Merge tag 'drm-fixes-2024-11-16' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Final week of fixes, lots of small amdgpu fixes, some i915 and xe
  fixes, the nouveau changes fix a recent regression and some laptop
  panel black screens, then a couple of other misc ones.

  It's probably a little busier than I'd like, but each fix seems fine.

  amdgpu:
   - PSR fix
   - Panel replay fixes
   - DML fix
   - vblank power fix
   - Fix video caps
   - SMU 14.0 fix
   - GPUVM fix
   - MES 12 fix
   - APU carve out fix
   - DC vbios fix
   - NBIO fix

  i915:
   - Don't load GSC on ARL-H and ARL-U if too old FW
   - Avoid potential OOPS in enabling/disabling TV output

  xe:
   - Fix unlock on exec ioctl error path
   - Fix hibernation on LNL due to ggtt getting lost
   - Fix missing runtime PM in OA release

  bridge:
   - tc358768: Fix DSI command tx

  nouveau:
   - Fix GSP AUX error handling
   - dp: Handle retires for AUX CH transfers with GSP
   - fw: Sync DMA after setup

  panthor:
   - Fix partial BO mappings to GPU

  rockchip:
   - vop: Avoid null-ptr deref in plane-state check

  vmwgfx:
   - Avoid null-ptr deref in surface creation"

* tag 'drm-fixes-2024-11-16' of https://gitlab.freedesktop.org/drm/kernel: (27 commits)
  drm/bridge: tc358768: Fix DSI command tx
  drm/vmwgfx: avoid null_ptr_deref in vmw_framebuffer_surface_create_handle
  nouveau/dp: handle retries for AUX CH transfers with GSP.
  nouveau: handle EBUSY and EAGAIN for GSP aux errors.
  nouveau: fw: sync dma after setup is called.
  drm/xe/oa: Fix "Missing outer runtime PM protection" warning
  drm/xe: handle flat ccs during hibernation on igpu
  drm/xe: improve hibernation on igpu
  drm/xe: Restore system memory GGTT mappings
  drm/xe: Ensure all locks released in exec IOCTL
  drm/panthor: Fix handling of partial GPU mapping of BOs
  drm/amd: Fix initialization mistake for NBIO 7.7.0
  Revert "drm/amd/display: parse umc_info or vram_info based on ASIC"
  drm/amd/display: Fix failure to read vram info due to static BP_RESULT
  drm/amdgpu: enable GTT fallback handling for dGPUs only
  drm/i915: Grab intel_display from the encoder to avoid potential oopsies
  drm/i915/gsc: ARL-H and ARL-U need a newer GSC FW.
  drm/amdgpu/mes12: correct kiq unmap latency
  drm/amdgpu: fix check in gmc_v9_0_get_vm_pte()
  drm/amd/pm: print pp_dpm_mclk in ascending order on SMU v14.0.0
  ...

34 files changed, 304 insertions, 196 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 44819cdba7fb..971419e3a9bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -161,7 +161,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		 * When GTT is just an alternative to VRAM make sure that we
 		 * only use it as fallback and still try to fill up VRAM first.
 		 */
-		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM)
+		if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
+		    !(adev->flags & AMD_IS_APU))
 			places[c].flags |= TTM_PL_FLAG_FALLBACK;
 		c++;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index c76ac0dfe572..7a45f3fdc734 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1124,8 +1124,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 					 uint64_t *flags)
 {
 	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM;
-	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | AMDGPU_GEM_CREATE_EXT_COHERENT);
+	bool is_vram = bo->tbo.resource &&
+		bo->tbo.resource->mem_type == TTM_PL_VRAM;
+	bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT |
+				     AMDGPU_GEM_CREATE_EXT_COHERENT);
 	bool ext_coherent = bo->flags & AMDGPU_GEM_CREATE_EXT_COHERENT;
 	bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED;
 	struct amdgpu_vm *vm = mapping->bo_va->base.vm;
@@ -1133,6 +1135,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 	bool snoop = false;
 	bool is_local;
 
+	dma_resv_assert_held(bo->tbo.base.resv);
+
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
 	case IP_VERSION(9, 4, 1):
 	case IP_VERSION(9, 4, 2):
@@ -1251,9 +1255,8 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
-	if (bo && bo->tbo.resource)
-		gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.bo,
-					     mapping, flags);
+	if ((*flags & AMDGPU_PTE_VALID) && bo)
+		gmc_v9_0_get_coherence_flags(adev, bo, mapping, flags);
 }
 
 static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index a37a6801c9ea..b3175ff676f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -550,7 +550,7 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_1_pkt.header.type = MES_API_TYPE_SCHEDULER;
 	mes_set_hw_res_1_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC_1;
 	mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
-	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100;
+	mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa;
 
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe,
 			&mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt),
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
index fb37e354a9d5..1ac730328516 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c
@@ -247,6 +247,12 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data);
 
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(7, 7, 0):
+		data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23);
+		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data);
+		break;
+	}
 }
 
 static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 4938e6b340e9..73065a85e0d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -67,8 +67,8 @@ static const struct amd_ip_funcs nv_common_ip_funcs;
 
 /* Navi */
 static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] = {
-	{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)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs nv_video_codecs_encode = {
@@ -94,8 +94,8 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = {
 
 /* Sienna Cichlid */
 static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codecs sc_video_codecs_encode = {
@@ -136,8 +136,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = {
 
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8d16dacdc172..307185c0e1b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -90,8 +90,8 @@ static const struct amd_ip_funcs soc15_common_ip_funcs;
 /* Vega, Raven, Arcturus */
 static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
 {
-	{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)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)},
 };
 
 static const struct amdgpu_video_codecs vega_video_codecs_encode =
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index d30ad7d56def..bba35880badb 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -49,13 +49,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs;
 
 /* SOC21 */
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
@@ -96,14 +96,14 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = {
 
 /* SRIOV SOC21, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = {
-	{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)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = {
-	{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)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 };
 
 static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = {
diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c
index fd4c3d4f8387..29a848f2466b 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc24.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc24.c
@@ -48,7 +48,7 @@
 static const struct amd_ip_funcs soc24_common_ip_funcs;
 
 static const struct amdgpu_video_codec_info vcn_5_0_0_video_codecs_encode_array_vcn0[] = {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)},
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index d39c670f6220..792b2eb6bbac 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -136,15 +136,15 @@ static const struct amdgpu_video_codec_info polaris_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_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.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_height = 4096,
+		.max_pixels_per_frame = 4096 * 4096,
 		.max_level = 0,
 	},
 };
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 07e9ce99694f..8d97f17ffe66 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6762,7 +6762,7 @@ create_stream_for_sink(struct drm_connector *connector,
 		if (stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22)
 			tf = TRANSFER_FUNC_GAMMA_22;
 		mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf);
-		aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
+		aconnector->sr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY;
 
 	}
 finish:
@@ -8875,6 +8875,56 @@ static void amdgpu_dm_update_cursor(struct drm_plane *plane,
 	}
 }
 
+static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach,
+					  const struct dm_crtc_state *acrtc_state,
+					  const u64 current_ts)
+{
+	struct psr_settings *psr = &acrtc_state->stream->link->psr_settings;
+	struct replay_settings *pr = &acrtc_state->stream->link->replay_settings;
+	struct amdgpu_dm_connector *aconn =
+		(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
+
+	if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+		if (pr->config.replay_supported && !pr->replay_feature_enabled)
+			amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
+		else if (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED &&
+			     !psr->psr_feature_enabled)
+			if (!aconn->disallow_edp_enter_psr)
+				amdgpu_dm_link_setup_psr(acrtc_state->stream);
+	}
+
+	/* Decrement skip count when SR is enabled and we're doing fast updates. */
+	if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
+	    (psr->psr_feature_enabled || pr->config.replay_supported)) {
+		if (aconn->sr_skip_count > 0)
+			aconn->sr_skip_count--;
+
+		/* Allow SR when skip count is 0. */
+		acrtc_attach->dm_irq_params.allow_sr_entry = !aconn->sr_skip_count;
+
+		/*
+		 * If sink supports PSR SU/Panel Replay, there is no need to rely on
+		 * a vblank event disable request to enable PSR/RP. PSR SU/RP
+		 * can be enabled immediately once OS demonstrates an
+		 * adequate number of fast atomic commits to notify KMD
+		 * of update events. See `vblank_control_worker()`.
+		 */
+		if (acrtc_attach->dm_irq_params.allow_sr_entry &&
+#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
+		    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
+#endif
+		    (current_ts - psr->psr_dirty_rects_change_timestamp_ns) > 500000000) {
+			if (pr->replay_feature_enabled && !pr->replay_allow_active)
+				amdgpu_dm_replay_enable(acrtc_state->stream, true);
+			if (psr->psr_version >= DC_PSR_VERSION_SU_1 &&
+			    !psr->psr_allow_active && !aconn->disallow_edp_enter_psr)
+				amdgpu_dm_psr_enable(acrtc_state->stream);
+		}
+	} else {
+		acrtc_attach->dm_irq_params.allow_sr_entry = false;
+	}
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_device *dev,
 				    struct amdgpu_display_manager *dm,
@@ -9028,7 +9078,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			 * during the PSR-SU was disabled.
 			 */
 			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
+			    acrtc_attach->dm_irq_params.allow_sr_entry &&
 #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
 			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
 #endif
@@ -9203,9 +9253,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			bundle->stream_update.abm_level = &acrtc_state->abm_level;
 
 		mutex_lock(&dm->dc_lock);
-		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
-				acrtc_state->stream->link->psr_settings.psr_allow_active)
-			amdgpu_dm_psr_disable(acrtc_state->stream);
+		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
+			if (acrtc_state->stream->link->replay_settings.replay_allow_active)
+				amdgpu_dm_replay_disable(acrtc_state->stream);
+			if (acrtc_state->stream->link->psr_settings.psr_allow_active)
+				amdgpu_dm_psr_disable(acrtc_state->stream);
+		}
 		mutex_unlock(&dm->dc_lock);
 
 		/*
@@ -9246,57 +9299,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			dm_update_pflip_irq_state(drm_to_adev(dev),
 						  acrtc_attach);
 
-		if (acrtc_state->update_type > UPDATE_TYPE_FAST) {
-			if (acrtc_state->stream->link->replay_settings.config.replay_supported &&
-					!acrtc_state->stream->link->replay_settings.replay_feature_enabled) {
-				struct amdgpu_dm_connector *aconn =
-					(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-				amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn);
-			} else if (acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED &&
-					!acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-
-				struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *)
-					acrtc_state->stream->dm_stream_context;
-
-				if (!aconn->disallow_edp_enter_psr)
-					amdgpu_dm_link_setup_psr(acrtc_state->stream);
-			}
-		}
-
-		/* Decrement skip count when PSR is enabled and we're doing fast updates. */
-		if (acrtc_state->update_type == UPDATE_TYPE_FAST &&
-		    acrtc_state->stream->link->psr_settings.psr_feature_enabled) {
-			struct amdgpu_dm_connector *aconn =
-				(struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context;
-
-			if (aconn->psr_skip_count > 0)
-				aconn->psr_skip_count--;
-
-			/* Allow PSR when skip count is 0. */
-			acrtc_attach->dm_irq_params.allow_psr_entry = !aconn->psr_skip_count;
-
-			/*
-			 * If sink supports PSR SU, there is no need to rely on
-			 * a vblank event disable request to enable PSR. PSR SU
-			 * can be enabled immediately once OS demonstrates an
-			 * adequate number of fast atomic commits to notify KMD
-			 * of update events. See `vblank_control_worker()`.
-			 */
-			if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 &&
-			    acrtc_attach->dm_irq_params.allow_psr_entry &&
-#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY
-			    !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) &&
-#endif
-			    !acrtc_state->stream->link->psr_settings.psr_allow_active &&
-			    !aconn->disallow_edp_enter_psr &&
-			    (timestamp_ns -
-			    acrtc_state->stream->link->psr_settings.psr_dirty_rects_change_timestamp_ns) >
-			    500000000)
-				amdgpu_dm_psr_enable(acrtc_state->stream);
-		} else {
-			acrtc_attach->dm_irq_params.allow_psr_entry = false;
-		}
-
+		amdgpu_dm_enable_self_refresh(acrtc_attach, acrtc_state, timestamp_ns);
 		mutex_unlock(&dm->dc_lock);
 	}
 
@@ -12080,7 +12083,7 @@ static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 			break;
 	}
 
-	while (j < EDID_LENGTH) {
+	while (j < EDID_LENGTH - sizeof(struct amd_vsdb_block)) {
 		struct amd_vsdb_block *amd_vsdb = (struct amd_vsdb_block *)&edid_ext[j];
 		unsigned int ieeeId = (amd_vsdb->ieee_id[2] << 16) | (amd_vsdb->ieee_id[1] << 8) | (amd_vsdb->ieee_id[0]);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 15d4690c74d6..90dfffec33cf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -727,7 +727,7 @@ struct amdgpu_dm_connector {
 	/* Cached display modes */
 	struct drm_display_mode freesync_vid_base;
 
-	int psr_skip_count;
+	int sr_skip_count;
 	bool disallow_edp_enter_psr;
 
 	/* Record progress status of mst*/
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index a2cf2c066a76..288be19db7c1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -266,11 +266,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	 * where the SU region is the full hactive*vactive region. See
 	 * fill_dc_dirty_rects().
 	 */
-	if (vblank_work->stream && vblank_work->stream->link) {
+	if (vblank_work->stream && vblank_work->stream->link && vblank_work->acrtc) {
 		amdgpu_dm_crtc_set_panel_sr_feature(
 			vblank_work, vblank_work->enable,
-			vblank_work->acrtc->dm_irq_params.allow_psr_entry ||
-			vblank_work->stream->link->replay_settings.replay_feature_enabled);
+			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
 	if (dm->active_vblank_irq_count == 0) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
index 5c9303241aeb..6a7ecc1e4602 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -33,7 +33,7 @@ struct dm_irq_params {
 	struct mod_vrr_params vrr_params;
 	struct dc_stream_state *stream;
 	int active_planes;
-	bool allow_psr_entry;
+	bool allow_sr_entry;
 	struct mod_freesync_config freesync_config;
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index be8fbb04ad98..c9a6de110b74 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -3122,14 +3122,12 @@ static enum bp_result bios_parser_get_vram_info(
 		struct dc_vram_info *info)
 {
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
-	static enum bp_result result = BP_RESULT_BADBIOSTABLE;
+	enum bp_result result = BP_RESULT_BADBIOSTABLE;
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
 
 	// vram info moved to umc_info for DCN4x
-	if (dcb->ctx->dce_version >= DCN_VERSION_4_01 &&
-		dcb->ctx->dce_version < DCN_VERSION_MAX &&
-		info && DATA_TABLES(umc_info)) {
+	if (info && DATA_TABLES(umc_info)) {
 		header = GET_IMAGE(struct atom_common_table_header,
 					DATA_TABLES(umc_info));
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
index 2597e3fd562b..e006f816ff2f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
@@ -265,6 +265,9 @@ struct dc_state *dc_state_create_copy(struct dc_state *src_state)
 	dc_state_copy_internal(new_state, src_state);
 
 #ifdef CONFIG_DRM_AMD_DC_FP
+	new_state->bw_ctx.dml2 = NULL;
+	new_state->bw_ctx.dml2_dc_power_source = NULL;
+
 	if (src_state->bw_ctx.dml2 &&
 			!dml2_create_copy(&new_state->bw_ctx.dml2, src_state->bw_ctx.dml2)) {
 		dc_state_release(new_state);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
index 1cf9015e854a..dd9971867f74 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c
@@ -8,6 +8,7 @@
 #include "dml2_pmo_dcn4_fams2.h"
 
 static const double MIN_VACTIVE_MARGIN_PCT = 0.25; // We need more than non-zero margin because DET buffer granularity can alter vactive latency hiding
+static const double MIN_BLANK_STUTTER_FACTOR = 3.0;
 
 static const struct dml2_pmo_pstate_strategy base_strategy_list_1_display[] = {
 	// VActive Preferred
@@ -2139,6 +2140,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 	struct dml2_pmo_instance *pmo = in_out->instance;
 	bool stutter_period_meets_z8_eco = true;
 	bool z8_stutter_optimization_too_expensive = false;
+	bool stutter_optimization_too_expensive = false;
 	double line_time_us, vblank_nom_time_us;
 
 	unsigned int i;
@@ -2160,10 +2162,15 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		line_time_us = (double)in_out->base_display_config->display_config.stream_descriptors[i].timing.h_total / (in_out->base_display_config->display_config.stream_descriptors[i].timing.pixel_clock_khz * 1000) * 1000000;
 		vblank_nom_time_us = line_time_us * in_out->base_display_config->display_config.stream_descriptors[i].timing.vblank_nom;
 
-		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us) {
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
 			z8_stutter_optimization_too_expensive = true;
 			break;
 		}
+
+		if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) {
+			stutter_optimization_too_expensive = true;
+			break;
+		}
 	}
 
 	pmo->scratch.pmo_dcn4.num_stutter_candidates = 0;
@@ -2179,7 +2186,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in
 		pmo->scratch.pmo_dcn4.z8_vblank_optimizable = false;
 	}
 
-	if (pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
+	if (!stutter_optimization_too_expensive && pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) {
 		pmo->scratch.pmo_dcn4.optimal_vblank_reserved_time_for_stutter_us[pmo->scratch.pmo_dcn4.num_stutter_candidates] = (unsigned int)pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us;
 		pmo->scratch.pmo_dcn4.num_stutter_candidates++;
 	}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
index 8798ebfcea83..84f9b007b59f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c
@@ -1132,7 +1132,7 @@ static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu,
 static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 					enum smu_clk_type clk_type, char *buf)
 {
-	int i, size = 0, ret = 0;
+	int i, idx, ret = 0, size = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t min, max;
 
@@ -1168,7 +1168,8 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu,
 			break;
 
 		for (i = 0; i < count; i++) {
-			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value);
+			idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i;
+			ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, idx, &value);
 			if (ret)
 				break;
 
diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c
index 0e8813278a2f..bb1750a3dab0 100644
--- a/drivers/gpu/drm/bridge/tc358768.c
+++ b/drivers/gpu/drm/bridge/tc358768.c
@@ -125,6 +125,9 @@
 #define TC358768_DSI_CONFW_MODE_CLR	(6 << 29)
 #define TC358768_DSI_CONFW_ADDR_DSI_CONTROL	(0x3 << 24)
 
+/* TC358768_DSICMD_TX (0x0600) register */
+#define TC358768_DSI_CMDTX_DC_START	BIT(0)
+
 static const char * const tc358768_supplies[] = {
 	"vddc", "vddmipi", "vddio"
 };
@@ -229,6 +232,21 @@ static void tc358768_update_bits(struct tc358768_priv *priv, u32 reg, u32 mask,
 		tc358768_write(priv, reg, tmp);
 }
 
+static void tc358768_dsicmd_tx(struct tc358768_priv *priv)
+{
+	u32 val;
+
+	/* start transfer */
+	tc358768_write(priv, TC358768_DSICMD_TX, TC358768_DSI_CMDTX_DC_START);
+	if (priv->error)
+		return;
+
+	/* wait transfer completion */
+	priv->error = regmap_read_poll_timeout(priv->regmap, TC358768_DSICMD_TX, val,
+					       (val & TC358768_DSI_CMDTX_DC_START) == 0,
+					       100, 100000);
+}
+
 static int tc358768_sw_reset(struct tc358768_priv *priv)
 {
 	/* Assert Reset */
@@ -516,8 +534,7 @@ static ssize_t tc358768_dsi_host_transfer(struct mipi_dsi_host *host,
 		}
 	}
 
-	/* start transfer */
-	tc358768_write(priv, TC358768_DSICMD_TX, 1);
+	tc358768_dsicmd_tx(priv);
 
 	ret = tc358768_clear_error(priv);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 581844d1db9a..5fee4be64592 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -928,7 +928,7 @@ intel_enable_tv(struct intel_atomic_state *state,
 		const struct intel_crtc_state *pipe_config,
 		const struct drm_connector_state *conn_state)
 {
-	struct intel_display *display = to_intel_display(state);
+	struct intel_display *display = to_intel_display(encoder);
 
 	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
 	intel_crtc_wait_for_next_vblank(to_intel_crtc(pipe_config->uapi.crtc));
@@ -942,7 +942,7 @@ intel_disable_tv(struct intel_atomic_state *state,
 		 const struct intel_crtc_state *old_crtc_state,
 		 const struct drm_connector_state *old_conn_state)
 {
-	struct intel_display *display = to_intel_display(state);
+	struct intel_display *display = to_intel_display(encoder);
 
 	intel_de_rmw(display, TV_CTL, TV_ENC_ENABLE, 0);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
index 551b0d7974ff..5dc0ccd07636 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
@@ -80,6 +80,7 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s
 	const struct intel_gsc_cpd_header_v2 *cpd_header = NULL;
 	const struct intel_gsc_cpd_entry *cpd_entry = NULL;
 	const struct intel_gsc_manifest_header *manifest;
+	struct intel_uc_fw_ver min_ver = { 0 };
 	size_t min_size = sizeof(*layout);
 	int i;
 
@@ -212,33 +213,46 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s
 		}
 	}
 
-	if (IS_ARROWLAKE(gt->i915)) {
+	/*
+	 * ARL SKUs require newer firmwares, but the blob is actually common
+	 * across all MTL and ARL SKUs, so we need to do an explicit version check
+	 * here rather than using a separate table entry. If a too old version
+	 * is found, then just don't use GSC rather than aborting the driver load.
+	 * Note that the major number in the GSC FW version is used to indicate
+	 * the platform, so we expect it to always be 102 for MTL/ARL binaries.
+	 */
+	if (IS_ARROWLAKE_S(gt->i915))
+		min_ver = (struct intel_uc_fw_ver){ 102, 0, 10, 1878 };
+	else if (IS_ARROWLAKE_H(gt->i915) || IS_ARROWLAKE_U(gt->i915))
+		min_ver = (struct intel_uc_fw_ver){ 102, 1, 15, 1926 };
+
+	if (IS_METEORLAKE(gt->i915) && gsc->release.major != 102) {
+		gt_info(gt, "Invalid GSC firmware for MTL/ARL, got %d.%d.%d.%d but need 102.x.x.x",
+			gsc->release.major, gsc->release.minor,
+			gsc->release.patch, gsc->release.build);
+			return -EINVAL;
+	}
+
+	if (min_ver.major) {
 		bool too_old = false;
 
-		/*
-		 * ARL requires a newer firmware than MTL did (102.0.10.1878) but the
-		 * firmware is actually common. So, need to do an explicit version check
-		 * here rather than using a separate table entry. And if the older
-		 * MTL-only version is found, then just don't use GSC rather than aborting
-		 * the driver load.
-		 */
-		if (gsc->release.major < 102) {
+		if (gsc->release.minor < min_ver.minor) {
 			too_old = true;
-		} else if (gsc->release.major == 102) {
-			if (gsc->release.minor == 0) {
-				if (gsc->release.patch < 10) {
+		} else if (gsc->release.minor == min_ver.minor) {
+			if (gsc->release.patch < min_ver.patch) {
+				too_old = true;
+			} else if (gsc->release.patch == min_ver.patch) {
+				if (gsc->release.build < min_ver.build)
 					too_old = true;
-				} else if (gsc->release.patch == 10) {
-					if (gsc->release.build < 1878)
-						too_old = true;
-				}
 			}
 		}
 
 		if (too_old) {
-			gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least 102.0.10.1878",
+			gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least %d.%d.%d.%d",
 				gsc->release.major, gsc->release.minor,
-				gsc->release.patch, gsc->release.build);
+				gsc->release.patch, gsc->release.build,
+				min_ver.major, min_ver.minor,
+				min_ver.patch, min_ver.build);
 			return -EINVAL;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 39f6614a0a99..aa0b1bfb38e0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -540,8 +540,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_LUNARLAKE(i915) (0 && i915)
 #define IS_BATTLEMAGE(i915)  (0 && i915)
 
-#define IS_ARROWLAKE(i915) \
-	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL)
+#define IS_ARROWLAKE_H(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_H)
+#define IS_ARROWLAKE_U(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_U)
+#define IS_ARROWLAKE_S(i915) \
+	IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_S)
 #define IS_DG2_G10(i915) \
 	IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10)
 #define IS_DG2_G11(i915) \
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 3c47c625993e..467999249b9a 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -200,8 +200,16 @@ static const u16 subplatform_g12_ids[] = {
 	INTEL_DG2_G12_IDS(ID),
 };
 
-static const u16 subplatform_arl_ids[] = {
-	INTEL_ARL_IDS(ID),
+static const u16 subplatform_arl_h_ids[] = {
+	INTEL_ARL_H_IDS(ID),
+};
+
+static const u16 subplatform_arl_u_ids[] = {
+	INTEL_ARL_U_IDS(ID),
+};
+
+static const u16 subplatform_arl_s_ids[] = {
+	INTEL_ARL_S_IDS(ID),
 };
 
 static bool find_devid(u16 id, const u16 *p, unsigned int num)
@@ -261,9 +269,15 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915)
 	} else if (find_devid(devid, subplatform_g12_ids,
 			      ARRAY_SIZE(subplatform_g12_ids))) {
 		mask = BIT(INTEL_SUBPLATFORM_G12);
-	} else if (find_devid(devid, subplatform_arl_ids,
-			      ARRAY_SIZE(subplatform_arl_ids))) {
-		mask = BIT(INTEL_SUBPLATFORM_ARL);
+	} else if (find_devid(devid, subplatform_arl_h_ids,
+			      ARRAY_SIZE(subplatform_arl_h_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_H);
+	} else if (find_devid(devid, subplatform_arl_u_ids,
+			      ARRAY_SIZE(subplatform_arl_u_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_U);
+	} else if (find_devid(devid, subplatform_arl_s_ids,
+			      ARRAY_SIZE(subplatform_arl_s_ids))) {
+		mask = BIT(INTEL_SUBPLATFORM_ARL_S);
 	}
 
 	GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK);
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 643ff1bf74ee..a9fcaf33df9e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -128,7 +128,9 @@ enum intel_platform {
 #define INTEL_SUBPLATFORM_RPLU  2
 
 /* MTL */
-#define INTEL_SUBPLATFORM_ARL	0
+#define INTEL_SUBPLATFORM_ARL_H	0
+#define INTEL_SUBPLATFORM_ARL_U	1
+#define INTEL_SUBPLATFORM_ARL_S	2
 
 enum intel_ppgtt_type {
 	INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
index 027867c2a8c5..99110ab2f44d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c
@@ -992,7 +992,7 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8
 		ctrl->data = data;
 
 		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
-		if (ret == -EAGAIN && ctrl->retryTimeMs) {
+		if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) {
 			/*
 			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
 			 * by GSP before retrying again
@@ -1060,33 +1060,44 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize)
 	NV0073_CTRL_DP_AUXCH_CTRL_PARAMS *ctrl;
 	u8 size = *psize;
 	int ret;
+	int retries;
 
-	ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl));
-	if (IS_ERR(ctrl))
-		return PTR_ERR(ctrl);
+	for (retries = 0; retries < 3; ++retries) {
+		ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl));
+		if (IS_ERR(ctrl))
+			return PTR_ERR(ctrl);
 
-	ctrl->subDeviceInstance = 0;
-	ctrl->displayId = BIT(outp->index);
-	ctrl->bAddrOnly = !size;
-	ctrl->cmd = type;
-	if (ctrl->bAddrOnly) {
-		ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE);
-		ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD,  I2C_MOT, FALSE);
-	}
-	ctrl->addr = addr;
-	ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
-	memcpy(ctrl->data, data, size);
+		ctrl->subDeviceInstance = 0;
+		ctrl->displayId = BIT(outp->index);
+		ctrl->bAddrOnly = !size;
+		ctrl->cmd = type;
+		if (ctrl->bAddrOnly) {
+			ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE);
+			ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD,  I2C_MOT, FALSE);
+		}
+		ctrl->addr = addr;
+		ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0;
+		memcpy(ctrl->data, data, size);
 
-	ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
-	if (ret) {
-		nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
-		return ret;
+		ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl));
+		if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) {
+			/*
+			 * Device (likely an eDP panel) isn't ready yet, wait for the time specified
+			 * by GSP before retrying again
+			 */
+			nvkm_debug(&disp->engine.subdev,
+				   "Waiting %dms for GSP LT panel delay before retrying in AUX\n",
+				   ctrl->retryTimeMs);
+			msleep(ctrl->retryTimeMs);
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+		} else {
+			memcpy(data, ctrl->data, size);
+			*psize = ctrl->size;
+			ret = ctrl->replyType;
+			nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
+			break;
+		}
 	}
-
-	memcpy(data, ctrl->data, size);
-	*psize = ctrl->size;
-	ret = ctrl->replyType;
-	nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
index a1c8545f1249..cac6d64ab67d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@@ -89,11 +89,6 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 		nvkm_falcon_fw_dtor_sigs(fw);
 	}
 
-	/* after last write to the img, sync dma mappings */
-	dma_sync_single_for_device(fw->fw.device->dev,
-				   fw->fw.phys,
-				   sg_dma_len(&fw->fw.mem.sgl),
-				   DMA_TO_DEVICE);
 
 	FLCNFW_DBG(fw, "resetting");
 	fw->func->reset(fw);
@@ -105,6 +100,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 			goto done;
 	}
 
+	/* after last write to the img, sync dma mappings */
+	dma_sync_single_for_device(fw->fw.device->dev,
+				   fw->fw.phys,
+				   sg_dma_len(&fw->fw.mem.sgl),
+				   DMA_TO_DEVICE);
+
 	ret = fw->func->load(fw);
 	if (ret)
 		goto done;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
index cf58f9da9139..d586aea30898 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
@@ -78,7 +78,7 @@ r535_rpc_status_to_errno(uint32_t rpc_status)
 	switch (rpc_status) {
 	case 0x55: /* NV_ERR_NOT_READY */
 	case 0x66: /* NV_ERR_TIMEOUT_RETRY */
-		return -EAGAIN;
+		return -EBUSY;
 	case 0x51: /* NV_ERR_NO_MEMORY */
 		return -ENOMEM;
 	default:
@@ -601,7 +601,7 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc)
 
 	if (rpc->status) {
 		ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status));
-		if (PTR_ERR(ret) != -EAGAIN)
+		if (PTR_ERR(ret) != -EAGAIN && PTR_ERR(ret) != -EBUSY)
 			nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status);
 	} else {
 		ret = repc ? rpc->params : NULL;
@@ -660,7 +660,7 @@ r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc)
 
 	if (rpc->status) {
 		ret = r535_rpc_status_to_errno(rpc->status);
-		if (ret != -EAGAIN)
+		if (ret != -EAGAIN && ret != -EBUSY)
 			nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n",
 				   object->client->object.handle, object->handle, rpc->cmd, rpc->status);
 	}
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 7db2edb3374c..0e6f94df690d 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -990,6 +990,8 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot,
 
 		if (!size)
 			break;
+
+		offset = 0;
 	}
 
 	return panthor_vm_flush_range(vm, start_iova, iova - start_iova);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index f161f40d8ce4..69900138295b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1093,10 +1093,10 @@ static int vop_plane_atomic_async_check(struct drm_plane *plane,
 	if (!plane->state->fb)
 		return -EINVAL;
 
-	if (state)
-		crtc_state = drm_atomic_get_existing_crtc_state(state,
-								new_plane_state->crtc);
-	else /* Special case for asynchronous cursor updates. */
+	crtc_state = drm_atomic_get_existing_crtc_state(state, new_plane_state->crtc);
+
+	/* Special case for asynchronous cursor updates. */
+	if (!crtc_state)
 		crtc_state = plane->crtc->state;
 
 	return drm_atomic_helper_check_plane_state(plane->state, crtc_state,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 63b8d7591253..10d596cb4b40 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1265,6 +1265,8 @@ static int vmw_framebuffer_surface_create_handle(struct drm_framebuffer *fb,
 	struct vmw_framebuffer_surface *vfbs = vmw_framebuffer_to_vfbs(fb);
 	struct vmw_bo *bo = vmw_user_object_buffer(&vfbs->uo);
 
+	if (WARN_ON(!bo))
+		return -EINVAL;
 	return drm_gem_handle_create(file_priv, &bo->tbo.base, handle);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index e5f51fd23c65..2a093540354e 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -886,8 +886,8 @@ int xe_bo_evict_pinned(struct xe_bo *bo)
 	if (WARN_ON(!xe_bo_is_pinned(bo)))
 		return -EINVAL;
 
-	if (WARN_ON(!xe_bo_is_vram(bo)))
-		return -EINVAL;
+	if (!xe_bo_is_vram(bo))
+		return 0;
 
 	ret = ttm_bo_mem_space(&bo->ttm, &placement, &new_mem, &ctx);
 	if (ret)
@@ -937,6 +937,7 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
 		.interruptible = false,
 	};
 	struct ttm_resource *new_mem;
+	struct ttm_place *place = &bo->placements[0];
 	int ret;
 
 	xe_bo_assert_held(bo);
@@ -947,9 +948,15 @@ int xe_bo_restore_pinned(struct xe_bo *bo)
 	if (WARN_ON(!xe_bo_is_pinned(bo)))
 		return -EINVAL;
 
-	if (WARN_ON(xe_bo_is_vram(bo) || !bo->ttm.ttm))
+	if (WARN_ON(xe_bo_is_vram(bo)))
+		return -EINVAL;
+
+	if (WARN_ON(!bo->ttm.ttm && !xe_bo_is_stolen(bo)))
 		return -EINVAL;
 
+	if (!mem_type_is_vram(place->mem_type))
+		return 0;
+
 	ret = ttm_bo_mem_space(&bo->ttm, &bo->placement, &new_mem, &ctx);
 	if (ret)
 		return ret;
@@ -1719,6 +1726,7 @@ int xe_bo_pin_external(struct xe_bo *bo)
 
 int xe_bo_pin(struct xe_bo *bo)
 {
+	struct ttm_place *place = &bo->placements[0];
 	struct xe_device *xe = xe_bo_device(bo);
 	int err;
 
@@ -1749,21 +1757,21 @@ int xe_bo_pin(struct xe_bo *bo)
 	 */
 	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
 	    bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
-		struct ttm_place *place = &(bo->placements[0]);
-
 		if (mem_type_is_vram(place->mem_type)) {
 			xe_assert(xe, place->flags & TTM_PL_FLAG_CONTIGUOUS);
 
 			place->fpfn = (xe_bo_addr(bo, 0, PAGE_SIZE) -
 				       vram_region_gpu_offset(bo->ttm.resource)) >> PAGE_SHIFT;
 			place->lpfn = place->fpfn + (bo->size >> PAGE_SHIFT);
-
-			spin_lock(&xe->pinned.lock);
-			list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
-			spin_unlock(&xe->pinned.lock);
 		}
 	}
 
+	if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+		spin_lock(&xe->pinned.lock);
+		list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present);
+		spin_unlock(&xe->pinned.lock);
+	}
+
 	ttm_bo_pin(&bo->ttm);
 
 	/*
@@ -1809,23 +1817,18 @@ void xe_bo_unpin_external(struct xe_bo *bo)
 
 void xe_bo_unpin(struct xe_bo *bo)
 {
+	struct ttm_place *place = &bo->placements[0];
 	struct xe_device *xe = xe_bo_device(bo);
 
 	xe_assert(xe, !bo->ttm.base.import_attach);
 	xe_assert(xe, xe_bo_is_pinned(bo));
 
-	if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) &&
-	    bo->flags & XE_BO_FLAG_INTERNAL_TEST)) {
-		struct ttm_place *place = &(bo->placements[0]);
-
-		if (mem_type_is_vram(place->mem_type)) {
-			spin_lock(&xe->pinned.lock);
-			xe_assert(xe, !list_empty(&bo->pinned_link));
-			list_del_init(&bo->pinned_link);
-			spin_unlock(&xe->pinned.lock);
-		}
+	if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) {
+		spin_lock(&xe->pinned.lock);
+		xe_assert(xe, !list_empty(&bo->pinned_link));
+		list_del_init(&bo->pinned_link);
+		spin_unlock(&xe->pinned.lock);
 	}
-
 	ttm_bo_unpin(&bo->ttm);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c
index 541b49007d73..8fb2be061003 100644
--- a/drivers/gpu/drm/xe/xe_bo_evict.c
+++ b/drivers/gpu/drm/xe/xe_bo_evict.c
@@ -34,14 +34,22 @@ int xe_bo_evict_all(struct xe_device *xe)
 	u8 id;
 	int ret;
 
-	if (!IS_DGFX(xe))
-		return 0;
-
 	/* User memory */
-	for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) {
+	for (mem_type = XE_PL_TT; mem_type <= XE_PL_VRAM1; ++mem_type) {
 		struct ttm_resource_manager *man =
 			ttm_manager_type(bdev, mem_type);
 
+		/*
+		 * On igpu platforms with flat CCS we need to ensure we save and restore any CCS
+		 * state since this state lives inside graphics stolen memory which doesn't survive
+		 * hibernation.
+		 *
+		 * This can be further improved by only evicting objects that we know have actually
+		 * used a compression enabled PAT index.
+		 */
+		if (mem_type == XE_PL_TT && (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe)))
+			continue;
+
 		if (man) {
 			ret = ttm_resource_manager_evict_all(bdev, man);
 			if (ret)
@@ -125,9 +133,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 	struct xe_bo *bo;
 	int ret;
 
-	if (!IS_DGFX(xe))
-		return 0;
-
 	spin_lock(&xe->pinned.lock);
 	for (;;) {
 		bo = list_first_entry_or_null(&xe->pinned.evicted,
@@ -159,7 +164,6 @@ int xe_bo_restore_kernel(struct xe_device *xe)
 		 * should setup the iosys map.
 		 */
 		xe_assert(xe, !iosys_map_is_null(&bo->vmap));
-		xe_assert(xe, xe_bo_is_vram(bo));
 
 		xe_bo_put(bo);
 
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 756b492f13b0..31cca938956f 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -203,14 +203,14 @@ retry:
 		write_locked = false;
 	}
 	if (err)
-		goto err_syncs;
+		goto err_hw_exec_mode;
 
 	if (write_locked) {
 		err = xe_vm_userptr_pin(vm);
 		downgrade_write(&vm->lock);
 		write_locked = false;
 		if (err)
-			goto err_hw_exec_mode;
+			goto err_unlock_list;
 	}
 
 	if (!args->num_batch_buffer) {
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 2804f14f8f29..78823f53d290 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1206,9 +1206,11 @@ static int xe_oa_release(struct inode *inode, struct file *file)
 	struct xe_oa_stream *stream = file->private_data;
 	struct xe_gt *gt = stream->gt;
 
+	xe_pm_runtime_get(gt_to_xe(gt));
 	mutex_lock(&gt->oa.gt_lock);
 	xe_oa_destroy_locked(stream);
 	mutex_unlock(&gt->oa.gt_lock);
+	xe_pm_runtime_put(gt_to_xe(gt));
 
 	/* Release the reference the OA stream kept on the driver */
 	drm_dev_put(&gt_to_xe(gt)->drm);
diff --git a/include/drm/intel/i915_pciids.h b/include/drm/intel/i915_pciids.h
index 2bf03ebfcf73..f35534522d33 100644
--- a/include/drm/intel/i915_pciids.h
+++ b/include/drm/intel/i915_pciids.h
@@ -771,13 +771,24 @@
 	INTEL_ATS_M150_IDS(MACRO__, ## __VA_ARGS__), \
 	INTEL_ATS_M75_IDS(MACRO__, ## __VA_ARGS__)
 
-/* MTL */
-#define INTEL_ARL_IDS(MACRO__, ...) \
-	MACRO__(0x7D41, ## __VA_ARGS__), \
+/* ARL */
+#define INTEL_ARL_H_IDS(MACRO__, ...) \
 	MACRO__(0x7D51, ## __VA_ARGS__), \
-	MACRO__(0x7D67, ## __VA_ARGS__), \
 	MACRO__(0x7DD1, ## __VA_ARGS__)
 
+#define INTEL_ARL_U_IDS(MACRO__, ...) \
+	MACRO__(0x7D41, ## __VA_ARGS__) \
+
+#define INTEL_ARL_S_IDS(MACRO__, ...) \
+	MACRO__(0x7D67, ## __VA_ARGS__), \
+	MACRO__(0xB640, ## __VA_ARGS__)
+
+#define INTEL_ARL_IDS(MACRO__, ...) \
+	INTEL_ARL_H_IDS(MACRO__, ## __VA_ARGS__), \
+	INTEL_ARL_U_IDS(MACRO__, ## __VA_ARGS__), \
+	INTEL_ARL_S_IDS(MACRO__, ## __VA_ARGS__)
+
+/* MTL */
 #define INTEL_MTL_IDS(MACRO__, ...) \
 	INTEL_ARL_IDS(MACRO__, ## __VA_ARGS__), \
 	MACRO__(0x7D40, ## __VA_ARGS__), \