Merge tag 'drm-fixes-2022-11-11' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly pull request for graphics, mostly amdgpu and i915, with a
  couple of fixes for vc4 and panfrost, panel quirks and a kconfig
  change for rcar-du. Nothing seems to be too strange at this stage.

  amdgpu:
   - Fix s/r in amdgpu_vram_mgr_new
   - SMU 13.0.4 update
   - GPUVM TLB race fix
   - DCN 3.1.4 fixes
   - DCN 3.2.x fixes
   - Vega10 fan fix
   - BACO fix for Beige Goby board
   - PSR fix
   - GPU VM PT locking fixes

  amdkfd:
   - CRIU fixes

  vc4:
   - HDMI fixes to vc4.

  panfrost:
   - Make panfrost's uapi header compile with C++.
   - Handle 1 gb boundary correctly in panfrost mmu code.

  panel:
   - Add rotation quirks for 2 panels.

  rcar-du:
   - DSI Kconfig fix

  i915:
   - Fix sg_table handling in map_dma_buf
   - Send PSR update also on invalidate
   - Do not set cache_dirty for DGFX
   - Restore userptr probe_range behaviour"

* tag 'drm-fixes-2022-11-11' of git://anongit.freedesktop.org/drm/drm: (29 commits)
  drm/amd/display: only fill dirty rectangles when PSR is enabled
  drm/amdgpu: disable BACO on special BEIGE_GOBY card
  drm/amdgpu: Drop eviction lock when allocating PT BO
  drm/amdgpu: Unlock bo_list_mutex after error handling
  Revert "drm/amdgpu: Revert "drm/amdgpu: getting fan speed pwm for vega10 properly""
  drm/amd/display: Enforce minimum prefetch time for low memclk on DCN32
  drm/amd/display: Fix gpio port mapping issue
  drm/amd/display: Fix reg timeout in enc314_enable_fifo
  drm/amd/display: Fix FCLK deviation and tool compile issues
  drm/amd/display: Zeromem mypipe heap struct before using it
  drm/amd/display: Update SR watermarks for DCN314
  drm/amdgpu: workaround for TLB seq race
  drm/amdkfd: Fix error handling in criu_checkpoint
  drm/amdkfd: Fix error handling in kfd_criu_restore_events
  drm/amd/pm: update SMU IP v13.0.4 msg interface header
  drm: rcar-du: Fix Kconfig dependency between RCAR_DU and RCAR_MIPI_DSI
  drm/panfrost: Split io-pgtable requests properly
  drm/amdgpu: Fix the lpfn checking condition in drm buddy
  drm: panel-orientation-quirks: Add quirk for Acer Switch V 10 (SW5-017)
  drm: panel-orientation-quirks: Add quirk for Nanote UMPC-01
  ...

36 files changed, 257 insertions, 128 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1bbd39b3b0fc..d371000a5727 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -992,6 +992,7 @@ out_free_user_pages:
 		kvfree(e->user_pages);
 		e->user_pages = NULL;
 	}
+	mutex_unlock(&p->bo_list->bo_list_mutex);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 2291aa14d888..003aa9e47085 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -143,32 +143,6 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	return 0;
 }
 
-/*
- * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS
- * happens while holding this lock anywhere to prevent deadlocks when
- * an MMU notifier runs in reclaim-FS context.
- */
-static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm)
-{
-	mutex_lock(&vm->eviction_lock);
-	vm->saved_flags = memalloc_noreclaim_save();
-}
-
-static inline int amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm)
-{
-	if (mutex_trylock(&vm->eviction_lock)) {
-		vm->saved_flags = memalloc_noreclaim_save();
-		return 1;
-	}
-	return 0;
-}
-
-static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm)
-{
-	memalloc_noreclaim_restore(vm->saved_flags);
-	mutex_unlock(&vm->eviction_lock);
-}
-
 /**
  * amdgpu_vm_bo_evicted - vm_bo is evicted
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 83acb7bd80fe..6546e786bf00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -492,7 +492,48 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m);
  */
 static inline uint64_t amdgpu_vm_tlb_seq(struct amdgpu_vm *vm)
 {
+	unsigned long flags;
+	spinlock_t *lock;
+
+	/*
+	 * Workaround to stop racing between the fence signaling and handling
+	 * the cb. The lock is static after initially setting it up, just make
+	 * sure that the dma_fence structure isn't freed up.
+	 */
+	rcu_read_lock();
+	lock = vm->last_tlb_flush->lock;
+	rcu_read_unlock();
+
+	spin_lock_irqsave(lock, flags);
+	spin_unlock_irqrestore(lock, flags);
+
 	return atomic64_read(&vm->tlb_seq);
 }
 
+/*
+ * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm)
+{
+	mutex_lock(&vm->eviction_lock);
+	vm->saved_flags = memalloc_noreclaim_save();
+}
+
+static inline bool amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm)
+{
+	if (mutex_trylock(&vm->eviction_lock)) {
+		vm->saved_flags = memalloc_noreclaim_save();
+		return true;
+	}
+	return false;
+}
+
+static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm)
+{
+	memalloc_noreclaim_restore(vm->saved_flags);
+	mutex_unlock(&vm->eviction_lock);
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 358b91243e37..b5f3bba851db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -597,7 +597,9 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev,
 	if (entry->bo)
 		return 0;
 
+	amdgpu_vm_eviction_unlock(vm);
 	r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt);
+	amdgpu_vm_eviction_lock(vm);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 73a517bcf5c1..80dd1343594c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -435,7 +435,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 	if (place->flags & TTM_PL_FLAG_TOPDOWN)
 		vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
 
-	if (fpfn || lpfn != man->size)
+	if (fpfn || lpfn != mgr->mm.size)
 		/* Allocate blocks in desired range */
 		vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 5feaba6a77de..6d291aa6386b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1950,7 +1950,7 @@ static int criu_checkpoint(struct file *filep,
 {
 	int ret;
 	uint32_t num_devices, num_bos, num_objects;
-	uint64_t priv_size, priv_offset = 0;
+	uint64_t priv_size, priv_offset = 0, bo_priv_offset;
 
 	if (!args->devices || !args->bos || !args->priv_data)
 		return -EINVAL;
@@ -1994,38 +1994,34 @@ static int criu_checkpoint(struct file *filep,
 	if (ret)
 		goto exit_unlock;
 
-	ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos,
-			    (uint8_t __user *)args->priv_data, &priv_offset);
-	if (ret)
-		goto exit_unlock;
+	/* Leave room for BOs in the private data. They need to be restored
+	 * before events, but we checkpoint them last to simplify the error
+	 * handling.
+	 */
+	bo_priv_offset = priv_offset;
+	priv_offset += num_bos * sizeof(struct kfd_criu_bo_priv_data);
 
 	if (num_objects) {
 		ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data,
 						 &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 
 		ret = kfd_criu_checkpoint_events(p, (uint8_t __user *)args->priv_data,
 						 &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 
 		ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset);
 		if (ret)
-			goto close_bo_fds;
+			goto exit_unlock;
 	}
 
-close_bo_fds:
-	if (ret) {
-		/* If IOCTL returns err, user assumes all FDs opened in criu_dump_bos are closed */
-		uint32_t i;
-		struct kfd_criu_bo_bucket *bo_buckets = (struct kfd_criu_bo_bucket *) args->bos;
-
-		for (i = 0; i < num_bos; i++) {
-			if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)
-				close_fd(bo_buckets[i].dmabuf_fd);
-		}
-	}
+	/* This must be the last thing in this function that can fail.
+	 * Otherwise we leak dmabuf file descriptors.
+	 */
+	ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos,
+			   (uint8_t __user *)args->priv_data, &bo_priv_offset);
 
 exit_unlock:
 	mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 83e3ce9f6049..729d26d648af 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -506,6 +506,7 @@ int kfd_criu_restore_event(struct file *devkfd,
 		ret = create_other_event(p, ev, &ev_priv->event_id);
 		break;
 	}
+	mutex_unlock(&p->event_mutex);
 
 exit:
 	if (ret)
@@ -513,8 +514,6 @@ exit:
 
 	kfree(ev_priv);
 
-	mutex_unlock(&p->event_mutex);
-
 	return ret;
 }
 
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 589bee9acf16..509739d83b5a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7622,9 +7622,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		bundle->surface_updates[planes_count].plane_info =
 			&bundle->plane_infos[planes_count];
 
-		fill_dc_dirty_rects(plane, old_plane_state, new_plane_state,
-				    new_crtc_state,
-				    &bundle->flip_addrs[planes_count]);
+		if (acrtc_state->stream->link->psr_settings.psr_feature_enabled)
+			fill_dc_dirty_rects(plane, old_plane_state,
+					    new_plane_state, new_crtc_state,
+					    &bundle->flip_addrs[planes_count]);
 
 		/*
 		 * Only allow immediate flips for fast updates that don't
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 1131c6d73f6c..20a06c04e4a1 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -363,32 +363,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 12.5,
+			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 12.5,
+			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 12.5,
+			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 12.5,
+			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
 		},
 	}
@@ -400,32 +400,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 16.5,
+			.sr_enter_plus_exit_time_us = 18.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 16.5,
+			.sr_enter_plus_exit_time_us = 18.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 16.5,
+			.sr_enter_plus_exit_time_us = 18.5,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 16.5,
+			.sr_enter_plus_exit_time_us = 18.5,
 			.valid = true,
 		},
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 737b221ca689..0598465fd1a1 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -853,6 +853,7 @@ struct dc_debug_options {
 	bool enable_dp_dig_pixel_rate_div_policy;
 	enum lttpr_mode lttpr_mode_override;
 	unsigned int dsc_delay_factor_wa_x1000;
+	unsigned int min_prefetch_in_strobe_ns;
 };
 
 struct gpu_info_soc_bounding_box_v1_0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
index 7e773bf7b895..38842f938bed 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
@@ -49,18 +49,30 @@
 #define CTX \
 	enc1->base.ctx
 
+static void enc314_reset_fifo(struct stream_encoder *enc, bool reset)
+{
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+	uint32_t reset_val = reset ? 1 : 0;
+	uint32_t is_symclk_on;
+
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, reset_val);
+	REG_GET(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, &is_symclk_on);
+
+	if (is_symclk_on)
+		REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, reset_val, 10, 5000);
+	else
+		udelay(10);
+}
 
 static void enc314_enable_fifo(struct stream_encoder *enc)
 {
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	/* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */
-	REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000);
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7);
-	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1);
-	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000);
-	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0);
-	REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000);
+
+	enc314_reset_fifo(enc, true);
+	enc314_reset_fifo(enc, false);
+
 	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 1);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index a88dd7b3d1c1..d1598e3131f6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -724,6 +724,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_dp_dig_pixel_rate_div_policy = 1,
 	.allow_sw_cursor_fallback = false,
 	.alloc_extra_way_for_cursor = true,
+	.min_prefetch_in_strobe_ns = 60000, // 60us
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 61087f2385a9..6292ac515d1a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -722,6 +722,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_dp_dig_pixel_rate_div_policy = 1,
 	.allow_sw_cursor_fallback = false,
 	.alloc_extra_way_for_cursor = true,
+	.min_prefetch_in_strobe_ns = 60000, // 60us
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index cf420ad2b8dc..34b6c763a455 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -146,8 +146,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
+	.sr_exit_time_us = 16.5,
+	.sr_enter_plus_exit_time_us = 18.5,
 	.sr_exit_z8_time_us = 442.0,
 	.sr_enter_plus_exit_z8_time_us = 560.0,
 	.writeback_latency_us = 12.0,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index f37c9a6b3b7e..659323ebd79d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -2364,6 +2364,8 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
 	/* DML DSC delay factor workaround */
 	dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
 
+	dcn3_2_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0;
+
 	/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
 	dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
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 3d184679f129..244fd15d24b4 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
@@ -786,6 +786,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 					v->SwathHeightY[k],
 					v->SwathHeightC[k],
 					TWait,
+					v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ?
+							mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
 					/* Output */
 					&v->DSTXAfterScaler[k],
 					&v->DSTYAfterScaler[k],
@@ -3192,6 +3194,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							mode_lib->vba.FCLKChangeLatency, mode_lib->vba.UrgLatency[i],
 							mode_lib->vba.SREnterPlusExitTime);
 
+					memset(&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull, 0, sizeof(DmlPipe));
 					v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dppclk = mode_lib->vba.RequiredDPPCLK[i][j][k];
 					v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dispclk = mode_lib->vba.RequiredDISPCLK[i][j];
 					v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.PixelClock = mode_lib->vba.PixelClock[k];
@@ -3244,6 +3247,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							v->swath_width_chroma_ub_this_state[k],
 							v->SwathHeightYThisState[k],
 							v->SwathHeightCThisState[k], v->TWait,
+							v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ?
+									mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
 
 							/* Output */
 							&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k],
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h
index c62e0991358b..f82e14cd9d8a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h
@@ -49,6 +49,9 @@
 #define BPP_INVALID 0
 #define BPP_BLENDED_PIPE 0xffffffff
 
+#define MEM_STROBE_FREQ_MHZ 1600
+#define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0
+
 struct display_mode_lib;
 
 void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index 968924c491c1..635fc54338fa 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -3417,6 +3417,7 @@ bool dml32_CalculatePrefetchSchedule(
 		unsigned int SwathHeightY,
 		unsigned int SwathHeightC,
 		double TWait,
+		double TPreReq,
 		/* Output */
 		double   *DSTXAfterScaler,
 		double   *DSTYAfterScaler,
@@ -3474,6 +3475,7 @@ bool dml32_CalculatePrefetchSchedule(
 	double  min_Lsw;
 	double  Tsw_est1 = 0;
 	double  Tsw_est3 = 0;
+	double  TPreMargin = 0;
 
 	if (v->GPUVMEnable == true && v->HostVMEnable == true)
 		HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels;
@@ -3699,6 +3701,8 @@ bool dml32_CalculatePrefetchSchedule(
 
 	dst_y_prefetch_equ = dml_floor(4.0 * (dst_y_prefetch_equ + 0.125), 1) / 4.0;
 	Tpre_rounded = dst_y_prefetch_equ * LineTime;
+
+	TPreMargin = Tpre_rounded - TPreReq;
 #ifdef __DML_VBA_DEBUG__
 	dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, dst_y_prefetch_equ);
 	dml_print("DML::%s: LineTime: %f\n", __func__, LineTime);
@@ -3726,7 +3730,7 @@ bool dml32_CalculatePrefetchSchedule(
 	*VRatioPrefetchY = 0;
 	*VRatioPrefetchC = 0;
 	*RequiredPrefetchPixDataBWLuma = 0;
-	if (dst_y_prefetch_equ > 1) {
+	if (dst_y_prefetch_equ > 1 && TPreMargin > 0.0) {
 		double PrefetchBandwidth1;
 		double PrefetchBandwidth2;
 		double PrefetchBandwidth3;
@@ -3872,7 +3876,11 @@ bool dml32_CalculatePrefetchSchedule(
 		}
 
 		if (dst_y_prefetch_oto < dst_y_prefetch_equ) {
-			*DestinationLinesForPrefetch = dst_y_prefetch_oto;
+			if (dst_y_prefetch_oto * LineTime < TPreReq) {
+				*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+			} else {
+				*DestinationLinesForPrefetch = dst_y_prefetch_oto;
+			}
 			TimeForFetchingMetaPTE = Tvm_oto;
 			TimeForFetchingRowInVBlank = Tr0_oto;
 			*PrefetchBandwidth = prefetch_bw_oto;
@@ -4397,7 +4405,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport(
 
 		if (v->NumberOfActiveSurfaces > 1) {
 			ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY
-					- (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k]
+					- (1.0 - 1.0 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k]
 							/ v->PixelClock[k] / v->VRatio[k];
 		}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
index 2c3827546ac7..3989c2a28fae 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
@@ -30,7 +30,7 @@
 #include "os_types.h"
 #include "../dc_features.h"
 #include "../display_mode_structs.h"
-#include "dml/display_mode_vba.h"
+#include "../display_mode_vba.h"
 
 unsigned int dml32_dscceComputeDelay(
 		unsigned int bpc,
@@ -743,6 +743,7 @@ bool dml32_CalculatePrefetchSchedule(
 		unsigned int SwathHeightY,
 		unsigned int SwathHeightC,
 		double TWait,
+		double TPreReq,
 		/* Output */
 		double   *DSTXAfterScaler,
 		double   *DSTYAfterScaler,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index ec0486efab14..432b4ecd01a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -544,6 +544,8 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 	/* DML DSC delay factor workaround */
 	dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
 
+	dcn3_21_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0;
+
 	/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
 	dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index d7be01ac0751..64d602e6412f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -367,6 +367,7 @@ struct _vcs_dpi_ip_params_st {
 
 	/* DM workarounds */
 	double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix
+	double min_prefetch_in_strobe_us;
 };
 
 struct _vcs_dpi_display_xfc_params_st {
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c
index d635b73af46f..0ea52ba5ac82 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c
@@ -108,6 +108,13 @@ static const struct ddc_registers ddc_data_regs_dcn[] = {
 	ddc_data_regs_dcn2(4),
 	ddc_data_regs_dcn2(5),
 	{
+		// add a dummy entry for cases no such port
+		{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,},
+		.ddc_setup = 0,
+		.phy_aux_cntl = 0,
+		.dc_gpio_aux_ctrl_5 = 0
+	},
+	{
 			DDC_GPIO_VGA_REG_LIST(DATA),
 			.ddc_setup = 0,
 			.phy_aux_cntl = 0,
@@ -122,6 +129,13 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = {
 	ddc_clk_regs_dcn2(4),
 	ddc_clk_regs_dcn2(5),
 	{
+		// add a dummy entry for cases no such port
+		{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,},
+		.ddc_setup = 0,
+		.phy_aux_cntl = 0,
+		.dc_gpio_aux_ctrl_5 = 0
+	},
+	{
 			DDC_GPIO_VGA_REG_LIST(CLK),
 			.ddc_setup = 0,
 			.phy_aux_cntl = 0,
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
index 6fd38cdd68c0..525bc8881950 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
@@ -94,11 +94,14 @@ static enum gpio_result set_config(
 		 * is required for detection of AUX mode */
 		if (hw_gpio->base.en != GPIO_DDC_LINE_VIP_PAD) {
 			if (!ddc_data_pd_en || !ddc_clk_pd_en) {
-
-				REG_SET_2(gpio.MASK_reg, regval,
+				if (hw_gpio->base.en == GPIO_DDC_LINE_DDC_VGA) {
+					// bit 4 of mask has different usage in some cases
+					REG_SET(gpio.MASK_reg, regval, DC_GPIO_DDC1DATA_PD_EN, 1);
+				} else {
+					REG_SET_2(gpio.MASK_reg, regval,
 						DC_GPIO_DDC1DATA_PD_EN, 1,
 						DC_GPIO_DDC1CLK_PD_EN, 1);
-
+				}
 				if (config_data->type ==
 						GPIO_CONFIG_TYPE_I2C_AUX_DUAL_MODE)
 					msleep(3);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
index dad3e3741a4e..190af79f3236 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c
@@ -67,22 +67,21 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr,
 int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr,
 		uint32_t *speed)
 {
-	uint32_t current_rpm;
-	uint32_t percent = 0;
-
-	if (hwmgr->thermal_controller.fanInfo.bNoFan)
-		return 0;
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t duty100, duty;
+	uint64_t tmp64;
 
-	if (vega10_get_current_rpm(hwmgr, &current_rpm))
-		return -1;
+	duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1),
+				CG_FDO_CTRL1, FMAX_DUTY100);
+	duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS),
+				CG_THERMAL_STATUS, FDO_PWM_DUTY);
 
-	if (hwmgr->thermal_controller.
-			advanceFanControlParameters.usMaxFanRPM != 0)
-		percent = current_rpm * 255 /
-			hwmgr->thermal_controller.
-			advanceFanControlParameters.usMaxFanRPM;
+	if (!duty100)
+		return -EINVAL;
 
-	*speed = MIN(percent, 255);
+	tmp64 = (uint64_t)duty * 255;
+	do_div(tmp64, duty100);
+	*speed = MIN((uint32_t)tmp64, 255);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h
index d9b0cd752200..f4d6c07b56ea 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h
@@ -54,14 +54,14 @@
 #define PPSMC_MSG_TestMessage                   0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team
 #define PPSMC_MSG_GetPmfwVersion                0x02 ///< Get PMFW version
 #define PPSMC_MSG_GetDriverIfVersion            0x03 ///< Get PMFW_DRIVER_IF version
-#define PPSMC_MSG_EnableGfxOff                  0x04 ///< Enable GFXOFF
-#define PPSMC_MSG_DisableGfxOff                 0x05 ///< Disable GFXOFF
+#define PPSMC_MSG_SPARE0                        0x04 ///< SPARE
+#define PPSMC_MSG_SPARE1                        0x05 ///< SPARE
 #define PPSMC_MSG_PowerDownVcn                  0x06 ///< Power down VCN
 #define PPSMC_MSG_PowerUpVcn                    0x07 ///< Power up VCN; VCN is power gated by default
 #define PPSMC_MSG_SetHardMinVcn                 0x08 ///< For wireless display
 #define PPSMC_MSG_SetSoftMinGfxclk              0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz
-#define PPSMC_MSG_ActiveProcessNotify           0x0A ///< Needs update
-#define PPSMC_MSG_ForcePowerDownGfx             0x0B ///< Force power down GFX, i.e. enter GFXOFF
+#define PPSMC_MSG_SPARE2                        0x0A ///< SPARE
+#define PPSMC_MSG_SPARE3                        0x0B ///< SPARE
 #define PPSMC_MSG_PrepareMp1ForUnload           0x0C ///< Prepare PMFW for GFX driver unload
 #define PPSMC_MSG_SetDriverDramAddrHigh         0x0D ///< Set high 32 bits of DRAM address for Driver table transfer
 #define PPSMC_MSG_SetDriverDramAddrLow          0x0E ///< Set low 32 bits of DRAM address for Driver table transfer
@@ -73,8 +73,7 @@
 #define PPSMC_MSG_SetSoftMinFclk                0x14 ///< Set hard min for FCLK
 #define PPSMC_MSG_SetSoftMinVcn                 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK)
 
-
-#define PPSMC_MSG_EnableGfxImu                  0x16 ///< Needs update
+#define PPSMC_MSG_EnableGfxImu                  0x16 ///< Enable GFX IMU
 
 #define PPSMC_MSG_GetGfxclkFrequency            0x17 ///< Get GFX clock frequency
 #define PPSMC_MSG_GetFclkFrequency              0x18 ///< Get FCLK frequency
@@ -102,8 +101,8 @@
 #define PPSMC_MSG_SetHardMinIspxclkByFreq       0x2C ///< Set HardMin by frequency for ISPXCLK
 #define PPSMC_MSG_PowerDownUmsch                0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler
 #define PPSMC_MSG_PowerUpUmsch                  0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler
-#define PPSMC_Message_IspStutterOn_MmhubPgDis   0x2F ///< ISP StutterOn mmHub PgDis
-#define PPSMC_Message_IspStutterOff_MmhubPgEn   0x30 ///< ISP StufferOff mmHub PgEn
+#define PPSMC_MSG_IspStutterOn_MmhubPgDis       0x2F ///< ISP StutterOn mmHub PgDis
+#define PPSMC_MSG_IspStutterOff_MmhubPgEn       0x30 ///< ISP StufferOff mmHub PgEn
 
 #define PPSMC_Message_Count                     0x31 ///< Total number of PPSMC messages
 /** @}*/
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
index 74996a8fb671..6212fd270857 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
@@ -377,7 +377,9 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu)
 		if (((adev->pdev->device == 0x73A1) &&
 		    (adev->pdev->revision == 0x00)) ||
 		    ((adev->pdev->device == 0x73BF) &&
-		    (adev->pdev->revision == 0xCF)))
+		    (adev->pdev->revision == 0xCF)) ||
+		    ((adev->pdev->device == 0x7422) &&
+		    (adev->pdev->revision == 0x00)))
 			smu_baco->platform_support = false;
 
 	}
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 8a0c0e0bb5bd..52d8800a8ab8 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* Acer Switch V 10 (SW5-017) */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Anbernic Win600 */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Anbernic"),
@@ -319,6 +325,12 @@ static const struct dmi_system_id orientation_data[] = {
 		 DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"),
 		},
 		.driver_data = (void *)&lcd1200x1920_rightside_up,
+	}, {	/* Nanote UMPC-01 */
+		.matches = {
+		 DMI_MATCH(DMI_SYS_VENDOR, "RWC CO.,LTD"),
+		 DMI_MATCH(DMI_PRODUCT_NAME, "UMPC-01"),
+		},
+		.driver_data = (void *)&lcd1200x1920_rightside_up,
 	}, {	/* OneGX1 Pro */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"),
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index d4cce627d7a8..15c3e448aa0e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2201,8 +2201,11 @@ static void _psr_invalidate_handle(struct intel_dp *intel_dp)
 	if (intel_dp->psr.psr2_sel_fetch_enabled) {
 		u32 val;
 
-		if (intel_dp->psr.psr2_sel_fetch_cff_enabled)
+		if (intel_dp->psr.psr2_sel_fetch_cff_enabled) {
+			/* Send one update otherwise lag is observed in screen */
+			intel_de_write(dev_priv, CURSURFLIVE(intel_dp->psr.pipe), 0);
 			return;
+		}
 
 		val = man_trk_ctl_enable_bit_get(dev_priv) |
 		      man_trk_ctl_partial_frame_bit_get(dev_priv) |
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index f5062d0c6333..824971a1ceec 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -40,13 +40,13 @@ static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachme
 		goto err;
 	}
 
-	ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL);
+	ret = sg_alloc_table(st, obj->mm.pages->orig_nents, GFP_KERNEL);
 	if (ret)
 		goto err_free;
 
 	src = obj->mm.pages->sgl;
 	dst = st->sgl;
-	for (i = 0; i < obj->mm.pages->nents; i++) {
+	for (i = 0; i < obj->mm.pages->orig_nents; i++) {
 		sg_set_page(dst, sg_page(src), src->length, 0);
 		dst = sg_next(dst);
 		src = sg_next(src);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 11125c32dd35..2f7804492cd5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -369,14 +369,14 @@ __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
 
 	__start_cpu_write(obj);
 	/*
-	 * On non-LLC platforms, force the flush-on-acquire if this is ever
+	 * On non-LLC igfx platforms, force the flush-on-acquire if this is ever
 	 * swapped-in. Our async flush path is not trust worthy enough yet(and
 	 * happens in the wrong order), and with some tricks it's conceivable
 	 * for userspace to change the cache-level to I915_CACHE_NONE after the
 	 * pages are swapped-in, and since execbuf binds the object before doing
 	 * the async flush, we have a race window.
 	 */
-	if (!HAS_LLC(i915))
+	if (!HAS_LLC(i915) && !IS_DGFX(i915))
 		obj->cache_dirty = true;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index f34e01a7fefb..ba14b18d65f3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -428,9 +428,10 @@ probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len)
 {
 	VMA_ITERATOR(vmi, mm, addr);
 	struct vm_area_struct *vma;
+	unsigned long end = addr + len;
 
 	mmap_read_lock(mm);
-	for_each_vma_range(vmi, vma, addr + len) {
+	for_each_vma_range(vmi, vma, end) {
 		/* Check for holes, note that we also update the addr below */
 		if (vma->vm_start > addr)
 			break;
@@ -442,7 +443,7 @@ probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len)
 	}
 	mmap_read_unlock(mm);
 
-	if (vma)
+	if (vma || addr < end)
 		return -EFAULT;
 	return 0;
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index e246d914e7f6..4e83a1891f3e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -250,13 +250,22 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev)
 
 static size_t get_pgsize(u64 addr, size_t size, size_t *count)
 {
+	/*
+	 * io-pgtable only operates on multiple pages within a single table
+	 * entry, so we need to split at boundaries of the table size, i.e.
+	 * the next block size up. The distance from address A to the next
+	 * boundary of block size B is logically B - A % B, but in unsigned
+	 * two's complement where B is a power of two we get the equivalence
+	 * B - A % B == (B - A) % B == (n * B - A) % B, and choose n = 0 :)
+	 */
 	size_t blk_offset = -addr % SZ_2M;
 
 	if (blk_offset || size < SZ_2M) {
 		*count = min_not_zero(blk_offset, size) / SZ_4K;
 		return SZ_4K;
 	}
-	*count = size / SZ_2M;
+	blk_offset = -addr % SZ_1G ?: SZ_1G;
+	*count = min(blk_offset, size) / SZ_2M;
 	return SZ_2M;
 }
 
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index c959e8c6be7d..fd2c2eaee26b 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -44,13 +44,18 @@ config DRM_RCAR_LVDS
 	select OF_FLATTREE
 	select OF_OVERLAY
 
-config DRM_RCAR_MIPI_DSI
-	tristate "R-Car DU MIPI DSI Encoder Support"
-	depends on DRM && DRM_BRIDGE && OF
-	select DRM_MIPI_DSI
+config DRM_RCAR_USE_MIPI_DSI
+	bool "R-Car DU MIPI DSI Encoder Support"
+	depends on DRM_BRIDGE && OF
+	default DRM_RCAR_DU
 	help
 	  Enable support for the R-Car Display Unit embedded MIPI DSI encoders.
 
+config DRM_RCAR_MIPI_DSI
+	def_tristate DRM_RCAR_DU
+	depends on DRM_RCAR_USE_MIPI_DSI
+	select DRM_MIPI_DSI
+
 config DRM_RCAR_VSP
 	bool "R-Car DU VSP Compositor Support" if ARM
 	default y if ARM64
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 2027063fdc30..8c329c071c62 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -476,7 +476,12 @@ static int __init vc4_drm_register(void)
 	if (ret)
 		return ret;
 
-	return platform_driver_register(&vc4_platform_driver);
+	ret = platform_driver_register(&vc4_platform_driver);
+	if (ret)
+		platform_unregister_drivers(component_drivers,
+					    ARRAY_SIZE(component_drivers));
+
+	return ret;
 }
 
 static void __exit vc4_drm_unregister(void)
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 596e311d6e58..470432c8fd70 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -349,27 +349,40 @@ static int vc4_hdmi_reset_link(struct drm_connector *connector,
 	if (!crtc_state->active)
 		return 0;
 
-	if (!vc4_hdmi_supports_scrambling(encoder))
+	mutex_lock(&vc4_hdmi->mutex);
+
+	if (!vc4_hdmi_supports_scrambling(encoder)) {
+		mutex_unlock(&vc4_hdmi->mutex);
 		return 0;
+	}
 
 	scrambling_needed = vc4_hdmi_mode_needs_scrambling(&vc4_hdmi->saved_adjusted_mode,
 							   vc4_hdmi->output_bpc,
 							   vc4_hdmi->output_format);
-	if (!scrambling_needed)
+	if (!scrambling_needed) {
+		mutex_unlock(&vc4_hdmi->mutex);
 		return 0;
+	}
 
 	if (conn_state->commit &&
-	    !try_wait_for_completion(&conn_state->commit->hw_done))
+	    !try_wait_for_completion(&conn_state->commit->hw_done)) {
+		mutex_unlock(&vc4_hdmi->mutex);
 		return 0;
+	}
 
 	ret = drm_scdc_readb(connector->ddc, SCDC_TMDS_CONFIG, &config);
 	if (ret < 0) {
 		drm_err(drm, "Failed to read TMDS config: %d\n", ret);
+		mutex_unlock(&vc4_hdmi->mutex);
 		return 0;
 	}
 
-	if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed)
+	if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed) {
+		mutex_unlock(&vc4_hdmi->mutex);
 		return 0;
+	}
+
+	mutex_unlock(&vc4_hdmi->mutex);
 
 	/*
 	 * HDMI 2.0 says that one should not send scrambled data
@@ -397,9 +410,8 @@ static void vc4_hdmi_handle_hotplug(struct vc4_hdmi *vc4_hdmi,
 	 * .adap_enable, which leads to that funtion being called with
 	 * our mutex held.
 	 *
-	 * A similar situation occurs with
-	 * drm_atomic_helper_connector_hdmi_reset_link() that will call
-	 * into our KMS hooks if the scrambling was enabled.
+	 * A similar situation occurs with vc4_hdmi_reset_link() that
+	 * will call into our KMS hooks if the scrambling was enabled.
 	 *
 	 * Concurrency isn't an issue at the moment since we don't share
 	 * any state with any of the other frameworks so we can ignore
@@ -3160,9 +3172,16 @@ static int vc4_hdmi_init_resources(struct drm_device *drm,
 		DRM_ERROR("Failed to get HDMI state machine clock\n");
 		return PTR_ERR(vc4_hdmi->hsm_clock);
 	}
+
 	vc4_hdmi->audio_clock = vc4_hdmi->hsm_clock;
 	vc4_hdmi->cec_clock = vc4_hdmi->hsm_clock;
 
+	vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi");
+	if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) {
+		DRM_ERROR("Failed to get HDMI state machine clock\n");
+		return PTR_ERR(vc4_hdmi->hsm_rpm_clock);
+	}
+
 	return 0;
 }
 
@@ -3245,6 +3264,12 @@ static int vc5_hdmi_init_resources(struct drm_device *drm,
 		return PTR_ERR(vc4_hdmi->hsm_clock);
 	}
 
+	vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi");
+	if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) {
+		DRM_ERROR("Failed to get HDMI state machine clock\n");
+		return PTR_ERR(vc4_hdmi->hsm_rpm_clock);
+	}
+
 	vc4_hdmi->pixel_bvb_clock = devm_clk_get(dev, "bvb");
 	if (IS_ERR(vc4_hdmi->pixel_bvb_clock)) {
 		DRM_ERROR("Failed to get pixel bvb clock\n");
@@ -3308,7 +3333,7 @@ static int vc4_hdmi_runtime_suspend(struct device *dev)
 {
 	struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev);
 
-	clk_disable_unprepare(vc4_hdmi->hsm_clock);
+	clk_disable_unprepare(vc4_hdmi->hsm_rpm_clock);
 
 	return 0;
 }
@@ -3326,11 +3351,11 @@ static int vc4_hdmi_runtime_resume(struct device *dev)
 	 * its frequency while the power domain is active so that it
 	 * keeps its rate.
 	 */
-	ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ);
+	ret = clk_set_min_rate(vc4_hdmi->hsm_rpm_clock, HSM_MIN_CLOCK_FREQ);
 	if (ret)
 		return ret;
 
-	ret = clk_prepare_enable(vc4_hdmi->hsm_clock);
+	ret = clk_prepare_enable(vc4_hdmi->hsm_rpm_clock);
 	if (ret)
 		return ret;
 
@@ -3343,7 +3368,7 @@ static int vc4_hdmi_runtime_resume(struct device *dev)
 	 * case, it will lead to a silent CPU stall. Let's make sure we
 	 * prevent such a case.
 	 */
-	rate = clk_get_rate(vc4_hdmi->hsm_clock);
+	rate = clk_get_rate(vc4_hdmi->hsm_rpm_clock);
 	if (!rate) {
 		ret = -EINVAL;
 		goto err_disable_clk;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h
index db823efb2563..1ad8e8c377e2 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.h
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.h
@@ -172,6 +172,7 @@ struct vc4_hdmi {
 	struct clk *cec_clock;
 	struct clk *pixel_clock;
 	struct clk *hsm_clock;
+	struct clk *hsm_rpm_clock;
 	struct clk *audio_clock;
 	struct clk *pixel_bvb_clock;