
+			*codecs = &yc_video_codecs_decode;
+		return 0;
 	case CHIP_BEIGE_GOBY:
 		if (encode)
 			*codecs = &bg_video_codecs_encode;
@@ -1387,7 +1236,10 @@ static int nv_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
-		adev->external_rev_id = adev->rev_id + 0x01;
+		if (adev->pdev->device == 0x1681)
+			adev->external_rev_id = adev->rev_id + 0x19;
+		else
+			adev->external_rev_id = adev->rev_id + 0x01;
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index b02436401d46..b7d350be8050 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -88,20 +88,8 @@
 /* Vega, Raven, Arcturus */
 static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 2304,
-		.max_pixels_per_frame = 4096 * 2304,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_encode =
@@ -113,48 +101,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode =
 /* Vega */
 static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_decode =
@@ -166,55 +118,13 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode =
 /* Raven */
 static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs rv_video_codecs_decode =
@@ -226,55 +136,13 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode =
 /* Renoir, Arcturus */
 static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
 {
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 3,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 5,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 52,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 4,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 186,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
-	{
-		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
-		.max_width = 8192,
-		.max_height = 4352,
-		.max_pixels_per_frame = 4096 * 4096,
-		.max_level = 0,
-	},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs rn_video_codecs_decode =
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 513676a6f52b..af7004b770ae 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
@@ -190,6 +190,10 @@ void dcn3_init_clocks(struct clk_mgr *clk_mgr_base)
 			&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
 			&num_levels);
 
+	/* SOCCLK */
+	dcn3_init_single_clock(clk_mgr, PPCLK_SOCCLK,
+					&clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz,
+					&num_levels);
 	// DPREFCLK ???
 
 	/* DISPCLK */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index 7b7d884d58be..4a4894e9d9c9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -48,6 +48,21 @@
 
 #include "dc_dmub_srv.h"
 
+#include "yellow_carp_offset.h"
+
+#define regCLK1_CLK_PLL_REQ			0x0237
+#define regCLK1_CLK_PLL_REQ_BASE_IDX		0
+
+#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT	0x0
+#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT	0xc
+#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT	0x10
+#define CLK1_CLK_PLL_REQ__FbMult_int_MASK	0x000001FFL
+#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
+#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
+
+#define REG(reg_name) \
+	(CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
+
 #define TO_CLK_MGR_DCN31(clk_mgr)\
 	container_of(clk_mgr, struct clk_mgr_dcn31, base)
 
@@ -124,10 +139,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
 	 * also if safe to lower is false, we just go in the higher state
 	 */
 	if (safe_to_lower) {
-		if (new_clocks->z9_support == DCN_Z9_SUPPORT_ALLOW &&
-				new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+		if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_ALLOW &&
+				new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
 			dcn31_smu_set_Z9_support(clk_mgr, true);
-			clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+			clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
 		}
 
 		if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
@@ -148,10 +163,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
 			}
 		}
 	} else {
-		if (new_clocks->z9_support == DCN_Z9_SUPPORT_DISALLOW &&
-				new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+		if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW &&
+				new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
 			dcn31_smu_set_Z9_support(clk_mgr, false);
-			clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+			clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
 		}
 
 		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
@@ -229,7 +244,32 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
 
 static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr)
 {
-	return 0;
+	/* get FbMult value */
+	struct fixed31_32 pll_req;
+	unsigned int fbmult_frac_val = 0;
+	unsigned int fbmult_int_val = 0;
+
+	/*
+	 * Register value of fbmult is in 8.16 format, we are converting to 31.32
+	 * to leverage the fix point operations available in driver
+	 */
+
+	REG_GET(CLK1_CLK_PLL_REQ, FbMult_frac, &fbmult_frac_val); /* 16 bit fractional part*/
+	REG_GET(CLK1_CLK_PLL_REQ, FbMult_int, &fbmult_int_val); /* 8 bit integer part */
+
+	pll_req = dc_fixpt_from_int(fbmult_int_val);
+
+	/*
+	 * since fractional part is only 16 bit in register definition but is 32 bit
+	 * in our fix point definiton, need to shift left by 16 to obtain correct value
+	 */
+	pll_req.value |= fbmult_frac_val << 16;
+
+	/* multiply by REFCLK period */
+	pll_req = dc_fixpt_mul_int(pll_req, clk_mgr->dfs_ref_freq_khz);
+
+	/* integer part is now VCO frequency in kHz */
+	return dc_fixpt_floor(pll_req);
 }
 
 static void dcn31_enable_pme_wa(struct clk_mgr *clk_mgr_base)
@@ -246,7 +286,7 @@ static void dcn31_init_clocks(struct clk_mgr *clk_mgr)
 	clk_mgr->clks.p_state_change_support = true;
 	clk_mgr->clks.prev_p_state_change_support = true;
 	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
-	clk_mgr->clks.z9_support = DCN_Z9_SUPPORT_UNKNOWN;
+	clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
 }
 
 static bool dcn31_are_clock_states_equal(struct dc_clocks *a,
@@ -260,7 +300,7 @@ static bool dcn31_are_clock_states_equal(struct dc_clocks *a,
 		return false;
 	else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz)
 		return false;
-	else if (a->z9_support != b->z9_support)
+	else if (a->zstate_support != b->zstate_support)
 		return false;
 	else if (a->dtbclk_en != b->dtbclk_en)
 		return false;
@@ -592,6 +632,7 @@ void dcn31_clk_mgr_construct(
 	clk_mgr->base.dprefclk_ss_percentage = 0;
 	clk_mgr->base.dprefclk_ss_divider = 1000;
 	clk_mgr->base.ss_on_dprefclk = false;
+	clk_mgr->base.dfs_ref_freq_khz = 48000;
 
 	clk_mgr->smu_wm_set.wm_set = (struct dcn31_watermarks *)dm_helpers_allocate_gpu_mem(
 				clk_mgr->base.base.ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
index cc21cf75eafd..f8f100535526 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
@@ -27,60 +27,6 @@
 #define __DCN31_CLK_MGR_H__
 #include "clk_mgr_internal.h"
 
-//CLK1_CLK_PLL_REQ
-#ifndef CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT                                                                   0x0
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT                                                                  0xc
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT                                                                  0x10
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int_MASK                                                                     0x000001FFL
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv_MASK                                                                    0x0000F000L
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac_MASK                                                                    0xFFFF0000L
-//CLK1_CLK0_DFS_CNTL
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER__SHIFT                                                               0x0
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER_MASK                                                                 0x0000007FL
-/*DPREF clock related*/
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT                                                               0x0
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK                                                                 0x0000007FL
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT                                                               0x0
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK                                                                 0x0000007FL
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT                                                               0x0
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK                                                                 0x0000007FL
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT                                                               0x0
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK                                                                 0x0000007FL
-
-//CLK3_0_CLK3_CLK_PLL_REQ
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int__SHIFT                                                            0x0
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv__SHIFT                                                           0xc
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac__SHIFT                                                           0x10
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int_MASK                                                              0x000001FFL
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv_MASK                                                             0x0000F000L
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac_MASK                                                             0xFFFF0000L
-
-#define mmCLK0_CLK3_DFS_CNTL                            0x16C60
-#define mmCLK00_CLK0_CLK3_DFS_CNTL                      0x16C60
-#define mmCLK01_CLK0_CLK3_DFS_CNTL                      0x16E60
-#define mmCLK02_CLK0_CLK3_DFS_CNTL                      0x17060
-#define mmCLK03_CLK0_CLK3_DFS_CNTL                      0x17260
-
-#define mmCLK0_CLK_PLL_REQ                              0x16C10
-#define mmCLK00_CLK0_CLK_PLL_REQ                        0x16C10
-#define mmCLK01_CLK0_CLK_PLL_REQ                        0x16E10
-#define mmCLK02_CLK0_CLK_PLL_REQ                        0x17010
-#define mmCLK03_CLK0_CLK_PLL_REQ                        0x17210
-
-#define mmCLK1_CLK_PLL_REQ                              0x1B00D
-#define mmCLK10_CLK1_CLK_PLL_REQ                        0x1B00D
-#define mmCLK11_CLK1_CLK_PLL_REQ                        0x1B20D
-#define mmCLK12_CLK1_CLK_PLL_REQ                        0x1B40D
-#define mmCLK13_CLK1_CLK_PLL_REQ                        0x1B60D
-
-#define mmCLK2_CLK_PLL_REQ                              0x17E0D
-
-/*AMCLK*/
-#define mmCLK11_CLK1_CLK0_DFS_CNTL                      0x1B23F
-#define mmCLK11_CLK1_CLK_PLL_REQ                        0x1B20D
-#endif
-
 struct dcn31_watermarks;
 
 struct dcn31_smu_watermark_set {
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 6da226bf11d5..9fb8c46dc606 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
@@ -1820,8 +1820,7 @@ bool perform_link_training_with_retries(
 					 */
 					panel_mode = DP_PANEL_MODE_DEFAULT;
 				}
-			} else
-				panel_mode = DP_PANEL_MODE_DEFAULT;
+			}
 		}
 #endif
 
@@ -4650,7 +4649,10 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link)
 		}
 	}
 
-	if (link->dpcd_caps.panel_mode_edp) {
+	if (link->dpcd_caps.panel_mode_edp &&
+		(link->connector_signal == SIGNAL_TYPE_EDP ||
+		 (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+		  link->is_internal_display))) {
 		return DP_PANEL_MODE_EDP;
 	}
 
@@ -4914,9 +4916,7 @@ bool dc_link_set_default_brightness_aux(struct dc_link *link)
 {
 	uint32_t default_backlight;
 
-	if (link &&
-		(link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 ||
-		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) {
+	if (link && link->dpcd_sink_ext_caps.bits.oled == 1) {
 		if (!dc_link_read_default_bl_aux(link, &default_backlight))
 			default_backlight = 150000;
 		// if < 5 nits or > 5000, it might be wrong readback
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index a6a67244a322..1596f6b7fed7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1062,7 +1062,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	 * so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3
 	 * did not show such problems, so this seems to be the exception.
 	 */
-	if (plane_state->ctx->dce_version != DCE_VERSION_11_0)
+	if (plane_state->ctx->dce_version > DCE_VERSION_11_0)
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
 	else
 		pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 45640f1c26c4..8dcea8ff5c5a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -354,10 +354,10 @@ enum dcn_pwr_state {
 };
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-enum dcn_z9_support_state {
-	DCN_Z9_SUPPORT_UNKNOWN,
-	DCN_Z9_SUPPORT_ALLOW,
-	DCN_Z9_SUPPORT_DISALLOW,
+enum dcn_zstate_support_state {
+	DCN_ZSTATE_SUPPORT_UNKNOWN,
+	DCN_ZSTATE_SUPPORT_ALLOW,
+	DCN_ZSTATE_SUPPORT_DISALLOW,
 };
 #endif
 /*
@@ -378,7 +378,7 @@ struct dc_clocks {
 	int dramclk_khz;
 	bool p_state_change_support;
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	enum dcn_z9_support_state z9_support;
+	enum dcn_zstate_support_state zstate_support;
 	bool dtbclk_en;
 #endif
 	enum dcn_pwr_state pwr_state;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index df6539e4c730..0464a8f3db3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -636,6 +636,7 @@ struct dce_hwseq_registers {
 	uint32_t ODM_MEM_PWR_CTRL3;
 	uint32_t DMU_MEM_PWR_CNTL;
 	uint32_t MMHUBBUB_MEM_PWR_CNTL;
+	uint32_t DCHUBBUB_ARB_HOSTVM_CNTL;
 };
  /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -1110,7 +1111,8 @@ struct dce_hwseq_registers {
 	type DOMAIN_POWER_FORCEON;\
 	type DOMAIN_POWER_GATE;\
 	type DOMAIN_PGFSM_PWR_STATUS;\
-	type HPO_HDMISTREAMCLK_G_GATE_DIS;
+	type HPO_HDMISTREAMCLK_G_GATE_DIS;\
+	type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index 673b93f4fea5..cb9767ddf93d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -217,6 +217,8 @@ static void dpp1_dscl_set_lb(
 	const struct line_buffer_params *lb_params,
 	enum lb_memory_config mem_size_config)
 {
+	uint32_t max_partitions = 63; /* Currently hardcoded on all ASICs before DCN 3.2 */
+
 	/* LB */
 	if (dpp->base.caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
 		/* DSCL caps: pixel data processed in fixed format */
@@ -239,9 +241,12 @@ static void dpp1_dscl_set_lb(
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
 
+	if (dpp->base.caps->max_lb_partitions == 31)
+		max_partitions = 31;
+
 	REG_SET_2(LB_MEMORY_CTRL, 0,
 		MEMORY_CONFIG, mem_size_config,
-		LB_MAX_PARTITIONS, 63);
+		LB_MAX_PARTITIONS, max_partitions);
 }
 
 static const uint16_t *dpp1_dscl_get_filter_coeffs_64p(int taps, struct fixed31_32 ratio)
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 1b05a37b674d..b173fa3653b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2093,8 +2093,10 @@ int dcn20_populate_dml_pipes_from_context(
 				- timing->v_border_bottom;
 		pipes[pipe_cnt].pipe.dest.htotal = timing->h_total;
 		pipes[pipe_cnt].pipe.dest.vtotal = v_total;
-		pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable;
-		pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable;
+		pipes[pipe_cnt].pipe.dest.hactive =
+			timing->h_addressable + timing->h_border_left + timing->h_border_right;
+		pipes[pipe_cnt].pipe.dest.vactive =
+			timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
 		pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE;
 		pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0;
 		if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
@@ -3079,6 +3081,37 @@ static bool is_dtbclk_required(struct dc *dc, struct dc_state *context)
 	return false;
 }
 
+static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+	int plane_count;
+	int i;
+
+	plane_count = 0;
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].plane_state)
+			plane_count++;
+	}
+
+	/*
+	 * Zstate is allowed in following scenarios:
+	 * 	1. Single eDP with PSR enabled
+	 * 	2. 0 planes (No memory requests)
+	 * 	3. Single eDP without PSR but > 5ms stutter period
+	 */
+	if (plane_count == 0)
+		return DCN_ZSTATE_SUPPORT_ALLOW;
+	else if (context->stream_count == 1 &&  context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+		struct dc_link *link = context->streams[0]->sink->link;
+
+		if ((link->link_index == 0 && link->psr_settings.psr_feature_enabled)
+				|| context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
+			return DCN_ZSTATE_SUPPORT_ALLOW;
+		else
+			return DCN_ZSTATE_SUPPORT_DISALLOW;
+	} else
+		return DCN_ZSTATE_SUPPORT_DISALLOW;
+}
+
 void dcn20_calculate_dlg_params(
 		struct dc *dc, struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
@@ -3086,7 +3119,6 @@ void dcn20_calculate_dlg_params(
 		int vlevel)
 {
 	int i, pipe_idx;
-	int plane_count;
 
 	/* Writeback MCIF_WB arbitration parameters */
 	dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt);
@@ -3102,17 +3134,7 @@ void dcn20_calculate_dlg_params(
 							!= dm_dram_clock_change_unsupported;
 	context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
 
-	context->bw_ctx.bw.dcn.clk.z9_support = (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) ?
-			DCN_Z9_SUPPORT_ALLOW : DCN_Z9_SUPPORT_DISALLOW;
-
-	plane_count = 0;
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].plane_state)
-			plane_count++;
-	}
-
-	if (plane_count == 0)
-		context->bw_ctx.bw.dcn.clk.z9_support = DCN_Z9_SUPPORT_ALLOW;
+	context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context);
 
 	context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
index 2140b75540cf..23a52d47e61c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
@@ -383,13 +383,6 @@ bool dpp3_get_optimal_number_of_taps(
 	int min_taps_y, min_taps_c;
 	enum lb_memory_config lb_config;
 
-	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
-	if (scl_data->viewport.width  != scl_data->h_active &&
-		scl_data->viewport.height != scl_data->v_active &&
-		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
-		scl_data->format == PIXEL_FORMAT_FP16)
-		return false;
-
 	if (scl_data->viewport.width > scl_data->h_active &&
 		dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
 		scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
@@ -1440,15 +1433,6 @@ bool dpp3_construct(
 	dpp->tf_shift = tf_shift;
 	dpp->tf_mask = tf_mask;
 
-	dpp->lb_pixel_depth_supported =
-		LB_PIXEL_DEPTH_18BPP |
-		LB_PIXEL_DEPTH_24BPP |
-		LB_PIXEL_DEPTH_30BPP |
-		LB_PIXEL_DEPTH_36BPP;
-
-	dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
-	dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/
-
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
index 3fa86cd090a0..ac644ae6b9f2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
@@ -154,6 +154,7 @@
 	SRI(COLOR_KEYER_BLUE, CNVC_CFG, id), \
 	SRI(CURSOR_CONTROL, CURSOR0_, id),\
 	SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\
+	SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
 	SRI(DSCL_MEM_PWR_CTRL, DSCL, id)
 
 #define DPP_REG_LIST_DCN30(id)\
@@ -163,8 +164,6 @@
 	SRI(CM_SHAPER_LUT_DATA, CM, id),\
 	SRI(CM_MEM_PWR_CTRL2, CM, id), \
 	SRI(CM_MEM_PWR_STATUS2, CM, id), \
-	SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
-	SRI(DSCL_MEM_PWR_CTRL, DSCL, id), \
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_B, CM, id),\
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_G, CM, id),\
 	SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_R, CM, id),\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
index 16a75ba0ca82..7d3ff5d44402 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
@@ -1398,11 +1398,18 @@ void dcn302_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 			dcn3_02_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
 			dcn3_02_soc.clock_limits[i].dppclk_mhz  = max_dppclk_mhz;
 			dcn3_02_soc.clock_limits[i].phyclk_mhz  = max_phyclk_mhz;
-			dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[0].dtbclk_mhz;
+			/* Populate from bw_params for DTBCLK, SOCCLK */
+			if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+				dcn3_02_soc.clock_limits[i].dtbclk_mhz  = dcn3_02_soc.clock_limits[i-1].dtbclk_mhz;
+			else
+				dcn3_02_soc.clock_limits[i].dtbclk_mhz  = bw_params->clk_table.entries[i].dtbclk_mhz;
+			if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+				dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz;
+			else
+				dcn3_02_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
 			/* These clocks cannot come from bw_params, always fill from dcn3_02_soc[1] */
-			/* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+			/* FCLK, PHYCLK_D18, DSCCLK */
 			dcn3_02_soc.clock_limits[i].phyclk_d18_mhz = dcn3_02_soc.clock_limits[0].phyclk_d18_mhz;
-			dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[0].socclk_mhz;
 			dcn3_02_soc.clock_limits[i].dscclk_mhz = dcn3_02_soc.clock_limits[0].dscclk_mhz;
 		}
 		/* re-init DML with updated bb */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 34b89464ae02..833ab13fa834 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -1326,11 +1326,18 @@ void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 			dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
 			dcn3_03_soc.clock_limits[i].dppclk_mhz  = max_dppclk_mhz;
 			dcn3_03_soc.clock_limits[i].phyclk_mhz  = max_phyclk_mhz;
-			dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[0].dtbclk_mhz;
+			/* Populate from bw_params for DTBCLK, SOCCLK */
+			if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+				dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz;
+			else
+				dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+			if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+				dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz;
+			else
+				dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
 			/* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */
-			/* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+			/* FCLK, PHYCLK_D18, DSCCLK */
 			dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz;
-			dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[0].socclk_mhz;
 			dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz;
 		}
 		/* re-init DML with updated bb */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 836864a5a5dc..6ac6faf0c533 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -47,6 +47,7 @@
 #include "dce/dmub_outbox.h"
 #include "dc_link_dp.h"
 #include "inc/link_dpcd.h"
+#include "dcn10/dcn10_hw_sequencer.h"
 
 #define DC_LOGGER_INIT(logger)
 
@@ -594,3 +595,20 @@ bool dcn31_is_abm_supported(struct dc *dc,
 	}
 	return false;
 }
+
+static void apply_riommu_invalidation_wa(struct dc *dc)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+
+	if (!hws->wa.early_riommu_invalidation)
+		return;
+
+	REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, 0);
+}
+
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context)
+{
+	dcn10_init_pipes(dc, context);
+	apply_riommu_invalidation_wa(dc);
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
index ff72f0fdd5be..40dfebe78fdd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
@@ -52,5 +52,6 @@ void dcn31_reset_hw_ctx_wrap(
 		struct dc_state *context);
 bool dcn31_is_abm_supported(struct dc *dc,
 		struct dc_state *context, struct dc_stream_state *stream);
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context);
 
 #endif /* __DC_HWSS_DCN31_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index e3048f8827d2..aaf2dbd095fe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -93,7 +93,6 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
 	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
 	.calc_vupdate_position = dcn10_calc_vupdate_position,
-	.apply_idle_power_optimizations = dcn30_apply_idle_power_optimizations,
 	.set_backlight_level = dcn21_set_backlight_level,
 	.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
 	.set_pipe = dcn21_set_pipe,
@@ -104,7 +103,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 };
 
 static const struct hwseq_private_funcs dcn31_private_funcs = {
-	.init_pipes = dcn10_init_pipes,
+	.init_pipes = dcn31_init_pipes,
 	.update_plane_addr = dcn20_update_plane_addr,
 	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
 	.update_mpcc = dcn20_update_mpcc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index c67bc9544f5d..38c010afade1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -220,6 +220,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
 	.sr_exit_z8_time_us = 402.0,
 	.sr_enter_plus_exit_z8_time_us = 520.0,
 	.writeback_latency_us = 12.0,
+	.dram_channel_width_bytes = 4,
 	.round_trip_ping_latency_dcfclk_cycles = 106,
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
@@ -741,6 +742,7 @@ static const struct dccg_mask dccg_mask = {
 
 #define HWSEQ_DCN31_REG_LIST()\
 	SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \
+	SR(DCHUBBUB_ARB_HOSTVM_CNTL), \
 	SR(DIO_MEM_PWR_CTRL), \
 	SR(ODM_MEM_PWR_CTRL3), \
 	SR(DMU_MEM_PWR_CNTL), \
@@ -801,6 +803,7 @@ static const struct dce_hwseq_registers hwseq_reg = {
 #define HWSEQ_DCN31_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
+	HWS_SF(, DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, mask_sh), \
 	HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
 	HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, mask_sh), \
 	HWS_SF(, DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
@@ -1299,6 +1302,7 @@ static struct dce_hwseq *dcn31_hwseq_create(
 		hws->regs = &hwseq_reg;
 		hws->shifts = &hwseq_shift;
 		hws->masks = &hwseq_mask;
+		hws->wa.early_riommu_invalidation = true;
 	}
 	return hws;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index c26e742e8137..d25a7d38d21f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -4889,7 +4889,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 			} while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true)
 					&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0]
-						|| mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode));
+						|| mode_lib->vba.NextPrefetchMode <= mode_lib->vba.MaxPrefetchMode));
 
 			if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) {
 				mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0];
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
index 2a0db2b03047..9ac9d5e8df8b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
@@ -289,6 +289,9 @@ struct dpp_caps {
 	/* DSCL processing pixel data in fixed or float format */
 	enum dscl_data_processing_format dscl_data_proc_format;
 
+	/* max LB partitions */
+	unsigned int max_lb_partitions;
+
 	/* Calculates the number of partitions in the line buffer.
 	 * The implementation of this function is overloaded for
 	 * different versions of DSCL LB.
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
index f7f7e4fff0c2..082549f75978 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -41,6 +41,7 @@ struct dce_hwseq_wa {
 	bool DEGVIDCN10_254;
 	bool DEGVIDCN21;
 	bool disallow_self_refresh_during_multi_plane_transition;
+	bool early_riommu_invalidation;
 };
 
 struct hwseq_wa_state {
diff --git a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
index 610266088ff1..35fa0d8e92dd 100644
--- a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
@@ -101,7 +101,8 @@
 #define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow  0x41
 
 #define PPSMC_MSG_GfxDriverResetRecovery	0x42
-#define PPSMC_Message_Count			0x43
+#define PPSMC_MSG_BoardPowerCalibration 	0x43
+#define PPSMC_Message_Count			0x44
 
 //PPSMC Reset Types
 #define PPSMC_RESET_TYPE_WARM_RESET              0x00
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 89a16dcd0fff..1d3765b873df 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -225,7 +225,8 @@
 	__SMU_DUMMY_MAP(DisableDeterminism),		\
 	__SMU_DUMMY_MAP(SetUclkDpmMode),		\
 	__SMU_DUMMY_MAP(LightSBR),			\
-	__SMU_DUMMY_MAP(GfxDriverResetRecovery),
+	__SMU_DUMMY_MAP(GfxDriverResetRecovery),	\
+	__SMU_DUMMY_MAP(BoardPowerCalibration),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
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 1962a5877191..f61b5c914a3d 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -34,7 +34,7 @@
 #define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE
 #define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03
 #define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF
-#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0x9
+#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0xD
 
 /* MP Apertures */
 #define MP0_Public			0x03800000
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 9316a726195c..cb5485cf243f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -134,6 +134,7 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT
 	MSG_MAP(DisableDeterminism,		     PPSMC_MSG_DisableDeterminism,		0),
 	MSG_MAP(SetUclkDpmMode,			     PPSMC_MSG_SetUclkDpmMode,			0),
 	MSG_MAP(GfxDriverResetRecovery,		     PPSMC_MSG_GfxDriverResetRecovery,		0),
+	MSG_MAP(BoardPowerCalibration,		     PPSMC_MSG_BoardPowerCalibration,		0),
 };
 
 static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = {
@@ -440,6 +441,39 @@ static int aldebaran_setup_pptable(struct smu_context *smu)
 	return ret;
 }
 
+static bool aldebaran_is_primary(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
+		return adev->smuio.funcs->get_die_id(adev) == 0;
+
+	return true;
+}
+
+static int aldebaran_run_board_btc(struct smu_context *smu)
+{
+	u32 smu_version;
+	int ret;
+
+	if (!aldebaran_is_primary(smu))
+		return 0;
+
+	ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
+	if (ret) {
+		dev_err(smu->adev->dev, "Failed to get smu version!\n");
+		return ret;
+	}
+	if (smu_version <= 0x00441d00)
+		return 0;
+
+	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BoardPowerCalibration, NULL);
+	if (ret)
+		dev_err(smu->adev->dev, "Board power calibration failed!\n");
+
+	return ret;
+}
+
 static int aldebaran_run_btc(struct smu_context *smu)
 {
 	int ret;
@@ -447,6 +481,8 @@ static int aldebaran_run_btc(struct smu_context *smu)
 	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL);
 	if (ret)
 		dev_err(smu->adev->dev, "RunDcBtc failed!\n");
+	else
+		ret = aldebaran_run_board_btc(smu);
 
 	return ret;
 }
@@ -524,16 +560,6 @@ static int aldebaran_freqs_in_same_level(int32_t frequency1,
 	return (abs(frequency1 - frequency2) <= EPSILON);
 }
 
-static bool aldebaran_is_primary(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-
-	if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
-		return adev->smuio.funcs->get_die_id(adev) == 0;
-
-	return true;
-}
-
 static int aldebaran_get_smu_metrics_data(struct smu_context *smu,
 					  MetricsMember_t member,
 					  uint32_t *value)
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 98ae00661656..f454e0424086 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -834,6 +834,9 @@ long drm_ioctl(struct file *filp,
 	if (drm_dev_is_unplugged(dev))
 		return -ENODEV;
 
+       if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE)
+               return -ENOTTY;
+
 	is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END;
 
 	if (is_driver_ioctl) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 8e195fa7626a..989ff064cf3a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,10 +25,8 @@
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
-#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
-#include "i915_memcpy.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -1456,6 +1454,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		int err;
 		struct intel_engine_cs *engine = eb->engine;
 
+		/* If we need to copy for the cmdparser, we will stall anyway */
+		if (eb_use_cmdparser(eb))
+			return ERR_PTR(-EWOULDBLOCK);
+
 		if (!reloc_can_use_engine(engine)) {
 			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
 			if (!engine)
@@ -2372,217 +2374,6 @@ shadow_batch_pin(struct i915_execbuffer *eb,
 	return vma;
 }
 
-struct eb_parse_work {
-	struct dma_fence_work base;
-	struct intel_engine_cs *engine;
-	struct i915_vma *batch;
-	struct i915_vma *shadow;
-	struct i915_vma *trampoline;
-	unsigned long batch_offset;
-	unsigned long batch_length;
-	unsigned long *jump_whitelist;
-	const void *batch_map;
-	void *shadow_map;
-};
-
-static int __eb_parse(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-	int ret;
-	bool cookie;
-
-	cookie = dma_fence_begin_signalling();
-	ret = intel_engine_cmd_parser(pw->engine,
-				      pw->batch,
-				      pw->batch_offset,
-				      pw->batch_length,
-				      pw->shadow,
-				      pw->jump_whitelist,
-				      pw->shadow_map,
-				      pw->batch_map);
-	dma_fence_end_signalling(cookie);
-
-	return ret;
-}
-
-static void __eb_parse_release(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-
-	if (!IS_ERR_OR_NULL(pw->jump_whitelist))
-		kfree(pw->jump_whitelist);
-
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(pw->batch->obj);
-	else
-		i915_gem_object_unpin_pages(pw->batch->obj);
-
-	i915_gem_object_unpin_map(pw->shadow->obj);
-
-	if (pw->trampoline)
-		i915_active_release(&pw->trampoline->active);
-	i915_active_release(&pw->shadow->active);
-	i915_active_release(&pw->batch->active);
-}
-
-static const struct dma_fence_work_ops eb_parse_ops = {
-	.name = "eb_parse",
-	.work = __eb_parse,
-	.release = __eb_parse_release,
-};
-
-static inline int
-__parser_mark_active(struct i915_vma *vma,
-		     struct intel_timeline *tl,
-		     struct dma_fence *fence)
-{
-	struct intel_gt_buffer_pool_node *node = vma->private;
-
-	return i915_active_ref(&node->active, tl->fence_context, fence);
-}
-
-static int
-parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl)
-{
-	int err;
-
-	mutex_lock(&tl->mutex);
-
-	err = __parser_mark_active(pw->shadow, tl, &pw->base.dma);
-	if (err)
-		goto unlock;
-
-	if (pw->trampoline) {
-		err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma);
-		if (err)
-			goto unlock;
-	}
-
-unlock:
-	mutex_unlock(&tl->mutex);
-	return err;
-}
-
-static int eb_parse_pipeline(struct i915_execbuffer *eb,
-			     struct i915_vma *shadow,
-			     struct i915_vma *trampoline)
-{
-	struct eb_parse_work *pw;
-	struct drm_i915_gem_object *batch = eb->batch->vma->obj;
-	bool needs_clflush;
-	int err;
-
-	GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
-	GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
-
-	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
-	if (!pw)
-		return -ENOMEM;
-
-	err = i915_active_acquire(&eb->batch->vma->active);
-	if (err)
-		goto err_free;
-
-	err = i915_active_acquire(&shadow->active);
-	if (err)
-		goto err_batch;
-
-	if (trampoline) {
-		err = i915_active_acquire(&trampoline->active);
-		if (err)
-			goto err_shadow;
-	}
-
-	pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB);
-	if (IS_ERR(pw->shadow_map)) {
-		err = PTR_ERR(pw->shadow_map);
-		goto err_trampoline;
-	}
-
-	needs_clflush =
-		!(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
-	pw->batch_map = ERR_PTR(-ENODEV);
-	if (needs_clflush && i915_has_memcpy_from_wc())
-		pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC);
-
-	if (IS_ERR(pw->batch_map)) {
-		err = i915_gem_object_pin_pages(batch);
-		if (err)
-			goto err_unmap_shadow;
-		pw->batch_map = NULL;
-	}
-
-	pw->jump_whitelist =
-		intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len,
-							     trampoline);
-	if (IS_ERR(pw->jump_whitelist)) {
-		err = PTR_ERR(pw->jump_whitelist);
-		goto err_unmap_batch;
-	}
-
-	dma_fence_work_init(&pw->base, &eb_parse_ops);
-
-	pw->engine = eb->engine;
-	pw->batch = eb->batch->vma;
-	pw->batch_offset = eb->batch_start_offset;
-	pw->batch_length = eb->batch_len;
-	pw->shadow = shadow;
-	pw->trampoline = trampoline;
-
-	/* Mark active refs early for this worker, in case we get interrupted */
-	err = parser_mark_active(pw, eb->context->timeline);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(pw->batch->resv, 1);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(shadow->resv, 1);
-	if (err)
-		goto err_commit;
-
-	/* Wait for all writes (and relocs) into the batch to complete */
-	err = i915_sw_fence_await_reservation(&pw->base.chain,
-					      pw->batch->resv, NULL, false,
-					      0, I915_FENCE_GFP);
-	if (err < 0)
-		goto err_commit;
-
-	/* Keep the batch alive and unwritten as we parse */
-	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
-
-	/* Force execution to wait for completion of the parser */
-	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-
-	dma_fence_work_commit_imm(&pw->base);
-	return 0;
-
-err_commit:
-	i915_sw_fence_set_error_once(&pw->base.chain, err);
-	dma_fence_work_commit_imm(&pw->base);
-	return err;
-
-err_unmap_batch:
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(batch);
-	else
-		i915_gem_object_unpin_pages(batch);
-err_unmap_shadow:
-	i915_gem_object_unpin_map(shadow->obj);
-err_trampoline:
-	if (trampoline)
-		i915_active_release(&trampoline->active);
-err_shadow:
-	i915_active_release(&shadow->active);
-err_batch:
-	i915_active_release(&eb->batch->vma->active);
-err_free:
-	kfree(pw);
-	return err;
-}
-
 static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
 {
 	/*
@@ -2672,7 +2463,15 @@ static int eb_parse(struct i915_execbuffer *eb)
 		goto err_trampoline;
 	}
 
-	err = eb_parse_pipeline(eb, shadow, trampoline);
+	err = dma_resv_reserve_shared(shadow->resv, 1);
+	if (err)
+		goto err_trampoline;
+
+	err = intel_engine_cmd_parser(eb->engine,
+				      eb->batch->vma,
+				      eb->batch_start_offset,
+				      eb->batch_len,
+				      shadow, trampoline);
 	if (err)
 		goto err_unpin_batch;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 4df505e4c53a..16162fc2782d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -125,6 +125,10 @@ static int igt_gpu_reloc(void *arg)
 	intel_gt_pm_get(&eb.i915->gt);
 
 	for_each_uabi_engine(eb.engine, eb.i915) {
+		if (intel_engine_requires_cmd_parser(eb.engine) ||
+		    intel_engine_using_cmd_parser(eb.engine))
+			continue;
+
 		reloc_cache_init(&eb.reloc_cache, eb.i915);
 		memset(map, POISON_INUSE, 4096);
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 98eb48c24c46..06024d321a1a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1977,6 +1977,21 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	if (drm_WARN_ON(&i915->drm, !engine))
 		return -EINVAL;
 
+	/*
+	 * Due to d3_entered is used to indicate skipping PPGTT invalidation on
+	 * vGPU reset, it's set on D0->D3 on PCI config write, and cleared after
+	 * vGPU reset if in resuming.
+	 * In S0ix exit, the device power state also transite from D3 to D0 as
+	 * S3 resume, but no vGPU reset (triggered by QEMU devic model). After
+	 * S0ix exit, all engines continue to work. However the d3_entered
+	 * remains set which will break next vGPU reset logic (miss the expected
+	 * PPGTT invalidation).
+	 * Engines can only work in D0. Thus the 1st elsp write gives GVT a
+	 * chance to clear d3_entered.
+	 */
+	if (vgpu->d3_entered)
+		vgpu->d3_entered = false;
+
 	execlist = &vgpu->submission.execlist[engine->id];
 
 	execlist->elsp_dwords.data[3 - execlist->elsp_dwords.index] = data;
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 3992c25a191d..a3b4d99d64b9 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1145,19 +1145,41 @@ find_reg(const struct intel_engine_cs *engine, u32 addr)
 static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		       struct drm_i915_gem_object *src_obj,
 		       unsigned long offset, unsigned long length,
-		       void *dst, const void *src)
+		       bool *needs_clflush_after)
 {
-	bool needs_clflush =
-		!(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
-	if (src) {
-		GEM_BUG_ON(!needs_clflush);
-		i915_unaligned_memcpy_from_wc(dst, src + offset, length);
-	} else {
-		struct scatterlist *sg;
+	unsigned int src_needs_clflush;
+	unsigned int dst_needs_clflush;
+	void *dst, *src;
+	int ret;
+
+	ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
+	if (ret)
+		return ERR_PTR(ret);
+
+	dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB);
+	i915_gem_object_finish_access(dst_obj);
+	if (IS_ERR(dst))
+		return dst;
+
+	ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+	if (ret) {
+		i915_gem_object_unpin_map(dst_obj);
+		return ERR_PTR(ret);
+	}
+
+	src = ERR_PTR(-ENODEV);
+	if (src_needs_clflush && i915_has_memcpy_from_wc()) {
+		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
+		if (!IS_ERR(src)) {
+			i915_unaligned_memcpy_from_wc(dst,
+						      src + offset,
+						      length);
+			i915_gem_object_unpin_map(src_obj);
+		}
+	}
+	if (IS_ERR(src)) {
+		unsigned long x, n, remain;
 		void *ptr;
-		unsigned int x, sg_ofs;
-		unsigned long remain;
 
 		/*
 		 * We can avoid clflushing partial cachelines before the write
@@ -1168,40 +1190,34 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		 * validate up to the end of the batch.
 		 */
 		remain = length;
-		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+		if (dst_needs_clflush & CLFLUSH_BEFORE)
 			remain = round_up(remain,
 					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
 		x = offset_in_page(offset);
-		sg = i915_gem_object_get_sg(src_obj, offset >> PAGE_SHIFT, &sg_ofs, false);
-
-		while (remain) {
-			unsigned long sg_max = sg->length >> PAGE_SHIFT;
-
-			for (; remain && sg_ofs < sg_max; sg_ofs++) {
-				unsigned long len = min(remain, PAGE_SIZE - x);
-				void *map;
-
-				map = kmap_atomic(nth_page(sg_page(sg), sg_ofs));
-				if (needs_clflush)
-					drm_clflush_virt_range(map + x, len);
-				memcpy(ptr, map + x, len);
-				kunmap_atomic(map);
-
-				ptr += len;
-				remain -= len;
-				x = 0;
-			}
-
-			sg_ofs = 0;
-			sg = sg_next(sg);
+		for (n = offset >> PAGE_SHIFT; remain; n++) {
+			int len = min(remain, PAGE_SIZE - x);
+
+			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
+			if (src_needs_clflush)
+				drm_clflush_virt_range(src + x, len);
+			memcpy(ptr, src + x, len);
+			kunmap_atomic(src);
+
+			ptr += len;
+			remain -= len;
+			x = 0;
 		}
 	}
 
+	i915_gem_object_finish_access(src_obj);
+
 	memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
 
 	/* dst_obj is returned with vmap pinned */
+	*needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
+
 	return dst;
 }
 
@@ -1360,6 +1376,9 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
 	if (target_cmd_index == offset)
 		return 0;
 
+	if (IS_ERR(jump_whitelist))
+		return PTR_ERR(jump_whitelist);
+
 	if (!test_bit(target_cmd_index, jump_whitelist)) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
 			  jump_target);
@@ -1369,28 +1388,10 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
 	return 0;
 }
 
-/**
- * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser()
- * @batch_length: length of the commands in batch_obj
- * @trampoline: Whether jump trampolines are used.
- *
- * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser().
- * This has to be preallocated, because the command parser runs in signaling context,
- * and may not allocate any memory.
- *
- * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use
- * IS_ERR() to check for errors. Must bre freed() with kfree().
- *
- * NULL is a valid value, meaning no allocation was required.
- */
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
-							    bool trampoline)
+static unsigned long *alloc_whitelist(u32 batch_length)
 {
 	unsigned long *jmp;
 
-	if (trampoline)
-		return NULL;
-
 	/*
 	 * We expect batch_length to be less than 256KiB for known users,
 	 * i.e. we need at most an 8KiB bitmap allocation which should be
@@ -1415,9 +1416,7 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
  * @batch_offset: byte offset in the batch at which execution starts
  * @batch_length: length of the commands in batch_obj
  * @shadow: validated copy of the batch buffer in question
- * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist()
- * @shadow_map: mapping to @shadow vma
- * @batch_map: mapping to @batch vma
+ * @trampoline: true if we need to trampoline into privileged execution
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1425,21 +1424,21 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
+
 int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    struct i915_vma *batch,
 			    unsigned long batch_offset,
 			    unsigned long batch_length,
 			    struct i915_vma *shadow,
-			    unsigned long *jump_whitelist,
-			    void *shadow_map,
-			    const void *batch_map)
+			    bool trampoline)
 {
 	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
+	bool needs_clflush_after = false;
+	unsigned long *jump_whitelist;
 	u64 batch_addr, shadow_addr;
 	int ret = 0;
-	bool trampoline = !jump_whitelist;
 
 	GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
 	GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
@@ -1447,8 +1446,18 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 				     batch->size));
 	GEM_BUG_ON(!batch_length);
 
-	cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length,
-			 shadow_map, batch_map);
+	cmd = copy_batch(shadow->obj, batch->obj,
+			 batch_offset, batch_length,
+			 &needs_clflush_after);
+	if (IS_ERR(cmd)) {
+		DRM_DEBUG("CMD: Failed to copy batch\n");
+		return PTR_ERR(cmd);
+	}
+
+	jump_whitelist = NULL;
+	if (!trampoline)
+		/* Defer failure until attempted use */
+		jump_whitelist = alloc_whitelist(batch_length);
 
 	shadow_addr = gen8_canonical_addr(shadow->node.start);
 	batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
@@ -1549,6 +1558,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 
 	i915_gem_object_flush_map(shadow->obj);
 
+	if (!IS_ERR_OR_NULL(jump_whitelist))
+		kfree(jump_whitelist);
+	i915_gem_object_unpin_map(shadow->obj);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fd9db6de5113..997fbe9532c1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1897,17 +1897,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
-							    bool trampoline);
-
 int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    struct i915_vma *batch,
 			    unsigned long batch_offset,
 			    unsigned long batch_length,
 			    struct i915_vma *shadow,
-			    unsigned long *jump_whitelist,
-			    void *shadow_map,
-			    const void *batch_map);
+			    bool trampoline);
 #define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
 
 /* intel_device_info.c */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1014c71cf7f5..37aef1308573 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1426,10 +1426,8 @@ i915_request_await_execution(struct i915_request *rq,
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
-			i915_sw_fence_set_error_once(&rq->submit, fence->error);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 			continue;
-		}
 
 		if (fence->context == rq->fence.context)
 			continue;
@@ -1527,10 +1525,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
-			i915_sw_fence_set_error_once(&rq->submit, fence->error);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 			continue;
-		}
 
 		/*
 		 * Requests on the same timeline are explicitly ordered, along
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index 2229f1af2ca8..46029c5610c8 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -447,7 +447,6 @@ static int rpi_touchscreen_remove(struct i2c_client *i2c)
 	drm_panel_remove(&ts->base);
 
 	mipi_dsi_device_unregister(ts->dsi);
-	kfree(ts->dsi);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20fbfd922266..ea4add2b9717 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -102,6 +102,9 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
 		return;
 	}
 
+	if (!mem)
+		return;
+
 	man = ttm_manager_type(bdev, mem->mem_type);
 	list_move_tail(&bo->lru, &man->lru[bo->priority]);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2f57f824e6db..763fa6f4e07d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -63,6 +63,9 @@ int ttm_mem_io_reserve(struct ttm_device *bdev,
 void ttm_mem_io_free(struct ttm_device *bdev,
 		     struct ttm_resource *mem)
 {
+	if (!mem)
+		return;
+
 	if (!mem->bus.offset && !mem->bus.addr)
 		return;
 
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index 5f31acec3ad7..519deea8e39b 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -100,6 +100,8 @@ static int ttm_global_init(void)
 	debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root,
 				&glob->bo_count);
 out:
+	if (ret)
+		--ttm_glob_use_count;
 	mutex_unlock(&ttm_global_mutex);
 	return ret;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index d4833c878ca9..b20530cf6a23 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1878,38 +1878,46 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi)
 	vc4_hdmi_cec_update_clk_div(vc4_hdmi);
 
 	if (vc4_hdmi->variant->external_irq_controller) {
-		ret = devm_request_threaded_irq(&pdev->dev,
-						platform_get_irq_byname(pdev, "cec-rx"),
-						vc4_cec_irq_handler_rx_bare,
-						vc4_cec_irq_handler_rx_thread, 0,
-						"vc4 hdmi cec rx", vc4_hdmi);
+		ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-rx"),
+					   vc4_cec_irq_handler_rx_bare,
+					   vc4_cec_irq_handler_rx_thread, 0,
+					   "vc4 hdmi cec rx", vc4_hdmi);
 		if (ret)
 			goto err_delete_cec_adap;
 
-		ret = devm_request_threaded_irq(&pdev->dev,
-						platform_get_irq_byname(pdev, "cec-tx"),
-						vc4_cec_irq_handler_tx_bare,
-						vc4_cec_irq_handler_tx_thread, 0,
-						"vc4 hdmi cec tx", vc4_hdmi);
+		ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-tx"),
+					   vc4_cec_irq_handler_tx_bare,
+					   vc4_cec_irq_handler_tx_thread, 0,
+					   "vc4 hdmi cec tx", vc4_hdmi);
 		if (ret)
-			goto err_delete_cec_adap;
+			goto err_remove_cec_rx_handler;
 	} else {
 		HDMI_WRITE(HDMI_CEC_CPU_MASK_SET, 0xffffffff);
 
-		ret = devm_request_threaded_irq(&pdev->dev, platform_get_irq(pdev, 0),
-						vc4_cec_irq_handler,
-						vc4_cec_irq_handler_thread, 0,
-						"vc4 hdmi cec", vc4_hdmi);
+		ret = request_threaded_irq(platform_get_irq(pdev, 0),
+					   vc4_cec_irq_handler,
+					   vc4_cec_irq_handler_thread, 0,
+					   "vc4 hdmi cec", vc4_hdmi);
 		if (ret)
 			goto err_delete_cec_adap;
 	}
 
 	ret = cec_register_adapter(vc4_hdmi->cec_adap, &pdev->dev);
 	if (ret < 0)
-		goto err_delete_cec_adap;
+		goto err_remove_handlers;
 
 	return 0;
 
+err_remove_handlers:
+	if (vc4_hdmi->variant->external_irq_controller)
+		free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+	else
+		free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+
+err_remove_cec_rx_handler:
+	if (vc4_hdmi->variant->external_irq_controller)
+		free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+
 err_delete_cec_adap:
 	cec_delete_adapter(vc4_hdmi->cec_adap);
 
@@ -1918,6 +1926,15 @@ err_delete_cec_adap:
 
 static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi)
 {
+	struct platform_device *pdev = vc4_hdmi->pdev;
+
+	if (vc4_hdmi->variant->external_irq_controller) {
+		free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+		free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+	} else {
+		free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+	}
+
 	cec_unregister_adapter(vc4_hdmi->cec_adap);
 }
 #else