Merge tag 'timers-v6.11-rc1' of https://git.linaro.org/people/daniel.lezcano/linux into timers/core

Pull clocksource/event driver updates from Daniel Lezcano: - Remove unnecessary local variables initialization as they will be initialized in the code path anyway right after on the ARM arch timer and the ARM global timer (Li kunyu) - Fix a race condition in the interrupt leading to a deadlock on the SH CMT driver. Note that this fix was not tested on the platform using this timer but the fix seems reasonable enough to be picked confidently (Niklas Söderlund) - Increase the rating of the gic-timer and use the configured width clocksource register on the MIPS architecture (Jiaxun Yang) - Add the DT bindings for the TMU on the Renesas platforms (Geert Uytterhoeven) - Add the DT bindings for the SOPHGO SG2002 clint on RiscV (Thomas Bonnefille) - Add the rtl-otto timer driver along with the DT bindings for the Realtek platform (Chris Packham) Link: https://lore.kernel.org/all/91cd05de-4c5d-4242-a381-3b8a4fe6a2a2@linaro.org
author: Thomas Gleixner <tglx@linutronix.de> 2024-07-13 12:07:10 +0200
committer: Thomas Gleixner <tglx@linutronix.de> 2024-07-13 12:07:10 +0200
commit: b7625d67eb1a63d33b0a2a4518ce4897d27f7465 (patch)
tree: 372459935f602bac331ad0185f2dc5cc23d76924 /drivers/gpu
parent: f7d43dd206e7e18c182f200e67a8db8c209907fa (diff)
parent: 4bdc3eaa102b6bedb0800f76f53eca516d5cf20c (diff)
download: lwn-b7625d67eb1a63d33b0a2a4518ce4897d27f7465.tar.gz
lwn-b7625d67eb1a63d33b0a2a4518ce4897d27f7465.zip
80 files changed, 712 insertions, 309 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 026444eeb5c6..d0aa277fc3bf 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -450,6 +450,7 @@ config DRM_PRIVACY_SCREEN
 config DRM_WERROR
 	bool "Compile the drm subsystem with warnings as errors"
 	depends on DRM && EXPERT
+	depends on !WERROR
 	default n
 	help
 	  A kernel build should not cause any compiler warnings, and this
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 108003bdf1e9..2e13c7c4b2b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -400,7 +400,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = vram_info->v30.channel_num;
 					mem_channel_width = vram_info->v30.channel_width;
 					if (vram_width)
-						*vram_width = mem_channel_number * (1 << mem_channel_width);
+						*vram_width = mem_channel_number * 16;
 					break;
 				default:
 					return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 932dc93b2e63..33f791d92ddf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5220,11 +5220,14 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
 
 	dev_info(adev->dev, "GPU mode1 reset\n");
 
+	/* Cache the state before bus master disable. The saved config space
+	 * values are used in other cases like restore after mode-2 reset.
+	 */
+	amdgpu_device_cache_pci_state(adev->pdev);
+
 	/* disable BM */
 	pci_clear_master(adev->pdev);
 
-	amdgpu_device_cache_pci_state(adev->pdev);
-
 	if (amdgpu_dpm_is_mode1_reset_supported(adev)) {
 		dev_info(adev->dev, "GPU smu mode1 reset\n");
 		ret = amdgpu_dpm_mode1_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 055ba2ea4c12..662d0f28f358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -41,8 +41,6 @@
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
 #include <linux/pci-p2pdma.h>
-#include <linux/pm_runtime.h>
-#include "amdgpu_trace.h"
 
 /**
  * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
@@ -58,42 +56,11 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	struct drm_gem_object *obj = dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	int r;
 
 	if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
 
-	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(1, __func__);
-	if (r < 0)
-		goto out;
-
 	return 0;
-
-out:
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(0, __func__);
-	return r;
-}
-
-/**
- * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
- *
- * @dmabuf: DMA-buf where we remove the attachment from
- * @attach: the attachment to remove
- *
- * Called when an attachment is removed from the DMA-buf.
- */
-static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
-				  struct dma_buf_attachment *attach)
-{
-	struct drm_gem_object *obj = dmabuf->priv;
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-
-	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
-	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(0, __func__);
 }
 
 /**
@@ -267,7 +234,6 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.attach = amdgpu_dma_buf_attach,
-	.detach = amdgpu_dma_buf_detach,
 	.pin = amdgpu_dma_buf_pin,
 	.unpin = amdgpu_dma_buf_unpin,
 	.map_dma_buf = amdgpu_dma_buf_map,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 10832b470448..bc3ac73b6b8d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -181,7 +181,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
 	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
-	trace_amdgpu_runpm_reference_dumps(1, __func__);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
 		struct dma_fence *old;
@@ -309,7 +308,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 		dma_fence_put(fence);
 		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
-		trace_amdgpu_runpm_reference_dumps(0, __func__);
 	} while (last_seq != seq);
 
 	return true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 67c234bcf89f..3adaa4670103 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -108,6 +108,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size,
 
 	memset(&bp, 0, sizeof(bp));
 	*obj = NULL;
+	flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
 
 	bp.size = size;
 	bp.byte_align = alignment;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index be4629cdac04..08b9dfb65335 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -684,12 +684,17 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	signed long r;
+	int r;
 	uint32_t seq;
 
-	if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready ||
-	    !down_read_trylock(&adev->reset_domain->sem)) {
+	/*
+	 * A GPU reset should flush all TLBs anyway, so no need to do
+	 * this while one is ongoing.
+	 */
+	if (!down_read_trylock(&adev->reset_domain->sem))
+		return 0;
 
+	if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) {
 		if (adev->gmc.flush_tlb_needs_extra_type_2)
 			adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid,
 								 2, all_hub,
@@ -703,43 +708,40 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 		adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid,
 							 flush_type, all_hub,
 							 inst);
-		return 0;
-	}
+		r = 0;
+	} else {
+		/* 2 dwords flush + 8 dwords fence */
+		ndw = kiq->pmf->invalidate_tlbs_size + 8;
 
-	/* 2 dwords flush + 8 dwords fence */
-	ndw = kiq->pmf->invalidate_tlbs_size + 8;
+		if (adev->gmc.flush_tlb_needs_extra_type_2)
+			ndw += kiq->pmf->invalidate_tlbs_size;
 
-	if (adev->gmc.flush_tlb_needs_extra_type_2)
-		ndw += kiq->pmf->invalidate_tlbs_size;
+		if (adev->gmc.flush_tlb_needs_extra_type_0)
+			ndw += kiq->pmf->invalidate_tlbs_size;
 
-	if (adev->gmc.flush_tlb_needs_extra_type_0)
-		ndw += kiq->pmf->invalidate_tlbs_size;
+		spin_lock(&adev->gfx.kiq[inst].ring_lock);
+		amdgpu_ring_alloc(ring, ndw);
+		if (adev->gmc.flush_tlb_needs_extra_type_2)
+			kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);
 
-	spin_lock(&adev->gfx.kiq[inst].ring_lock);
-	amdgpu_ring_alloc(ring, ndw);
-	if (adev->gmc.flush_tlb_needs_extra_type_2)
-		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);
+		if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0)
+			kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub);
 
-	if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0)
-		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub);
+		kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub);
+		r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+		if (r) {
+			amdgpu_ring_undo(ring);
+			spin_unlock(&adev->gfx.kiq[inst].ring_lock);
+			goto error_unlock_reset;
+		}
 
-	kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub);
-	r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
-	if (r) {
-		amdgpu_ring_undo(ring);
+		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		goto error_unlock_reset;
-	}
-
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-	r = amdgpu_fence_wait_polling(ring, seq, usec_timeout);
-	if (r < 1) {
-		dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
-		r = -ETIME;
-		goto error_unlock_reset;
+		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+			dev_err(adev->dev, "timeout waiting for kiq fence\n");
+			r = -ETIME;
+		}
 	}
-	r = 0;
 
 error_unlock_reset:
 	up_read(&adev->reset_domain->sem);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 8d8c39be6129..c556c8b653fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -604,8 +604,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (!amdgpu_bo_support_uswc(bo->flags))
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
 
-	bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
-
 	bo->tbo.bdev = &adev->mman.bdev;
 	if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA |
 			  AMDGPU_GEM_DOMAIN_GDS))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 4bd4602d11b1..cef9dd0a012b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -640,6 +640,20 @@ static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id)
 	}
 }
 
+static bool psp_err_warn(struct psp_context *psp)
+{
+	struct psp_gfx_cmd_resp *cmd = psp->cmd_buf_mem;
+
+	/* This response indicates reg list is already loaded */
+	if (amdgpu_ip_version(psp->adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 2) &&
+	    cmd->cmd_id == GFX_CMD_ID_LOAD_IP_FW &&
+	    cmd->cmd.cmd_load_ip_fw.fw_type == GFX_FW_TYPE_REG_LIST &&
+	    cmd->resp.status == TEE_ERROR_CANCEL)
+		return false;
+
+	return true;
+}
+
 static int
 psp_cmd_submit_buf(struct psp_context *psp,
 		   struct amdgpu_firmware_info *ucode,
@@ -699,10 +713,13 @@ psp_cmd_submit_buf(struct psp_context *psp,
 			dev_warn(psp->adev->dev,
 				 "failed to load ucode %s(0x%X) ",
 				 amdgpu_ucode_name(ucode->ucode_id), ucode->ucode_id);
-		dev_warn(psp->adev->dev,
-			 "psp gfx command %s(0x%X) failed and response status is (0x%X)\n",
-			 psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id), psp->cmd_buf_mem->cmd_id,
-			 psp->cmd_buf_mem->resp.status);
+		if (psp_err_warn(psp))
+			dev_warn(
+				psp->adev->dev,
+				"psp gfx command %s(0x%X) failed and response status is (0x%X)\n",
+				psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id),
+				psp->cmd_buf_mem->cmd_id,
+				psp->cmd_buf_mem->resp.status);
 		/* If any firmware (including CAP) load fails under SRIOV, it should
 		 * return failure to stop the VF from initializing.
 		 * Also return failure in case of timeout
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 7aafeb763e5d..383fce40d4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -554,21 +554,6 @@ TRACE_EVENT(amdgpu_reset_reg_dumps,
 		      __entry->value)
 );
 
-TRACE_EVENT(amdgpu_runpm_reference_dumps,
-	    TP_PROTO(uint32_t index, const char *func),
-	    TP_ARGS(index, func),
-	    TP_STRUCT__entry(
-			     __field(uint32_t, index)
-			     __string(func, func)
-			     ),
-	    TP_fast_assign(
-			   __entry->index = index;
-			   __assign_str(func);
-			   ),
-	    TP_printk("amdgpu runpm reference dump 0x%x: 0x%s\n",
-		      __entry->index,
-		      __get_str(func))
-);
 #undef AMDGPU_JOB_GET_TIMELINE_NAME
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index e30eecd02ae1..fde66225c481 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -3,6 +3,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_simple_kms_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_vblank.h>
 
 #include "amdgpu.h"
@@ -314,7 +315,13 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane,
 		return 0;
 	}
 	afb = to_amdgpu_framebuffer(new_state->fb);
-	obj = new_state->fb->obj[0];
+
+	obj = drm_gem_fb_get_obj(new_state->fb, 0);
+	if (!obj) {
+		DRM_ERROR("Failed to get obj from framebuffer\n");
+		return -EINVAL;
+	}
+
 	rbo = gem_to_amdgpu_bo(obj);
 	adev = amdgpu_ttm_adev(rbo->tbo.bdev);
 
@@ -368,12 +375,19 @@ static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane,
 				   struct drm_plane_state *old_state)
 {
 	struct amdgpu_bo *rbo;
+	struct drm_gem_object *obj;
 	int r;
 
 	if (!old_state->fb)
 		return;
 
-	rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]);
+	obj = drm_gem_fb_get_obj(old_state->fb, 0);
+	if (!obj) {
+		DRM_ERROR("Failed to get obj from framebuffer\n");
+		return;
+	}
+
+	rbo = gem_to_amdgpu_bo(obj);
 	r = amdgpu_bo_reserve(rbo, false);
 	if (unlikely(r)) {
 		DRM_ERROR("failed to reserve rbo before unpin\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 7b16e8cca86a..f5b9f443cfdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -4195,9 +4195,10 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_i
 static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 				 struct amdgpu_cu_info *cu_info)
 {
-	int i, j, k, counter, xcc_id, active_cu_number = 0;
-	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0;
+	int i, j, k, prev_counter, counter, xcc_id, active_cu_number = 0;
+	u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0, tmp;
 	unsigned disable_masks[4 * 4];
+	bool is_symmetric_cus;
 
 	if (!adev || !cu_info)
 		return -EINVAL;
@@ -4215,6 +4216,7 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) {
+		is_symmetric_cus = true;
 		for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
 			for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
 				mask = 1;
@@ -4242,6 +4244,15 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev,
 					ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8));
 				cu_info->ao_cu_bitmap[i][j] = ao_bitmap;
 			}
+			if (i && is_symmetric_cus && prev_counter != counter)
+				is_symmetric_cus = false;
+			prev_counter = counter;
+		}
+		if (is_symmetric_cus) {
+			tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG);
+			tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_RELAUNCH_DISABLE, 1);
+			tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_DISPATCH_DISABLE, 1);
+			WREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG, tmp);
 		}
 		gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff,
 					    xcc_id);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 0d1407f25005..32d4519541c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -154,18 +154,18 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 						    void *pkt, int size,
 						    int api_status_off)
 {
-	int ndw = size / 4;
-	signed long r;
-	union MESAPI__MISC *x_pkt = pkt;
-	struct MES_API_STATUS *api_status;
+	union MESAPI__QUERY_MES_STATUS mes_status_pkt;
+	signed long timeout = 3000000; /* 3000 ms */
 	struct amdgpu_device *adev = mes->adev;
 	struct amdgpu_ring *ring = &mes->ring;
-	unsigned long flags;
-	signed long timeout = 3000000; /* 3000 ms */
+	struct MES_API_STATUS *api_status;
+	union MESAPI__MISC *x_pkt = pkt;
 	const char *op_str, *misc_op_str;
-	u32 fence_offset;
-	u64 fence_gpu_addr;
-	u64 *fence_ptr;
+	unsigned long flags;
+	u64 status_gpu_addr;
+	u32 status_offset;
+	u64 *status_ptr;
+	signed long r;
 	int ret;
 
 	if (x_pkt->header.opcode >= MES_SCH_API_MAX)
@@ -177,28 +177,38 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 		/* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
 		timeout = 15 * 600 * 1000;
 	}
-	BUG_ON(size % 4 != 0);
 
-	ret = amdgpu_device_wb_get(adev, &fence_offset);
+	ret = amdgpu_device_wb_get(adev, &status_offset);
 	if (ret)
 		return ret;
-	fence_gpu_addr =
-		adev->wb.gpu_addr + (fence_offset * 4);
-	fence_ptr = (u64 *)&adev->wb.wb[fence_offset];
-	*fence_ptr = 0;
+
+	status_gpu_addr = adev->wb.gpu_addr + (status_offset * 4);
+	status_ptr = (u64 *)&adev->wb.wb[status_offset];
+	*status_ptr = 0;
 
 	spin_lock_irqsave(&mes->ring_lock, flags);
-	if (amdgpu_ring_alloc(ring, ndw)) {
-		spin_unlock_irqrestore(&mes->ring_lock, flags);
-		amdgpu_device_wb_free(adev, fence_offset);
-		return -ENOMEM;
-	}
+	r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4);
+	if (r)
+		goto error_unlock_free;
 
 	api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
-	api_status->api_completion_fence_addr = fence_gpu_addr;
+	api_status->api_completion_fence_addr = status_gpu_addr;
 	api_status->api_completion_fence_value = 1;
 
-	amdgpu_ring_write_multiple(ring, pkt, ndw);
+	amdgpu_ring_write_multiple(ring, pkt, size / 4);
+
+	memset(&mes_status_pkt, 0, sizeof(mes_status_pkt));
+	mes_status_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS;
+	mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+	mes_status_pkt.api_status.api_completion_fence_addr =
+		ring->fence_drv.gpu_addr;
+	mes_status_pkt.api_status.api_completion_fence_value =
+		++ring->fence_drv.sync_seq;
+
+	amdgpu_ring_write_multiple(ring, &mes_status_pkt,
+				   sizeof(mes_status_pkt) / 4);
+
 	amdgpu_ring_commit(ring);
 	spin_unlock_irqrestore(&mes->ring_lock, flags);
 
@@ -206,15 +216,16 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 	misc_op_str = mes_v11_0_get_misc_op_string(x_pkt);
 
 	if (misc_op_str)
-		dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, misc_op_str);
+		dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str,
+			misc_op_str);
 	else if (op_str)
 		dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str);
 	else
-		dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode);
+		dev_dbg(adev->dev, "MES msg=%d was emitted\n",
+			x_pkt->header.opcode);
 
-	r = amdgpu_mes_fence_wait_polling(fence_ptr, (u64)1, timeout);
-	amdgpu_device_wb_free(adev, fence_offset);
-	if (r < 1) {
+	r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
+	if (r < 1 || !*status_ptr) {
 
 		if (misc_op_str)
 			dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n",
@@ -229,10 +240,19 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
 		while (halt_if_hws_hang)
 			schedule();
 
-		return -ETIMEDOUT;
+		r = -ETIMEDOUT;
+		goto error_wb_free;
 	}
 
+	amdgpu_device_wb_free(adev, status_offset);
 	return 0;
+
+error_unlock_free:
+	spin_unlock_irqrestore(&mes->ring_lock, flags);
+
+error_wb_free:
+	amdgpu_device_wb_free(adev, status_offset);
+	return r;
 }
 
 static int convert_to_mes_queue_type(int queue_type)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 7566973ed8f5..37b5ddd6f13b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -464,8 +464,9 @@ struct psp_gfx_rb_frame
 #define PSP_ERR_UNKNOWN_COMMAND 0x00000100
 
 enum tee_error_code {
-    TEE_SUCCESS                         = 0x00000000,
-    TEE_ERROR_NOT_SUPPORTED             = 0xFFFF000A,
+	TEE_SUCCESS			= 0x00000000,
+	TEE_ERROR_CANCEL		= 0xFFFF0002,
+	TEE_ERROR_NOT_SUPPORTED		= 0xFFFF000A,
 };
 
 #endif /* _PSP_TEE_GFX_IF_H_ */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
index f08a32c18694..40b28298af30 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c
@@ -32,7 +32,9 @@
 #include "mp/mp_14_0_2_sh_mask.h"
 
 MODULE_FIRMWARE("amdgpu/psp_14_0_2_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_2_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_14_0_3_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_14_0_3_ta.bin");
 
 /* For large FW files the time to complete can be very long */
 #define USBC_PD_POLLING_LIMIT_S 240
@@ -66,6 +68,9 @@ static int psp_v14_0_init_microcode(struct psp_context *psp)
 		err = psp_init_sos_microcode(psp, ucode_prefix);
 		if (err)
 			return err;
+		err = psp_init_ta_microcode(psp, ucode_prefix);
+		if (err)
+			return err;
 		break;
 	default:
 		BUG();
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 5fcd4f778dc3..47b8b49da8a7 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -8,7 +8,7 @@ config DRM_AMD_DC
 	depends on BROKEN || !CC_IS_CLANG || ARM64 || RISCV || SPARC64 || X86_64
 	select SND_HDA_COMPONENT if SND_HDA_CORE
 	# !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752
-	select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && (!ARM64 || !CC_IS_CLANG)
+	select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || RISCV))
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
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 f1d67c6f4b98..3cdcadd41be1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -9169,9 +9169,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	trace_amdgpu_dm_atomic_commit_tail_begin(state);
 
-	if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed)
-		dc_allow_idle_optimizations(dm->dc, false);
-
 	drm_atomic_helper_update_legacy_modeset_state(dev, state);
 	drm_dp_mst_atomic_wait_for_dependencies(state);
 
@@ -10051,6 +10048,7 @@ skip_modeset:
 	}
 
 	/* Update Freesync settings. */
+	reset_freesync_config_for_crtc(dm_new_crtc_state);
 	get_freesync_config_for_crtc(dm_new_crtc_state,
 				     dm_new_conn_state);
 
@@ -11184,6 +11182,49 @@ static bool parse_edid_cea(struct amdgpu_dm_connector *aconnector,
 	return ret;
 }
 
+static void parse_edid_displayid_vrr(struct drm_connector *connector,
+		struct edid *edid)
+{
+	u8 *edid_ext = NULL;
+	int i;
+	int j = 0;
+	u16 min_vfreq;
+	u16 max_vfreq;
+
+	if (edid == NULL || edid->extensions == 0)
+		return;
+
+	/* Find DisplayID extension */
+	for (i = 0; i < edid->extensions; i++) {
+		edid_ext = (void *)(edid + (i + 1));
+		if (edid_ext[0] == DISPLAYID_EXT)
+			break;
+	}
+
+	if (edid_ext == NULL)
+		return;
+
+	while (j < EDID_LENGTH) {
+		/* Get dynamic video timing range from DisplayID if available */
+		if (EDID_LENGTH - j > 13 && edid_ext[j] == 0x25	&&
+		    (edid_ext[j+1] & 0xFE) == 0 && (edid_ext[j+2] == 9)) {
+			min_vfreq = edid_ext[j+9];
+			if (edid_ext[j+1] & 7)
+				max_vfreq = edid_ext[j+10] + ((edid_ext[j+11] & 3) << 8);
+			else
+				max_vfreq = edid_ext[j+10];
+
+			if (max_vfreq && min_vfreq) {
+				connector->display_info.monitor_range.max_vfreq = max_vfreq;
+				connector->display_info.monitor_range.min_vfreq = min_vfreq;
+
+				return;
+			}
+		}
+		j++;
+	}
+}
+
 static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector,
 			  struct edid *edid, struct amdgpu_hdmi_vsdb_info *vsdb_info)
 {
@@ -11305,6 +11346,11 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 	if (!adev->dm.freesync_module)
 		goto update;
 
+	/* Some eDP panels only have the refresh rate range info in DisplayID */
+	if ((connector->display_info.monitor_range.min_vfreq == 0 ||
+	     connector->display_info.monitor_range.max_vfreq == 0))
+		parse_edid_displayid_vrr(connector, edid);
+
 	if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT ||
 		     sink->sink_signal == SIGNAL_TYPE_EDP)) {
 		bool edid_check_required = false;
@@ -11312,9 +11358,11 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector,
 		if (is_dp_capable_without_timing_msa(adev->dm.dc,
 						     amdgpu_dm_connector)) {
 			if (edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ) {
-				freesync_capable = true;
 				amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq;
 				amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq;
+				if (amdgpu_dm_connector->max_vfreq -
+				    amdgpu_dm_connector->min_vfreq > 10)
+					freesync_capable = true;
 			} else {
 				edid_check_required = edid->version > 1 ||
 						      (edid->version == 1 &&
@@ -11440,6 +11488,12 @@ void amdgpu_dm_trigger_timing_sync(struct drm_device *dev)
 	mutex_unlock(&adev->dm.dc_lock);
 }
 
+static inline void amdgpu_dm_exit_ips_for_hw_access(struct dc *dc)
+{
+	if (dc->ctx->dmub_srv && !dc->ctx->dmub_srv->idle_exit_counter)
+		dc_exit_ips_for_hw_access(dc);
+}
+
 void dm_write_reg_func(const struct dc_context *ctx, uint32_t address,
 		       u32 value, const char *func_name)
 {
@@ -11450,6 +11504,8 @@ void dm_write_reg_func(const struct dc_context *ctx, uint32_t address,
 		return;
 	}
 #endif
+
+	amdgpu_dm_exit_ips_for_hw_access(ctx->dc);
 	cgs_write_register(ctx->cgs_device, address, value);
 	trace_amdgpu_dc_wreg(&ctx->perf_trace->write_count, address, value);
 }
@@ -11473,6 +11529,8 @@ uint32_t dm_read_reg_func(const struct dc_context *ctx, uint32_t address,
 		return 0;
 	}
 
+	amdgpu_dm_exit_ips_for_hw_access(ctx->dc);
+
 	value = cgs_read_register(ctx->cgs_device, address);
 
 	trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
index 6c84b0fa40f4..0782a34689a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
@@ -3364,6 +3364,9 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							&mode_lib->vba.UrgentBurstFactorLumaPre[k],
 							&mode_lib->vba.UrgentBurstFactorChromaPre[k],
 							&mode_lib->vba.NotUrgentLatencyHidingPre[k]);
+
+					v->cursor_bw_pre[k] = mode_lib->vba.NumberOfCursors[k] * mode_lib->vba.CursorWidth[k][0] * mode_lib->vba.CursorBPP[k][0] /
+							8.0 / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]) * v->VRatioPreY[i][j][k];
 				}
 
 				{
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index 60f251cf973b..beed7adbbd43 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -177,7 +177,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
 	.urgent_latency_vm_data_only_us = 4.0,
-	.dram_clock_change_latency_us = 11.72,
+	.dram_clock_change_latency_us = 34.0,
 	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index e4f333d4fb54..a201dbb743d7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -215,7 +215,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = {
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
 	.urgent_latency_vm_data_only_us = 4.0,
-	.dram_clock_change_latency_us = 11.72,
+	.dram_clock_change_latency_us = 34,
 	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index a41812598ce8..8ecc972dbffd 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -234,6 +234,7 @@ void dml2_init_socbb_params(struct dml2_context *dml2, const struct dc *in_dc, s
 		out->round_trip_ping_latency_dcfclk_cycles = 106;
 		out->smn_latency_us = 2;
 		out->dispclk_dppclk_vco_speed_mhz = 3600;
+		out->pct_ideal_dram_bw_after_urgent_pixel_only = 65.0;
 		break;
 
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
index 0f8b3336e26d..cbd1c1f26b7a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_utils.c
@@ -294,7 +294,7 @@ void dml2_calculate_rq_and_dlg_params(const struct dc *dc, struct dc_state *cont
 	context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = (unsigned int)in_ctx->v20.dml_core_ctx.mp.DCFCLKDeepSleep * 1000;
 	context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
 
-	if (in_ctx->v20.dml_core_ctx.ms.support.FCLKChangeSupport[in_ctx->v20.scratch.mode_support_params.out_lowest_state_idx] == dml_fclock_change_unsupported)
+	if (in_ctx->v20.dml_core_ctx.ms.support.FCLKChangeSupport[0] == dml_fclock_change_unsupported)
 		context->bw_ctx.bw.dcn.clk.fclk_p_state_change_support = false;
 	else
 		context->bw_ctx.bw.dcn.clk.fclk_p_state_change_support = true;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index 5295f52e4fc8..dcced89c07b3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -1439,3 +1439,75 @@ void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx,
 		}
 	}
 }
+
+static bool should_avoid_empty_tu(struct pipe_ctx *pipe_ctx)
+{
+	/* Calculate average pixel count per TU, return false if under ~2.00 to
+	 * avoid empty TUs. This is only required for DPIA tunneling as empty TUs
+	 * are legal to generate for native DP links. Assume TU size 64 as there
+	 * is currently no scenario where it's reprogrammed from HW default.
+	 * MTPs have no such limitation, so this does not affect MST use cases.
+	 */
+	unsigned int pix_clk_mhz;
+	unsigned int symclk_mhz;
+	unsigned int avg_pix_per_tu_x1000;
+	unsigned int tu_size_bytes = 64;
+	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
+	struct dc_link_settings *link_settings = &pipe_ctx->link_config.dp_link_settings;
+	const struct dc *dc = pipe_ctx->stream->link->dc;
+
+	if (pipe_ctx->stream->link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
+		return false;
+
+	// Not necessary for MST configurations
+	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
+		return false;
+
+	pix_clk_mhz = timing->pix_clk_100hz / 10000;
+
+	// If this is true, can't block due to dynamic ODM
+	if (pix_clk_mhz > dc->clk_mgr->bw_params->clk_table.entries[0].dispclk_mhz)
+		return false;
+
+	switch (link_settings->link_rate) {
+	case LINK_RATE_LOW:
+		symclk_mhz = 162;
+		break;
+	case LINK_RATE_HIGH:
+		symclk_mhz = 270;
+		break;
+	case LINK_RATE_HIGH2:
+		symclk_mhz = 540;
+		break;
+	case LINK_RATE_HIGH3:
+		symclk_mhz = 810;
+		break;
+	default:
+		// We shouldn't be tunneling any other rates, something is wrong
+		ASSERT(0);
+		return false;
+	}
+
+	avg_pix_per_tu_x1000 = (1000 * pix_clk_mhz * tu_size_bytes)
+		/ (symclk_mhz * link_settings->lane_count);
+
+	// Add small empirically-decided margin to account for potential jitter
+	return (avg_pix_per_tu_x1000 < 2020);
+}
+
+bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx)
+{
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
+
+	if (!is_h_timing_divisible_by_2(pipe_ctx->stream))
+		return false;
+
+	if (should_avoid_empty_tu(pipe_ctx))
+		return false;
+
+	if (dc_is_dp_signal(pipe_ctx->stream->signal) && !dc->link_srv->dp_is_128b_132b_signal(pipe_ctx) &&
+		dc->debug.enable_dp_dig_pixel_rate_div_policy)
+		return true;
+
+	return false;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
index a731c8880d60..f0ea7d1511ae 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
@@ -95,4 +95,6 @@ void dcn35_set_static_screen_control(struct pipe_ctx **pipe_ctx,
 void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx,
 		int num_pipes, uint32_t v_total_min, uint32_t v_total_max);
 
+bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx);
+
 #endif /* __DC_HWSS_DCN35_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
index df3bf77f3fb4..199781233fd5 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
@@ -158,7 +158,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	.setup_hpo_hw_control = dcn35_setup_hpo_hw_control,
 	.calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values,
 	.set_pixels_per_cycle = dcn32_set_pixels_per_cycle,
-	.is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy,
+	.is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy,
 	.dsc_pg_control = dcn35_dsc_pg_control,
 	.dsc_pg_status = dcn32_dsc_pg_status,
 	.enable_plane = dcn35_enable_plane,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index a01d0842bf8e..d487dfcd219b 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -1590,9 +1590,17 @@ static bool retrieve_link_cap(struct dc_link *link)
 			return false;
 	}
 
-	if (dp_is_lttpr_present(link))
+	if (dp_is_lttpr_present(link)) {
 		configure_lttpr_mode_transparent(link);
 
+		// Echo TOTAL_LTTPR_CNT back downstream
+		core_link_write_dpcd(
+				link,
+				DP_TOTAL_LTTPR_CNT,
+				&link->dpcd_caps.lttpr_caps.phy_repeater_cnt,
+				sizeof(link->dpcd_caps.lttpr_caps.phy_repeater_cnt));
+	}
+
 	/* Read DP tunneling information. */
 	status = dpcd_get_tunneling_device_data(link);
 
diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
index 914f28e9f224..aee5170f5fb2 100644
--- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h
+++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
@@ -177,4 +177,9 @@ enum dpcd_psr_sink_states {
 #define DP_SINK_PR_PIXEL_DEVIATION_PER_LINE     0x379
 #define DP_SINK_PR_MAX_NUMBER_OF_DEVIATION_LINE 0x37A
 
+/* Remove once drm_dp_helper.h is updated upstream */
+#ifndef DP_TOTAL_LTTPR_CNT
+#define DP_TOTAL_LTTPR_CNT                                  0xF000A /* 2.1 */
+#endif
+
 #endif /* __DAL_DPCD_DEFS_H__ */
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 571691837200..09cbc3afd6d8 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -734,7 +734,7 @@ struct atom_gpio_pin_lut_v2_1
 {
   struct  atom_common_table_header  table_header;
   /*the real number of this included in the structure is calcualted by using the (whole structure size - the header size)/size of atom_gpio_pin_lut  */
-  struct  atom_gpio_pin_assignment  gpio_pin[8];
+  struct  atom_gpio_pin_assignment  gpio_pin[];
 };
 
 
diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h
index 2e8e6c9875f6..f83ace2d7ec3 100644
--- a/drivers/gpu/drm/amd/include/pptable.h
+++ b/drivers/gpu/drm/amd/include/pptable.h
@@ -477,31 +477,30 @@ typedef struct _ATOM_PPLIB_STATE_V2
 } ATOM_PPLIB_STATE_V2;
 
 typedef struct _StateArray{
-    //how many states we have 
-    UCHAR ucNumEntries;
-    
-    ATOM_PPLIB_STATE_V2 states[1];
+	//how many states we have
+	UCHAR ucNumEntries;
+
+	ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */;
 }StateArray;
 
 
 typedef struct _ClockInfoArray{
-    //how many clock levels we have
-    UCHAR ucNumEntries;
-    
-    //sizeof(ATOM_PPLIB_CLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    UCHAR clockInfo[];
+	//how many clock levels we have
+	UCHAR ucNumEntries;
+
+	//sizeof(ATOM_PPLIB_CLOCK_INFO)
+	UCHAR ucEntrySize;
+
+	UCHAR clockInfo[];
 }ClockInfoArray;
 
 typedef struct _NonClockInfoArray{
+	//how many non-clock levels we have. normally should be same as number of states
+	UCHAR ucNumEntries;
+	//sizeof(ATOM_PPLIB_NONCLOCK_INFO)
+	UCHAR ucEntrySize;
 
-    //how many non-clock levels we have. normally should be same as number of states
-    UCHAR ucNumEntries;
-    //sizeof(ATOM_PPLIB_NONCLOCK_INFO)
-    UCHAR ucEntrySize;
-    
-    ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[];
+	ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries);
 }NonClockInfoArray;
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
@@ -513,8 +512,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table
 {
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1];             // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_Clock_Voltage_Dependency_Table;
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
@@ -529,8 +530,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table
 {
-    UCHAR ucNumEntries;                                                // Number of entries.
-    ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1];                  // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_Clock_Voltage_Limit_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_Clock_Voltage_Limit_Table;
 
 union _ATOM_PPLIB_CAC_Leakage_Record
@@ -553,8 +556,10 @@ typedef union _ATOM_PPLIB_CAC_Leakage_Record ATOM_PPLIB_CAC_Leakage_Record;
 
 typedef struct _ATOM_PPLIB_CAC_Leakage_Table
 {
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_CAC_Leakage_Record entries[1];                           // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_CAC_Leakage_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_CAC_Leakage_Table;
 
 typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
@@ -568,8 +573,10 @@ typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record
 
 typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table
 {
-    UCHAR ucNumEntries;                                                 // Number of entries.
-    ATOM_PPLIB_PhaseSheddingLimits_Record entries[1];                   // Dynamically allocate entries.
+	// Number of entries.
+	UCHAR ucNumEntries;
+	// Dynamically allocate entries.
+	ATOM_PPLIB_PhaseSheddingLimits_Record entries[] __counted_by(ucNumEntries);
 }ATOM_PPLIB_PhaseSheddingLimits_Table;
 
 typedef struct _VCEClockInfo{
@@ -580,8 +587,8 @@ typedef struct _VCEClockInfo{
 }VCEClockInfo;
 
 typedef struct _VCEClockInfoArray{
-    UCHAR ucNumEntries;
-    VCEClockInfo entries[1];
+	UCHAR ucNumEntries;
+	VCEClockInfo entries[] __counted_by(ucNumEntries);
 }VCEClockInfoArray;
 
 typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
@@ -592,8 +599,8 @@ typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_VCE_State_Record
@@ -604,8 +611,8 @@ typedef struct _ATOM_PPLIB_VCE_State_Record
 
 typedef struct _ATOM_PPLIB_VCE_State_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_VCE_State_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_VCE_State_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_VCE_State_Table;
 
 
@@ -626,8 +633,8 @@ typedef struct _UVDClockInfo{
 }UVDClockInfo;
 
 typedef struct _UVDClockInfoArray{
-    UCHAR ucNumEntries;
-    UVDClockInfo entries[1];
+	UCHAR ucNumEntries;
+	UVDClockInfo entries[] __counted_by(ucNumEntries);
 }UVDClockInfoArray;
 
 typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
@@ -638,8 +645,8 @@ typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record
 
 typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table
 {
-    UCHAR numEntries;
-    ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_UVD_Table
@@ -657,8 +664,8 @@ typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record
 }ATOM_PPLIB_SAMClk_Voltage_Limit_Record;
 
 typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{
-    UCHAR numEntries;
-    ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[];
+	UCHAR numEntries;
+	ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_SAMClk_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_SAMU_Table
@@ -675,8 +682,8 @@ typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Record
 }ATOM_PPLIB_ACPClk_Voltage_Limit_Record;
 
 typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Table{
-    UCHAR numEntries;
-    ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[1];
+	UCHAR numEntries;
+	ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[] __counted_by(numEntries);
 }ATOM_PPLIB_ACPClk_Voltage_Limit_Table;
 
 typedef struct _ATOM_PPLIB_ACP_Table
@@ -743,9 +750,9 @@ typedef struct ATOM_PPLIB_VQ_Budgeting_Record{
 } ATOM_PPLIB_VQ_Budgeting_Record;
 
 typedef struct ATOM_PPLIB_VQ_Budgeting_Table {
-    UCHAR revid;
-    UCHAR numEntries;
-    ATOM_PPLIB_VQ_Budgeting_Record         entries[1];
+	UCHAR revid;
+	UCHAR numEntries;
+	ATOM_PPLIB_VQ_Budgeting_Record entries[] __counted_by(numEntries);
 } ATOM_PPLIB_VQ_Budgeting_Table;
 
 #pragma pack()
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 6bb42d04b247..e8b6989a40f3 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -164,6 +164,8 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev,
 
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) {
 		if (table[i].ulSupportedSCLK != 0) {
+			if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES)
+				continue;
 			vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit =
 				table[i].usVoltageID;
 			vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit =
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 7789b313285c..e1796ecf9c05 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -324,6 +324,18 @@ static int smu_dpm_set_umsch_mm_enable(struct smu_context *smu,
 	return ret;
 }
 
+static int smu_set_mall_enable(struct smu_context *smu)
+{
+	int ret = 0;
+
+	if (!smu->ppt_funcs->set_mall_enable)
+		return 0;
+
+	ret = smu->ppt_funcs->set_mall_enable(smu);
+
+	return ret;
+}
+
 /**
  * smu_dpm_set_power_gate - power gate/ungate the specific IP block
  *
@@ -1791,6 +1803,7 @@ static int smu_hw_init(void *handle)
 		smu_dpm_set_jpeg_enable(smu, true);
 		smu_dpm_set_vpe_enable(smu, true);
 		smu_dpm_set_umsch_mm_enable(smu, true);
+		smu_set_mall_enable(smu);
 		smu_set_gfx_cgpg(smu, true);
 	}
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 0917dec8efe3..64ccdb5f14ea 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1395,6 +1395,11 @@ struct pptable_funcs {
 	int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable);
 
 	/**
+	 * @set_mall_enable: Init MALL power gating control.
+	 */
+	int (*set_mall_enable)(struct smu_context *smu);
+
+	/**
 	 * @notify_rlc_state: Notify RLC power state to SMU.
 	 */
 	int (*notify_rlc_state)(struct smu_context *smu, bool en);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
index c4dc5881d8df..e7f5ef49049f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h
@@ -106,8 +106,8 @@
 #define PPSMC_MSG_DisableLSdma                  0x35 ///< Disable LSDMA
 #define PPSMC_MSG_SetSoftMaxVpe                 0x36 ///<
 #define PPSMC_MSG_SetSoftMinVpe                 0x37 ///<
-#define PPSMC_MSG_AllocMALLCache                0x38 ///< Allocating MALL Cache
-#define PPSMC_MSG_ReleaseMALLCache              0x39 ///< Releasing MALL Cache
+#define PPSMC_MSG_MALLPowerController           0x38 ///< Set MALL control
+#define PPSMC_MSG_MALLPowerState                0x39 ///< Enter/Exit MALL PG
 #define PPSMC_Message_Count                     0x3A ///< Total number of PPSMC messages
 /** @}*/
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index c48214e3dc8e..2e32b085824a 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -272,7 +272,9 @@
 	__SMU_DUMMY_MAP(SetSoftMinVpe), \
 	__SMU_DUMMY_MAP(GetMetricsVersion), \
 	__SMU_DUMMY_MAP(EnableUCLKShadow), \
-	__SMU_DUMMY_MAP(RmaDueToBadPageThreshold),
+	__SMU_DUMMY_MAP(RmaDueToBadPageThreshold), \
+	__SMU_DUMMY_MAP(MALLPowerController), \
+	__SMU_DUMMY_MAP(MALLPowerState),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
index bc241b593db1..b6257f34a7c6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
@@ -226,15 +226,17 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	if (!en && adev->in_s4) {
-		/* Adds a GFX reset as workaround just before sending the
-		 * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
-		 * an invalid state.
-		 */
-		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
-						      SMU_RESET_MODE_2, NULL);
-		if (ret)
-			return ret;
+	if (!en && !adev->in_s0ix) {
+		if (adev->in_s4) {
+			/* Adds a GFX reset as workaround just before sending the
+			 * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering
+			 * an invalid state.
+			 */
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset,
+							      SMU_RESET_MODE_2, NULL);
+			if (ret)
+				return ret;
+		}
 
 		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL);
 	}
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 e4419e1561ef..18abfbd6d059 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
@@ -52,6 +52,19 @@
 #define mmMP1_SMN_C2PMSG_90			0x029a
 #define mmMP1_SMN_C2PMSG_90_BASE_IDX		    0
 
+/* MALLPowerController message arguments (Defines for the Cache mode control) */
+#define SMU_MALL_PMFW_CONTROL 0
+#define SMU_MALL_DRIVER_CONTROL 1
+
+/*
+ * MALLPowerState message arguments
+ * (Defines for the Allocate/Release Cache mode if in driver mode)
+ */
+#define SMU_MALL_EXIT_PG 0
+#define SMU_MALL_ENTER_PG 1
+
+#define SMU_MALL_PG_CONFIG_DEFAULT SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON
+
 #define FEATURE_MASK(feature) (1ULL << feature)
 #define SMC_DPM_FEATURE ( \
 	FEATURE_MASK(FEATURE_CCLK_DPM_BIT) | \
@@ -66,6 +79,12 @@
 	FEATURE_MASK(FEATURE_GFX_DPM_BIT)	| \
 	FEATURE_MASK(FEATURE_VPE_DPM_BIT))
 
+enum smu_mall_pg_config {
+	SMU_MALL_PG_CONFIG_PMFW_CONTROL = 0,
+	SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON = 1,
+	SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_OFF = 2,
+};
+
 static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,                    PPSMC_MSG_TestMessage,				1),
 	MSG_MAP(GetSmuVersion,                  PPSMC_MSG_GetPmfwVersion,			1),
@@ -113,6 +132,8 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(PowerDownUmsch,                 PPSMC_MSG_PowerDownUmsch,			1),
 	MSG_MAP(SetSoftMaxVpe,                  PPSMC_MSG_SetSoftMaxVpe,			1),
 	MSG_MAP(SetSoftMinVpe,                  PPSMC_MSG_SetSoftMinVpe,			1),
+	MSG_MAP(MALLPowerController,            PPSMC_MSG_MALLPowerController,		1),
+	MSG_MAP(MALLPowerState,                 PPSMC_MSG_MALLPowerState,			1),
 };
 
 static struct cmn2asic_mapping smu_v14_0_0_feature_mask_map[SMU_FEATURE_COUNT] = {
@@ -1423,6 +1444,57 @@ static int smu_v14_0_common_get_dpm_table(struct smu_context *smu, struct dpm_cl
 	return 0;
 }
 
+static int smu_v14_0_1_init_mall_power_gating(struct smu_context *smu, enum smu_mall_pg_config pg_config)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+
+	if (pg_config == SMU_MALL_PG_CONFIG_PMFW_CONTROL) {
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerController,
+								SMU_MALL_PMFW_CONTROL, NULL);
+		if (ret) {
+			dev_err(adev->dev, "Init MALL PMFW CONTROL Failure\n");
+			return ret;
+		}
+	} else {
+		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerController,
+								SMU_MALL_DRIVER_CONTROL, NULL);
+		if (ret) {
+			dev_err(adev->dev, "Init MALL Driver CONTROL Failure\n");
+			return ret;
+		}
+
+		if (pg_config == SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON) {
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerState,
+									SMU_MALL_EXIT_PG, NULL);
+			if (ret) {
+				dev_err(adev->dev, "EXIT MALL PG Failure\n");
+				return ret;
+			}
+		} else if (pg_config == SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_OFF) {
+			ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerState,
+									SMU_MALL_ENTER_PG, NULL);
+			if (ret) {
+				dev_err(adev->dev, "Enter MALL PG Failure\n");
+				return ret;
+			}
+		}
+	}
+
+	return ret;
+}
+
+static int smu_v14_0_common_set_mall_enable(struct smu_context *smu)
+{
+	enum smu_mall_pg_config pg_config = SMU_MALL_PG_CONFIG_DEFAULT;
+	int ret = 0;
+
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1))
+		ret = smu_v14_0_1_init_mall_power_gating(smu, pg_config);
+
+	return ret;
+}
+
 static const struct pptable_funcs smu_v14_0_0_ppt_funcs = {
 	.check_fw_status = smu_v14_0_check_fw_status,
 	.check_fw_version = smu_v14_0_check_fw_version,
@@ -1454,6 +1526,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = {
 	.dpm_set_vpe_enable = smu_v14_0_0_set_vpe_enable,
 	.dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable,
 	.get_dpm_clock_table = smu_v14_0_common_get_dpm_table,
+	.set_mall_enable = smu_v14_0_common_set_mall_enable,
 };
 
 static void smu_v14_0_0_set_smu_mailbox_registers(struct smu_context *smu)
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
index d8e449e6ebda..50cb8f7ee6b2 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
@@ -72,11 +72,6 @@ struct gamma_curve_sector {
 	u32 segment_width;
 };
 
-struct gamma_curve_segment {
-	u32 start;
-	u32 end;
-};
-
 static struct gamma_curve_sector sector_tbl[] = {
 	{ 0,    4,  4   },
 	{ 16,   4,  4   },
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
index 14ee79becacb..5ba62e637a61 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
@@ -12,10 +12,8 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/dma-mapping.h>
-#ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-#endif
 
 #include <drm/drm_print.h>
 
@@ -43,7 +41,6 @@ static int komeda_register_show(struct seq_file *sf, void *x)
 
 DEFINE_SHOW_ATTRIBUTE(komeda_register);
 
-#ifdef CONFIG_DEBUG_FS
 static void komeda_debugfs_init(struct komeda_dev *mdev)
 {
 	if (!debugfs_initialized())
@@ -55,7 +52,6 @@ static void komeda_debugfs_init(struct komeda_dev *mdev)
 	debugfs_create_x16("err_verbosity", 0664, mdev->debugfs_root,
 			   &mdev->err_verbosity);
 }
-#endif
 
 static ssize_t
 core_id_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -265,9 +261,7 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 
 	mdev->err_verbosity = KOMEDA_DEV_PRINT_ERR_EVENTS;
 
-#ifdef CONFIG_DEBUG_FS
 	komeda_debugfs_init(mdev);
-#endif
 
 	return mdev;
 
@@ -286,9 +280,7 @@ void komeda_dev_destroy(struct komeda_dev *mdev)
 
 	sysfs_remove_group(&dev->kobj, &komeda_sysfs_attr_group);
 
-#ifdef CONFIG_DEBUG_FS
 	debugfs_remove_recursive(mdev->debugfs_root);
-#endif
 
 	if (mdev->aclk)
 		clk_prepare_enable(mdev->aclk);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index f3e744172673..f4e76b46ca32 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c,
 	u32 avail_scalers;
 
 	pipe_st = komeda_pipeline_get_state(c->pipeline, state);
-	if (!pipe_st)
+	if (IS_ERR_OR_NULL(pipe_st))
 		return NULL;
 
 	avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 32506524d9a2..fe5fb08c9fc4 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -360,9 +360,12 @@ EXPORT_SYMBOL(drm_panel_bridge_set_orientation);
 
 static void devm_drm_panel_bridge_release(struct device *dev, void *res)
 {
-	struct drm_bridge **bridge = res;
+	struct drm_bridge *bridge = *(struct drm_bridge **)res;
 
-	drm_panel_bridge_remove(*bridge);
+	if (!bridge)
+		return;
+
+	drm_bridge_remove(bridge);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d612133e2cf7..117237d3528b 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -524,6 +524,9 @@ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper)
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
+	if (!drm_leak_fbdev_smem)
+		info->flags |= FBINFO_HIDE_SMEM_START;
+
 	ret = fb_alloc_cmap(&info->cmap, 256, 0);
 	if (ret)
 		goto err_release;
@@ -1860,9 +1863,6 @@ __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper)
 	info = fb_helper->info;
 	info->var.pixclock = 0;
 
-	if (!drm_leak_fbdev_smem)
-		info->flags |= FBINFO_HIDE_SMEM_START;
-
 	/* Need to drop locks to avoid recursive deadlock in
 	 * register_framebuffer. This is ok because the only thing left to do is
 	 * register the fbdev emulation instance in kernel_fb_helper_list. */
diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index 6c9427bb4053..13cd754af311 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -130,7 +130,10 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
 		info->flags |= FBINFO_READS_FAST; /* signal caching */
 	info->screen_size = sizes->surface_height * fb->pitches[0];
 	info->screen_buffer = map.vaddr;
-	info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
+		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
+			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+	}
 	info->fix.smem_len = info->screen_size;
 
 	return 0;
diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c
index 97e579c33d84..1e200d815e1a 100644
--- a/drivers/gpu/drm/drm_fbdev_generic.c
+++ b/drivers/gpu/drm/drm_fbdev_generic.c
@@ -84,7 +84,8 @@ static int drm_fbdev_generic_helper_fb_probe(struct drm_fb_helper *fb_helper,
 		    sizes->surface_width, sizes->surface_height,
 		    sizes->surface_bpp);
 
-	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
+	format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp,
+					     sizes->surface_depth);
 	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
 					       sizes->surface_height, format);
 	if (IS_ERR(buffer))
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 638ffa4444f5..714e42b05108 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -469,14 +469,12 @@ void drm_file_update_pid(struct drm_file *filp)
 
 	dev = filp->minor->dev;
 	mutex_lock(&dev->filelist_mutex);
+	get_pid(pid);
 	old = rcu_replace_pointer(filp->pid, pid, 1);
 	mutex_unlock(&dev->filelist_mutex);
 
-	if (pid != old) {
-		get_pid(pid);
-		synchronize_rcu();
-		put_pid(old);
-	}
+	synchronize_rcu();
+	put_pid(old);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index aa93129c3397..3860a8ce1e2d 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -202,6 +202,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_MATCH(DMI_BOARD_NAME, "NEXT"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* AYA NEO KUN */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"),
+		  DMI_MATCH(DMI_BOARD_NAME, "KUN"),
+		},
+		.driver_data = (void *)&lcd1600x2560_rightside_up,
 	}, {	/* Chuwi HiBook (CWI514) */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
@@ -414,13 +420,20 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Galaxy Book 10.6"),
 		},
 		.driver_data = (void *)&lcd1280x1920_rightside_up,
-	}, {	/* Valve Steam Deck */
+	}, {	/* Valve Steam Deck (Jupiter) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Valve"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Jupiter"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Valve Steam Deck (Galileo) */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Valve"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Galileo"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "1"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* VIOS LTH17 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "VIOS"),
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index f48c4343f469..3e6d4c6aa877 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -285,7 +285,6 @@ struct platform_driver dp_driver = {
 	.remove_new	= exynos_dp_remove,
 	.driver		= {
 		.name	= "exynos-dp",
-		.owner	= THIS_MODULE,
 		.pm	= pm_ptr(&exynos_dp_pm_ops),
 		.of_match_table = exynos_dp_match,
 	},
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index fab135308b70..11a720fef32b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector)
 	struct vidi_context *ctx = ctx_from_connector(connector);
 	struct edid *edid;
 	int edid_len;
+	int count;
 
 	/*
 	 * the edid data comes from user side and it would be set
@@ -328,7 +329,11 @@ static int vidi_get_modes(struct drm_connector *connector)
 
 	drm_connector_update_edid_property(connector, edid);
 
-	return drm_add_edid_modes(connector, edid);
+	count = drm_add_edid_modes(connector, edid);
+
+	kfree(edid);
+
+	return count;
 }
 
 static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index e968824a4c72..1e26cd4f8347 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (!hdata->ddc_adpt)
-		return 0;
+		goto no_edid;
 
 	edid = drm_get_edid(connector, hdata->ddc_adpt);
 	if (!edid)
-		return 0;
+		goto no_edid;
 
 	hdata->dvi_mode = !connector->display_info.is_hdmi;
 	DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n",
@@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector)
 	kfree(edid);
 
 	return ret;
+
+no_edid:
+	return drm_add_modes_noedid(connector, 640, 480);
 }
 
 static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock)
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 3c3fc53376ce..6bff169fa8d4 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2088,6 +2088,9 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 	u32 ln0, ln1, pin_assignment;
 	u8 width;
 
+	if (DISPLAY_VER(dev_priv) >= 14)
+		return;
+
 	if (!intel_encoder_is_tc(&dig_port->base) ||
 	    intel_tc_port_in_tbt_alt_mode(dig_port))
 		return;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index e05e25cd4a94..5b3b6ae1e3d7 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -442,6 +442,10 @@ bool intel_dp_has_bigjoiner(struct intel_dp *intel_dp)
 	struct intel_encoder *encoder = &intel_dig_port->base;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
+	/* eDP MSO is not compatible with joiner */
+	if (intel_dp->mso_link_count)
+		return false;
+
 	return DISPLAY_VER(dev_priv) >= 12 ||
 		(DISPLAY_VER(dev_priv) == 11 &&
 		 encoder->port != PORT_A);
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index 40371b8a9bbb..93bc1cc1ee7e 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -298,6 +298,7 @@ void i915_vma_revoke_fence(struct i915_vma *vma)
 		return;
 
 	GEM_BUG_ON(fence->vma != vma);
+	i915_active_wait(&fence->active);
 	GEM_BUG_ON(!i915_active_is_idle(&fence->active));
 	GEM_BUG_ON(atomic_read(&fence->pin_count));
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index b5f605751b0a..de811e2265da 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -952,6 +952,13 @@ static void mtk_drm_remove(struct platform_device *pdev)
 		of_node_put(private->comp_node[i]);
 }
 
+static void mtk_drm_shutdown(struct platform_device *pdev)
+{
+	struct mtk_drm_private *private = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(private->drm);
+}
+
 static int mtk_drm_sys_prepare(struct device *dev)
 {
 	struct mtk_drm_private *private = dev_get_drvdata(dev);
@@ -983,6 +990,7 @@ static const struct dev_pm_ops mtk_drm_pm_ops = {
 static struct platform_driver mtk_drm_platform_driver = {
 	.probe	= mtk_drm_probe,
 	.remove_new = mtk_drm_remove,
+	.shutdown = mtk_drm_shutdown,
 	.driver	= {
 		.name	= "mediatek-drm",
 		.pm     = &mtk_drm_pm_ops,
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index 13705c5f1497..4b7497a8755c 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -68,7 +68,7 @@ nv04_display_fini(struct drm_device *dev, bool runtime, bool suspend)
 	if (nv_two_heads(dev))
 		NVWriteCRTC(dev, 1, NV_PCRTC_INTR_EN_0, 0);
 
-	if (!runtime)
+	if (!runtime && !drm->headless)
 		cancel_work_sync(&drm->hpd_work);
 
 	if (!suspend)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 670c9739e5e1..2033214c4b78 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -209,6 +209,8 @@ static int nv17_tv_get_ld_modes(struct drm_encoder *encoder,
 		struct drm_display_mode *mode;
 
 		mode = drm_mode_duplicate(encoder->dev, tv_mode);
+		if (!mode)
+			continue;
 
 		mode->clock = tv_norm->tv_enc_mode.vrefresh *
 			mode->htotal / 1000 *
@@ -258,6 +260,8 @@ static int nv17_tv_get_hd_modes(struct drm_encoder *encoder,
 		if (modes[i].hdisplay == output_mode->hdisplay &&
 		    modes[i].vdisplay == output_mode->vdisplay) {
 			mode = drm_mode_duplicate(encoder->dev, output_mode);
+			if (!mode)
+				continue;
 			mode->type |= DRM_MODE_TYPE_PREFERRED;
 
 		} else {
@@ -265,6 +269,8 @@ static int nv17_tv_get_hd_modes(struct drm_encoder *encoder,
 					    modes[i].vdisplay, 60, false,
 					    (output_mode->flags &
 					     DRM_MODE_FLAG_INTERLACE), false);
+			if (!mode)
+				continue;
 		}
 
 		/* CVT modes are sometimes unsuitable... */
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 88728a0b2c25..674dc567e179 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2680,7 +2680,7 @@ nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend)
 			nv50_mstm_fini(nouveau_encoder(encoder));
 	}
 
-	if (!runtime)
+	if (!runtime && !drm->headless)
 		cancel_work_sync(&drm->hpd_work);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 79cfab53f80e..8c3c1f1e01c5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -43,11 +43,6 @@
 #define BIOSLOG(sip, fmt, arg...) NV_DEBUG(sip->dev, fmt, ##arg)
 #define LOG_OLD_VALUE(x)
 
-struct init_exec {
-	bool execute;
-	bool repeat;
-};
-
 static bool nv_cksum(const uint8_t *data, unsigned int length)
 {
 	/*
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 856b3ef5edb8..0c71d761d378 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1001,6 +1001,9 @@ nouveau_connector_get_modes(struct drm_connector *connector)
 		struct drm_display_mode *mode;
 
 		mode = drm_mode_duplicate(dev, nv_connector->native_mode);
+		if (!mode)
+			return 0;
+
 		drm_mode_probed_add(connector, mode);
 		ret = 1;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index aed5d5b51b43..d4725a968827 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -450,6 +450,9 @@ nouveau_display_hpd_resume(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
+	if (drm->headless)
+		return;
+
 	spin_lock_irq(&drm->hpd_lock);
 	drm->hpd_pending = ~0;
 	spin_unlock_irq(&drm->hpd_lock);
@@ -635,7 +638,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime)
 	}
 	drm_connector_list_iter_end(&conn_iter);
 
-	if (!runtime)
+	if (!runtime && !drm->headless)
 		cancel_work_sync(&drm->hpd_work);
 
 	drm_kms_helper_poll_disable(dev);
@@ -729,6 +732,7 @@ nouveau_display_create(struct drm_device *dev)
 		/* no display hw */
 		if (ret == -ENODEV) {
 			ret = 0;
+			drm->headless = true;
 			goto disp_create_err;
 		}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index e239c6bf4afa..25fca98a20bc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -276,6 +276,7 @@ struct nouveau_drm {
 	/* modesetting */
 	struct nvbios vbios;
 	struct nouveau_display *display;
+	bool headless;
 	struct work_struct hpd_work;
 	spinlock_t hpd_lock;
 	u32 hpd_pending;
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index dcb6d0b6ced0..c8cdc8356c58 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2752,6 +2752,7 @@ static const struct display_timing koe_tx26d202vm0bwa_timing = {
 	.vfront_porch = { 3, 5, 10 },
 	.vback_porch = { 2, 5, 10 },
 	.vsync_len = { 5, 5, 5 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
 };
 
 static const struct panel_desc koe_tx26d202vm0bwa = {
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index e8f385b9c618..28bfc48a9127 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -643,7 +643,9 @@ static int st7789v_probe(struct spi_device *spi)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to get backlight\n");
 
-	of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation);
+	ret = of_drm_get_panel_orientation(spi->dev.of_node, &ctx->orientation);
+	if (ret)
+		return dev_err_probe(&spi->dev, ret, "Failed to get orientation\n");
 
 	drm_panel_add(&ctx->panel);
 
diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
index b8a84f26b3ef..b5e7b919f241 100644
--- a/drivers/gpu/drm/panthor/panthor_drv.c
+++ b/drivers/gpu/drm/panthor/panthor_drv.c
@@ -86,15 +86,15 @@ panthor_get_uobj_array(const struct drm_panthor_obj_array *in, u32 min_stride,
 	int ret = 0;
 	void *out_alloc;
 
+	if (!in->count)
+		return NULL;
+
 	/* User stride must be at least the minimum object size, otherwise it might
 	 * lack useful information.
 	 */
 	if (in->stride < min_stride)
 		return ERR_PTR(-EINVAL);
 
-	if (!in->count)
-		return NULL;
-
 	out_alloc = kvmalloc_array(in->count, obj_size, GFP_KERNEL);
 	if (!out_alloc)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index 79ffcbc41d78..9a0ff48f7061 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -459,6 +459,16 @@ struct panthor_queue {
 		atomic64_t seqno;
 
 		/**
+		 * @last_fence: Fence of the last submitted job.
+		 *
+		 * We return this fence when we get an empty command stream.
+		 * This way, we are guaranteed that all earlier jobs have completed
+		 * when drm_sched_job::s_fence::finished without having to feed
+		 * the CS ring buffer with a dummy job that only signals the fence.
+		 */
+		struct dma_fence *last_fence;
+
+		/**
 		 * @in_flight_jobs: List containing all in-flight jobs.
 		 *
 		 * Used to keep track and signal panthor_job::done_fence when the
@@ -829,6 +839,9 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 	panthor_kernel_bo_destroy(queue->ringbuf);
 	panthor_kernel_bo_destroy(queue->iface.mem);
 
+	/* Release the last_fence we were holding, if any. */
+	dma_fence_put(queue->fence_ctx.last_fence);
+
 	kfree(queue);
 }
 
@@ -2784,9 +2797,6 @@ static void group_sync_upd_work(struct work_struct *work)
 
 		spin_lock(&queue->fence_ctx.lock);
 		list_for_each_entry_safe(job, job_tmp, &queue->fence_ctx.in_flight_jobs, node) {
-			if (!job->call_info.size)
-				continue;
-
 			if (syncobj->seqno < job->done_fence->seqno)
 				break;
 
@@ -2865,11 +2875,14 @@ queue_run_job(struct drm_sched_job *sched_job)
 	static_assert(sizeof(call_instrs) % 64 == 0,
 		      "call_instrs is not aligned on a cacheline");
 
-	/* Stream size is zero, nothing to do => return a NULL fence and let
-	 * drm_sched signal the parent.
+	/* Stream size is zero, nothing to do except making sure all previously
+	 * submitted jobs are done before we signal the
+	 * drm_sched_job::s_fence::finished fence.
 	 */
-	if (!job->call_info.size)
-		return NULL;
+	if (!job->call_info.size) {
+		job->done_fence = dma_fence_get(queue->fence_ctx.last_fence);
+		return dma_fence_get(job->done_fence);
+	}
 
 	ret = pm_runtime_resume_and_get(ptdev->base.dev);
 	if (drm_WARN_ON(&ptdev->base, ret))
@@ -2928,6 +2941,10 @@ queue_run_job(struct drm_sched_job *sched_job)
 		}
 	}
 
+	/* Update the last fence. */
+	dma_fence_put(queue->fence_ctx.last_fence);
+	queue->fence_ctx.last_fence = dma_fence_get(job->done_fence);
+
 	done_fence = dma_fence_get(job->done_fence);
 
 out_unlock:
@@ -3378,10 +3395,15 @@ panthor_job_create(struct panthor_file *pfile,
 		goto err_put_job;
 	}
 
-	job->done_fence = kzalloc(sizeof(*job->done_fence), GFP_KERNEL);
-	if (!job->done_fence) {
-		ret = -ENOMEM;
-		goto err_put_job;
+	/* Empty command streams don't need a fence, they'll pick the one from
+	 * the previously submitted job.
+	 */
+	if (job->call_info.size) {
+		job->done_fence = kzalloc(sizeof(*job->done_fence), GFP_KERNEL);
+		if (!job->done_fence) {
+			ret = -ENOMEM;
+			goto err_put_job;
+		}
 	}
 
 	ret = drm_sched_job_init(&job->base,
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 2ef201a072f1..e66a230331ee 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -642,7 +642,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev,
 	if (r)
 		goto error_unlock;
 
-	if (bo_va->it.start)
+	if (bo_va->it.start && bo_va->bo)
 		r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource);
 
 error_unlock:
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index 21d27e6235f3..b11f7c5bbcbe 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -1619,6 +1619,8 @@ void sumo_construct_vid_mapping_table(struct radeon_device *rdev,
 
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) {
 		if (table[i].ulSupportedSCLK != 0) {
+			if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES)
+				continue;
 			vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit =
 				table[i].usVoltageID;
 			vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit =
diff --git a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c
index e83c3e52251d..0250d5f00bf1 100644
--- a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c
@@ -171,6 +171,13 @@ static void shmob_drm_remove(struct platform_device *pdev)
 	drm_kms_helper_poll_fini(ddev);
 }
 
+static void shmob_drm_shutdown(struct platform_device *pdev)
+{
+	struct shmob_drm_device *sdev = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(&sdev->ddev);
+}
+
 static int shmob_drm_probe(struct platform_device *pdev)
 {
 	struct shmob_drm_platform_data *pdata = pdev->dev.platform_data;
@@ -273,6 +280,7 @@ static const struct of_device_id shmob_drm_of_table[] __maybe_unused = {
 static struct platform_driver shmob_drm_platform_driver = {
 	.probe		= shmob_drm_probe,
 	.remove_new	= shmob_drm_remove,
+	.shutdown	= shmob_drm_shutdown,
 	.driver		= {
 		.name	= "shmob-drm",
 		.of_match_table = of_match_ptr(shmob_drm_of_table),
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 6396dece0db1..2427be8bc97f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -346,6 +346,7 @@ static void ttm_bo_release(struct kref *kref)
 		if (!dma_resv_test_signaled(bo->base.resv,
 					    DMA_RESV_USAGE_BOOKKEEP) ||
 		    (want_init_on_free() && (bo->ttm != NULL)) ||
+		    bo->type == ttm_bo_type_sg ||
 		    !dma_resv_trylock(bo->base.resv)) {
 			/* The BO is not idle, resurrect it for delayed destroy */
 			ttm_bo_flush_all_fences(bo);
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index faddae3d6ac2..6f1ac940cbae 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -2,7 +2,7 @@
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
 	depends on DRM && PCI && MMU
-	depends on X86 || ARM64
+	depends on (X86 && HYPERVISOR_GUEST) || ARM64
 	select DRM_TTM
 	select DRM_TTM_HELPER
 	select MAPPING_DIRTY_HELPERS
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 8f1730aeacc9..823d8d2da17c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -746,7 +746,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		dev->vram_size = pci_resource_len(pdev, 2);
 
 		drm_info(&dev->drm,
-			"Register MMIO at 0x%pa size is %llu kiB\n",
+			"Register MMIO at 0x%pa size is %llu KiB\n",
 			 &rmmio_start, (uint64_t)rmmio_size / 1024);
 		dev->rmmio = devm_ioremap(dev->drm.dev,
 					  rmmio_start,
@@ -765,7 +765,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		fifo_size = pci_resource_len(pdev, 2);
 
 		drm_info(&dev->drm,
-			 "FIFO at %pa size is %llu kiB\n",
+			 "FIFO at %pa size is %llu KiB\n",
 			 &fifo_start, (uint64_t)fifo_size / 1024);
 		dev->fifo_mem = devm_memremap(dev->drm.dev,
 					      fifo_start,
@@ -790,7 +790,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 	 * SVGA_REG_VRAM_SIZE.
 	 */
 	drm_info(&dev->drm,
-		 "VRAM at %pa size is %llu kiB\n",
+		 "VRAM at %pa size is %llu KiB\n",
 		 &dev->vram_start, (uint64_t)dev->vram_size / 1024);
 
 	return 0;
@@ -960,13 +960,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 				vmw_read(dev_priv,
 					 SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB);
 
-		/*
-		 * Workaround for low memory 2D VMs to compensate for the
-		 * allocation taken by fbdev
-		 */
-		if (!(dev_priv->capabilities & SVGA_CAP_3D))
-			mem_size *= 3;
-
 		dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE;
 		dev_priv->max_primary_mem =
 			vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM);
@@ -991,13 +984,13 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 		dev_priv->max_primary_mem = dev_priv->vram_size;
 	}
 	drm_info(&dev_priv->drm,
-		 "Legacy memory limits: VRAM = %llu kB, FIFO = %llu kB, surface = %u kB\n",
+		 "Legacy memory limits: VRAM = %llu KiB, FIFO = %llu KiB, surface = %u KiB\n",
 		 (u64)dev_priv->vram_size / 1024,
 		 (u64)dev_priv->fifo_mem_size / 1024,
 		 dev_priv->memory_size / 1024);
 
 	drm_info(&dev_priv->drm,
-		 "MOB limits: max mob size = %u kB, max mob pages = %u\n",
+		 "MOB limits: max mob size = %u KiB, max mob pages = %u\n",
 		 dev_priv->max_mob_size / 1024, dev_priv->max_mob_pages);
 
 	ret = vmw_dma_masks(dev_priv);
@@ -1015,7 +1008,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id)
 			 (unsigned)dev_priv->max_gmr_pages);
 	}
 	drm_info(&dev_priv->drm,
-		 "Maximum display memory size is %llu kiB\n",
+		 "Maximum display memory size is %llu KiB\n",
 		 (uint64_t)dev_priv->max_primary_mem / 1024);
 
 	/* Need mmio memory to check for fifo pitchlock cap. */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 4ecaea0026fc..a1ce41e1c468 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1043,9 +1043,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 int vmw_kms_write_svga(struct vmw_private *vmw_priv,
 		       unsigned width, unsigned height, unsigned pitch,
 		       unsigned bpp, unsigned depth);
-bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
-				uint32_t pitch,
-				uint32_t height);
 int vmw_kms_present(struct vmw_private *dev_priv,
 		    struct drm_file *file_priv,
 		    struct vmw_framebuffer *vfb,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index a0b47c9b33f5..5bd967fbcf55 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -94,14 +94,14 @@ static int vmw_gmrid_man_get_node(struct ttm_resource_manager *man,
 			} else
 				new_max_pages = gman->max_gmr_pages * 2;
 			if (new_max_pages > gman->max_gmr_pages && new_max_pages >= gman->used_gmr_pages) {
-				DRM_WARN("vmwgfx: increasing guest mob limits to %u kB.\n",
+				DRM_WARN("vmwgfx: increasing guest mob limits to %u KiB.\n",
 					 ((new_max_pages) << (PAGE_SHIFT - 10)));
 
 				gman->max_gmr_pages = new_max_pages;
 			} else {
 				char buf[256];
 				snprintf(buf, sizeof(buf),
-					 "vmwgfx, error: guest graphics is out of memory (mob limit at: %ukB).\n",
+					 "vmwgfx, error: guest graphics is out of memory (mob limit at: %u KiB).\n",
 					 ((gman->max_gmr_pages) << (PAGE_SHIFT - 10)));
 				vmw_host_printf(buf);
 				DRM_WARN("%s", buf);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 13b2820cae51..00c4ff684130 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -224,7 +224,7 @@ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps,
 	new_image = vmw_du_cursor_plane_acquire_image(new_vps);
 
 	changed = false;
-	if (old_image && new_image)
+	if (old_image && new_image && old_image != new_image)
 		changed = memcmp(old_image, new_image, size) != 0;
 
 	return changed;
@@ -2171,13 +2171,12 @@ int vmw_kms_write_svga(struct vmw_private *vmw_priv,
 	return 0;
 }
 
+static
 bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
-				uint32_t pitch,
-				uint32_t height)
+				u64 pitch,
+				u64 height)
 {
-	return ((u64) pitch * (u64) height) < (u64)
-		((dev_priv->active_display_unit == vmw_du_screen_target) ?
-		 dev_priv->max_primary_mem : dev_priv->vram_size);
+	return (pitch * height) < (u64)dev_priv->vram_size;
 }
 
 /**
@@ -2873,25 +2872,18 @@ out_unref:
 enum drm_mode_status vmw_connector_mode_valid(struct drm_connector *connector,
 					      struct drm_display_mode *mode)
 {
+	enum drm_mode_status ret;
 	struct drm_device *dev = connector->dev;
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	u32 max_width = dev_priv->texture_max_width;
-	u32 max_height = dev_priv->texture_max_height;
 	u32 assumed_cpp = 4;
 
 	if (dev_priv->assume_16bpp)
 		assumed_cpp = 2;
 
-	if (dev_priv->active_display_unit == vmw_du_screen_target) {
-		max_width  = min(dev_priv->stdu_max_width,  max_width);
-		max_height = min(dev_priv->stdu_max_height, max_height);
-	}
-
-	if (max_width < mode->hdisplay)
-		return MODE_BAD_HVALUE;
-
-	if (max_height < mode->vdisplay)
-		return MODE_BAD_VVALUE;
+	ret = drm_mode_validate_size(mode, dev_priv->texture_max_width,
+				     dev_priv->texture_max_height);
+	if (ret != MODE_OK)
+		return ret;
 
 	if (!vmw_kms_validate_mode_vram(dev_priv,
 					mode->hdisplay * assumed_cpp,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 2041c4d48daa..a04e0736318d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -43,7 +43,14 @@
 #define vmw_connector_to_stdu(x) \
 	container_of(x, struct vmw_screen_target_display_unit, base.connector)
 
-
+/*
+ * Some renderers such as llvmpipe will align the width and height of their
+ * buffers to match their tile size. We need to keep this in mind when exposing
+ * modes to userspace so that this possible over-allocation will not exceed
+ * graphics memory. 64x64 pixels seems to be a reasonable upper bound for the
+ * tile size of current renderers.
+ */
+#define GPU_TILE_SIZE 64
 
 enum stdu_content_type {
 	SAME_AS_DISPLAY = 0,
@@ -85,11 +92,6 @@ struct vmw_stdu_update {
 	SVGA3dCmdUpdateGBScreenTarget body;
 };
 
-struct vmw_stdu_dma {
-	SVGA3dCmdHeader     header;
-	SVGA3dCmdSurfaceDMA body;
-};
-
 struct vmw_stdu_surface_copy {
 	SVGA3dCmdHeader      header;
 	SVGA3dCmdSurfaceCopy body;
@@ -414,6 +416,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
+	struct drm_crtc_state *new_crtc_state;
 	int ret;
 
 	if (!crtc) {
@@ -423,6 +426,7 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	stdu     = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
+	new_crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 	if (dev_priv->vkms_enabled)
 		drm_crtc_vblank_off(crtc);
@@ -434,6 +438,14 @@ static void vmw_stdu_crtc_atomic_disable(struct drm_crtc *crtc,
 
 		(void) vmw_stdu_update_st(dev_priv, stdu);
 
+		/* Don't destroy the Screen Target if we are only setting the
+		 * display as inactive
+		 */
+		if (new_crtc_state->enable &&
+		    !new_crtc_state->active &&
+		    !new_crtc_state->mode_changed)
+			return;
+
 		ret = vmw_stdu_destroy_st(dev_priv, stdu);
 		if (ret)
 			DRM_ERROR("Failed to destroy Screen Target\n");
@@ -829,7 +841,41 @@ static void vmw_stdu_connector_destroy(struct drm_connector *connector)
 	vmw_stdu_destroy(vmw_connector_to_stdu(connector));
 }
 
+static enum drm_mode_status
+vmw_stdu_connector_mode_valid(struct drm_connector *connector,
+			      struct drm_display_mode *mode)
+{
+	enum drm_mode_status ret;
+	struct drm_device *dev = connector->dev;
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	u64 assumed_cpp = dev_priv->assume_16bpp ? 2 : 4;
+	/* Align width and height to account for GPU tile over-alignment */
+	u64 required_mem = ALIGN(mode->hdisplay, GPU_TILE_SIZE) *
+			   ALIGN(mode->vdisplay, GPU_TILE_SIZE) *
+			   assumed_cpp;
+	required_mem = ALIGN(required_mem, PAGE_SIZE);
+
+	ret = drm_mode_validate_size(mode, dev_priv->stdu_max_width,
+				     dev_priv->stdu_max_height);
+	if (ret != MODE_OK)
+		return ret;
+
+	ret = drm_mode_validate_size(mode, dev_priv->texture_max_width,
+				     dev_priv->texture_max_height);
+	if (ret != MODE_OK)
+		return ret;
 
+	if (required_mem > dev_priv->max_primary_mem)
+		return MODE_MEM;
+
+	if (required_mem > dev_priv->max_mob_pages * PAGE_SIZE)
+		return MODE_MEM;
+
+	if (required_mem > dev_priv->max_mob_size)
+		return MODE_MEM;
+
+	return MODE_OK;
+}
 
 static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 	.dpms = vmw_du_connector_dpms,
@@ -845,7 +891,7 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 static const struct
 drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = {
 	.get_modes = vmw_connector_get_modes,
-	.mode_valid = vmw_connector_mode_valid
+	.mode_valid = vmw_stdu_connector_mode_valid
 };
 
 
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index 8fc0f3f6ecc5..944770fb2daf 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -147,6 +147,13 @@ static const struct attribute *gt_idle_attrs[] = {
 static void gt_idle_sysfs_fini(struct drm_device *drm, void *arg)
 {
 	struct kobject *kobj = arg;
+	struct xe_gt *gt = kobj_to_gt(kobj->parent);
+
+	if (gt_to_xe(gt)->info.skip_guc_pc) {
+		XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FW_GT));
+		xe_gt_idle_disable_c6(gt);
+		xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+	}
 
 	sysfs_remove_files(kobj, gt_idle_attrs);
 	kobject_put(kobj);
@@ -199,7 +206,7 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt)
 void xe_gt_idle_disable_c6(struct xe_gt *gt)
 {
 	xe_device_assert_mem_access(gt_to_xe(gt));
-	xe_force_wake_assert_held(gt_to_fw(gt), XE_FORCEWAKE_ALL);
+	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);
 
 	xe_mmio_write32(gt, PG_ENABLE, 0);
 	xe_mmio_write32(gt, RC_CONTROL, 0);
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 577bd7043740..0443e07880a0 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -342,7 +342,7 @@ static void init_steering_oaddrm(struct xe_gt *gt)
 	else
 		gt->steering[OADDRM].group_target = 1;
 
-	gt->steering[DSS].instance_target = 0;		/* unused */
+	gt->steering[OADDRM].instance_target = 0;	/* unused */
 }
 
 static void init_steering_sqidi_psmi(struct xe_gt *gt)
@@ -357,8 +357,8 @@ static void init_steering_sqidi_psmi(struct xe_gt *gt)
 
 static void init_steering_inst0(struct xe_gt *gt)
 {
-	gt->steering[DSS].group_target = 0;		/* unused */
-	gt->steering[DSS].instance_target = 0;		/* unused */
+	gt->steering[INSTANCE0].group_target = 0;	/* unused */
+	gt->steering[INSTANCE0].instance_target = 0;	/* unused */
 }
 
 static const struct {
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 79116ad58620..6c2cfc54442c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1274,6 +1274,9 @@ static void pf_reset_vf_lmtt(struct xe_device *xe, unsigned int vfid)
 	struct xe_tile *tile;
 	unsigned int tid;
 
+	xe_assert(xe, IS_DGFX(xe));
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
 	for_each_tile(tile, xe, tid) {
 		lmtt = &tile->sriov.pf.lmtt;
 		xe_lmtt_drop_pages(lmtt, vfid);
@@ -1292,6 +1295,9 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid)
 	unsigned int tid;
 	int err;
 
+	xe_assert(xe, IS_DGFX(xe));
+	xe_assert(xe, IS_SRIOV_PF(xe));
+
 	total = 0;
 	for_each_tile(tile, xe, tid)
 		total += pf_get_vf_config_lmem(tile->primary_gt, vfid);
@@ -1337,6 +1343,7 @@ fail:
 
 static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config)
 {
+	xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt)));
 	xe_gt_assert(gt, !xe_gt_is_media_type(gt));
 	lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt));
 
@@ -1355,6 +1362,7 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size)
 	int err;
 
 	xe_gt_assert(gt, vfid);
+	xe_gt_assert(gt, IS_DGFX(xe));
 	xe_gt_assert(gt, !xe_gt_is_media_type(gt));
 
 	size = round_up(size, pf_get_lmem_alignment(gt));
@@ -1745,10 +1753,14 @@ static void pf_reset_config_sched(struct xe_gt *gt, struct xe_gt_sriov_config *c
 static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid)
 {
 	struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid);
+	struct xe_device *xe = gt_to_xe(gt);
 
 	if (!xe_gt_is_media_type(gt)) {
 		pf_release_vf_config_ggtt(gt, config);
-		pf_release_vf_config_lmem(gt, config);
+		if (IS_DGFX(xe)) {
+			pf_release_vf_config_lmem(gt, config);
+			pf_update_vf_lmtt(xe, vfid);
+		}
 	}
 	pf_release_config_ctxs(gt, config);
 	pf_release_config_dbs(gt, config);
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 240e7a4bbff1..5faca4fc2fef 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -631,8 +631,6 @@ int xe_guc_enable_communication(struct xe_guc *guc)
 	struct xe_device *xe = guc_to_xe(guc);
 	int err;
 
-	guc_enable_irq(guc);
-
 	if (IS_SRIOV_VF(xe) && xe_device_has_memirq(xe)) {
 		struct xe_gt *gt = guc_to_gt(guc);
 		struct xe_tile *tile = gt_to_tile(gt);
@@ -640,6 +638,8 @@ int xe_guc_enable_communication(struct xe_guc *guc)
 		err = xe_memirq_init_guc(&tile->sriov.vf.memirq, guc);
 		if (err)
 			return err;
+	} else {
+		guc_enable_irq(guc);
 	}
 
 	xe_mmio_rmw32(guc_to_gt(guc), PMINTRMSK,
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 509649d0e65e..23382ced4ea7 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -895,12 +895,6 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc)
 static void xe_guc_pc_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_pc *pc = arg;
-	struct xe_device *xe = pc_to_xe(pc);
-
-	if (xe->info.skip_guc_pc) {
-		xe_gt_idle_disable_c6(pc_to_gt(pc));
-		return;
-	}
 
 	XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL));
 	XE_WARN_ON(xe_guc_pc_gucrc_disable(pc));
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 65e5a3f4c340..198f5c2189cb 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1334,7 +1334,7 @@ xe_migrate_update_pgtables(struct xe_migrate *m,
 						 GFP_KERNEL, true, 0);
 			if (IS_ERR(sa_bo)) {
 				err = PTR_ERR(sa_bo);
-				goto err;
+				goto err_bb;
 			}
 
 			ppgtt_ofs = NUM_KERNEL_PDE +
@@ -1385,7 +1385,7 @@ xe_migrate_update_pgtables(struct xe_migrate *m,
 					 update_idx);
 	if (IS_ERR(job)) {
 		err = PTR_ERR(job);
-		goto err_bb;
+		goto err_sa;
 	}
 
 	/* Wait on BO move */
@@ -1434,12 +1434,12 @@ xe_migrate_update_pgtables(struct xe_migrate *m,
 
 err_job:
 	xe_sched_job_put(job);
+err_sa:
+	drm_suballoc_free(sa_bo, NULL);
 err_bb:
 	if (!q)
 		mutex_unlock(&m->job_mutex);
 	xe_bb_free(bb, NULL);
-err:
-	drm_suballoc_free(sa_bo, NULL);
 	return ERR_PTR(err);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index d42b3f33bd7a..aca7a9af6e84 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -80,6 +80,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i)
 	return i;
 }
 
+static int emit_flush_dw(u32 *dw, int i)
+{
+	dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW;
+	dw[i++] = 0;
+	dw[i++] = 0;
+	dw[i++] = 0;
+
+	return i;
+}
+
 static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb,
 			       u32 *dw, int i)
 {
@@ -234,10 +244,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
-	if (job->user_fence.used)
+	if (job->user_fence.used) {
+		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
 						job->user_fence.value,
 						dw, i);
+	}
 
 	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
 
@@ -293,10 +305,12 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
-	if (job->user_fence.used)
+	if (job->user_fence.used) {
+		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
 						job->user_fence.value,
 						dw, i);
+	}
 
 	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i);
author	Thomas Gleixner <tglx@linutronix.de>	2024-07-13 12:07:10 +0200
committer	Thomas Gleixner <tglx@linutronix.de>	2024-07-13 12:07:10 +0200
commit	b7625d67eb1a63d33b0a2a4518ce4897d27f7465 (patch)
tree	372459935f602bac331ad0185f2dc5cc23d76924 /drivers/gpu
parent	f7d43dd206e7e18c182f200e67a8db8c209907fa (diff)
parent	4bdc3eaa102b6bedb0800f76f53eca516d5cf20c (diff)
download	lwn-b7625d67eb1a63d33b0a2a4518ce4897d27f7465.tar.gz lwn-b7625d67eb1a63d33b0a2a4518ce4897d27f7465.zip