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 371531b2a3d0..ddc064b4fc32 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8327,6 +8327,122 @@ static inline uint32_t get_mem_type(struct drm_framebuffer *fb)
 	return abo->tbo.resource ? abo->tbo.resource->mem_type : 0;
 }
 
+/* TODO remove duplicate */
+static int amdgpu_dm_plane_get_cursor_position(struct drm_plane *plane, struct drm_crtc *crtc,
+					       struct dc_cursor_position *position)
+{
+	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	int x, y;
+	int xorigin = 0, yorigin = 0;
+
+	if (!crtc || !plane->state->fb)
+		return 0;
+
+	if ((plane->state->crtc_w > amdgpu_crtc->max_cursor_width) ||
+	    (plane->state->crtc_h > amdgpu_crtc->max_cursor_height)) {
+		DRM_ERROR("%s: bad cursor width or height %d x %d\n",
+			  __func__,
+			  plane->state->crtc_w,
+			  plane->state->crtc_h);
+		return -EINVAL;
+	}
+
+	x = plane->state->crtc_x;
+	y = plane->state->crtc_y;
+
+	if (x <= -amdgpu_crtc->max_cursor_width ||
+	    y <= -amdgpu_crtc->max_cursor_height)
+		return 0;
+
+	if (x < 0) {
+		xorigin = min(-x, amdgpu_crtc->max_cursor_width - 1);
+		x = 0;
+	}
+	if (y < 0) {
+		yorigin = min(-y, amdgpu_crtc->max_cursor_height - 1);
+		y = 0;
+	}
+	position->enable = true;
+	position->translate_by_source = true;
+	position->x = x;
+	position->y = y;
+	position->x_hotspot = xorigin;
+	position->y_hotspot = yorigin;
+
+	return 0;
+}
+
+static void amdgpu_dm_update_cursor(struct drm_plane *plane,
+				    struct drm_plane_state *old_plane_state,
+				    struct dc_stream_update *update)
+{
+	struct amdgpu_device *adev = drm_to_adev(plane->dev);
+	struct amdgpu_framebuffer *afb = to_amdgpu_framebuffer(plane->state->fb);
+	struct drm_crtc *crtc = afb ? plane->state->crtc : old_plane_state->crtc;
+	struct dm_crtc_state *crtc_state = crtc ? to_dm_crtc_state(crtc->state) : NULL;
+	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	uint64_t address = afb ? afb->address : 0;
+	struct dc_cursor_position position = {0};
+	struct dc_cursor_attributes attributes;
+	int ret;
+
+	if (!plane->state->fb && !old_plane_state->fb)
+		return;
+
+	drm_dbg_atomic(plane->dev, "crtc_id=%d with size %d to %d\n",
+		       amdgpu_crtc->crtc_id, plane->state->crtc_w,
+		       plane->state->crtc_h);
+
+	ret = amdgpu_dm_plane_get_cursor_position(plane, crtc, &position);
+	if (ret)
+		return;
+
+	if (!position.enable) {
+		/* turn off cursor */
+		if (crtc_state && crtc_state->stream) {
+			dc_stream_set_cursor_position(crtc_state->stream,
+						      &position);
+			update->cursor_position = &crtc_state->stream->cursor_position;
+		}
+		return;
+	}
+
+	amdgpu_crtc->cursor_width = plane->state->crtc_w;
+	amdgpu_crtc->cursor_height = plane->state->crtc_h;
+
+	memset(&attributes, 0, sizeof(attributes));
+	attributes.address.high_part = upper_32_bits(address);
+	attributes.address.low_part  = lower_32_bits(address);
+	attributes.width             = plane->state->crtc_w;
+	attributes.height            = plane->state->crtc_h;
+	attributes.color_format      = CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA;
+	attributes.rotation_angle    = 0;
+	attributes.attribute_flags.value = 0;
+
+	/* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM
+	 * legacy gamma setup.
+	 */
+	if (crtc_state->cm_is_degamma_srgb &&
+	    adev->dm.dc->caps.color.dpp.gamma_corr)
+		attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1;
+
+	attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0];
+
+	if (crtc_state->stream) {
+		if (!dc_stream_set_cursor_attributes(crtc_state->stream,
+						     &attributes))
+			DRM_ERROR("DC failed to set cursor attributes\n");
+
+		update->cursor_attributes = &crtc_state->stream->cursor_attributes;
+
+		if (!dc_stream_set_cursor_position(crtc_state->stream,
+						   &position))
+			DRM_ERROR("DC failed to set cursor position\n");
+
+		update->cursor_position = &crtc_state->stream->cursor_position;
+	}
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_device *dev,
 				    struct amdgpu_display_manager *dm,
@@ -8350,6 +8466,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	bool cursor_update = false;
 	bool pflip_present = false;
 	bool dirty_rects_changed = false;
+	bool updated_planes_and_streams = false;
 	struct {
 		struct dc_surface_update surface_updates[MAX_SURFACES];
 		struct dc_plane_info plane_infos[MAX_SURFACES];
@@ -8386,8 +8503,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		/* Cursor plane is handled after stream updates */
 		if (plane->type == DRM_PLANE_TYPE_CURSOR) {
 			if ((fb && crtc == pcrtc) ||
-			    (old_plane_state->fb && old_plane_state->crtc == pcrtc))
+			    (old_plane_state->fb && old_plane_state->crtc == pcrtc)) {
 				cursor_update = true;
+				amdgpu_dm_update_cursor(plane, old_plane_state, &bundle->stream_update);
+			    }
 
 			continue;
 		}
@@ -8660,6 +8779,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 					 acrtc_state->stream,
 					 &bundle->stream_update,
 					 bundle->surface_updates);
+		updated_planes_and_streams = true;
 
 		/**
 		 * Enable or disable the interrupts on the backend.
@@ -8737,7 +8857,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	 * This avoids redundant programming in the case where we're going
 	 * to be disabling a single plane - those pipes are being disabled.
 	 */
-	if (acrtc_state->active_planes)
+	if (acrtc_state->active_planes && !updated_planes_and_streams)
 		amdgpu_dm_commit_cursors(state);
 
 cleanup:
@@ -8925,7 +9045,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
 
 			memset(&position, 0, sizeof(position));
 			mutex_lock(&dm->dc_lock);
-			dc_stream_set_cursor_position(dm_old_crtc_state->stream, &position);
+			dc_stream_program_cursor_position(dm_old_crtc_state->stream, &position);
 			mutex_unlock(&dm->dc_lock);
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 779880c64575..8c8d0d209d7a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1254,7 +1254,7 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
 		/* turn off cursor */
 		if (crtc_state && crtc_state->stream) {
 			mutex_lock(&adev->dm.dc_lock);
-			dc_stream_set_cursor_position(crtc_state->stream,
+			dc_stream_program_cursor_position(crtc_state->stream,
 						      &position);
 			mutex_unlock(&adev->dm.dc_lock);
 		}
@@ -1284,11 +1284,11 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
 
 	if (crtc_state->stream) {
 		mutex_lock(&adev->dm.dc_lock);
-		if (!dc_stream_set_cursor_attributes(crtc_state->stream,
+		if (!dc_stream_program_cursor_attributes(crtc_state->stream,
 							 &attributes))
 			DRM_ERROR("DC failed to set cursor attributes\n");
 
-		if (!dc_stream_set_cursor_position(crtc_state->stream,
+		if (!dc_stream_program_cursor_position(crtc_state->stream,
 						   &position))
 			DRM_ERROR("DC failed to set cursor position\n");
 		mutex_unlock(&adev->dm.dc_lock);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index d68c83e40d4d..575290784c61 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3188,6 +3188,83 @@ static bool update_planes_and_stream_state(struct dc *dc,
 
 }
 
+static void program_cursor_attributes(
+	struct dc *dc,
+	struct dc_stream_state *stream)
+{
+	int i;
+	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
+
+	if (!stream)
+		return;
+
+	res_ctx = &dc->current_state->res_ctx;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
+
+		if (pipe_ctx->stream != stream)
+			continue;
+
+		if (!pipe_to_program) {
+			pipe_to_program = pipe_ctx;
+			dc->hwss.cursor_lock(dc, pipe_to_program, true);
+			if (pipe_to_program->next_odm_pipe)
+				dc->hwss.cursor_lock(dc, pipe_to_program->next_odm_pipe, true);
+		}
+
+		dc->hwss.set_cursor_attribute(pipe_ctx);
+		if (dc->ctx->dmub_srv)
+			dc_send_update_cursor_info_to_dmu(pipe_ctx, i);
+		if (dc->hwss.set_cursor_sdr_white_level)
+			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+	}
+
+	if (pipe_to_program) {
+		dc->hwss.cursor_lock(dc, pipe_to_program, false);
+		if (pipe_to_program->next_odm_pipe)
+			dc->hwss.cursor_lock(dc, pipe_to_program->next_odm_pipe, false);
+	}
+}
+
+static void program_cursor_position(
+	struct dc *dc,
+	struct dc_stream_state *stream)
+{
+	int i;
+	struct resource_context *res_ctx;
+	struct pipe_ctx *pipe_to_program = NULL;
+
+	if (!stream)
+		return;
+
+	res_ctx = &dc->current_state->res_ctx;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
+
+		if (pipe_ctx->stream != stream ||
+				(!pipe_ctx->plane_res.mi  && !pipe_ctx->plane_res.hubp) ||
+				!pipe_ctx->plane_state ||
+				(!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp) ||
+				(!pipe_ctx->plane_res.ipp && !pipe_ctx->plane_res.dpp))
+			continue;
+
+		if (!pipe_to_program) {
+			pipe_to_program = pipe_ctx;
+			dc->hwss.cursor_lock(dc, pipe_to_program, true);
+		}
+
+		dc->hwss.set_cursor_position(pipe_ctx);
+		if (dc->ctx->dmub_srv)
+			dc_send_update_cursor_info_to_dmu(pipe_ctx, i);
+	}
+
+	if (pipe_to_program)
+		dc->hwss.cursor_lock(dc, pipe_to_program, false);
+}
+
 static void commit_planes_do_stream_update(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_stream_update *stream_update,
@@ -3248,6 +3325,13 @@ static void commit_planes_do_stream_update(struct dc *dc,
 				}
 			}
 
+			if (stream_update->cursor_attributes) {
+				program_cursor_attributes(dc, stream);
+			}
+
+			if (stream_update->cursor_position) {
+				program_cursor_position(dc, stream);
+			}
 
 			/* Full fe update*/
 			if (update_type == UPDATE_TYPE_FAST)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 51a970fcb5d0..5601ee8a8d41 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -278,7 +278,6 @@ bool dc_stream_set_cursor_attributes(
 	const struct dc_cursor_attributes *attributes)
 {
 	struct dc  *dc;
-	bool reset_idle_optimizations = false;
 
 	if (NULL == stream) {
 		dm_error("DC: dc_stream is NULL!\n");
@@ -309,20 +308,36 @@ bool dc_stream_set_cursor_attributes(
 
 	stream->cursor_attributes = *attributes;
 
-	dc_z10_restore(dc);
-	/* disable idle optimizations while updating cursor */
-	if (dc->idle_optimizations_allowed) {
-		dc_allow_idle_optimizations(dc, false);
-		reset_idle_optimizations = true;
-	}
+	return true;
+}
 
-	program_cursor_attributes(dc, stream, attributes);
+bool dc_stream_program_cursor_attributes(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_attributes *attributes)
+{
+	struct dc  *dc;
+	bool reset_idle_optimizations = false;
 
-	/* re-enable idle optimizations if necessary */
-	if (reset_idle_optimizations)
-		dc_allow_idle_optimizations(dc, true);
+	dc = stream ? stream->ctx->dc : NULL;
 
-	return true;
+	if (dc_stream_set_cursor_attributes(stream, attributes)) {
+		dc_z10_restore(dc);
+		/* disable idle optimizations while updating cursor */
+		if (dc->idle_optimizations_allowed) {
+			dc_allow_idle_optimizations(dc, false);
+			reset_idle_optimizations = true;
+		}
+
+		program_cursor_attributes(dc, stream, attributes);
+
+		/* re-enable idle optimizations if necessary */
+		if (reset_idle_optimizations)
+			dc_allow_idle_optimizations(dc, true);
+
+		return true;
+	}
+
+	return false;
 }
 
 static void program_cursor_position(
@@ -367,9 +382,6 @@ bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position)
 {
-	struct dc *dc;
-	bool reset_idle_optimizations = false;
-
 	if (NULL == stream) {
 		dm_error("DC: dc_stream is NULL!\n");
 		return false;
@@ -380,24 +392,43 @@ bool dc_stream_set_cursor_position(
 		return false;
 	}
 
+	stream->cursor_position = *position;
+
+	return true;
+}
+
+bool dc_stream_program_cursor_position(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_position *position)
+{
+	struct dc *dc;
+	bool reset_idle_optimizations = false;
+	const struct dc_cursor_position *old_position;
+
+	old_position = stream ? &stream->cursor_position : NULL;
 	dc = stream->ctx->dc;
-	dc_z10_restore(dc);
 
-	/* disable idle optimizations if enabling cursor */
-	if (dc->idle_optimizations_allowed && (!stream->cursor_position.enable || dc->debug.exit_idle_opt_for_cursor_updates)
-			&& position->enable) {
-		dc_allow_idle_optimizations(dc, false);
-		reset_idle_optimizations = true;
-	}
+	if (dc_stream_set_cursor_position(stream, position)) {
+		dc_z10_restore(dc);
 
-	stream->cursor_position = *position;
+		/* disable idle optimizations if enabling cursor */
+		if (dc->idle_optimizations_allowed &&
+		    (!old_position->enable || dc->debug.exit_idle_opt_for_cursor_updates) &&
+		    position->enable) {
+			dc_allow_idle_optimizations(dc, false);
+			reset_idle_optimizations = true;
+		}
 
-	program_cursor_position(dc, stream, position);
-	/* re-enable idle optimizations if necessary */
-	if (reset_idle_optimizations)
-		dc_allow_idle_optimizations(dc, true);
 
-	return true;
+		program_cursor_position(dc, stream, position);
+		/* re-enable idle optimizations if necessary */
+		if (reset_idle_optimizations)
+			dc_allow_idle_optimizations(dc, true);
+
+		return true;
+	}
+
+	return false;
 }
 
 bool dc_stream_add_writeback(struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index ee10941caa59..df86668f560f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -327,6 +327,9 @@ struct dc_stream_update {
 
 	struct test_pattern *pending_test_pattern;
 	struct dc_crtc_timing_adjust *crtc_timing_adjust;
+
+	struct dc_cursor_attributes *cursor_attributes;
+	struct dc_cursor_position *cursor_position;
 };
 
 bool dc_is_stream_unchanged(
@@ -478,10 +481,17 @@ bool dc_stream_set_cursor_attributes(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_attributes *attributes);
 
+bool dc_stream_program_cursor_attributes(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_attributes *attributes);
+
 bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position);
 
+bool dc_stream_program_cursor_position(
+	struct dc_stream_state *stream,
+	const struct dc_cursor_position *position);
 
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 				struct dc_stream_state *stream,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
index 8bc3d01537bb..f91169c80f7f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
@@ -1042,7 +1042,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
 
 					/* Use copied cursor, and it's okay to not switch back */
 					cursor_attr.address.quad_part = cmd.mall.cursor_copy_dst.quad_part;
-					dc_stream_set_cursor_attributes(stream, &cursor_attr);
+					dc_stream_program_cursor_attributes(stream, &cursor_attr);
 				}
 
 				/* Enable MALL */
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1e020620748d..082f87834503 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4269,6 +4269,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	}
 }
 
+static void clear_extent_buffer_reading(struct extent_buffer *eb)
+{
+	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
+	smp_mb__after_atomic();
+	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+}
+
 static void end_bbio_meta_read(struct btrfs_bio *bbio)
 {
 	struct extent_buffer *eb = bbio->private;
@@ -4277,6 +4284,13 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 	struct folio_iter fi;
 	u32 bio_offset = 0;
 
+	/*
+	 * If the extent buffer is marked UPTODATE before the read operation
+	 * completes, other calls to read_extent_buffer_pages() will return
+	 * early without waiting for the read to finish, causing data races.
+	 */
+	WARN_ON(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags));
+
 	eb->read_mirror = bbio->mirror_num;
 
 	if (uptodate &&
@@ -4303,9 +4317,7 @@ static void end_bbio_meta_read(struct btrfs_bio *bbio)
 		bio_offset += len;
 	}
 
-	clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-	smp_mb__after_atomic();
-	wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+	clear_extent_buffer_reading(eb);
 	free_extent_buffer(eb);
 
 	bio_put(&bbio->bio);
@@ -4339,9 +4351,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,
 	 * will now be set, and we shouldn't read it in again.
 	 */
 	if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) {
-		clear_bit(EXTENT_BUFFER_READING, &eb->bflags);
-		smp_mb__after_atomic();
-		wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING);
+		clear_extent_buffer_reading(eb);
 		return 0;
 	}
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index cf12bfa2a78c..2acf8634008d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -644,14 +644,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
 	cant_migrate();
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
 		struct bpf_prog_stats *stats;
-		u64 start = sched_clock();
+		u64 duration, start = sched_clock();
 		unsigned long flags;
 
 		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
+
+		duration = sched_clock() - start;
 		stats = this_cpu_ptr(prog->stats);
 		flags = u64_stats_update_begin_irqsave(&stats->syncp);
 		u64_stats_inc(&stats->cnt);
-		u64_stats_add(&stats->nsecs, sched_clock() - start);
+		u64_stats_add(&stats->nsecs, duration);
 		u64_stats_update_end_irqrestore(&stats->syncp, flags);
 	} else {
 		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index db7599c59c78..146de96e99b8 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -883,12 +883,13 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
 	     * Hence check that 'start' is valid.
 	     */
 	    start > NO_START_TIME) {
+		u64 duration = sched_clock() - start;
 		unsigned long flags;
 
 		stats = this_cpu_ptr(prog->stats);
 		flags = u64_stats_update_begin_irqsave(&stats->syncp);
 		u64_stats_inc(&stats->cnt);
-		u64_stats_add(&stats->nsecs, sched_clock() - start);
+		u64_stats_add(&stats->nsecs, duration);
 		u64_stats_update_end_irqrestore(&stats->syncp, flags);
 	}
 }
-- 
2.45.2