Merge tag 'v6.18-rc6' into drm-next

Linux 6.18-rc6

Backmerge in order to merge msm next

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

47 files changed, 315 insertions, 140 deletions

diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index c2672f369aed..7789f42027ff 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -246,7 +246,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
       cmd_hdrtest = \
 		$(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \
-		 PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
+		 PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \
 		touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index c1461317eb29..e22cfa7c6d32 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -95,6 +95,18 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
 	    bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
 		attach->peer2peer = false;
 
+	/*
+	 * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+.
+	 * Such buffers cannot be safely accessed over P2P due to device-local
+	 * compression metadata. Fallback to system-memory path instead.
+	 * Device supports GFX12 (GC 12.x or newer)
+	 * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag
+	 *
+	 */
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) &&
+	    bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
+		attach->peer2peer = false;
+
 	if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) &&
 	    pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0)
 		attach->peer2peer = false;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
index 5e2813e9ae2f..c21eb34b8cc3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
@@ -75,7 +75,6 @@
  */
 #define MAX_LINK_ENCODERS (MAX_DIG_LINK_ENCODERS + MAX_DAC_LINK_ENCODERS)
 
-#define MAX_DIG_LINK_ENCODERS 7
 #define MAX_DWB_PIPES	1
 #define MAX_HPO_DP2_ENCODERS	4
 #define MAX_HPO_DP2_LINK_ENCODERS	4
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 7be36a358e74..787e38c6c17d 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -298,13 +298,13 @@ static inline void __ast_write8_i(void __iomem *addr, u32 reg, u8 index, u8 val)
 	__ast_write8(addr, reg + 1, val);
 }
 
-static inline void __ast_write8_i_masked(void __iomem *addr, u32 reg, u8 index, u8 read_mask,
+static inline void __ast_write8_i_masked(void __iomem *addr, u32 reg, u8 index, u8 preserve_mask,
 					 u8 val)
 {
-	u8 tmp = __ast_read8_i_masked(addr, reg, index, read_mask);
+	u8 tmp = __ast_read8_i_masked(addr, reg, index, preserve_mask);
 
-	tmp |= val;
-	__ast_write8_i(addr, reg, index, tmp);
+	val &= ~preserve_mask;
+	__ast_write8_i(addr, reg, index, tmp | val);
 }
 
 static inline u32 ast_read32(struct ast_device *ast, u32 reg)
diff --git a/drivers/gpu/drm/ci/gitlab-ci.yml b/drivers/gpu/drm/ci/gitlab-ci.yml
index d502d146b177..56638814bb28 100644
--- a/drivers/gpu/drm/ci/gitlab-ci.yml
+++ b/drivers/gpu/drm/ci/gitlab-ci.yml
@@ -280,7 +280,7 @@ sanity:
     GIT_STRATEGY: none
   script:
     # ci-fairy check-commits --junit-xml=check-commits.xml
-    - ci-fairy check-merge-request --require-allow-collaboration --junit-xml=check-merge-request.xml
+    # - ci-fairy check-merge-request --require-allow-collaboration --junit-xml=check-merge-request.xml
     - |
       set -eu
       image_tags=(
diff --git a/drivers/gpu/drm/clients/drm_client_setup.c b/drivers/gpu/drm/clients/drm_client_setup.c
index 72480db1f00d..515aceac22b1 100644
--- a/drivers/gpu/drm/clients/drm_client_setup.c
+++ b/drivers/gpu/drm/clients/drm_client_setup.c
@@ -13,8 +13,8 @@
 static char drm_client_default[16] = CONFIG_DRM_CLIENT_DEFAULT;
 module_param_string(active, drm_client_default, sizeof(drm_client_default), 0444);
 MODULE_PARM_DESC(active,
-		 "Choose which drm client to start, default is"
-		 CONFIG_DRM_CLIENT_DEFAULT "]");
+		 "Choose which drm client to start, default is "
+		 CONFIG_DRM_CLIENT_DEFAULT);
 
 /**
  * drm_client_setup() - Setup in-kernel DRM clients
diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c
index cbb029cc656a..569d41a65a0b 100644
--- a/drivers/gpu/drm/drm_gem_atomic_helper.c
+++ b/drivers/gpu/drm/drm_gem_atomic_helper.c
@@ -310,8 +310,12 @@ EXPORT_SYMBOL(drm_gem_destroy_shadow_plane_state);
 void __drm_gem_reset_shadow_plane(struct drm_plane *plane,
 				  struct drm_shadow_plane_state *shadow_plane_state)
 {
-	__drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base);
-	drm_format_conv_state_init(&shadow_plane_state->fmtcnv_state);
+	if (shadow_plane_state) {
+		__drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base);
+		drm_format_conv_state_init(&shadow_plane_state->fmtcnv_state);
+	} else {
+		__drm_atomic_helper_plane_reset(plane, NULL);
+	}
 }
 EXPORT_SYMBOL(__drm_gem_reset_shadow_plane);
 
diff --git a/drivers/gpu/drm/drm_panic.c b/drivers/gpu/drm/drm_panic.c
index 1d6312fa1429..d4b6ea42db0f 100644
--- a/drivers/gpu/drm/drm_panic.c
+++ b/drivers/gpu/drm/drm_panic.c
@@ -174,6 +174,33 @@ static void drm_panic_write_pixel24(void *vaddr, unsigned int offset, u32 color)
 	*p = color & 0xff;
 }
 
+/*
+ * Special case if the pixel crosses page boundaries
+ */
+static void drm_panic_write_pixel24_xpage(void *vaddr, struct page *next_page,
+					  unsigned int offset, u32 color)
+{
+	u8 *vaddr2;
+	u8 *p = vaddr + offset;
+
+	vaddr2 = kmap_local_page_try_from_panic(next_page);
+
+	*p++ = color & 0xff;
+	color >>= 8;
+
+	if (offset == PAGE_SIZE - 1)
+		p = vaddr2;
+
+	*p++ = color & 0xff;
+	color >>= 8;
+
+	if (offset == PAGE_SIZE - 2)
+		p = vaddr2;
+
+	*p = color & 0xff;
+	kunmap_local(vaddr2);
+}
+
 static void drm_panic_write_pixel32(void *vaddr, unsigned int offset, u32 color)
 {
 	u32 *p = vaddr + offset;
@@ -231,7 +258,14 @@ static void drm_panic_blit_page(struct page **pages, unsigned int dpitch,
 					page = new_page;
 					vaddr = kmap_local_page_try_from_panic(pages[page]);
 				}
-				if (vaddr)
+				if (!vaddr)
+					continue;
+
+				// Special case for 24bit, as a pixel might cross page boundaries
+				if (cpp == 3 && offset + 3 > PAGE_SIZE)
+					drm_panic_write_pixel24_xpage(vaddr, pages[page + 1],
+								      offset, fg32);
+				else
 					drm_panic_write_pixel(vaddr, offset, fg32, cpp);
 			}
 		}
@@ -321,7 +355,15 @@ static void drm_panic_fill_page(struct page **pages, unsigned int dpitch,
 				page = new_page;
 				vaddr = kmap_local_page_try_from_panic(pages[page]);
 			}
-			drm_panic_write_pixel(vaddr, offset, color, cpp);
+			if (!vaddr)
+				continue;
+
+			// Special case for 24bit, as a pixel might cross page boundaries
+			if (cpp == 3 && offset + 3 > PAGE_SIZE)
+				drm_panic_write_pixel24_xpage(vaddr, pages[page + 1],
+							      offset, color);
+			else
+				drm_panic_write_pixel(vaddr, offset, color, cpp);
 		}
 	}
 	if (vaddr)
@@ -429,6 +471,9 @@ static void drm_panic_logo_rect(struct drm_rect *rect, const struct font_desc *f
 static void drm_panic_logo_draw(struct drm_scanout_buffer *sb, struct drm_rect *rect,
 				const struct font_desc *font, u32 fg_color)
 {
+	if (rect->x2 > sb->width || rect->y2 > sb->height)
+		return;
+
 	if (logo_mono)
 		drm_panic_blit(sb, rect, logo_mono->data,
 			       DIV_ROUND_UP(drm_rect_width(rect), 8), 1, fg_color);
@@ -477,7 +522,7 @@ static int draw_line_with_wrap(struct drm_scanout_buffer *sb, const struct font_
 			       struct drm_panic_line *line, int yoffset, u32 fg_color)
 {
 	int chars_per_row = sb->width / font->width;
-	struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, sb->height);
+	struct drm_rect r_txt = DRM_RECT_INIT(0, yoffset, sb->width, font->height);
 	struct drm_panic_line line_wrap;
 
 	if (line->len > chars_per_row) {
@@ -520,7 +565,7 @@ static void draw_panic_static_kmsg(struct drm_scanout_buffer *sb)
 	struct drm_panic_line line;
 	int yoffset;
 
-	if (!font)
+	if (!font || font->width > sb->width)
 		return;
 
 	yoffset = sb->height - font->height - (sb->height % font->height) / 2;
@@ -733,7 +778,10 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb)
 	pr_debug("QR width %d and scale %d\n", qr_width, scale);
 	r_qr_canvas = DRM_RECT_INIT(0, 0, qr_canvas_width * scale, qr_canvas_width * scale);
 
-	v_margin = (sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg)) / 5;
+	v_margin = sb->height - drm_rect_height(&r_qr_canvas) - drm_rect_height(&r_msg);
+	if (v_margin < 0)
+		return -ENOSPC;
+	v_margin /= 5;
 
 	drm_rect_translate(&r_qr_canvas, (sb->width - r_qr_canvas.x2) / 2, 2 * v_margin);
 	r_qr = DRM_RECT_INIT(r_qr_canvas.x1 + QR_MARGIN * scale, r_qr_canvas.y1 + QR_MARGIN * scale,
@@ -746,7 +794,7 @@ static int _draw_panic_static_qr_code(struct drm_scanout_buffer *sb)
 	/* Fill with the background color, and draw text on top */
 	drm_panic_fill(sb, &r_screen, bg_color);
 
-	if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr))
+	if (!drm_rect_overlap(&r_logo, &r_msg) && !drm_rect_overlap(&r_logo, &r_qr_canvas))
 		drm_panic_logo_draw(sb, &r_logo, font, fg_color);
 
 	draw_txt_rectangle(sb, font, panic_msg, panic_msg_lines, true, &r_msg, fg_color);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
index d4f1307d574f..ad5e6f7b23f9 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_buffer.c
@@ -348,7 +348,7 @@ void etnaviv_buffer_queue(struct etnaviv_gpu *gpu, u32 exec_state,
 	u32 link_target, link_dwords;
 	bool switch_context = gpu->exec_state != exec_state;
 	bool switch_mmu_context = gpu->mmu_context != mmu_context;
-	unsigned int new_flush_seq = READ_ONCE(gpu->mmu_context->flush_seq);
+	unsigned int new_flush_seq = READ_ONCE(mmu_context->flush_seq);
 	bool need_flush = switch_mmu_context || gpu->flush_seq != new_flush_seq;
 	bool has_blt = !!(gpu->identity.minor_features5 &
 			  chipMinorFeatures5_BLT_ENGINE);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 49c86a0d44f9..7c89e5e0a277 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -426,7 +426,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += kvmgt.o
 #
 # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build
 ifdef CONFIG_DRM_I915_WERROR
-    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none -Werror $<
+    cmd_checkdoc = PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none -Werror $<
 endif
 
 # header test
diff --git a/drivers/gpu/drm/imagination/Kconfig b/drivers/gpu/drm/imagination/Kconfig
index 682dd2633d0c..0482bfcefdde 100644
--- a/drivers/gpu/drm/imagination/Kconfig
+++ b/drivers/gpu/drm/imagination/Kconfig
@@ -7,6 +7,7 @@ config DRM_POWERVR
 	depends on DRM
 	depends on MMU
 	depends on PM
+	depends on POWER_SEQUENCING || !POWER_SEQUENCING
 	select DRM_EXEC
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_SCHED
diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
index 61fab3698807..6fbf505d2801 100644
--- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c
+++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c
@@ -25,19 +25,18 @@
 
 struct imx_parallel_display_encoder {
 	struct drm_encoder encoder;
-	struct drm_bridge bridge;
-	struct imx_parallel_display *pd;
 };
 
 struct imx_parallel_display {
 	struct device *dev;
 	u32 bus_format;
 	struct drm_bridge *next_bridge;
+	struct drm_bridge bridge;
 };
 
 static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b)
 {
-	return container_of(b, struct imx_parallel_display_encoder, bridge)->pd;
+	return container_of(b, struct imx_parallel_display, bridge);
 }
 
 static const u32 imx_pd_bus_fmts[] = {
@@ -195,15 +194,13 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data)
 	if (IS_ERR(imxpd_encoder))
 		return PTR_ERR(imxpd_encoder);
 
-	imxpd_encoder->pd = imxpd;
 	encoder = &imxpd_encoder->encoder;
-	bridge = &imxpd_encoder->bridge;
+	bridge = &imxpd->bridge;
 
 	ret = imx_drm_encoder_parse_of(drm, encoder, imxpd->dev->of_node);
 	if (ret)
 		return ret;
 
-	bridge->funcs = &imx_pd_bridge_funcs;
 	drm_bridge_attach(encoder, bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR);
 
 	connector = drm_bridge_connector_init(drm, encoder);
@@ -228,9 +225,10 @@ static int imx_pd_probe(struct platform_device *pdev)
 	u32 bus_format = 0;
 	const char *fmt;
 
-	imxpd = devm_kzalloc(dev, sizeof(*imxpd), GFP_KERNEL);
-	if (!imxpd)
-		return -ENOMEM;
+	imxpd = devm_drm_bridge_alloc(dev, struct imx_parallel_display, bridge,
+				      &imx_pd_bridge_funcs);
+	if (IS_ERR(imxpd))
+		return PTR_ERR(imxpd);
 
 	/* port@1 is the output port */
 	imxpd->next_bridge = devm_drm_of_get_bridge(dev, np, 1, 0);
@@ -258,6 +256,8 @@ static int imx_pd_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, imxpd);
 
+	devm_drm_bridge_add(dev, &imxpd->bridge);
+
 	return component_add(dev, &imx_pd_ops);
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index 68646a61f74d..991cdb3d7d5f 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -284,6 +284,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
 	unsigned int i;
 	unsigned long flags;
 
+	/* release GCE HW usage and start autosuspend */
+	pm_runtime_mark_last_busy(cmdq_cl->chan->mbox->dev);
+	pm_runtime_put_autosuspend(cmdq_cl->chan->mbox->dev);
+
 	if (data->sta < 0)
 		return;
 
@@ -619,6 +623,9 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
 		mtk_crtc->config_updating = false;
 		spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
 
+		if (pm_runtime_resume_and_get(mtk_crtc->cmdq_client.chan->mbox->dev) < 0)
+			goto update_config_out;
+
 		mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle);
 		mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
 		goto update_config_out;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index eb5537f0ac90..31ff2922758a 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -686,10 +686,6 @@ err_free:
 	for (i = 0; i < private->data->mmsys_dev_num; i++)
 		private->all_drm_private[i]->drm = NULL;
 err_put_dev:
-	for (i = 0; i < private->data->mmsys_dev_num; i++) {
-		/* For device_find_child in mtk_drm_get_all_priv() */
-		put_device(private->all_drm_private[i]->dev);
-	}
 	put_device(private->mutex_dev);
 	return ret;
 }
@@ -697,18 +693,12 @@ err_put_dev:
 static void mtk_drm_unbind(struct device *dev)
 {
 	struct mtk_drm_private *private = dev_get_drvdata(dev);
-	int i;
 
 	/* for multi mmsys dev, unregister drm dev in mmsys master */
 	if (private->drm_master) {
 		drm_dev_unregister(private->drm);
 		mtk_drm_kms_deinit(private->drm);
 		drm_dev_put(private->drm);
-
-		for (i = 0; i < private->data->mmsys_dev_num; i++) {
-			/* For device_find_child in mtk_drm_get_all_priv() */
-			put_device(private->all_drm_private[i]->dev);
-		}
 		put_device(private->mutex_dev);
 	}
 	private->mtk_drm_bound = false;
diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index c22166476423..5043e0377270 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -22,9 +22,6 @@
 
 static const u64 modifiers[] = {
 	DRM_FORMAT_MOD_LINEAR,
-	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE),
 	DRM_FORMAT_MOD_INVALID,
 };
 
@@ -72,26 +69,7 @@ static bool mtk_plane_format_mod_supported(struct drm_plane *plane,
 					   uint32_t format,
 					   uint64_t modifier)
 {
-	if (modifier == DRM_FORMAT_MOD_LINEAR)
-		return true;
-
-	if (modifier != DRM_FORMAT_MOD_ARM_AFBC(
-				AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
-				AFBC_FORMAT_MOD_SPLIT |
-				AFBC_FORMAT_MOD_SPARSE))
-		return false;
-
-	if (format != DRM_FORMAT_XRGB8888 &&
-	    format != DRM_FORMAT_ARGB8888 &&
-	    format != DRM_FORMAT_BGRX8888 &&
-	    format != DRM_FORMAT_BGRA8888 &&
-	    format != DRM_FORMAT_ABGR8888 &&
-	    format != DRM_FORMAT_XBGR8888 &&
-	    format != DRM_FORMAT_RGB888 &&
-	    format != DRM_FORMAT_BGR888)
-		return false;
-
-	return true;
+	return modifier == DRM_FORMAT_MOD_LINEAR;
 }
 
 static void mtk_plane_destroy_state(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index fc62fef2fed8..4e6dc16e4a4c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -780,6 +780,9 @@ static bool fw_block_mem(struct a6xx_gmu_bo *bo, const struct block_header *blk)
 	return true;
 }
 
+#define NEXT_BLK(blk) \
+	((const struct block_header *)((const char *)(blk) + sizeof(*(blk)) + (blk)->size))
+
 static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 {
 	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
@@ -811,7 +814,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 
 	for (blk = (const struct block_header *) fw_image->data;
 	     (const u8*) blk < fw_image->data + fw_image->size;
-	     blk = (const struct block_header *) &blk->data[blk->size >> 2]) {
+	     blk = NEXT_BLK(blk)) {
 		if (blk->size == 0)
 			continue;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index afaa3cfefd35..4b5a4edd0702 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -348,13 +348,6 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 	return 0;
 }
 
-static bool
-adreno_smmu_has_prr(struct msm_gpu *gpu)
-{
-	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev);
-	return adreno_smmu && adreno_smmu->set_prr_addr;
-}
-
 int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
 		     uint32_t param, uint64_t *value, uint32_t *len)
 {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 4b970a59deaf..2f8156051d9b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1545,6 +1545,9 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc,
 	adjusted_mode_clk = dpu_core_perf_adjusted_mode_clk(mode->clock,
 							    dpu_kms->perf.perf_cfg);
 
+	if (dpu_kms->catalog->caps->has_3d_merge)
+		adjusted_mode_clk /= 2;
+
 	/*
 	 * The given mode, adjusted for the perf clock factor, should not exceed
 	 * the max core clock rate
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 6641455c4ec6..9f8d1bba9139 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -267,8 +267,8 @@ static const u32 wb2_formats_rgb_yuv[] = {
 		.base = 0x200, .len = 0xa0,}, \
 	.csc_blk = {.name = "csc", \
 		.base = 0x320, .len = 0x100,}, \
-	.format_list = plane_formats_yuv, \
-	.num_formats = ARRAY_SIZE(plane_formats_yuv), \
+	.format_list = plane_formats, \
+	.num_formats = ARRAY_SIZE(plane_formats), \
 	.rotation_cfg = NULL, \
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index f54cf0faa1c7..905524ceeb1f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -500,13 +500,15 @@ static void _dpu_plane_setup_pixel_ext(struct dpu_hw_scaler3_cfg *scale_cfg,
 	int i;
 
 	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		uint32_t w = src_w, h = src_h;
+
 		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
-			src_w /= chroma_subsmpl_h;
-			src_h /= chroma_subsmpl_v;
+			w /= chroma_subsmpl_h;
+			h /= chroma_subsmpl_v;
 		}
 
-		pixel_ext->num_ext_pxls_top[i] = src_h;
-		pixel_ext->num_ext_pxls_left[i] = src_w;
+		pixel_ext->num_ext_pxls_top[i] = h;
+		pixel_ext->num_ext_pxls_left[i] = w;
 	}
 }
 
@@ -740,7 +742,7 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
 	 * We already have verified scaling against platform limitations.
 	 * Now check if the SSPP supports scaling at all.
 	 */
-	if (!sblk->scaler_blk.len &&
+	if (!(sblk->scaler_blk.len && pipe->sspp->ops.setup_scaler) &&
 	    ((drm_rect_width(&new_plane_state->src) >> 16 !=
 	      drm_rect_width(&new_plane_state->dst)) ||
 	     (drm_rect_height(&new_plane_state->src) >> 16 !=
@@ -1278,7 +1280,7 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state,
 							     state, plane_state,
 							     prev_adjacent_plane_state);
 		if (ret)
-			break;
+			return ret;
 
 		prev_adjacent_plane_state = plane_state;
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index 2c77c74fac0f..d9c3b0a1d091 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -842,7 +842,7 @@ struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm,
 
 	if (!reqs->scale && !reqs->yuv)
 		hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_DMA);
-	if (!hw_sspp && reqs->scale)
+	if (!hw_sspp && !reqs->yuv)
 		hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_RGB);
 	if (!hw_sspp)
 		hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_VIG);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
index cd73468e369a..7545c0293efb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
@@ -72,6 +72,9 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector,
 		DPU_ERROR("invalid fb w=%d, maxlinewidth=%u\n",
 			  fb->width, dpu_wb_conn->maxlinewidth);
 		return -EINVAL;
+	} else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) {
+		DPU_ERROR("unsupported fb modifier:%#llx\n", fb->modifier);
+		return -EINVAL;
 	}
 
 	return drm_atomic_helper_check_wb_connector_state(conn_state->connector, conn_state->state);
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index e391505fdaf0..3cbf08231492 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -109,7 +109,6 @@ struct msm_dsi_phy {
 	struct msm_dsi_dphy_timing timing;
 	const struct msm_dsi_phy_cfg *cfg;
 	void *tuning_cfg;
-	void *pll_data;
 
 	enum msm_dsi_phy_usecase usecase;
 	bool regulator_ldo_mode;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 32f06edd21a9..c5e1d2016bcc 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -426,11 +426,8 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll)
 	u32 data;
 
 	spin_lock_irqsave(&pll->pll_enable_lock, flags);
-	if (pll->pll_enable_cnt++) {
-		spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
-		WARN_ON(pll->pll_enable_cnt == INT_MAX);
-		return;
-	}
+	pll->pll_enable_cnt++;
+	WARN_ON(pll->pll_enable_cnt == INT_MAX);
 
 	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0);
 	data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB;
@@ -876,7 +873,6 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy)
 	spin_lock_init(&pll_7nm->pll_enable_lock);
 
 	pll_7nm->phy = phy;
-	phy->pll_data = pll_7nm;
 
 	ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws);
 	if (ret) {
@@ -965,10 +961,8 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 	u32 const delay_us = 5;
 	u32 const timeout_us = 1000;
 	struct msm_dsi_dphy_timing *timing = &phy->timing;
-	struct dsi_pll_7nm *pll = phy->pll_data;
 	void __iomem *base = phy->base;
 	bool less_than_1500_mhz;
-	unsigned long flags;
 	u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0;
 	u32 glbl_pemph_ctrl_0;
 	u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0;
@@ -1090,13 +1084,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy,
 		glbl_rescode_bot_ctrl = 0x3c;
 	}
 
-	spin_lock_irqsave(&pll->pll_enable_lock, flags);
-	pll->pll_enable_cnt = 1;
 	/* de-assert digital and pll power down */
 	data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B |
 	       DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB;
 	writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
-	spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
 
 	/* Assert PLL core reset */
 	writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL);
@@ -1209,9 +1200,7 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable)
 
 static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 {
-	struct dsi_pll_7nm *pll = phy->pll_data;
 	void __iomem *base = phy->base;
-	unsigned long flags;
 	u32 data;
 
 	DBG("");
@@ -1238,11 +1227,8 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy)
 	writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
 	writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0);
 
-	spin_lock_irqsave(&pll->pll_enable_lock, flags);
-	pll->pll_enable_cnt = 0;
 	/* Turn off all PHY blocks */
 	writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0);
-	spin_unlock_irqrestore(&pll->pll_enable_lock, flags);
 
 	/* make sure phy is turned off */
 	wmb();
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 688705a871cf..435c0067c264 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1143,12 +1143,16 @@ static void msm_gem_free_object(struct drm_gem_object *obj)
 		put_pages(obj);
 	}
 
-	if (obj->resv != &obj->_resv) {
+	/*
+	 * In error paths, we could end up here before msm_gem_new_handle()
+	 * has changed obj->resv to point to the shared resv.  In this case,
+	 * we don't want to drop a ref to the shared r_obj that we haven't
+	 * taken yet.
+	 */
+	if ((msm_obj->flags & MSM_BO_NO_SHARE) && (obj->resv != &obj->_resv)) {
 		struct drm_gem_object *r_obj =
 			container_of(obj->resv, struct drm_gem_object, _resv);
 
-		WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE));
-
 		/* Drop reference we hold to shared resv obj: */
 		drm_gem_object_put(r_obj);
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3ab3b27134f9..75d9f3574370 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -414,6 +414,11 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit)
 					 submit->user_fence,
 					 DMA_RESV_USAGE_BOOKKEEP,
 					 DMA_RESV_USAGE_BOOKKEEP);
+
+		last_fence = vm->last_fence;
+		vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence);
+		dma_fence_put(last_fence);
+
 		return;
 	}
 
@@ -427,10 +432,6 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit)
 			dma_resv_add_fence(obj->resv, submit->user_fence,
 					   DMA_RESV_USAGE_READ);
 	}
-
-	last_fence = vm->last_fence;
-	vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence);
-	dma_fence_put(last_fence);
 }
 
 static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 8316af1723c2..89a95977f41e 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -971,6 +971,7 @@ static int
 lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op)
 {
 	struct drm_device *dev = job->vm->drm;
+	struct msm_drm_private *priv = dev->dev_private;
 	int i = job->nr_ops++;
 	int ret = 0;
 
@@ -1017,6 +1018,11 @@ lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op)
 		break;
 	}
 
+	if ((op->op == MSM_VM_BIND_OP_MAP_NULL) &&
+	    !adreno_smmu_has_prr(priv->gpu)) {
+		ret = UERR(EINVAL, dev, "PRR not supported\n");
+	}
+
 	return ret;
 }
 
@@ -1421,7 +1427,7 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file)
 	 * Maybe we could allow just UNMAP ops?  OTOH userspace should just
 	 * immediately close the device file and all will be torn down.
 	 */
-	if (to_msm_vm(ctx->vm)->unusable)
+	if (to_msm_vm(msm_context_vm(dev, ctx))->unusable)
 		return UERR(EPIPE, dev, "context is unusable");
 
 	/*
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index a597f2bee30b..2894fc118485 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -299,6 +299,17 @@ static inline struct msm_gpu *dev_to_gpu(struct device *dev)
 	return container_of(adreno_smmu, struct msm_gpu, adreno_smmu);
 }
 
+static inline bool
+adreno_smmu_has_prr(struct msm_gpu *gpu)
+{
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev);
+
+	if (!adreno_smmu)
+		return false;
+
+	return adreno_smmu && adreno_smmu->set_prr_addr;
+}
+
 /* It turns out that all targets use the same ringbuffer size */
 #define MSM_GPU_RINGBUFFER_SZ SZ_32K
 #define MSM_GPU_RINGBUFFER_BLKSIZE 32
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 0e18619f96cb..a188617653e8 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -338,6 +338,8 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall
 
 	ret = kmem_cache_alloc_bulk(pt_cache, GFP_KERNEL, p->count, p->pages);
 	if (ret != p->count) {
+		kfree(p->pages);
+		p->pages = NULL;
 		p->count = ret;
 		return -ENOMEM;
 	}
@@ -351,6 +353,9 @@ msm_iommu_pagetable_prealloc_cleanup(struct msm_mmu *mmu, struct msm_mmu_preallo
 	struct kmem_cache *pt_cache = get_pt_cache(mmu);
 	uint32_t remaining_pt_count = p->count - p->ptr;
 
+	if (!p->pages)
+		return;
+
 	if (p->count > 0)
 		trace_msm_mmu_prealloc_cleanup(p->count, remaining_pt_count);
 
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index e97e39abf3a2..12b1dba8e05d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2867,7 +2867,9 @@ nv50_display_create(struct drm_device *dev)
 	}
 
 	/* Assign the correct format modifiers */
-	if (disp->disp->object.oclass >= TU102_DISP)
+	if (disp->disp->object.oclass >= GB202_DISP)
+		nouveau_display(dev)->format_modifiers = wndwca7e_modifiers;
+	else if (disp->disp->object.oclass >= TU102_DISP)
 		nouveau_display(dev)->format_modifiers = wndwc57e_modifiers;
 	else
 	if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_FERMI)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 15f9242b72ac..5d998f0319dc 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -104,4 +104,5 @@ struct nouveau_encoder *nv50_real_outp(struct drm_encoder *encoder);
 extern const u64 disp50xx_modifiers[];
 extern const u64 disp90xx_modifiers[];
 extern const u64 wndwc57e_modifiers[];
+extern const u64 wndwca7e_modifiers[];
 #endif
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index e2c55f4b9c5a..ef9e410babbf 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -786,13 +786,14 @@ nv50_wndw_destroy(struct drm_plane *plane)
 }
 
 /* This function assumes the format has already been validated against the plane
- * and the modifier was validated against the device-wides modifier list at FB
+ * and the modifier was validated against the device-wide modifier list at FB
  * creation time.
  */
 static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 					    u32 format, u64 modifier)
 {
 	struct nouveau_drm *drm = nouveau_drm(plane->dev);
+	const struct drm_format_info *info = drm_format_info(format);
 	uint8_t i;
 
 	/* All chipsets can display all formats in linear layout */
@@ -800,13 +801,32 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 		return true;
 
 	if (drm->client.device.info.chipset < 0xc0) {
-		const struct drm_format_info *info = drm_format_info(format);
 		const uint8_t kind = (modifier >> 12) & 0xff;
 
 		if (!format) return false;
 
 		for (i = 0; i < info->num_planes; i++)
 			if ((info->cpp[i] != 4) && kind != 0x70) return false;
+	} else if (drm->client.device.info.chipset >= 0x1b2) {
+		const uint8_t slayout = ((modifier >> 22) & 0x1) |
+			((modifier >> 25) & 0x6);
+
+		if (!format)
+			return false;
+
+		/*
+		 * Note in practice this implies only formats where cpp is equal
+		 * for each plane, or >= 4 for all planes, are supported.
+		 */
+		for (i = 0; i < info->num_planes; i++) {
+			if (((info->cpp[i] == 2) && slayout != 3) ||
+			    ((info->cpp[i] == 1) && slayout != 2) ||
+			    ((info->cpp[i] >= 4) && slayout != 1))
+				return false;
+
+			/* 24-bit not supported. It has yet another layout */
+			WARN_ON(info->cpp[i] == 3);
+		}
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
index 0d8e9a9d1a57..2cec8cfbd546 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwca7e.c
@@ -179,6 +179,39 @@ wndwca7e_ntfy_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	return 0;
 }
 
+/****************************************************************
+ *            Log2(block height) ----------------------------+  *
+ *            Page Kind ----------------------------------+  |  *
+ *            Gob Height/Page Kind Generation ------+     |  |  *
+ *                          Sector layout -------+  |     |  |  *
+ *                          Compression ------+  |  |     |  |  */
+const u64 wndwca7e_modifiers[] = { /*         |  |  |     |  |  */
+	/* 4cpp+ modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 1, 2, 0x06, 5),
+	/* 1cpp/8bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 2, 2, 0x06, 5),
+	/* 2cpp/16bpp modifiers */
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 0),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 1),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 2),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 3),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 4),
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 3, 2, 0x06, 5),
+	/* All formats support linear */
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 static const struct nv50_wndw_func
 wndwca7e = {
 	.acquire = wndwc37e_acquire,
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index e60f7892f5ce..a7bf539e5d86 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -482,6 +482,17 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
 	return 0;
 }
 
+static bool
+nouveau_sched_job_list_empty(struct nouveau_sched *sched)
+{
+	bool empty;
+
+	spin_lock(&sched->job.list.lock);
+	empty = list_empty(&sched->job.list.head);
+	spin_unlock(&sched->job.list.lock);
+
+	return empty;
+}
 
 static void
 nouveau_sched_fini(struct nouveau_sched *sched)
@@ -489,8 +500,7 @@ nouveau_sched_fini(struct nouveau_sched *sched)
 	struct drm_gpu_scheduler *drm_sched = &sched->base;
 	struct drm_sched_entity *entity = &sched->entity;
 
-	rmb(); /* for list_empty to work without lock */
-	wait_event(sched->job.wq, list_empty(&sched->job.list.head));
+	wait_event(sched->job.wq, nouveau_sched_job_list_empty(sched));
 
 	drm_sched_entity_fini(entity);
 	drm_sched_fini(drm_sched);
diff --git a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
index 2fc7b0779b37..893af9b16756 100644
--- a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
+++ b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
@@ -359,7 +359,7 @@ static int kingdisplay_panel_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 4;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET;
 
 	kingdisplay = devm_drm_panel_alloc(&dsi->dev, __typeof(*kingdisplay), base,
 					   &kingdisplay_panel_funcs,
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 04d91929eedd..d5f821d6b23c 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -249,6 +249,11 @@ static const struct drm_display_mode default_mode = {
 	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
 };
 
+/*
+ * The mode data for this panel has been reverse engineered without access
+ * to the panel datasheet / manual. Using DRM_MODE_FLAG_PHSYNC like all
+ * other panels results in garbage data on the display.
+ */
 static const struct drm_display_mode t28cp45tn89_mode = {
 	.clock = 6008,
 	.hdisplay = 240,
@@ -261,7 +266,7 @@ static const struct drm_display_mode t28cp45tn89_mode = {
 	.vtotal = 320 + 8 + 4 + 4,
 	.width_mm = 43,
 	.height_mm = 57,
-	.flags = DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC,
+	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_PVSYNC,
 };
 
 static const struct drm_display_mode et028013dma_mode = {
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index f369cc3e2a5f..2c12c1c58e2b 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -281,6 +281,23 @@ panthor_gem_create_with_handle(struct drm_file *file,
 
 	panthor_gem_debugfs_set_usage_flags(bo, 0);
 
+	/* If this is a write-combine mapping, we query the sgt to force a CPU
+	 * cache flush (dma_map_sgtable() is called when the sgt is created).
+	 * This ensures the zero-ing is visible to any uncached mapping created
+	 * by vmap/mmap.
+	 * FIXME: Ideally this should be done when pages are allocated, not at
+	 * BO creation time.
+	 */
+	if (shmem->map_wc) {
+		struct sg_table *sgt;
+
+		sgt = drm_gem_shmem_get_pages_sgt(shmem);
+		if (IS_ERR(sgt)) {
+			ret = PTR_ERR(sgt);
+			goto out_put_gem;
+		}
+	}
+
 	/*
 	 * Allocate an id of idr table where the obj is registered
 	 * and handle has the id what user can see.
@@ -289,6 +306,7 @@ panthor_gem_create_with_handle(struct drm_file *file,
 	if (!ret)
 		*size = bo->base.base.size;
 
+out_put_gem:
 	/* drop reference from allocate - handle holds it now. */
 	drm_gem_object_put(&shmem->base);
 
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 2ec745ffdeff..478ea98db95c 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -1143,10 +1143,14 @@ panthor_vm_op_ctx_prealloc_vmas(struct panthor_vm_op_ctx *op_ctx)
 		break;
 
 	case DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP:
-		/* Partial unmaps might trigger a remap with either a prev or a next VA,
-		 * but not both.
+		/* Two VMAs can be needed for an unmap, as an unmap can happen
+		 * in the middle of a drm_gpuva, requiring a remap with both
+		 * prev & next VA. Or an unmap can span more than one drm_gpuva
+		 * where the first and last ones are covered partially, requring
+		 * a remap for the first with a prev VA and remap for the last
+		 * with a next VA.
 		 */
-		vma_count = 1;
+		vma_count = 2;
 		break;
 
 	default:
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
index 7b613997bb50..727cdf768161 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
@@ -361,7 +361,7 @@ static void dw_hdmi_rk3228_setup_hpd(struct dw_hdmi *dw_hdmi, void *data)
 
 	regmap_write(hdmi->regmap, RK3228_GRF_SOC_CON2,
 		     FIELD_PREP_WM16(RK3228_HDMI_SDAIN_MSK, 1) |
-		     FIELD_PREP_WM16(RK3328_HDMI_SCLIN_MSK, 1));
+		     FIELD_PREP_WM16(RK3228_HDMI_SCLIN_MSK, 1));
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 5a4697f636f2..fe174a4857be 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -70,6 +70,7 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	entity->guilty = guilty;
 	entity->num_sched_list = num_sched_list;
 	entity->priority = priority;
+	entity->last_user = current->group_leader;
 	/*
 	 * It's perfectly valid to initialize an entity without having a valid
 	 * scheduler attached. It's just not valid to use the scheduler before it
@@ -172,26 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_error);
 
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb);
+
 static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
 {
 	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
-
-	drm_sched_fence_scheduled(job->s_fence, NULL);
-	drm_sched_fence_finished(job->s_fence, -ESRCH);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
-}
-
-/* Signal the scheduler finished fence when the entity in question is killed. */
-static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
-					  struct dma_fence_cb *cb)
-{
-	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
-						 finish_cb);
+	struct dma_fence *f;
 	unsigned long index;
 
-	dma_fence_put(f);
-
 	/* Wait for all dependencies to avoid data corruptions */
 	xa_for_each(&job->dependencies, index, f) {
 		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
@@ -219,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 		dma_fence_put(f);
 	}
 
+	drm_sched_fence_scheduled(job->s_fence, NULL);
+	drm_sched_fence_finished(job->s_fence, -ESRCH);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+/* Signal the scheduler finished fence when the entity in question is killed. */
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+
+	dma_fence_put(f);
+
 	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
 	schedule_work(&job->work);
 }
@@ -302,7 +307,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 
 	/* For a killed process disallow further enqueueing of jobs. */
 	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
-	if ((!last_user || last_user == current->group_leader) &&
+	if (last_user == current->group_leader &&
 	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
 		drm_sched_entity_kill(entity);
 
@@ -552,10 +557,11 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 		drm_sched_rq_remove_entity(entity->rq, entity);
 		entity->rq = rq;
 	}
-	spin_unlock(&entity->lock);
 
 	if (entity->num_sched_list == 1)
 		entity->sched_list = NULL;
+
+	spin_unlock(&entity->lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 7d9e85e932d7..f0e72d4b6a47 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -85,6 +85,7 @@ config DRM_PANEL_MIPI_DBI
 config DRM_PIXPAPER
         tristate "DRM support for PIXPAPER display panels"
         depends on DRM && SPI
+        depends on MMU
         select DRM_CLIENT_SELECTION
         select DRM_GEM_SHMEM_HELPER
         select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
index 718832b08d96..c46f17ba7236 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
@@ -100,8 +100,10 @@ vmw_cursor_update_type(struct vmw_private *vmw, struct vmw_plane_state *vps)
 	if (vmw->has_mob) {
 		if ((vmw->capabilities2 & SVGA_CAP2_CURSOR_MOB) != 0)
 			return VMW_CURSOR_UPDATE_MOB;
+		else
+			return VMW_CURSOR_UPDATE_GB_ONLY;
 	}
-
+	drm_warn_once(&vmw->drm, "Unknown Cursor Type!\n");
 	return VMW_CURSOR_UPDATE_NONE;
 }
 
@@ -139,6 +141,7 @@ static u32 vmw_cursor_mob_size(enum vmw_cursor_update_type update_type,
 {
 	switch (update_type) {
 	case VMW_CURSOR_UPDATE_LEGACY:
+	case VMW_CURSOR_UPDATE_GB_ONLY:
 	case VMW_CURSOR_UPDATE_NONE:
 		return 0;
 	case VMW_CURSOR_UPDATE_MOB:
@@ -623,6 +626,7 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane,
 		if (!surface || vps->cursor.legacy.id == surface->snooper.id)
 			vps->cursor.update_type = VMW_CURSOR_UPDATE_NONE;
 		break;
+	case VMW_CURSOR_UPDATE_GB_ONLY:
 	case VMW_CURSOR_UPDATE_MOB: {
 		bo = vmw_user_object_buffer(&vps->uo);
 		if (bo) {
@@ -737,6 +741,7 @@ void
 vmw_cursor_plane_atomic_update(struct drm_plane *plane,
 			       struct drm_atomic_state *state)
 {
+	struct vmw_bo *bo;
 	struct drm_plane_state *new_state =
 		drm_atomic_get_new_plane_state(state, plane);
 	struct drm_plane_state *old_state =
@@ -762,6 +767,15 @@ vmw_cursor_plane_atomic_update(struct drm_plane *plane,
 	case VMW_CURSOR_UPDATE_MOB:
 		vmw_cursor_update_mob(dev_priv, vps);
 		break;
+	case VMW_CURSOR_UPDATE_GB_ONLY:
+		bo = vmw_user_object_buffer(&vps->uo);
+		if (bo)
+			vmw_send_define_cursor_cmd(dev_priv, bo->map.virtual,
+						   vps->base.crtc_w,
+						   vps->base.crtc_h,
+						   vps->base.hotspot_x,
+						   vps->base.hotspot_y);
+		break;
 	case VMW_CURSOR_UPDATE_NONE:
 		/* do nothing */
 		break;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
index 40694925a70e..0c2cc0699b0d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h
@@ -33,6 +33,7 @@ static const u32 __maybe_unused vmw_cursor_plane_formats[] = {
 enum vmw_cursor_update_type {
 	VMW_CURSOR_UPDATE_NONE = 0,
 	VMW_CURSOR_UPDATE_LEGACY,
+	VMW_CURSOR_UPDATE_GB_ONLY,
 	VMW_CURSOR_UPDATE_MOB,
 };
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index d539f25b5fbe..3057f8baa7d2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3668,6 +3668,11 @@ static int vmw_cmd_check(struct vmw_private *dev_priv,
 
 
 	cmd_id = header->id;
+	if (header->size > SVGA_CMD_MAX_DATASIZE) {
+		VMW_DEBUG_USER("SVGA3D command: %d is too big.\n",
+			       cmd_id + SVGA_3D_CMD_BASE);
+		return -E2BIG;
+	}
 	*size = header->size + sizeof(SVGA3dCmdHeader);
 
 	cmd_id -= SVGA_3D_CMD_BASE;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 7de20e56082c..fd4e76486f2d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -32,22 +32,22 @@ enum vmw_bo_dirty_method {
 
 /**
  * struct vmw_bo_dirty - Dirty information for buffer objects
+ * @ref_count: Reference count for this structure. Must be first member!
  * @start: First currently dirty bit
  * @end: Last currently dirty bit + 1
  * @method: The currently used dirty method
  * @change_count: Number of consecutive method change triggers
- * @ref_count: Reference count for this structure
  * @bitmap_size: The size of the bitmap in bits. Typically equal to the
  * nuber of pages in the bo.
  * @bitmap: A bitmap where each bit represents a page. A set bit means a
  * dirty page.
  */
 struct vmw_bo_dirty {
+	struct   kref ref_count;
 	unsigned long start;
 	unsigned long end;
 	enum vmw_bo_dirty_method method;
 	unsigned int change_count;
-	unsigned int ref_count;
 	unsigned long bitmap_size;
 	unsigned long bitmap[];
 };
@@ -221,7 +221,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo)
 	int ret;
 
 	if (dirty) {
-		dirty->ref_count++;
+		kref_get(&dirty->ref_count);
 		return 0;
 	}
 
@@ -235,7 +235,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo)
 	dirty->bitmap_size = num_pages;
 	dirty->start = dirty->bitmap_size;
 	dirty->end = 0;
-	dirty->ref_count = 1;
+	kref_init(&dirty->ref_count);
 	if (num_pages < PAGE_SIZE / sizeof(pte_t)) {
 		dirty->method = VMW_BO_DIRTY_PAGETABLE;
 	} else {
@@ -274,10 +274,8 @@ void vmw_bo_dirty_release(struct vmw_bo *vbo)
 {
 	struct vmw_bo_dirty *dirty = vbo->dirty;
 
-	if (dirty && --dirty->ref_count == 0) {
-		kvfree(dirty);
+	if (dirty && kref_put(&dirty->ref_count, (void *)kvfree))
 		vbo->dirty = NULL;
-	}
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 8724f8de67e2..12adfc3a0547 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -394,6 +394,9 @@ void xe_exec_queue_destroy(struct kref *ref)
 	if (q->ufence_syncobj)
 		drm_syncobj_put(q->ufence_syncobj);
 
+	if (q->ufence_syncobj)
+		drm_syncobj_put(q->ufence_syncobj);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 6d479948bf21..dbb5e7a9bc6a 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -879,7 +879,6 @@ err_out:
 err_fail:
 	xe_gt_err(gt, "reset failed (%pe)\n", ERR_PTR(err));
 	xe_device_declare_wedged(gt_to_xe(gt));
-
 err_pm_put:
 	xe_pm_runtime_put(gt_to_xe(gt));
 }