Merge tag 'amd-drm-fixes-6.14-2025-03-20' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.14-2025-03-20:

amdgpu:
- Fix video caps limits on several asics
- SMU 14.x fixes
- GC 12 fixes
- eDP fixes
- DMUB fix

amdkfd:
- GC 12 trap handler fix
- GC 7/8 queue validation fix

radeon:
- VCE IB parsing fix

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250320210800.1358992-1-alexander.deucher@amd.com

drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c

@@ -2437,7 +2437,7 @@ static int gfx_v12_0_cp_gfx_load_me_microcode_rs64(struct amdgpu_device *adev)
 				      (void **)&adev->gfx.me.me_fw_data_ptr);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to create me data bo\n", r);
-		gfx_v12_0_pfp_fini(adev);
+		gfx_v12_0_me_fini(adev);
 		return r;
 	}
 

drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c

@@ -501,9 +501,6 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
 				 uint64_t *flags)
 {
 	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
-	struct amdgpu_device *bo_adev;
-	bool coherent, is_system;
-
 
 	*flags &= ~AMDGPU_PTE_EXECUTABLE;
 	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
@@ -519,26 +516,11 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
-	if (!bo)
-		return;
-
-	if (bo->flags & (AMDGPU_GEM_CREATE_COHERENT |
-			       AMDGPU_GEM_CREATE_UNCACHED))
-		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_UC);
-
-	bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT;
-	is_system = bo->tbo.resource &&
-		(bo->tbo.resource->mem_type == TTM_PL_TT ||
-		 bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT);
-
 	if (bo && bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
 		*flags |= AMDGPU_PTE_DCC;
 
-	/* WA for HW bug */
-	if (is_system || ((bo_adev != adev) && coherent))
-		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_NC);
-
+	if (bo && bo->flags & AMDGPU_GEM_CREATE_UNCACHED)
+		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_UC);
 }
 
 static unsigned gmc_v12_0_get_vbios_fb_size(struct amdgpu_device *adev)

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

@@ -78,12 +78,12 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode = {
 
 /* Navi1x */
 static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 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_JPEG, 8192, 8192, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
 };
 
@@ -104,10 +104,10 @@ static const struct amdgpu_video_codecs sc_video_codecs_encode = {
 };
 
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
@@ -115,10 +115,10 @@ static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[]
 };
 
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},

drivers/gpu/drm/amd/amdgpu/soc15.c

@@ -103,12 +103,11 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode =
 /* Vega */
 static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 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 =
@@ -120,12 +119,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode =
 /* Raven */
 static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 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_JPEG, 8192, 8192, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
 };
 
@@ -138,10 +137,10 @@ 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_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4096, 5)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 1920, 1088, 3)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 1920, 1088, 5)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 52)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4096, 4)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 1920, 1088, 4)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 16384, 16384, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},

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

@@ -167,16 +167,16 @@ static const struct amdgpu_video_codec_info tonga_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_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.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_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 5,
 	},
 	{
@@ -188,9 +188,9 @@ static const struct amdgpu_video_codec_info tonga_video_codecs_decode_array[] =
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 4,
 	},
 };
@@ -206,16 +206,16 @@ static const struct amdgpu_video_codec_info cz_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_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.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_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 5,
 	},
 	{
@@ -227,9 +227,9 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 	},
 	{
 		.codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
-		.max_width = 4096,
-		.max_height = 4096,
-		.max_pixels_per_frame = 4096 * 4096,
+		.max_width = 1920,
+		.max_height = 1088,
+		.max_pixels_per_frame = 1920 * 1088,
 		.max_level = 4,
 	},
 	{
@@ -239,13 +239,6 @@ static const struct amdgpu_video_codec_info cz_video_codecs_decode_array[] =
 		.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,
-	},
 };
 
 static const struct amdgpu_video_codecs cz_video_codecs_decode =

drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm

@@ -30,6 +30,7 @@
 #define CHIP_GFX12 37
 
 #define SINGLE_STEP_MISSED_WORKAROUND 1	//workaround for lost TRAP_AFTER_INST exception when SAVECTX raised
+#define HAVE_VALU_SGPR_HAZARD (ASIC_FAMILY == CHIP_GFX12)
 
 var SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK	= 0x4
 var SQ_WAVE_STATE_PRIV_SCC_SHIFT		= 9
@@ -351,6 +352,7 @@ L_HAVE_VGPRS:
 	v_writelane_b32	v0, ttmp13, 0xD
 	v_writelane_b32	v0, exec_lo, 0xE
 	v_writelane_b32	v0, exec_hi, 0xF
+	valu_sgpr_hazard()
 
 	s_mov_b32	exec_lo, 0x3FFF
 	s_mov_b32	exec_hi, 0x0
@@ -417,7 +419,6 @@ L_SAVE_HWREG:
 	v_mov_b32	v0, 0x0							//Offset[31:0] from buffer resource
 	v_mov_b32	v1, 0x0							//Offset[63:32] from buffer resource
 	v_mov_b32	v2, 0x0							//Set of SGPRs for TCP store
-	s_mov_b32	m0, 0x0							//Next lane of v2 to write to
 
 	// Ensure no further changes to barrier or LDS state.
 	// STATE_PRIV.BARRIER_COMPLETE may change up to this point.
@@ -430,40 +431,41 @@ L_SAVE_HWREG:
 	s_andn2_b32	s_save_state_priv, s_save_state_priv, SQ_WAVE_STATE_PRIV_BARRIER_COMPLETE_MASK
 	s_or_b32	s_save_state_priv, s_save_state_priv, s_save_tmp
 
-	write_hwreg_to_v2(s_save_m0)
-	write_hwreg_to_v2(s_save_pc_lo)
 	s_andn2_b32	s_save_tmp, s_save_pc_hi, S_SAVE_PC_HI_FIRST_WAVE_MASK
-	write_hwreg_to_v2(s_save_tmp)
-	write_hwreg_to_v2(s_save_exec_lo)
-	write_hwreg_to_v2(s_save_exec_hi)
-	write_hwreg_to_v2(s_save_state_priv)
+	v_writelane_b32	v2, s_save_m0, 0x0
+	v_writelane_b32	v2, s_save_pc_lo, 0x1
+	v_writelane_b32	v2, s_save_tmp, 0x2
+	v_writelane_b32	v2, s_save_exec_lo, 0x3
+	v_writelane_b32	v2, s_save_exec_hi, 0x4
+	v_writelane_b32	v2, s_save_state_priv, 0x5
+	v_writelane_b32	v2, s_save_xnack_mask, 0x7
+	valu_sgpr_hazard()
 
 	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_EXCP_FLAG_PRIV)
-	write_hwreg_to_v2(s_save_tmp)
+	v_writelane_b32	v2, s_save_tmp, 0x6
 
-	write_hwreg_to_v2(s_save_xnack_mask)
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_MODE)
+	v_writelane_b32	v2, s_save_tmp, 0x8
 
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_MODE)
-	write_hwreg_to_v2(s_save_m0)
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_SCRATCH_BASE_LO)
+	v_writelane_b32	v2, s_save_tmp, 0x9
 
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_SCRATCH_BASE_LO)
-	write_hwreg_to_v2(s_save_m0)
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_SCRATCH_BASE_HI)
+	v_writelane_b32	v2, s_save_tmp, 0xA
 
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_SCRATCH_BASE_HI)
-	write_hwreg_to_v2(s_save_m0)
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
+	v_writelane_b32	v2, s_save_tmp, 0xB
 
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_EXCP_FLAG_USER)
-	write_hwreg_to_v2(s_save_m0)
-
-	s_getreg_b32	s_save_m0, hwreg(HW_REG_WAVE_TRAP_CTRL)
-	write_hwreg_to_v2(s_save_m0)
+	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_TRAP_CTRL)
+	v_writelane_b32	v2, s_save_tmp, 0xC
 
 	s_getreg_b32	s_save_tmp, hwreg(HW_REG_WAVE_STATUS)
-	write_hwreg_to_v2(s_save_tmp)
+	v_writelane_b32	v2, s_save_tmp, 0xD
 
 	s_get_barrier_state s_save_tmp, -1
 	s_wait_kmcnt (0)
-	write_hwreg_to_v2(s_save_tmp)
+	v_writelane_b32	v2, s_save_tmp, 0xE
+	valu_sgpr_hazard()
 
 	// Write HWREGs with 16 VGPR lanes. TTMPs occupy space after this.
 	s_mov_b32       exec_lo, 0xFFFF
@@ -497,10 +499,12 @@ L_SAVE_SGPR_LOOP:
 	s_movrels_b64	s12, s12						//s12 = s[12+m0], s13 = s[13+m0]
 	s_movrels_b64	s14, s14						//s14 = s[14+m0], s15 = s[15+m0]
 
-	write_16sgpr_to_v2(s0)
-
-	s_cmp_eq_u32	ttmp13, 0x20						//have 32 VGPR lanes filled?
-	s_cbranch_scc0	L_SAVE_SGPR_SKIP_TCP_STORE
+	s_cmp_eq_u32	ttmp13, 0x0
+	s_cbranch_scc0	L_WRITE_V2_SECOND_HALF
+	write_16sgpr_to_v2(s0, 0x0)
+	s_branch	L_SAVE_SGPR_SKIP_TCP_STORE
+L_WRITE_V2_SECOND_HALF:
+	write_16sgpr_to_v2(s0, 0x10)
 
 	buffer_store_dword	v2, v0, s_save_buf_rsrc0, s_save_mem_offset scope:SCOPE_SYS
 	s_add_u32	s_save_mem_offset, s_save_mem_offset, 0x80
@@ -1056,27 +1060,21 @@ L_END_PGM:
 	s_endpgm_saved
 end
 
-function write_hwreg_to_v2(s)
-	// Copy into VGPR for later TCP store.
-	v_writelane_b32	v2, s, m0
-	s_add_u32	m0, m0, 0x1
-end
-
-
-function write_16sgpr_to_v2(s)
+function write_16sgpr_to_v2(s, lane_offset)
 	// Copy into VGPR for later TCP store.
 	for var sgpr_idx = 0; sgpr_idx < 16; sgpr_idx ++
-		v_writelane_b32	v2, s[sgpr_idx], ttmp13
-		s_add_u32	ttmp13, ttmp13, 0x1
+		v_writelane_b32	v2, s[sgpr_idx], sgpr_idx + lane_offset
 	end
+	valu_sgpr_hazard()
+	s_add_u32	ttmp13, ttmp13, 0x10
 end
 
 function write_12sgpr_to_v2(s)
 	// Copy into VGPR for later TCP store.
 	for var sgpr_idx = 0; sgpr_idx < 12; sgpr_idx ++
-		v_writelane_b32	v2, s[sgpr_idx], ttmp13
-		s_add_u32	ttmp13, ttmp13, 0x1
+		v_writelane_b32	v2, s[sgpr_idx], sgpr_idx
 	end
+	valu_sgpr_hazard()
 end
 
 function read_hwreg_from_mem(s, s_rsrc, s_mem_offset)
@@ -1128,3 +1126,11 @@ function get_wave_size2(s_reg)
 	s_getreg_b32	s_reg, hwreg(HW_REG_WAVE_STATUS,SQ_WAVE_STATUS_WAVE64_SHIFT,SQ_WAVE_STATUS_WAVE64_SIZE)
 	s_lshl_b32	s_reg, s_reg, S_WAVE_SIZE
 end
+
+function valu_sgpr_hazard
+#if HAVE_VALU_SGPR_HAZARD
+	for var rep = 0; rep < 8; rep ++
+		ds_nop
+	end
+#endif
+end

drivers/gpu/drm/amd/amdkfd/kfd_queue.c

@@ -233,6 +233,7 @@ void kfd_queue_buffer_put(struct amdgpu_bo **bo)
 int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_properties *properties)
 {
 	struct kfd_topology_device *topo_dev;
+	u64 expected_queue_size;
 	struct amdgpu_vm *vm;
 	u32 total_cwsr_size;
 	int err;
@@ -241,6 +242,15 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	if (!topo_dev)
 		return -EINVAL;
 
+	/* AQL queues on GFX7 and GFX8 appear twice their actual size */
+	if (properties->type == KFD_QUEUE_TYPE_COMPUTE &&
+	    properties->format == KFD_QUEUE_FORMAT_AQL &&
+	    topo_dev->node_props.gfx_target_version >= 70000 &&
+	    topo_dev->node_props.gfx_target_version < 90000)
+		expected_queue_size = properties->queue_size / 2;
+	else
+		expected_queue_size = properties->queue_size;
+
 	vm = drm_priv_to_vm(pdd->drm_priv);
 	err = amdgpu_bo_reserve(vm->root.bo, false);
 	if (err)
@@ -255,7 +265,7 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 		goto out_err_unreserve;
 
 	err = kfd_queue_buffer_get(vm, (void *)properties->queue_address,
-				   &properties->ring_bo, properties->queue_size);
+				   &properties->ring_bo, expected_queue_size);
 	if (err)
 		goto out_err_unreserve;
 

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -1286,13 +1286,7 @@ svm_range_get_pte_flags(struct kfd_node *node,
 		break;
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
-		if (domain == SVM_RANGE_VRAM_DOMAIN) {
-			if (bo_node != node)
-				mapping_flags |= AMDGPU_VM_MTYPE_NC;
-		} else {
-			mapping_flags |= coherent ?
-				AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
-		}
+		mapping_flags |= AMDGPU_VM_MTYPE_NC;
 		break;
 	default:
 		mapping_flags |= coherent ?

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1745,7 +1745,7 @@ static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_
 	}
 	if (quirk_entries.support_edp0_on_dp1) {
 		init_data->flags.support_edp0_on_dp1 = true;
-		drm_info(dev, "aux_hpd_discon_quirk attached\n");
+		drm_info(dev, "support_edp0_on_dp1 attached\n");
 	}
 }
 

drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c

@@ -69,5 +69,16 @@ bool should_use_dmub_lock(struct dc_link *link)
 	if (link->replay_settings.replay_feature_enabled)
 		return true;
 
+	/* only use HW lock for PSR1 on single eDP */
+	if (link->psr_settings.psr_version == DC_PSR_VERSION_1) {
+		struct dc_link *edp_links[MAX_NUM_EDP];
+		int edp_num;
+
+		dc_get_edp_links(link->dc, edp_links, &edp_num);
+
+		if (edp_num == 1)
+			return true;
+	}
+
 	return false;
 }

drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c

@@ -704,7 +704,7 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub,
 	cw6.region.base = DMUB_CW6_BASE;
 	cw6.region.top = cw6.region.base + fw_state_fb->size;
 
-	dmub->fw_state = fw_state_fb->cpu_addr;
+	dmub->fw_state = (void *)((uintptr_t)(fw_state_fb->cpu_addr) + DMUB_DEBUG_FW_STATE_OFFSET);
 
 	region6.offset.quad_part = shared_state_fb->gpu_addr;
 	region6.region.base = DMUB_CW6_BASE;

drivers/gpu/drm/amd/pm/amdgpu_pm.c

@@ -2421,6 +2421,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		case IP_VERSION(11, 0, 1):
 		case IP_VERSION(11, 0, 2):
 		case IP_VERSION(11, 0, 3):
+		case IP_VERSION(12, 0, 0):
+		case IP_VERSION(12, 0, 1):
 			*states = ATTR_STATE_SUPPORTED;
 			break;
 		default:

drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c

@@ -1193,16 +1193,9 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 							 PP_OD_FEATURE_GFXCLK_BIT))
 			break;
 
-		PPTable_t *pptable = smu->smu_table.driver_pptable;
-		const OverDriveLimits_t * const overdrive_upperlimits =
-					&pptable->SkuTable.OverDriveLimitsBasicMax;
-		const OverDriveLimits_t * const overdrive_lowerlimits =
-					&pptable->SkuTable.OverDriveLimitsBasicMin;
-
 		size += sysfs_emit_at(buf, size, "OD_SCLK_OFFSET:\n");
-		size += sysfs_emit_at(buf, size, "0: %dMhz\n1: %uMhz\n",
-					overdrive_lowerlimits->GfxclkFoffset,
-					overdrive_upperlimits->GfxclkFoffset);
+		size += sysfs_emit_at(buf, size, "%dMhz\n",
+					od_table->OverDriveTable.GfxclkFoffset);
 		break;
 
 	case SMU_OD_MCLK:
@@ -1336,13 +1329,9 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 		size += sysfs_emit_at(buf, size, "%s:\n", "OD_RANGE");
 
 		if (smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_GFXCLK_BIT)) {
-			smu_v14_0_2_get_od_setting_limits(smu,
-							  PP_OD_FEATURE_GFXCLK_FMIN,
-							  &min_value,
-							  NULL);
 			smu_v14_0_2_get_od_setting_limits(smu,
 							  PP_OD_FEATURE_GFXCLK_FMAX,
-							  NULL,
+							  &min_value,
 							  &max_value);
 			size += sysfs_emit_at(buf, size, "SCLK_OFFSET: %7dMhz %10uMhz\n",
 					      min_value, max_value);
@@ -1627,6 +1616,39 @@ out:
 	adev->unique_id = ((uint64_t)upper32 << 32) | lower32;
 }
 
+static int smu_v14_0_2_get_fan_speed_pwm(struct smu_context *smu,
+					 uint32_t *speed)
+{
+	int ret;
+
+	if (!speed)
+		return -EINVAL;
+
+	ret = smu_v14_0_2_get_smu_metrics_data(smu,
+					       METRICS_CURR_FANPWM,
+					       speed);
+	if (ret) {
+		dev_err(smu->adev->dev, "Failed to get fan speed(PWM)!");
+		return ret;
+	}
+
+	/* Convert the PMFW output which is in percent to pwm(255) based */
+	*speed = min(*speed * 255 / 100, (uint32_t)255);
+
+	return 0;
+}
+
+static int smu_v14_0_2_get_fan_speed_rpm(struct smu_context *smu,
+					 uint32_t *speed)
+{
+	if (!speed)
+		return -EINVAL;
+
+	return smu_v14_0_2_get_smu_metrics_data(smu,
+						METRICS_CURR_FANSPEED,
+						speed);
+}
+
 static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 				       uint32_t *current_power_limit,
 				       uint32_t *default_power_limit,
@@ -2417,36 +2439,24 @@ static int smu_v14_0_2_od_edit_dpm_table(struct smu_context *smu,
 			return -ENOTSUPP;
 		}
 
-		for (i = 0; i < size; i += 2) {
-			if (i + 2 > size) {
-				dev_info(adev->dev, "invalid number of input parameters %d\n", size);
-				return -EINVAL;
-			}
-
-			switch (input[i]) {
-			case 1:
-				smu_v14_0_2_get_od_setting_limits(smu,
-								  PP_OD_FEATURE_GFXCLK_FMAX,
-								  &minimum,
-								  &maximum);
-				if (input[i + 1] < minimum ||
-				    input[i + 1] > maximum) {
-					dev_info(adev->dev, "GfxclkFmax (%ld) must be within [%u, %u]!\n",
-						input[i + 1], minimum, maximum);
-					return -EINVAL;
-				}
-
-				od_table->OverDriveTable.GfxclkFoffset = input[i + 1];
-				od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
-				break;
-
-			default:
-				dev_info(adev->dev, "Invalid SCLK_VDDC_TABLE index: %ld\n", input[i]);
-				dev_info(adev->dev, "Supported indices: [0:min,1:max]\n");
-				return -EINVAL;
-			}
+		if (size != 1) {
+			dev_info(adev->dev, "invalid number of input parameters %d\n", size);
+			return -EINVAL;
 		}
 
+		smu_v14_0_2_get_od_setting_limits(smu,
+						  PP_OD_FEATURE_GFXCLK_FMAX,
+						  &minimum,
+						  &maximum);
+		if (input[0] < minimum ||
+		    input[0] > maximum) {
+			dev_info(adev->dev, "GfxclkFoffset must be within [%d, %u]!\n",
+				 minimum, maximum);
+			return -EINVAL;
+		}
+
+		od_table->OverDriveTable.GfxclkFoffset = input[0];
+		od_table->OverDriveTable.FeatureCtrlMask |= 1U << PP_OD_FEATURE_GFXCLK_BIT;
 		break;
 
 	case PP_OD_EDIT_MCLK_VDDC_TABLE:
@@ -2804,6 +2814,8 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = {
 	.set_performance_level = smu_v14_0_set_performance_level,
 	.gfx_off_control = smu_v14_0_gfx_off_control,
 	.get_unique_id = smu_v14_0_2_get_unique_id,
+	.get_fan_speed_pwm = smu_v14_0_2_get_fan_speed_pwm,
+	.get_fan_speed_rpm = smu_v14_0_2_get_fan_speed_rpm,
 	.get_power_limit = smu_v14_0_2_get_power_limit,
 	.set_power_limit = smu_v14_0_2_set_power_limit,
 	.get_power_profile_mode = smu_v14_0_2_get_power_profile_mode,

drivers/gpu/drm/radeon/radeon_vce.c

@@ -557,7 +557,7 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 {
 	int session_idx = -1;
 	bool destroyed = false, created = false, allocated = false;
-	uint32_t tmp, handle = 0;
+	uint32_t tmp = 0, handle = 0;
 	uint32_t *size = &tmp;
 	int i, r = 0;