Merge tag 'drm-misc-fixes-2026-07-30' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-fixes

drm-misc-fies for v7.2-rc6:
- vmwgfx:
  - Improve various size checks and limit checks.
  - Fix oops when submitting  invalid execbuf ioctl.
  - Correctly lock in vmfwgx fence signaling path.
  - More validation of execbuf ioctl.
  - Fix oops in vmwgfx vkms init failure path.
  - Overflow handling in shader path.
- Improve firmware validation in panthor.
- Fix small leak in bridge/display-connector
- Improve imagination trace points.
- Fix QAIC transaction length check.
- Restrict some DP bandwidth calculations to HDMI DFP.

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

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patch.msgid.link/178a513f-2d7f-4e3a-811b-cd0d9dc309eb@linux.intel.com

18 files changed, 230 insertions, 65 deletions

diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index bb94d3556904..50bf3340e49c 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -786,7 +786,7 @@ static int encode_message(struct qaic_device *qdev, struct manage_msg *user_msg,
 			break;
 		}
 		trans_hdr = (struct qaic_manage_trans_hdr *)(user_msg->data + user_len);
-		if (trans_hdr->len < sizeof(trans_hdr) ||
+		if (trans_hdr->len < sizeof(*trans_hdr) ||
 		    size_add(user_len, trans_hdr->len) > user_msg->len) {
 			ret = -EINVAL;
 			break;
diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c
index 16c0631adeb1..6b128fabe3a9 100644
--- a/drivers/gpu/drm/bridge/display-connector.c
+++ b/drivers/gpu/drm/bridge/display-connector.c
@@ -40,6 +40,13 @@ static int display_connector_attach(struct drm_bridge *bridge,
 	return flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR ? 0 : -EINVAL;
 }
 
+static void display_connector_destroy(struct drm_bridge *bridge)
+{
+	struct display_connector *conn = to_display_connector(bridge);
+
+	i2c_put_adapter(conn->bridge.ddc);
+}
+
 static enum drm_connector_status display_connector_detect(struct drm_bridge *bridge)
 {
 	struct display_connector *conn = to_display_connector(bridge);
@@ -177,6 +184,7 @@ static u32 *display_connector_get_input_bus_fmts(struct drm_bridge *bridge,
 
 static const struct drm_bridge_funcs display_connector_bridge_funcs = {
 	.attach = display_connector_attach,
+	.destroy = display_connector_destroy,
 	.detect = display_connector_bridge_detect,
 	.edid_read = display_connector_edid_read,
 	.atomic_get_output_bus_fmts = display_connector_get_output_bus_fmts,
@@ -403,9 +411,6 @@ static void display_connector_remove(struct platform_device *pdev)
 		regulator_disable(conn->supply);
 
 	drm_bridge_remove(&conn->bridge);
-
-	if (!IS_ERR(conn->bridge.ddc))
-		i2c_put_adapter(conn->bridge.ddc);
 }
 
 static const struct of_device_id display_connector_match[] = {
diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 9c31e14cc413..e623ccb4c1d8 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -3686,6 +3686,18 @@ int drm_dp_get_pcon_max_frl_bw(const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 	int bw;
 	u8 buf;
 
+	if (!drm_dp_is_branch(dpcd))
+		return 0;
+
+	if (dpcd[DP_DPCD_REV] < 0x11)
+		return 0;
+
+	if ((dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DETAILED_CAP_INFO_AVAILABLE) == 0)
+		return 0;
+
+	if ((port_cap[0] & DP_DS_PORT_TYPE_MASK) != DP_DS_PORT_TYPE_HDMI)
+		return 0;
+
 	buf = port_cap[2];
 	bw = buf & DP_PCON_MAX_FRL_BW;
 
diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index 941c017399fc..d13726401d92 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -726,8 +726,6 @@ static void pvr_queue_submit_job_to_cccb(struct pvr_job *job)
 		cmd->partial_render_geom_frag_fence.value = job->done_fence->seqno - 1;
 	}
 
-	trace_pvr_job_submit_fw(job);
-
 	/* Submit job to FW */
 	pvr_cccb_write_command_with_header(cccb, job->fw_ccb_cmd_type, job->cmd_len, job->cmd,
 					   job->id, job->id);
@@ -802,6 +800,9 @@ static struct dma_fence *pvr_queue_run_job(struct drm_sched_job *sched_job)
 						 job->hwrt,
 						 frag_job->fw_ccb_cmd_type ==
 						 ROGUE_FWIF_CCB_CMD_TYPE_FRAG_PR);
+
+		trace_pvr_job_submit_fw(geom_job);
+		trace_pvr_job_submit_fw(frag_job);
 	} else {
 		struct pvr_queue *queue = container_of(job->base.sched,
 						       struct pvr_queue, scheduler);
@@ -809,6 +810,8 @@ static struct dma_fence *pvr_queue_run_job(struct drm_sched_job *sched_job)
 		pvr_cccb_send_kccb_kick(pvr_dev, &queue->cccb,
 					pvr_context_get_fw_addr(job->ctx) + queue->ctx_offset,
 					job->hwrt);
+
+		trace_pvr_job_submit_fw(job);
 	}
 
 	return dma_fence_get(job->done_fence);
diff --git a/drivers/gpu/drm/imagination/pvr_trace.h b/drivers/gpu/drm/imagination/pvr_trace.h
index ffbbde3b2bcc..943d6b2418cb 100644
--- a/drivers/gpu/drm/imagination/pvr_trace.h
+++ b/drivers/gpu/drm/imagination/pvr_trace.h
@@ -41,6 +41,17 @@ TRACE_EVENT(pvr_job_submit_ioctl,
 		      __entry->count)
 );
 
+#define PVR_JOB_GET_HWRT_FW_ADDR(job)                                                  \
+	({                                                                             \
+		struct pvr_job *_job = (job);                                          \
+		u32 _hwrt_fw_addr = 0;                                                 \
+										       \
+		if (_job && _job->hwrt)                                                \
+			pvr_fw_object_get_fw_addr(_job->hwrt->fw_obj, &_hwrt_fw_addr); \
+										       \
+		_hwrt_fw_addr;                                                         \
+	})
+
 #define PVR_JOB_TYPE_TO_STR(val)                                         \
 	__print_symbolic(val,                                            \
 			 { DRM_PVR_JOB_TYPE_GEOMETRY, "geometry" },      \
@@ -64,9 +75,7 @@ TRACE_EVENT(pvr_job_create,
 			   __entry->ctx = job->ctx;
 			   __entry->fw_obj = job->ctx->fw_obj;
 			   pvr_fw_object_get_fw_addr(job->ctx->fw_obj, &__entry->fw_addr);
-			   __entry->hwrt_addr = job->hwrt ?
-						job->hwrt->fw_obj->fw_addr_offset :
-						0;
+			   __entry->hwrt_addr = PVR_JOB_GET_HWRT_FW_ADDR(job);
 			   __entry->job = job;
 			   __entry->job_type = job->type;
 			   __entry->sync_op_count = sync_op_count;),
@@ -82,6 +91,7 @@ TRACE_EVENT(pvr_job_create,
 );
 
 #undef PVR_JOB_TYPE_TO_STR
+#undef PVR_JOB_GET_HWRT_FW_ADDR
 
 TRACE_EVENT(pvr_job_submit_fw,
 	    TP_PROTO(struct pvr_job *job),
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index 90f59d782a80..e45933e333b5 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -545,6 +545,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 	struct panthor_fw_binary_section_entry_hdr hdr;
 	struct panthor_fw_section *section;
 	u32 section_size;
+	u32 data_size;
 	u32 name_len;
 	int ret;
 
@@ -595,6 +596,13 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 		return -EINVAL;
 	}
 
+	section_size = hdr.va.end - hdr.va.start;
+	data_size = hdr.data.end - hdr.data.start;
+	if (data_size > section_size) {
+		drm_err(&ptdev->base, "Firmware corrupted, section data exceeds section size\n");
+		return -EINVAL;
+	}
+
 	name_len = iter->size - iter->offset;
 
 	section = drmm_kzalloc(&ptdev->base, sizeof(*section), GFP_KERNEL);
@@ -603,7 +611,7 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 
 	list_add_tail(&section->node, &ptdev->fw->sections);
 	section->flags = hdr.flags;
-	section->data.size = hdr.data.end - hdr.data.start;
+	section->data.size = data_size;
 
 	if (section->data.size > 0) {
 		void *data = drmm_kmalloc(&ptdev->base, section->data.size, GFP_KERNEL);
@@ -626,7 +634,6 @@ static int panthor_fw_load_section_entry(struct panthor_device *ptdev,
 		section->name = name;
 	}
 
-	section_size = hdr.va.end - hdr.va.start;
 	if (section_size) {
 		u32 cache_mode = hdr.flags & CSF_FW_BINARY_IFACE_ENTRY_CACHE_MODE_MASK;
 		struct panthor_gem_object *bo;
@@ -857,18 +864,24 @@ out:
  * iface_fw_to_cpu_addr() - Turn an MCU address into a CPU address
  * @ptdev: Device.
  * @mcu_va: MCU address.
+ * @size: Size of the object pointed to by @mcu_va.
  *
- * Return: NULL if the address is not part of the shared section, non-NULL otherwise.
+ * Return: NULL if the object is not part of the shared section, non-NULL otherwise.
  */
-static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va)
+static void *iface_fw_to_cpu_addr(struct panthor_device *ptdev, u32 mcu_va, size_t size)
 {
 	u64 shared_mem_start = panthor_kernel_bo_gpuva(ptdev->fw->shared_section->mem);
-	u64 shared_mem_end = shared_mem_start +
-			     panthor_kernel_bo_size(ptdev->fw->shared_section->mem);
-	if (mcu_va < shared_mem_start || mcu_va >= shared_mem_end)
+	size_t shared_mem_size = panthor_kernel_bo_size(ptdev->fw->shared_section->mem);
+	u64 offset;
+
+	if (mcu_va < shared_mem_start)
+		return NULL;
+
+	offset = mcu_va - shared_mem_start;
+	if (offset > shared_mem_size || size > shared_mem_size - offset)
 		return NULL;
 
-	return ptdev->fw->shared_section->mem->kmap + (mcu_va - shared_mem_start);
+	return ptdev->fw->shared_section->mem->kmap + offset;
 }
 
 static int panthor_init_cs_iface(struct panthor_device *ptdev,
@@ -890,8 +903,10 @@ static int panthor_init_cs_iface(struct panthor_device *ptdev,
 
 	spin_lock_init(&cs_iface->lock);
 	cs_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset;
-	cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va);
-	cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va);
+	cs_iface->input = iface_fw_to_cpu_addr(ptdev, cs_iface->control->input_va,
+					       sizeof(*cs_iface->input));
+	cs_iface->output = iface_fw_to_cpu_addr(ptdev, cs_iface->control->output_va,
+						sizeof(*cs_iface->output));
 
 	if (!cs_iface->input || !cs_iface->output) {
 		drm_err(&ptdev->base, "Invalid stream control interface input/output VA");
@@ -941,8 +956,10 @@ static int panthor_init_csg_iface(struct panthor_device *ptdev,
 
 	spin_lock_init(&csg_iface->lock);
 	csg_iface->control = ptdev->fw->shared_section->mem->kmap + iface_offset;
-	csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va);
-	csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va);
+	csg_iface->input = iface_fw_to_cpu_addr(ptdev, csg_iface->control->input_va,
+						sizeof(*csg_iface->input));
+	csg_iface->output = iface_fw_to_cpu_addr(ptdev, csg_iface->control->output_va,
+						 sizeof(*csg_iface->output));
 
 	if (csg_iface->control->stream_num < MIN_CS_PER_CSG ||
 	    csg_iface->control->stream_num > MAX_CS_PER_CSG)
@@ -999,8 +1016,10 @@ static int panthor_fw_init_ifaces(struct panthor_device *ptdev)
 		return -EINVAL;
 	}
 
-	glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va);
-	glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va);
+	glb_iface->input = iface_fw_to_cpu_addr(ptdev, glb_iface->control->input_va,
+						sizeof(*glb_iface->input));
+	glb_iface->output = iface_fw_to_cpu_addr(ptdev, glb_iface->control->output_va,
+						 sizeof(*glb_iface->output));
 	if (!glb_iface->input || !glb_iface->output) {
 		drm_err(&ptdev->base, "Invalid global control interface input/output VA");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 8e5141bb5075..7877d493d80e 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -104,7 +104,7 @@ vc4_overflow_mem_work(struct work_struct *work)
 	vc4->bin_alloc_overflow = BIT(bin_bo_slot);
 
 	V3D_WRITE(V3D_BPOA, bo->base.dma_addr + bin_bo_slot * vc4->bin_alloc_size);
-	V3D_WRITE(V3D_BPOS, bo->base.base.size);
+	V3D_WRITE(V3D_BPOS, vc4->bin_alloc_size);
 	V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM);
 	V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM);
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index 7f2fadfde7a8..d2a65c968b1f 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -385,6 +385,23 @@ validate_tile_binning_config(VALIDATE_ARGS)
 		return -EINVAL;
 	}
 
+	/* The tile state data array is 48 bytes per tile, and we put it at
+	 * the start of a BO containing both it and the tile alloc.
+	 */
+	tile_state_size = 48 * tile_count;
+
+	/* Since the tile alloc array will follow us, align. */
+	tile_state_size = roundup(tile_state_size, 4096);
+
+	/* Reject configurations whose tile state would leave no room for
+	 * the tile alloc pool that follows it in the slot.
+	 */
+	if (tile_state_size >= vc4->bin_alloc_size) {
+		DRM_DEBUG("Tile binning config of %dx%d too large\n",
+			  exec->bin_tiles_x, exec->bin_tiles_y);
+		return -EINVAL;
+	}
+
 	bin_slot = vc4_v3d_get_bin_slot(vc4);
 	if (bin_slot < 0) {
 		if (bin_slot != -EINTR && bin_slot != -ERESTARTSYS) {
@@ -400,13 +417,13 @@ validate_tile_binning_config(VALIDATE_ARGS)
 	exec->bin_slots |= BIT(bin_slot);
 	bin_addr = vc4->bin_bo->base.dma_addr + bin_slot * vc4->bin_alloc_size;
 
-	/* The tile state data array is 48 bytes per tile, and we put it at
-	 * the start of a BO containing both it and the tile alloc.
-	 */
-	tile_state_size = 48 * tile_count;
+	exec->tile_alloc_offset = bin_addr + tile_state_size;
 
-	/* Since the tile alloc array will follow us, align. */
-	exec->tile_alloc_offset = bin_addr + roundup(tile_state_size, 4096);
+	/* The TSDA area must be zeroed out before use, otherwise the PTB might
+	 * consume a stale tile state.
+	 */
+	memset(vc4->bin_bo->base.vaddr + bin_slot * vc4->bin_alloc_size, 0,
+	       tile_state_size);
 
 	*(uint8_t *)(validated + 14) =
 		((flags & ~(VC4_BIN_CONFIG_ALLOC_INIT_BLOCK_SIZE_MASK |
diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c
index 2421b0dd057c..f9042bafdc93 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_object.c
+++ b/drivers/gpu/drm/vmwgfx/ttm_object.c
@@ -547,14 +547,17 @@ int ttm_prime_fd_to_handle(struct ttm_object_file *tfile,
 	if (IS_ERR(dma_buf))
 		return PTR_ERR(dma_buf);
 
-	if (dma_buf->ops != &tdev->ops)
-		return -ENOSYS;
+	if (dma_buf->ops != &tdev->ops) {
+		ret = -ENOSYS;
+		goto out;
+	}
 
 	prime = (struct ttm_prime_object *) dma_buf->priv;
 	base = &prime->base;
 	*handle = base->handle;
 	ret = ttm_ref_object_add(tfile, base, NULL, false);
 
+out:
 	dma_buf_put(dma_buf);
 
 	return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index 135b75a3e013..56f965ec99dc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -30,6 +30,7 @@
 
 #include "vmwgfx_bo.h"
 #include <linux/highmem.h>
+#include <linux/overflow.h>
 
 /*
  * Template that implements find_first_diff() for a generic
@@ -463,19 +464,42 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset,
 		container_of(dst->tbo.bdev, struct vmw_private, bdev);
 	size_t dst_size = dst->tbo.resource->size;
 	size_t src_size = src->tbo.resource->size;
+	size_t dst_end, src_end;
 	struct iosys_map dst_map = {0};
 	struct iosys_map src_map = {0};
+	bool dst_mapped = false;
+	bool src_mapped = false;
 	int ret, i;
 	int x_in_bytes;
 	u8 *vsrc;
 	u8 *vdst;
 
+	if (!height || !width_in_bytes)
+		return 0;
+
+	if (!dst_stride || !src_stride)
+		return -EINVAL;
+	if (dst_stride < width_in_bytes || src_stride < width_in_bytes)
+		return -EINVAL;
+	if (check_mul_overflow((size_t)dst_stride, (size_t)height - 1, &dst_end) ||
+	    check_add_overflow(dst_end, (size_t)width_in_bytes, &dst_end) ||
+	    check_add_overflow((size_t)dst_offset, dst_end, &dst_end) ||
+	    dst_end > dst_size ||
+	    check_mul_overflow((size_t)src_stride, (size_t)height - 1, &src_end) ||
+	    check_add_overflow(src_end, (size_t)width_in_bytes, &src_end) ||
+	    check_add_overflow((size_t)src_offset, src_end, &src_end) ||
+	    src_end > src_size) {
+		drm_dbg_driver(&vmw->drm, "Out-of-bounds external BO copy\n");
+		return -EINVAL;
+	}
+
 	vsrc = map_external(src, &src_map);
 	if (!vsrc) {
 		drm_dbg_driver(&vmw->drm, "Wasn't able to map src\n");
 		ret = -ENOMEM;
 		goto out;
 	}
+	src_mapped = true;
 
 	vdst = map_external(dst, &dst_map);
 	if (!vdst) {
@@ -483,16 +507,13 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset,
 		ret = -ENOMEM;
 		goto out;
 	}
+	dst_mapped = true;
 
 	vsrc += src_offset;
 	vdst += dst_offset;
-	if (src_stride == dst_stride) {
-		dst_size -= dst_offset;
-		src_size -= src_offset;
-		memcpy(vdst, vsrc,
-		       min(dst_stride * height, min(dst_size, src_size)));
+	if (src_stride == dst_stride && width_in_bytes == dst_stride) {
+		memcpy(vdst, vsrc, dst_stride * (size_t)height);
 	} else {
-		WARN_ON(dst_stride < width_in_bytes);
 		for (i = 0; i < height; ++i) {
 			memcpy(vdst, vsrc, width_in_bytes);
 			vsrc += src_stride;
@@ -508,8 +529,10 @@ static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset,
 
 	ret = 0;
 out:
-	unmap_external(src, &src_map);
-	unmap_external(dst, &dst_map);
+	if (src_mapped)
+		unmap_external(src, &src_map);
+	if (dst_mapped)
+		unmap_external(dst, &dst_map);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
index b010fc7ca68e..d1e7df500190 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c
@@ -432,6 +432,7 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps)
 	u32 size = vmw_cursor_mob_size(vps->cursor.update_type,
 				       vps->base.crtc_w, vps->base.crtc_h);
 	struct vmw_bo *vbo = vps->cursor.mob;
+	void *map;
 
 	if (!vbo)
 		return -EINVAL;
@@ -446,11 +447,15 @@ vmw_cursor_mob_map(struct vmw_plane_state *vps)
 	if (unlikely(ret != 0))
 		return -ENOMEM;
 
-	vmw_bo_map_and_cache(vbo);
+	map = vmw_bo_map_and_cache(vbo);
+	if (!map) {
+		vmw_bo_unmap(vbo);
+		ret = -ENOMEM;
+	}
 
 	ttm_bo_unreserve(&vbo->tbo);
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -663,9 +668,15 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane,
 			    !vmw_cursor_buffer_changed(vps, old_vps)) {
 				vps->cursor.update_type =
 					VMW_CURSOR_UPDATE_NONE;
-			} else {
-				vmw_cursor_mob_get(vcp, vps);
-				vmw_cursor_mob_map(vps);
+			} else if (vps->cursor.update_type ==
+				   VMW_CURSOR_UPDATE_MOB &&
+				   (vmw_cursor_mob_get(vcp, vps) ||
+				    vmw_cursor_mob_map(vps))) {
+				/*
+				 * Reset the cursor to avoid crashes later.
+				 */
+				vps->cursor.update_type =
+					VMW_CURSOR_UPDATE_NONE;
 			}
 		}
 	}
@@ -732,6 +743,34 @@ int vmw_cursor_plane_atomic_check(struct drm_plane *plane,
 				 "surface not suitable for cursor\n");
 			return -EINVAL;
 		}
+	} else if (update_type == VMW_CURSOR_UPDATE_GB_ONLY ||
+		   update_type == VMW_CURSOR_UPDATE_MOB) {
+		u32 cursor_max_dim =
+			vmw_read(vmw, SVGA_REG_CURSOR_MAX_DIMENSION);
+
+		if (new_state->crtc_w > cursor_max_dim ||
+		    new_state->crtc_h > cursor_max_dim) {
+			drm_warn(&vmw->drm,
+				 "Cursor dimensions (%d, %d) exceed device max %u\n",
+				 new_state->crtc_w, new_state->crtc_h,
+				 cursor_max_dim);
+			return -EINVAL;
+		}
+
+		if (update_type == VMW_CURSOR_UPDATE_MOB) {
+			u32 mob_max_size =
+				vmw_read(vmw, SVGA_REG_MOB_MAX_SIZE);
+			u64 mob_size = (u64)new_state->crtc_w *
+				       new_state->crtc_h * sizeof(u32) +
+				       sizeof(SVGAGBCursorHeader);
+
+			if (mob_size > mob_max_size) {
+				drm_warn(&vmw->drm,
+					 "Cursor MOB size %llu exceeds device max %u\n",
+					 mob_size, mob_max_size);
+				return -EINVAL;
+			}
+		}
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index e1f18020170a..a9136a6523cb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1272,9 +1272,13 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 				 SVGA3dCmdHeader *header)
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXBindQuery);
+	struct vmw_ctx_validation_info *ctx_node = VMW_GET_CTX_NODE(sw_context);
 	struct vmw_bo *vmw_bo;
 	int ret;
 
+	if (!ctx_node)
+		return -EINVAL;
+
 	cmd = container_of(header, typeof(*cmd), header);
 
 	/*
@@ -1288,7 +1292,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 		return ret;
 
 	sw_context->dx_query_mob = vmw_bo;
-	sw_context->dx_query_ctx = sw_context->dx_ctx_node->ctx;
+	sw_context->dx_query_ctx = ctx_node->ctx;
 	return 0;
 }
 
@@ -1506,6 +1510,12 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 	bool dirty;
 
 	cmd = container_of(header, typeof(*cmd), header);
+
+	if (unlikely(header->size < sizeof(cmd->body) + sizeof(*suffix))) {
+		VMW_DEBUG_USER("Illegal SVGA_3D_CMD_SURFACE_DMA size.\n");
+		return -EINVAL;
+	}
+
 	suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->body +
 					       header->size - sizeof(*suffix));
 
@@ -1567,11 +1577,17 @@ static int vmw_cmd_draw(struct vmw_private *dev_priv,
 	uint32_t maxnum;
 	int ret;
 
+	cmd = container_of(header, typeof(*cmd), header);
+
+	if (unlikely(header->size < sizeof(cmd->body))) {
+		VMW_DEBUG_USER("Illegal DRAW_PRIMITIVES header size.\n");
+		return -EINVAL;
+	}
+
 	ret = vmw_cmd_cid_check(dev_priv, sw_context, header);
 	if (unlikely(ret != 0))
 		return ret;
 
-	cmd = container_of(header, typeof(*cmd), header);
 	maxnum = (header->size - sizeof(cmd->body)) / sizeof(*decl);
 
 	if (unlikely(cmd->body.numVertexDecls > maxnum)) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 4ef84ff9b638..384c6736cf6b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -367,13 +367,24 @@ void vmw_fence_fifo_down(struct vmw_fence_manager *fman)
 		ret = vmw_fence_obj_wait(fence, false, false,
 					 VMW_FENCE_WAIT_TIMEOUT);
 
+		spin_lock(&fman->lock);
 		if (unlikely(ret != 0)) {
+			bool cookie = dma_fence_begin_signalling();
+
 			list_del_init(&fence->head);
-			dma_fence_signal(&fence->base);
+			if (fence->waiter_added) {
+				vmw_seqno_waiter_remove(fman->dev_priv);
+				fence->waiter_added = false;
+			}
+			dma_fence_signal_locked(&fence->base);
+			dma_fence_end_signalling(cookie);
 		}
 
 		BUG_ON(!list_empty(&fence->head));
+		spin_unlock(&fman->lock);
+
 		dma_fence_put(&fence->base);
+
 		spin_lock(&fman->lock);
 	}
 	spin_unlock(&fman->lock);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
index 45561bc1c9ef..8ab88f388652 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c
@@ -311,7 +311,7 @@ void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res)
 		return;
 
 	cur = max(res_start, dirty->start);
-	res_end = max(res_end, dirty->end);
+	res_end = min(res_end, dirty->end);
 	while (cur < res_end) {
 		unsigned long num;
 
@@ -347,7 +347,7 @@ void vmw_bo_dirty_clear(struct vmw_bo *vbo)
 		return;
 
 	cur = max(res_start, dirty->start);
-	res_end = max(res_end, dirty->end);
+	res_end = min(res_end, dirty->end);
 	while (cur < res_end) {
 		unsigned long num;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 388011696941..e3a187a2c7a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -136,7 +136,7 @@ static void vmw_resource_release(struct kref *kref)
 			val_buf.num_shared = 0;
 			res->func->unbind(res, false, &val_buf);
 		}
-		res->guest_memory_size = false;
+		res->guest_memory_dirty = false;
 		vmw_resource_mob_detach(res);
 		if (res->dirty)
 			res->func->dirty_free(res);
@@ -773,7 +773,7 @@ void vmw_resource_unbind_list(struct vmw_bo *vbo)
 		if (!WARN_ON_ONCE(!res->func->unbind))
 			(void) res->func->unbind(res, res->res_dirty, &val_buf);
 
-		res->guest_memory_size = true;
+		res->guest_memory_dirty = true;
 		res->res_dirty = false;
 		vmw_resource_mob_detach(res);
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index eca4e3e97eb4..39811cf19db1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -25,6 +25,8 @@
  *
  **************************************************************************/
 
+#include <linux/overflow.h>
+
 #include <drm/ttm/ttm_placement.h>
 
 #include "vmwgfx_binding.h"
@@ -685,7 +687,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data,
 static int vmw_user_shader_alloc(struct vmw_private *dev_priv,
 				 struct vmw_bo *buffer,
 				 size_t shader_size,
-				 size_t offset,
+				 u64 offset,
 				 SVGA3dShaderType shader_type,
 				 uint8_t num_input_sig,
 				 uint8_t num_output_sig,
@@ -739,7 +741,7 @@ out:
 static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv,
 					     struct vmw_bo *buffer,
 					     size_t shader_size,
-					     size_t offset,
+					     u64 offset,
 					     SVGA3dShaderType shader_type)
 {
 	struct vmw_shader *shader;
@@ -768,7 +770,7 @@ out_err:
 
 static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 			     enum drm_vmw_shader_type shader_type_drm,
-			     u32 buffer_handle, size_t size, size_t offset,
+			     u32 buffer_handle, size_t size, u64 offset,
 			     uint8_t num_input_sig, uint8_t num_output_sig,
 			     uint32_t *shader_handle)
 {
@@ -779,13 +781,16 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 	int ret;
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
+		u64 end;
+
 		ret = vmw_user_bo_lookup(file_priv, buffer_handle, &buffer);
 		if (unlikely(ret != 0)) {
 			VMW_DEBUG_USER("Couldn't find buffer for shader creation.\n");
 			return ret;
 		}
 
-		if ((u64)buffer->tbo.base.size < (u64)size + (u64)offset) {
+		if (check_add_overflow((u64)size, (u64)offset, &end) ||
+		    end > buffer->tbo.base.size) {
 			VMW_DEBUG_USER("Illegal buffer- or shader size.\n");
 			ret = -EINVAL;
 			goto out_bad_arg;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index 35dc94c3db39..45fde7ec514f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -309,7 +309,8 @@ int vmw_validation_add_resource(struct vmw_validation_context *ctx,
 	}
 	node->res = vmw_resource_reference_unless_doomed(res);
 	if (!node->res) {
-		hash_del_rcu(&node->hash.head);
+		if (ctx->sw_context)
+			hash_del_rcu(&node->hash.head);
 		return -ESRCH;
 	}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
index 7b8163b5e501..3d0d5dfa869f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
@@ -206,14 +206,14 @@ vmw_vkms_init(struct vmw_private *vmw)
 	vmw->vkms_enabled = false;
 
 	ret = vmw_host_get_guestinfo(GUESTINFO_VBLANK, buffer, &buf_len);
-	if (ret || buf_len > max_buf_len)
-		return;
-	buffer[buf_len] = '\0';
+	if (!ret && buf_len <= max_buf_len) {
+		buffer[buf_len] = '\0';
 
-	ret = kstrtobool(buffer, &vmw->vkms_enabled);
-	if (!ret && vmw->vkms_enabled) {
-		ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS);
-		vmw->vkms_enabled = (ret == 0);
+		ret = kstrtobool(buffer, &vmw->vkms_enabled);
+		if (!ret && vmw->vkms_enabled) {
+			ret = drm_vblank_init(&vmw->drm, VMWGFX_NUM_DISPLAY_UNITS);
+			vmw->vkms_enabled = (ret == 0);
+		}
 	}
 
 	vmw->crc_workq = alloc_ordered_workqueue("vmwgfx_crc_generator", 0);
@@ -228,7 +228,8 @@ vmw_vkms_init(struct vmw_private *vmw)
 void
 vmw_vkms_cleanup(struct vmw_private *vmw)
 {
-	destroy_workqueue(vmw->crc_workq);
+	if (vmw->crc_workq)
+		destroy_workqueue(vmw->crc_workq);
 }
 
 bool