Merging upstream version 6.10.4.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

63 files changed, 1254 insertions, 797 deletions

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 7ecc67deec..93900c3734 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -3012,6 +3012,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		btintel_set_dsm_reset_method(hdev, &ver_tlv);
 
 		err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
+		if (err)
+			goto exit_error;
+
 		btintel_register_devcoredump_support(hdev);
 		btintel_print_fseq_info(hdev);
 		break;
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 359b68adaf..79628ff837 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -253,6 +253,7 @@ config DRM_EXEC
 config DRM_GPUVM
 	tristate
 	depends on DRM
+	select DRM_EXEC
 	help
 	  GPU-VM representation providing helpers to manage a GPUs virtual
 	  address space
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index ec888fc6ea..13eb2bc69e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1763,7 +1763,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va_mapping *mapping;
-	int r;
+	int i, r;
 
 	addr /= AMDGPU_GPU_PAGE_SIZE;
 
@@ -1778,13 +1778,13 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 	if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket)
 		return -EINVAL;
 
-	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
-		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-		amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
-		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
-		if (r)
-			return r;
-	}
+	(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
+	for (i = 0; i < (*bo)->placement.num_placement; i++)
+		(*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS;
+	r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
+	if (r)
+		return r;
 
 	return amdgpu_ttm_alloc_gart(&(*bo)->tbo);
 }
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index 1e92594169..e6c7f0d64e 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -158,7 +158,14 @@ void ast_dp_launch(struct drm_device *dev)
 			       ASTDP_HOST_EDID_READ_DONE);
 }
 
+bool ast_dp_power_is_on(struct ast_device *ast)
+{
+	u8 vgacre3;
+
+	vgacre3 = ast_get_index_reg(ast, AST_IO_VGACRI, 0xe3);
 
+	return !(vgacre3 & AST_DP_PHY_SLEEP);
+}
 
 void ast_dp_power_on_off(struct drm_device *dev, bool on)
 {
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index f8c49ba68e..af2368f6f0 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -391,6 +391,11 @@ static int ast_drm_freeze(struct drm_device *dev)
 
 static int ast_drm_thaw(struct drm_device *dev)
 {
+	struct ast_device *ast = to_ast_device(dev);
+
+	ast_enable_vga(ast->ioregs);
+	ast_open_key(ast->ioregs);
+	ast_enable_mmio(dev->dev, ast->ioregs);
 	ast_post_gpu(dev);
 
 	return drm_mode_config_helper_resume(dev);
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index ba3d869739..47bab5596c 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -472,6 +472,7 @@ void ast_init_3rdtx(struct drm_device *dev);
 bool ast_astdp_is_connected(struct ast_device *ast);
 int ast_astdp_read_edid(struct drm_device *dev, u8 *ediddata);
 void ast_dp_launch(struct drm_device *dev);
+bool ast_dp_power_is_on(struct ast_device *ast);
 void ast_dp_power_on_off(struct drm_device *dev, bool no);
 void ast_dp_set_on_off(struct drm_device *dev, bool no);
 void ast_dp_set_mode(struct drm_crtc *crtc, struct ast_vbios_mode_info *vbios_mode);
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 6695af7076..88f830a7d2 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -28,6 +28,7 @@
  * Authors: Dave Airlie <airlied@redhat.com>
  */
 
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/pci.h>
 
@@ -1641,11 +1642,35 @@ static int ast_astdp_connector_helper_detect_ctx(struct drm_connector *connector
 						 struct drm_modeset_acquire_ctx *ctx,
 						 bool force)
 {
+	struct drm_device *dev = connector->dev;
 	struct ast_device *ast = to_ast_device(connector->dev);
+	enum drm_connector_status status = connector_status_disconnected;
+	struct drm_connector_state *connector_state = connector->state;
+	bool is_active = false;
+
+	mutex_lock(&ast->modeset_lock);
+
+	if (connector_state && connector_state->crtc) {
+		struct drm_crtc_state *crtc_state = connector_state->crtc->state;
+
+		if (crtc_state && crtc_state->active)
+			is_active = true;
+	}
+
+	if (!is_active && !ast_dp_power_is_on(ast)) {
+		ast_dp_power_on_off(dev, true);
+		msleep(50);
+	}
 
 	if (ast_astdp_is_connected(ast))
-		return connector_status_connected;
-	return connector_status_disconnected;
+		status = connector_status_connected;
+
+	if (!is_active && status == connector_status_disconnected)
+		ast_dp_power_on_off(dev, false);
+
+	mutex_unlock(&ast->modeset_lock);
+
+	return status;
 }
 
 static const struct drm_connector_helper_funcs ast_astdp_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index fc16fddee5..02b1235c6d 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -1066,7 +1066,10 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
 			break;
 		}
 
-		if (async_flip && prop != config->prop_fb_id) {
+		if (async_flip &&
+		    prop != config->prop_fb_id &&
+		    prop != config->prop_in_fence_fd &&
+		    prop != config->prop_fb_damage_clips) {
 			ret = drm_atomic_plane_get_property(plane, plane_state,
 							    prop, &old_val);
 			ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop);
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index 2803ac111b..bfedcbf516 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -355,7 +355,7 @@ int drm_client_buffer_vmap_local(struct drm_client_buffer *buffer,
 
 err_drm_gem_vmap_unlocked:
 	drm_gem_unlock(gem);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(drm_client_buffer_vmap_local);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 90998b0373..292d163036 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -1658,7 +1658,7 @@ static void skl_wrpll_params_populate(struct skl_wrpll_params *params,
 }
 
 static int
-skl_ddi_calculate_wrpll(int clock /* in Hz */,
+skl_ddi_calculate_wrpll(int clock,
 			int ref_clock,
 			struct skl_wrpll_params *wrpll_params)
 {
@@ -1683,7 +1683,7 @@ skl_ddi_calculate_wrpll(int clock /* in Hz */,
 	};
 	unsigned int dco, d, i;
 	unsigned int p0, p1, p2;
-	u64 afe_clock = clock * 5; /* AFE Clock is 5x Pixel clock */
+	u64 afe_clock = (u64)clock * 1000 * 5; /* AFE Clock is 5x Pixel clock, in Hz */
 
 	for (d = 0; d < ARRAY_SIZE(dividers); d++) {
 		for (dco = 0; dco < ARRAY_SIZE(dco_central_freq); dco++) {
@@ -1808,7 +1808,7 @@ static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state)
 	struct skl_wrpll_params wrpll_params = {};
 	int ret;
 
-	ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000,
+	ret = skl_ddi_calculate_wrpll(crtc_state->port_clock,
 				      i915->display.dpll.ref_clks.nssc, &wrpll_params);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
index a568a457e5..f590d7f48b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
@@ -251,7 +251,7 @@
 #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \
 					(TRANS_HDCP(dev_priv) ? \
 					 TRANS_HDCP2_STREAM_STATUS(trans) : \
-					 PIPE_HDCP2_STREAM_STATUS(pipe))
+					 PIPE_HDCP2_STREAM_STATUS(port))
 
 #define _PORTA_HDCP2_AUTH_STREAM		0x66F00
 #define _PORTB_HDCP2_AUTH_STREAM		0x66F04
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0b1cd4c7a5..025a79fe59 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2749,26 +2749,6 @@ oa_configure_all_contexts(struct i915_perf_stream *stream,
 }
 
 static int
-gen12_configure_all_contexts(struct i915_perf_stream *stream,
-			     const struct i915_oa_config *oa_config,
-			     struct i915_active *active)
-{
-	struct flex regs[] = {
-		{
-			GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE),
-			CTX_R_PWR_CLK_STATE,
-		},
-	};
-
-	if (stream->engine->class != RENDER_CLASS)
-		return 0;
-
-	return oa_configure_all_contexts(stream,
-					 regs, ARRAY_SIZE(regs),
-					 active);
-}
-
-static int
 lrc_configure_all_contexts(struct i915_perf_stream *stream,
 			   const struct i915_oa_config *oa_config,
 			   struct i915_active *active)
@@ -2874,7 +2854,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	struct intel_uncore *uncore = stream->uncore;
-	struct i915_oa_config *oa_config = stream->oa_config;
 	bool periodic = stream->periodic;
 	u32 period_exponent = stream->period_exponent;
 	u32 sqcnt1;
@@ -2919,15 +2898,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
 	intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1);
 
 	/*
-	 * Update all contexts prior writing the mux configurations as we need
-	 * to make sure all slices/subslices are ON before writing to NOA
-	 * registers.
-	 */
-	ret = gen12_configure_all_contexts(stream, oa_config, active);
-	if (ret)
-		return ret;
-
-	/*
 	 * For Gen12, performance counters are context
 	 * saved/restored. Only enable it for the context that
 	 * requested this.
@@ -2980,9 +2950,6 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 				   _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING));
 	}
 
-	/* Reset all contexts' slices/subslices configurations. */
-	gen12_configure_all_contexts(stream, NULL, NULL);
-
 	/* disable the context save/restore or OAR counters */
 	if (stream->ctx)
 		gen12_configure_oar_context(stream, NULL);
diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
index b58ab595fa..cd95446d68 100644
--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
+++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
@@ -64,7 +64,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev,
 	 * to the caller, instead of a normal nouveau_bo ttm reference. */
 	ret = drm_gem_object_init(dev, &nvbo->bo.base, size);
 	if (ret) {
-		nouveau_bo_ref(NULL, &nvbo);
+		drm_gem_object_release(&nvbo->bo.base);
+		kfree(nvbo);
 		obj = ERR_PTR(-ENOMEM);
 		goto unlock;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index ee02cd833c..84a36fe7c3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1803,6 +1803,7 @@ nouveau_uvmm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 {
 	struct nouveau_bo *nvbo = nouveau_gem_object(vm_bo->obj);
 
+	nouveau_bo_placement_set(nvbo, nvbo->valid_domains, 0);
 	return nouveau_bo_validate(nvbo, true, false);
 }
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index a2c516fe6d..1d535abedc 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -556,6 +556,10 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo);
 void v3d_mmu_remove_ptes(struct v3d_bo *bo);
 
 /* v3d_sched.c */
+void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info,
+				   unsigned int count);
+void v3d_performance_query_info_free(struct v3d_performance_query_info *query_info,
+				     unsigned int count);
 void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue);
 int v3d_sched_init(struct v3d_dev *v3d);
 void v3d_sched_fini(struct v3d_dev *v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 7cd8c335cd..30d5366d62 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -73,24 +73,44 @@ v3d_sched_job_free(struct drm_sched_job *sched_job)
 	v3d_job_cleanup(job);
 }
 
+void
+v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info,
+			      unsigned int count)
+{
+	if (query_info->queries) {
+		unsigned int i;
+
+		for (i = 0; i < count; i++)
+			drm_syncobj_put(query_info->queries[i].syncobj);
+
+		kvfree(query_info->queries);
+	}
+}
+
+void
+v3d_performance_query_info_free(struct v3d_performance_query_info *query_info,
+				unsigned int count)
+{
+	if (query_info->queries) {
+		unsigned int i;
+
+		for (i = 0; i < count; i++)
+			drm_syncobj_put(query_info->queries[i].syncobj);
+
+		kvfree(query_info->queries);
+	}
+}
+
 static void
 v3d_cpu_job_free(struct drm_sched_job *sched_job)
 {
 	struct v3d_cpu_job *job = to_cpu_job(sched_job);
-	struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query;
-	struct v3d_performance_query_info *performance_query = &job->performance_query;
 
-	if (timestamp_query->queries) {
-		for (int i = 0; i < timestamp_query->count; i++)
-			drm_syncobj_put(timestamp_query->queries[i].syncobj);
-		kvfree(timestamp_query->queries);
-	}
+	v3d_timestamp_query_info_free(&job->timestamp_query,
+				      job->timestamp_query.count);
 
-	if (performance_query->queries) {
-		for (int i = 0; i < performance_query->count; i++)
-			drm_syncobj_put(performance_query->queries[i].syncobj);
-		kvfree(performance_query->queries);
-	}
+	v3d_performance_query_info_free(&job->performance_query,
+					job->performance_query.count);
 
 	v3d_job_cleanup(&job->base);
 }
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index 88f63d526b..4cdfabbf49 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -452,6 +452,8 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv,
 {
 	u32 __user *offsets, *syncs;
 	struct drm_v3d_timestamp_query timestamp;
+	unsigned int i;
+	int err;
 
 	if (!job) {
 		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
@@ -480,26 +482,34 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv,
 	offsets = u64_to_user_ptr(timestamp.offsets);
 	syncs = u64_to_user_ptr(timestamp.syncs);
 
-	for (int i = 0; i < timestamp.count; i++) {
+	for (i = 0; i < timestamp.count; i++) {
 		u32 offset, sync;
 
 		if (copy_from_user(&offset, offsets++, sizeof(offset))) {
-			kvfree(job->timestamp_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		job->timestamp_query.queries[i].offset = offset;
 
 		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
-			kvfree(job->timestamp_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+		if (!job->timestamp_query.queries[i].syncobj) {
+			err = -ENOENT;
+			goto error;
+		}
 	}
 	job->timestamp_query.count = timestamp.count;
 
 	return 0;
+
+error:
+	v3d_timestamp_query_info_free(&job->timestamp_query, i);
+	return err;
 }
 
 static int
@@ -509,6 +519,8 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv,
 {
 	u32 __user *syncs;
 	struct drm_v3d_reset_timestamp_query reset;
+	unsigned int i;
+	int err;
 
 	if (!job) {
 		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
@@ -533,21 +545,29 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv,
 
 	syncs = u64_to_user_ptr(reset.syncs);
 
-	for (int i = 0; i < reset.count; i++) {
+	for (i = 0; i < reset.count; i++) {
 		u32 sync;
 
 		job->timestamp_query.queries[i].offset = reset.offset + 8 * i;
 
 		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
-			kvfree(job->timestamp_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+		if (!job->timestamp_query.queries[i].syncobj) {
+			err = -ENOENT;
+			goto error;
+		}
 	}
 	job->timestamp_query.count = reset.count;
 
 	return 0;
+
+error:
+	v3d_timestamp_query_info_free(&job->timestamp_query, i);
+	return err;
 }
 
 /* Get data for the copy timestamp query results job submission. */
@@ -558,7 +578,8 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
 {
 	u32 __user *offsets, *syncs;
 	struct drm_v3d_copy_timestamp_query copy;
-	int i;
+	unsigned int i;
+	int err;
 
 	if (!job) {
 		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
@@ -591,18 +612,22 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
 		u32 offset, sync;
 
 		if (copy_from_user(&offset, offsets++, sizeof(offset))) {
-			kvfree(job->timestamp_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		job->timestamp_query.queries[i].offset = offset;
 
 		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
-			kvfree(job->timestamp_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+		if (!job->timestamp_query.queries[i].syncobj) {
+			err = -ENOENT;
+			goto error;
+		}
 	}
 	job->timestamp_query.count = copy.count;
 
@@ -613,6 +638,10 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
 	job->copy.stride = copy.stride;
 
 	return 0;
+
+error:
+	v3d_timestamp_query_info_free(&job->timestamp_query, i);
+	return err;
 }
 
 static int
@@ -623,6 +652,8 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
 	u32 __user *syncs;
 	u64 __user *kperfmon_ids;
 	struct drm_v3d_reset_performance_query reset;
+	unsigned int i, j;
+	int err;
 
 	if (!job) {
 		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
@@ -637,6 +668,9 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
 	if (copy_from_user(&reset, ext, sizeof(reset)))
 		return -EFAULT;
 
+	if (reset.nperfmons > V3D_MAX_PERFMONS)
+		return -EINVAL;
+
 	job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY;
 
 	job->performance_query.queries = kvmalloc_array(reset.count,
@@ -648,39 +682,47 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
 	syncs = u64_to_user_ptr(reset.syncs);
 	kperfmon_ids = u64_to_user_ptr(reset.kperfmon_ids);
 
-	for (int i = 0; i < reset.count; i++) {
+	for (i = 0; i < reset.count; i++) {
 		u32 sync;
 		u64 ids;
 		u32 __user *ids_pointer;
 		u32 id;
 
 		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
-			kvfree(job->performance_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
-		job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
-
 		if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) {
-			kvfree(job->performance_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		ids_pointer = u64_to_user_ptr(ids);
 
-		for (int j = 0; j < reset.nperfmons; j++) {
+		for (j = 0; j < reset.nperfmons; j++) {
 			if (copy_from_user(&id, ids_pointer++, sizeof(id))) {
-				kvfree(job->performance_query.queries);
-				return -EFAULT;
+				err = -EFAULT;
+				goto error;
 			}
 
 			job->performance_query.queries[i].kperfmon_ids[j] = id;
 		}
+
+		job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+		if (!job->performance_query.queries[i].syncobj) {
+			err = -ENOENT;
+			goto error;
+		}
 	}
 	job->performance_query.count = reset.count;
 	job->performance_query.nperfmons = reset.nperfmons;
 
 	return 0;
+
+error:
+	v3d_performance_query_info_free(&job->performance_query, i);
+	return err;
 }
 
 static int
@@ -691,6 +733,8 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
 	u32 __user *syncs;
 	u64 __user *kperfmon_ids;
 	struct drm_v3d_copy_performance_query copy;
+	unsigned int i, j;
+	int err;
 
 	if (!job) {
 		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
@@ -708,6 +752,9 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
 	if (copy.pad)
 		return -EINVAL;
 
+	if (copy.nperfmons > V3D_MAX_PERFMONS)
+		return -EINVAL;
+
 	job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY;
 
 	job->performance_query.queries = kvmalloc_array(copy.count,
@@ -719,34 +766,38 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
 	syncs = u64_to_user_ptr(copy.syncs);
 	kperfmon_ids = u64_to_user_ptr(copy.kperfmon_ids);
 
-	for (int i = 0; i < copy.count; i++) {
+	for (i = 0; i < copy.count; i++) {
 		u32 sync;
 		u64 ids;
 		u32 __user *ids_pointer;
 		u32 id;
 
 		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
-			kvfree(job->performance_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
-		job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
-
 		if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) {
-			kvfree(job->performance_query.queries);
-			return -EFAULT;
+			err = -EFAULT;
+			goto error;
 		}
 
 		ids_pointer = u64_to_user_ptr(ids);
 
-		for (int j = 0; j < copy.nperfmons; j++) {
+		for (j = 0; j < copy.nperfmons; j++) {
 			if (copy_from_user(&id, ids_pointer++, sizeof(id))) {
-				kvfree(job->performance_query.queries);
-				return -EFAULT;
+				err = -EFAULT;
+				goto error;
 			}
 
 			job->performance_query.queries[i].kperfmon_ids[j] = id;
 		}
+
+		job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+		if (!job->performance_query.queries[i].syncobj) {
+			err = -ENOENT;
+			goto error;
+		}
 	}
 	job->performance_query.count = copy.count;
 	job->performance_query.nperfmons = copy.nperfmons;
@@ -759,6 +810,10 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
 	job->copy.stride = copy.stride;
 
 	return 0;
+
+error:
+	v3d_performance_query_info_free(&job->performance_query, i);
+	return err;
 }
 
 /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data
diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c
index 1c7c7f61a2..7d34cf83f5 100644
--- a/drivers/gpu/drm/virtio/virtgpu_submit.c
+++ b/drivers/gpu/drm/virtio/virtgpu_submit.c
@@ -48,7 +48,7 @@ struct virtio_gpu_submit {
 static int virtio_gpu_do_fence_wait(struct virtio_gpu_submit *submit,
 				    struct dma_fence *in_fence)
 {
-	u32 context = submit->fence_ctx + submit->ring_idx;
+	u64 context = submit->fence_ctx + submit->ring_idx;
 
 	if (dma_fence_match_context(in_fence, context))
 		return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
index b0d87c5f58..1ac3cb151b 100644
--- a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
+++ b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
@@ -1,6 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2021 VMware, Inc.
- * SPDX-License-Identifier: GPL-2.0 OR MIT
+ *
+ * Copyright (c) 2021-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
@@ -31,6 +33,10 @@
 
 #include <drm/vmwgfx_drm.h>
 
+#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) ((svga3d_flags) >> 32)
+#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
+	((svga3d_flags) & ((uint64_t)U32_MAX))
+
 static inline u32 clamped_umul32(u32 a, u32 b)
 {
 	uint64_t tmp = (uint64_t) a*b;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index 00144632c6..f42ebc4a7c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2023 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright (c) 2011-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -28,15 +28,39 @@
 
 #include "vmwgfx_bo.h"
 #include "vmwgfx_drv.h"
-
+#include "vmwgfx_resource_priv.h"
 
 #include <drm/ttm/ttm_placement.h>
 
 static void vmw_bo_release(struct vmw_bo *vbo)
 {
+	struct vmw_resource *res;
+
 	WARN_ON(vbo->tbo.base.funcs &&
 		kref_read(&vbo->tbo.base.refcount) != 0);
 	vmw_bo_unmap(vbo);
+
+	xa_destroy(&vbo->detached_resources);
+	WARN_ON(vbo->is_dumb && !vbo->dumb_surface);
+	if (vbo->is_dumb && vbo->dumb_surface) {
+		res = &vbo->dumb_surface->res;
+		WARN_ON(vbo != res->guest_memory_bo);
+		WARN_ON(!res->guest_memory_bo);
+		if (res->guest_memory_bo) {
+			/* Reserve and switch the backing mob. */
+			mutex_lock(&res->dev_priv->cmdbuf_mutex);
+			(void)vmw_resource_reserve(res, false, true);
+			vmw_resource_mob_detach(res);
+			if (res->coherent)
+				vmw_bo_dirty_release(res->guest_memory_bo);
+			res->guest_memory_bo = NULL;
+			res->guest_memory_offset = 0;
+			vmw_resource_unreserve(res, false, false, false, NULL,
+					       0);
+			mutex_unlock(&res->dev_priv->cmdbuf_mutex);
+		}
+		vmw_surface_unreference(&vbo->dumb_surface);
+	}
 	drm_gem_object_release(&vbo->tbo.base);
 }
 
@@ -326,6 +350,11 @@ void vmw_bo_pin_reserved(struct vmw_bo *vbo, bool pin)
  */
 void *vmw_bo_map_and_cache(struct vmw_bo *vbo)
 {
+	return vmw_bo_map_and_cache_size(vbo, vbo->tbo.base.size);
+}
+
+void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
+{
 	struct ttm_buffer_object *bo = &vbo->tbo;
 	bool not_used;
 	void *virtual;
@@ -335,9 +364,10 @@ void *vmw_bo_map_and_cache(struct vmw_bo *vbo)
 	if (virtual)
 		return virtual;
 
-	ret = ttm_bo_kmap(bo, 0, PFN_UP(bo->base.size), &vbo->map);
+	ret = ttm_bo_kmap(bo, 0, PFN_UP(size), &vbo->map);
 	if (ret)
-		DRM_ERROR("Buffer object map failed: %d.\n", ret);
+		DRM_ERROR("Buffer object map failed: %d (size: bo = %zu, map = %zu).\n",
+			  ret, bo->base.size, size);
 
 	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
 }
@@ -390,6 +420,7 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
 	BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3);
 	vmw_bo->tbo.priority = 3;
 	vmw_bo->res_tree = RB_ROOT;
+	xa_init(&vmw_bo->detached_resources);
 
 	params->size = ALIGN(params->size, PAGE_SIZE);
 	drm_gem_private_object_init(vdev, &vmw_bo->tbo.base, params->size);
@@ -654,52 +685,6 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
 	dma_fence_put(&fence->base);
 }
 
-
-/**
- * vmw_dumb_create - Create a dumb kms buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @args: Pointer to a struct drm_mode_create_dumb structure
- * Return: Zero on success, negative error code on failure.
- *
- * This is a driver callback for the core drm create_dumb functionality.
- * Note that this is very similar to the vmw_bo_alloc ioctl, except
- * that the arguments have a different format.
- */
-int vmw_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_bo *vbo;
-	int cpp = DIV_ROUND_UP(args->bpp, 8);
-	int ret;
-
-	switch (cpp) {
-	case 1: /* DRM_FORMAT_C8 */
-	case 2: /* DRM_FORMAT_RGB565 */
-	case 4: /* DRM_FORMAT_XRGB8888 */
-		break;
-	default:
-		/*
-		 * Dumb buffers don't allow anything else.
-		 * This is tested via IGT's dumb_buffers
-		 */
-		return -EINVAL;
-	}
-
-	args->pitch = args->width * cpp;
-	args->size = ALIGN(args->pitch * args->height, PAGE_SIZE);
-
-	ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
-						args->size, &args->handle,
-						&vbo);
-	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_put(&vbo->tbo.base);
-	return ret;
-}
-
 /**
  * vmw_bo_swap_notify - swapout notify callback.
  *
@@ -853,3 +838,43 @@ void vmw_bo_placement_set_default_accelerated(struct vmw_bo *bo)
 
 	vmw_bo_placement_set(bo, domain, domain);
 }
+
+void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
+{
+	xa_store(&vbo->detached_resources, (unsigned long)res, res, GFP_KERNEL);
+}
+
+void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
+{
+	xa_erase(&vbo->detached_resources, (unsigned long)res);
+}
+
+struct vmw_surface *vmw_bo_surface(struct vmw_bo *vbo)
+{
+	unsigned long index;
+	struct vmw_resource *res = NULL;
+	struct vmw_surface *surf = NULL;
+	struct rb_node *rb_itr = vbo->res_tree.rb_node;
+
+	if (vbo->is_dumb && vbo->dumb_surface) {
+		res = &vbo->dumb_surface->res;
+		goto out;
+	}
+
+	xa_for_each(&vbo->detached_resources, index, res) {
+		if (res->func->res_type == vmw_res_surface)
+			goto out;
+	}
+
+	for (rb_itr = rb_first(&vbo->res_tree); rb_itr;
+	     rb_itr = rb_next(rb_itr)) {
+		res = rb_entry(rb_itr, struct vmw_resource, mob_node);
+		if (res->func->res_type == vmw_res_surface)
+			goto out;
+	}
+
+out:
+	if (res)
+		surf = vmw_res_to_srf(res);
+	return surf;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
index f349642e61..62b4342d5f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright 2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2023-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -35,11 +36,13 @@
 
 #include <linux/rbtree_types.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 
 struct vmw_bo_dirty;
 struct vmw_fence_obj;
 struct vmw_private;
 struct vmw_resource;
+struct vmw_surface;
 
 enum vmw_bo_domain {
 	VMW_BO_DOMAIN_SYS           = BIT(0),
@@ -85,11 +88,15 @@ struct vmw_bo {
 
 	struct rb_root res_tree;
 	u32 res_prios[TTM_MAX_BO_PRIORITY];
+	struct xarray detached_resources;
 
 	atomic_t cpu_writers;
 	/* Not ref-counted.  Protected by binding_mutex */
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_bo_dirty *dirty;
+
+	bool is_dumb;
+	struct vmw_surface *dumb_surface;
 };
 
 void vmw_bo_placement_set(struct vmw_bo *bo, u32 domain, u32 busy_domain);
@@ -124,15 +131,21 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
 			 struct vmw_fence_obj *fence);
 
 void *vmw_bo_map_and_cache(struct vmw_bo *vbo);
+void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size);
 void vmw_bo_unmap(struct vmw_bo *vbo);
 
 void vmw_bo_move_notify(struct ttm_buffer_object *bo,
 			struct ttm_resource *mem);
 void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 
+void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
+void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
+struct vmw_surface *vmw_bo_surface(struct vmw_bo *vbo);
+
 int vmw_user_bo_lookup(struct drm_file *filp,
 		       u32 handle,
 		       struct vmw_bo **out);
+
 /**
  * vmw_bo_adjust_prio - Adjust the buffer object eviction priority
  * according to attached resources
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a1ce41e1c4..32f50e5958 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -763,6 +764,26 @@ extern int vmw_gmr_bind(struct vmw_private *dev_priv,
 extern void vmw_gmr_unbind(struct vmw_private *dev_priv, int gmr_id);
 
 /**
+ * User handles
+ */
+struct vmw_user_object {
+	struct vmw_surface *surface;
+	struct vmw_bo *buffer;
+};
+
+int vmw_user_object_lookup(struct vmw_private *dev_priv, struct drm_file *filp,
+			   u32 handle, struct vmw_user_object *uo);
+struct vmw_user_object *vmw_user_object_ref(struct vmw_user_object *uo);
+void vmw_user_object_unref(struct vmw_user_object *uo);
+bool vmw_user_object_is_null(struct vmw_user_object *uo);
+struct vmw_surface *vmw_user_object_surface(struct vmw_user_object *uo);
+struct vmw_bo *vmw_user_object_buffer(struct vmw_user_object *uo);
+void *vmw_user_object_map(struct vmw_user_object *uo);
+void *vmw_user_object_map_size(struct vmw_user_object *uo, size_t size);
+void vmw_user_object_unmap(struct vmw_user_object *uo);
+bool vmw_user_object_is_mapped(struct vmw_user_object *uo);
+
+/**
  * Resource utilities - vmwgfx_resource.c
  */
 struct vmw_user_resource_conv;
@@ -776,11 +797,6 @@ extern int vmw_resource_validate(struct vmw_resource *res, bool intr,
 extern int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
 				bool no_backup);
 extern bool vmw_resource_needs_backup(const struct vmw_resource *res);
-extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
-				  struct drm_file *filp,
-				  uint32_t handle,
-				  struct vmw_surface **out_surf,
-				  struct vmw_bo **out_buf);
 extern int vmw_user_resource_lookup_handle(
 	struct vmw_private *dev_priv,
 	struct ttm_object_file *tfile,
@@ -1057,9 +1073,6 @@ int vmw_kms_suspend(struct drm_device *dev);
 int vmw_kms_resume(struct drm_device *dev);
 void vmw_kms_lost_device(struct drm_device *dev);
 
-int vmw_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args);
 extern int vmw_resource_pin(struct vmw_resource *res, bool interruptible);
 extern void vmw_resource_unpin(struct vmw_resource *res);
 extern enum vmw_res_type vmw_res_type(const struct vmw_resource *res);
@@ -1176,6 +1189,15 @@ extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev,
 int vmw_gb_surface_define(struct vmw_private *dev_priv,
 			  const struct vmw_surface_metadata *req,
 			  struct vmw_surface **srf_out);
+struct vmw_surface *vmw_lookup_surface_for_buffer(struct vmw_private *vmw,
+						  struct vmw_bo *bo,
+						  u32 handle);
+u32 vmw_lookup_surface_handle_for_buffer(struct vmw_private *vmw,
+					 struct vmw_bo *bo,
+					 u32 handle);
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args);
 
 /*
  * Shader management - vmwgfx_shader.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 5efc6a766f..588d50abab 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -32,7 +32,6 @@
 #define VMW_FENCE_WRAP (1 << 31)
 
 struct vmw_fence_manager {
-	int num_fence_objects;
 	struct vmw_private *dev_priv;
 	spinlock_t lock;
 	struct list_head fence_list;
@@ -124,13 +123,13 @@ static void vmw_fence_obj_destroy(struct dma_fence *f)
 {
 	struct vmw_fence_obj *fence =
 		container_of(f, struct vmw_fence_obj, base);
-
 	struct vmw_fence_manager *fman = fman_from_fence(fence);
 
-	spin_lock(&fman->lock);
-	list_del_init(&fence->head);
-	--fman->num_fence_objects;
-	spin_unlock(&fman->lock);
+	if (!list_empty(&fence->head)) {
+		spin_lock(&fman->lock);
+		list_del_init(&fence->head);
+		spin_unlock(&fman->lock);
+	}
 	fence->destroy(fence);
 }
 
@@ -257,7 +256,6 @@ static const struct dma_fence_ops vmw_fence_ops = {
 	.release = vmw_fence_obj_destroy,
 };
 
-
 /*
  * Execute signal actions on fences recently signaled.
  * This is done from a workqueue so we don't have to execute
@@ -355,7 +353,6 @@ static int vmw_fence_obj_init(struct vmw_fence_manager *fman,
 		goto out_unlock;
 	}
 	list_add_tail(&fence->head, &fman->fence_list);
-	++fman->num_fence_objects;
 
 out_unlock:
 	spin_unlock(&fman->lock);
@@ -403,7 +400,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
 				      u32 passed_seqno)
 {
 	u32 goal_seqno;
-	struct vmw_fence_obj *fence;
+	struct vmw_fence_obj *fence, *next_fence;
 
 	if (likely(!fman->seqno_valid))
 		return false;
@@ -413,7 +410,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
 		return false;
 
 	fman->seqno_valid = false;
-	list_for_each_entry(fence, &fman->fence_list, head) {
+	list_for_each_entry_safe(fence, next_fence, &fman->fence_list, head) {
 		if (!list_empty(&fence->seq_passed_actions)) {
 			fman->seqno_valid = true;
 			vmw_fence_goal_write(fman->dev_priv,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 00c4ff6841..288ed0bb75 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -193,13 +194,16 @@ static u32 vmw_du_cursor_mob_size(u32 w, u32 h)
  */
 static u32 *vmw_du_cursor_plane_acquire_image(struct vmw_plane_state *vps)
 {
-	if (vps->surf) {
-		if (vps->surf_mapped)
-			return vmw_bo_map_and_cache(vps->surf->res.guest_memory_bo);
-		return vps->surf->snooper.image;
-	} else if (vps->bo)
-		return vmw_bo_map_and_cache(vps->bo);
-	return NULL;
+	struct vmw_surface *surf;
+
+	if (vmw_user_object_is_null(&vps->uo))
+		return NULL;
+
+	surf = vmw_user_object_surface(&vps->uo);
+	if (surf && !vmw_user_object_is_mapped(&vps->uo))
+		return surf->snooper.image;
+
+	return vmw_user_object_map(&vps->uo);
 }
 
 static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps,
@@ -536,22 +540,16 @@ void vmw_du_primary_plane_destroy(struct drm_plane *plane)
  * vmw_du_plane_unpin_surf - unpins resource associated with a framebuffer surface
  *
  * @vps: plane state associated with the display surface
- * @unreference: true if we also want to unreference the display.
  */
-void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps,
-			     bool unreference)
+void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps)
 {
-	if (vps->surf) {
+	struct vmw_surface *surf = vmw_user_object_surface(&vps->uo);
+
+	if (surf) {
 		if (vps->pinned) {
-			vmw_resource_unpin(&vps->surf->res);
+			vmw_resource_unpin(&surf->res);
 			vps->pinned--;
 		}
-
-		if (unreference) {
-			if (vps->pinned)
-				DRM_ERROR("Surface still pinned\n");
-			vmw_surface_unreference(&vps->surf);
-		}
 	}
 }
 
@@ -572,7 +570,7 @@ vmw_du_plane_cleanup_fb(struct drm_plane *plane,
 {
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
 
-	vmw_du_plane_unpin_surf(vps, false);
+	vmw_du_plane_unpin_surf(vps);
 }
 
 
@@ -661,25 +659,14 @@ vmw_du_cursor_plane_cleanup_fb(struct drm_plane *plane,
 	struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane);
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
 
-	if (vps->surf_mapped) {
-		vmw_bo_unmap(vps->surf->res.guest_memory_bo);
-		vps->surf_mapped = false;
-	}
+	if (!vmw_user_object_is_null(&vps->uo))
+		vmw_user_object_unmap(&vps->uo);
 
 	vmw_du_cursor_plane_unmap_cm(vps);
 	vmw_du_put_cursor_mob(vcp, vps);
 
-	vmw_du_plane_unpin_surf(vps, false);
-
-	if (vps->surf) {
-		vmw_surface_unreference(&vps->surf);
-		vps->surf = NULL;
-	}
-
-	if (vps->bo) {
-		vmw_bo_unreference(&vps->bo);
-		vps->bo = NULL;
-	}
+	vmw_du_plane_unpin_surf(vps);
+	vmw_user_object_unref(&vps->uo);
 }
 
 
@@ -698,64 +685,48 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_framebuffer *fb = new_state->fb;
 	struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane);
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state);
+	struct vmw_bo *bo = NULL;
 	int ret = 0;
 
-	if (vps->surf) {
-		if (vps->surf_mapped) {
-			vmw_bo_unmap(vps->surf->res.guest_memory_bo);
-			vps->surf_mapped = false;
-		}
-		vmw_surface_unreference(&vps->surf);
-		vps->surf = NULL;
-	}
-
-	if (vps->bo) {
-		vmw_bo_unreference(&vps->bo);
-		vps->bo = NULL;
+	if (!vmw_user_object_is_null(&vps->uo)) {
+		vmw_user_object_unmap(&vps->uo);
+		vmw_user_object_unref(&vps->uo);
 	}
 
 	if (fb) {
 		if (vmw_framebuffer_to_vfb(fb)->bo) {
-			vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer;
-			vmw_bo_reference(vps->bo);
+			vps->uo.buffer = vmw_framebuffer_to_vfbd(fb)->buffer;
+			vps->uo.surface = NULL;
 		} else {
-			vps->surf = vmw_framebuffer_to_vfbs(fb)->surface;
-			vmw_surface_reference(vps->surf);
+			memcpy(&vps->uo, &vmw_framebuffer_to_vfbs(fb)->uo, sizeof(vps->uo));
 		}
+		vmw_user_object_ref(&vps->uo);
 	}
 
-	if (!vps->surf && vps->bo) {
-		const u32 size = new_state->crtc_w * new_state->crtc_h * sizeof(u32);
+	bo = vmw_user_object_buffer(&vps->uo);
+	if (bo) {
+		struct ttm_operation_ctx ctx = {false, false};
 
-		/*
-		 * Not using vmw_bo_map_and_cache() helper here as we need to
-		 * reserve the ttm_buffer_object first which
-		 * vmw_bo_map_and_cache() omits.
-		 */
-		ret = ttm_bo_reserve(&vps->bo->tbo, true, false, NULL);
-
-		if (unlikely(ret != 0))
+		ret = ttm_bo_reserve(&bo->tbo, true, false, NULL);
+		if (ret != 0)
 			return -ENOMEM;
 
-		ret = ttm_bo_kmap(&vps->bo->tbo, 0, PFN_UP(size), &vps->bo->map);
-
-		ttm_bo_unreserve(&vps->bo->tbo);
-
-		if (unlikely(ret != 0))
+		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+		if (ret != 0)
 			return -ENOMEM;
-	} else if (vps->surf && !vps->bo && vps->surf->res.guest_memory_bo) {
 
-		WARN_ON(vps->surf->snooper.image);
-		ret = ttm_bo_reserve(&vps->surf->res.guest_memory_bo->tbo, true, false,
-				     NULL);
-		if (unlikely(ret != 0))
-			return -ENOMEM;
-		vmw_bo_map_and_cache(vps->surf->res.guest_memory_bo);
-		ttm_bo_unreserve(&vps->surf->res.guest_memory_bo->tbo);
-		vps->surf_mapped = true;
+		vmw_bo_pin_reserved(bo, true);
+		if (vmw_framebuffer_to_vfb(fb)->bo) {
+			const u32 size = new_state->crtc_w * new_state->crtc_h * sizeof(u32);
+
+			(void)vmw_bo_map_and_cache_size(bo, size);
+		} else {
+			vmw_bo_map_and_cache(bo);
+		}
+		ttm_bo_unreserve(&bo->tbo);
 	}
 
-	if (vps->surf || vps->bo) {
+	if (!vmw_user_object_is_null(&vps->uo)) {
 		vmw_du_get_cursor_mob(vcp, vps);
 		vmw_du_cursor_plane_map_cm(vps);
 	}
@@ -777,14 +748,17 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state);
 	struct vmw_plane_state *old_vps = vmw_plane_state_to_vps(old_state);
+	struct vmw_bo *old_bo = NULL;
+	struct vmw_bo *new_bo = NULL;
 	s32 hotspot_x, hotspot_y;
+	int ret;
 
 	hotspot_x = du->hotspot_x + new_state->hotspot_x;
 	hotspot_y = du->hotspot_y + new_state->hotspot_y;
 
-	du->cursor_surface = vps->surf;
+	du->cursor_surface = vmw_user_object_surface(&vps->uo);
 
-	if (!vps->surf && !vps->bo) {
+	if (vmw_user_object_is_null(&vps->uo)) {
 		vmw_cursor_update_position(dev_priv, false, 0, 0);
 		return;
 	}
@@ -792,10 +766,26 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	vps->cursor.hotspot_x = hotspot_x;
 	vps->cursor.hotspot_y = hotspot_y;
 
-	if (vps->surf) {
+	if (du->cursor_surface)
 		du->cursor_age = du->cursor_surface->snooper.age;
+
+	if (!vmw_user_object_is_null(&old_vps->uo)) {
+		old_bo = vmw_user_object_buffer(&old_vps->uo);
+		ret = ttm_bo_reserve(&old_bo->tbo, false, false, NULL);
+		if (ret != 0)
+			return;
 	}
 
+	if (!vmw_user_object_is_null(&vps->uo)) {
+		new_bo = vmw_user_object_buffer(&vps->uo);
+		if (old_bo != new_bo) {
+			ret = ttm_bo_reserve(&new_bo->tbo, false, false, NULL);
+			if (ret != 0)
+				return;
+		} else {
+			new_bo = NULL;
+		}
+	}
 	if (!vmw_du_cursor_plane_has_changed(old_vps, vps)) {
 		/*
 		 * If it hasn't changed, avoid making the device do extra
@@ -813,6 +803,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 						hotspot_x, hotspot_y);
 	}
 
+	if (old_bo)
+		ttm_bo_unreserve(&old_bo->tbo);
+	if (new_bo)
+		ttm_bo_unreserve(&new_bo->tbo);
+
 	du->cursor_x = new_state->crtc_x + du->set_gui_x;
 	du->cursor_y = new_state->crtc_y + du->set_gui_y;
 
@@ -913,7 +908,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 	}
 
 	if (!vmw_framebuffer_to_vfb(fb)->bo) {
-		surface = vmw_framebuffer_to_vfbs(fb)->surface;
+		surface = vmw_user_object_surface(&vmw_framebuffer_to_vfbs(fb)->uo);
 
 		WARN_ON(!surface);
 
@@ -1074,12 +1069,7 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane)
 	memset(&vps->cursor, 0, sizeof(vps->cursor));
 
 	/* Each ref counted resource needs to be acquired again */
-	if (vps->surf)
-		(void) vmw_surface_reference(vps->surf);
-
-	if (vps->bo)
-		(void) vmw_bo_reference(vps->bo);
-
+	vmw_user_object_ref(&vps->uo);
 	state = &vps->base;
 
 	__drm_atomic_helper_plane_duplicate_state(plane, state);
@@ -1128,11 +1118,7 @@ vmw_du_plane_destroy_state(struct drm_plane *plane,
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(state);
 
 	/* Should have been freed by cleanup_fb */
-	if (vps->surf)
-		vmw_surface_unreference(&vps->surf);
-
-	if (vps->bo)
-		vmw_bo_unreference(&vps->bo);
+	vmw_user_object_unref(&vps->uo);
 
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
@@ -1227,7 +1213,7 @@ static void vmw_framebuffer_surface_destroy(struct drm_framebuffer *framebuffer)
 		vmw_framebuffer_to_vfbs(framebuffer);
 
 	drm_framebuffer_cleanup(framebuffer);
-	vmw_surface_unreference(&vfbs->surface);
+	vmw_user_object_unref(&vfbs->uo);
 
 	kfree(vfbs);
 }
@@ -1272,29 +1258,41 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
 	return -ENOSYS;
 }
 
+static int vmw_framebuffer_surface_create_handle(struct drm_framebuffer *fb,
+						 struct drm_file *file_priv,
+						 unsigned int *handle)
+{
+	struct vmw_framebuffer_surface *vfbs = vmw_framebuffer_to_vfbs(fb);
+	struct vmw_bo *bo = vmw_user_object_buffer(&vfbs->uo);
+
+	return drm_gem_handle_create(file_priv, &bo->tbo.base, handle);
+}
 
 static const struct drm_framebuffer_funcs vmw_framebuffer_surface_funcs = {
+	.create_handle = vmw_framebuffer_surface_create_handle,
 	.destroy = vmw_framebuffer_surface_destroy,
 	.dirty = drm_atomic_helper_dirtyfb,
 };
 
 static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
-					   struct vmw_surface *surface,
+					   struct vmw_user_object *uo,
 					   struct vmw_framebuffer **out,
 					   const struct drm_mode_fb_cmd2
-					   *mode_cmd,
-					   bool is_bo_proxy)
+					   *mode_cmd)
 
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct vmw_framebuffer_surface *vfbs;
 	enum SVGA3dSurfaceFormat format;
+	struct vmw_surface *surface;
 	int ret;
 
 	/* 3D is only supported on HWv8 and newer hosts */
 	if (dev_priv->active_display_unit == vmw_du_legacy)
 		return -ENOSYS;
 
+	surface = vmw_user_object_surface(uo);
+
 	/*
 	 * Sanity checks.
 	 */
@@ -1357,8 +1355,8 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd);
-	vfbs->surface = vmw_surface_reference(surface);
-	vfbs->is_bo_proxy = is_bo_proxy;
+	memcpy(&vfbs->uo, uo, sizeof(vfbs->uo));
+	vmw_user_object_ref(&vfbs->uo);
 
 	*out = &vfbs->base;
 
@@ -1370,7 +1368,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	return 0;
 
 out_err2:
-	vmw_surface_unreference(&surface);
+	vmw_user_object_unref(&vfbs->uo);
 	kfree(vfbs);
 out_err1:
 	return ret;
@@ -1386,7 +1384,6 @@ static int vmw_framebuffer_bo_create_handle(struct drm_framebuffer *fb,
 {
 	struct vmw_framebuffer_bo *vfbd =
 			vmw_framebuffer_to_vfbd(fb);
-
 	return drm_gem_handle_create(file_priv, &vfbd->buffer->tbo.base, handle);
 }
 
@@ -1407,86 +1404,6 @@ static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = {
 	.dirty = drm_atomic_helper_dirtyfb,
 };
 
-/**
- * vmw_create_bo_proxy - create a proxy surface for the buffer object
- *
- * @dev: DRM device
- * @mode_cmd: parameters for the new surface
- * @bo_mob: MOB backing the buffer object
- * @srf_out: newly created surface
- *
- * When the content FB is a buffer object, we create a surface as a proxy to the
- * same buffer.  This way we can do a surface copy rather than a surface DMA.
- * This is a more efficient approach
- *
- * RETURNS:
- * 0 on success, error code otherwise
- */
-static int vmw_create_bo_proxy(struct drm_device *dev,
-			       const struct drm_mode_fb_cmd2 *mode_cmd,
-			       struct vmw_bo *bo_mob,
-			       struct vmw_surface **srf_out)
-{
-	struct vmw_surface_metadata metadata = {0};
-	uint32_t format;
-	struct vmw_resource *res;
-	unsigned int bytes_pp;
-	int ret;
-
-	switch (mode_cmd->pixel_format) {
-	case DRM_FORMAT_ARGB8888:
-	case DRM_FORMAT_XRGB8888:
-		format = SVGA3D_X8R8G8B8;
-		bytes_pp = 4;
-		break;
-
-	case DRM_FORMAT_RGB565:
-	case DRM_FORMAT_XRGB1555:
-		format = SVGA3D_R5G6B5;
-		bytes_pp = 2;
-		break;
-
-	case 8:
-		format = SVGA3D_P8;
-		bytes_pp = 1;
-		break;
-
-	default:
-		DRM_ERROR("Invalid framebuffer format %p4cc\n",
-			  &mode_cmd->pixel_format);
-		return -EINVAL;
-	}
-
-	metadata.format = format;
-	metadata.mip_levels[0] = 1;
-	metadata.num_sizes = 1;
-	metadata.base_size.width = mode_cmd->pitches[0] / bytes_pp;
-	metadata.base_size.height =  mode_cmd->height;
-	metadata.base_size.depth = 1;
-	metadata.scanout = true;
-
-	ret = vmw_gb_surface_define(vmw_priv(dev), &metadata, srf_out);
-	if (ret) {
-		DRM_ERROR("Failed to allocate proxy content buffer\n");
-		return ret;
-	}
-
-	res = &(*srf_out)->res;
-
-	/* Reserve and switch the backing mob. */
-	mutex_lock(&res->dev_priv->cmdbuf_mutex);
-	(void) vmw_resource_reserve(res, false, true);
-	vmw_user_bo_unref(&res->guest_memory_bo);
-	res->guest_memory_bo = vmw_user_bo_ref(bo_mob);
-	res->guest_memory_offset = 0;
-	vmw_resource_unreserve(res, false, false, false, NULL, 0);
-	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
-
-	return 0;
-}
-
-
-
 static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
 				      struct vmw_bo *bo,
 				      struct vmw_framebuffer **out,
@@ -1565,55 +1482,24 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height)
  * vmw_kms_new_framebuffer - Create a new framebuffer.
  *
  * @dev_priv: Pointer to device private struct.
- * @bo: Pointer to buffer object to wrap the kms framebuffer around.
- * Either @bo or @surface must be NULL.
- * @surface: Pointer to a surface to wrap the kms framebuffer around.
- * Either @bo or @surface must be NULL.
- * @only_2d: No presents will occur to this buffer object based framebuffer.
- * This helps the code to do some important optimizations.
+ * @uo: Pointer to user object to wrap the kms framebuffer around.
+ * Either the buffer or surface inside the user object must be NULL.
  * @mode_cmd: Frame-buffer metadata.
  */
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_bo *bo,
-			struct vmw_surface *surface,
-			bool only_2d,
+			struct vmw_user_object *uo,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct vmw_framebuffer *vfb = NULL;
-	bool is_bo_proxy = false;
 	int ret;
 
-	/*
-	 * We cannot use the SurfaceDMA command in an non-accelerated VM,
-	 * therefore, wrap the buffer object in a surface so we can use the
-	 * SurfaceCopy command.
-	 */
-	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
-	    bo && only_2d &&
-	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
-	    dev_priv->active_display_unit == vmw_du_screen_target) {
-		ret = vmw_create_bo_proxy(&dev_priv->drm, mode_cmd,
-					  bo, &surface);
-		if (ret)
-			return ERR_PTR(ret);
-
-		is_bo_proxy = true;
-	}
-
 	/* Create the new framebuffer depending one what we have */
-	if (surface) {
-		ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb,
-						      mode_cmd,
-						      is_bo_proxy);
-		/*
-		 * vmw_create_bo_proxy() adds a reference that is no longer
-		 * needed
-		 */
-		if (is_bo_proxy)
-			vmw_surface_unreference(&surface);
-	} else if (bo) {
-		ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb,
+	if (vmw_user_object_surface(uo)) {
+		ret = vmw_kms_new_framebuffer_surface(dev_priv, uo, &vfb,
+						      mode_cmd);
+	} else if (uo->buffer) {
+		ret = vmw_kms_new_framebuffer_bo(dev_priv, uo->buffer, &vfb,
 						 mode_cmd);
 	} else {
 		BUG();
@@ -1635,14 +1521,12 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct vmw_framebuffer *vfb = NULL;
-	struct vmw_surface *surface = NULL;
-	struct vmw_bo *bo = NULL;
+	struct vmw_user_object uo = {0};
 	int ret;
 
 	/* returns either a bo or surface */
-	ret = vmw_user_lookup_handle(dev_priv, file_priv,
-				     mode_cmd->handles[0],
-				     &surface, &bo);
+	ret = vmw_user_object_lookup(dev_priv, file_priv, mode_cmd->handles[0],
+				     &uo);
 	if (ret) {
 		DRM_ERROR("Invalid buffer object handle %u (0x%x).\n",
 			  mode_cmd->handles[0], mode_cmd->handles[0]);
@@ -1650,7 +1534,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	}
 
 
-	if (!bo &&
+	if (vmw_user_object_surface(&uo) &&
 	    !vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)) {
 		DRM_ERROR("Surface size cannot exceed %dx%d\n",
 			dev_priv->texture_max_width,
@@ -1659,20 +1543,15 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	}
 
 
-	vfb = vmw_kms_new_framebuffer(dev_priv, bo, surface,
-				      !(dev_priv->capabilities & SVGA_CAP_3D),
-				      mode_cmd);
+	vfb = vmw_kms_new_framebuffer(dev_priv, &uo, mode_cmd);
 	if (IS_ERR(vfb)) {
 		ret = PTR_ERR(vfb);
 		goto err_out;
 	}
 
 err_out:
-	/* vmw_user_lookup_handle takes one ref so does new_fb */
-	if (bo)
-		vmw_user_bo_unref(&bo);
-	if (surface)
-		vmw_surface_unreference(&surface);
+	/* vmw_user_object_lookup takes one ref so does new_fb */
+	vmw_user_object_unref(&uo);
 
 	if (ret) {
 		DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret);
@@ -2585,72 +2464,6 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv,
 }
 
 /**
- * vmw_kms_update_proxy - Helper function to update a proxy surface from
- * its backing MOB.
- *
- * @res: Pointer to the surface resource
- * @clips: Clip rects in framebuffer (surface) space.
- * @num_clips: Number of clips in @clips.
- * @increment: Integer with which to increment the clip counter when looping.
- * Used to skip a predetermined number of clip rects.
- *
- * This function makes sure the proxy surface is updated from its backing MOB
- * using the region given by @clips. The surface resource @res and its backing
- * MOB needs to be reserved and validated on call.
- */
-int vmw_kms_update_proxy(struct vmw_resource *res,
-			 const struct drm_clip_rect *clips,
-			 unsigned num_clips,
-			 int increment)
-{
-	struct vmw_private *dev_priv = res->dev_priv;
-	struct drm_vmw_size *size = &vmw_res_to_srf(res)->metadata.base_size;
-	struct {
-		SVGA3dCmdHeader header;
-		SVGA3dCmdUpdateGBImage body;
-	} *cmd;
-	SVGA3dBox *box;
-	size_t copy_size = 0;
-	int i;
-
-	if (!clips)
-		return 0;
-
-	cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd) * num_clips);
-	if (!cmd)
-		return -ENOMEM;
-
-	for (i = 0; i < num_clips; ++i, clips += increment, ++cmd) {
-		box = &cmd->body.box;
-
-		cmd->header.id = SVGA_3D_CMD_UPDATE_GB_IMAGE;
-		cmd->header.size = sizeof(cmd->body);
-		cmd->body.image.sid = res->id;
-		cmd->body.image.face = 0;
-		cmd->body.image.mipmap = 0;
-
-		if (clips->x1 > size->width || clips->x2 > size->width ||
-		    clips->y1 > size->height || clips->y2 > size->height) {
-			DRM_ERROR("Invalid clips outsize of framebuffer.\n");
-			return -EINVAL;
-		}
-
-		box->x = clips->x1;
-		box->y = clips->y1;
-		box->z = 0;
-		box->w = clips->x2 - clips->x1;
-		box->h = clips->y2 - clips->y1;
-		box->d = 1;
-
-		copy_size += sizeof(*cmd);
-	}
-
-	vmw_cmd_commit(dev_priv, copy_size);
-
-	return 0;
-}
-
-/**
  * vmw_kms_create_implicit_placement_property - Set up the implicit placement
  * property.
  *
@@ -2784,8 +2597,9 @@ int vmw_du_helper_plane_update(struct vmw_du_update_plane *update)
 	} else {
 		struct vmw_framebuffer_surface *vfbs =
 			container_of(update->vfb, typeof(*vfbs), base);
+		struct vmw_surface *surf = vmw_user_object_surface(&vfbs->uo);
 
-		ret = vmw_validation_add_resource(&val_ctx, &vfbs->surface->res,
+		ret = vmw_validation_add_resource(&val_ctx, &surf->res,
 						  0, VMW_RES_DIRTY_NONE, NULL,
 						  NULL);
 	}
@@ -2941,3 +2755,93 @@ int vmw_connector_get_modes(struct drm_connector *connector)
 
 	return num_modes;
 }
+
+struct vmw_user_object *vmw_user_object_ref(struct vmw_user_object *uo)
+{
+	if (uo->buffer)
+		vmw_user_bo_ref(uo->buffer);
+	else if (uo->surface)
+		vmw_surface_reference(uo->surface);
+	return uo;
+}
+
+void vmw_user_object_unref(struct vmw_user_object *uo)
+{
+	if (uo->buffer)
+		vmw_user_bo_unref(&uo->buffer);
+	else if (uo->surface)
+		vmw_surface_unreference(&uo->surface);
+}
+
+struct vmw_bo *
+vmw_user_object_buffer(struct vmw_user_object *uo)
+{
+	if (uo->buffer)
+		return uo->buffer;
+	else if (uo->surface)
+		return uo->surface->res.guest_memory_bo;
+	return NULL;
+}
+
+struct vmw_surface *
+vmw_user_object_surface(struct vmw_user_object *uo)
+{
+	if (uo->buffer)
+		return uo->buffer->dumb_surface;
+	return uo->surface;
+}
+
+void *vmw_user_object_map(struct vmw_user_object *uo)
+{
+	struct vmw_bo *bo = vmw_user_object_buffer(uo);
+
+	WARN_ON(!bo);
+	return vmw_bo_map_and_cache(bo);
+}
+
+void *vmw_user_object_map_size(struct vmw_user_object *uo, size_t size)
+{
+	struct vmw_bo *bo = vmw_user_object_buffer(uo);
+
+	WARN_ON(!bo);
+	return vmw_bo_map_and_cache_size(bo, size);
+}
+
+void vmw_user_object_unmap(struct vmw_user_object *uo)
+{
+	struct vmw_bo *bo = vmw_user_object_buffer(uo);
+	int ret;
+
+	WARN_ON(!bo);
+
+	/* Fence the mob creation so we are guarateed to have the mob */
+	ret = ttm_bo_reserve(&bo->tbo, false, false, NULL);
+	if (ret != 0)
+		return;
+
+	vmw_bo_unmap(bo);
+	vmw_bo_pin_reserved(bo, false);
+
+	ttm_bo_unreserve(&bo->tbo);
+}
+
+bool vmw_user_object_is_mapped(struct vmw_user_object *uo)
+{
+	struct vmw_bo *bo;
+
+	if (!uo || vmw_user_object_is_null(uo))
+		return false;
+
+	bo = vmw_user_object_buffer(uo);
+
+	if (WARN_ON(!bo))
+		return false;
+
+	WARN_ON(bo->map.bo && !bo->map.virtual);
+	return bo->map.virtual;
+}
+
+bool vmw_user_object_is_null(struct vmw_user_object *uo)
+{
+	return !uo->buffer && !uo->surface;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index bf24f2f0dc..6141fadf81 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -221,11 +222,9 @@ struct vmw_framebuffer {
 
 struct vmw_framebuffer_surface {
 	struct vmw_framebuffer base;
-	struct vmw_surface *surface;
-	bool is_bo_proxy;  /* true if this is proxy surface for DMA buf */
+	struct vmw_user_object uo;
 };
 
-
 struct vmw_framebuffer_bo {
 	struct vmw_framebuffer base;
 	struct vmw_bo *buffer;
@@ -277,8 +276,7 @@ struct vmw_cursor_plane_state {
  */
 struct vmw_plane_state {
 	struct drm_plane_state base;
-	struct vmw_surface *surf;
-	struct vmw_bo *bo;
+	struct vmw_user_object uo;
 
 	int content_fb_type;
 	unsigned long bo_size;
@@ -457,9 +455,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
 		     uint32_t num_clips);
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_bo *bo,
-			struct vmw_surface *surface,
-			bool only_2d,
+			struct vmw_user_object *uo,
 			const struct drm_mode_fb_cmd2 *mode_cmd);
 void vmw_guess_mode_timing(struct drm_display_mode *mode);
 void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv);
@@ -486,8 +482,7 @@ void vmw_du_plane_reset(struct drm_plane *plane);
 struct drm_plane_state *vmw_du_plane_duplicate_state(struct drm_plane *plane);
 void vmw_du_plane_destroy_state(struct drm_plane *plane,
 				struct drm_plane_state *state);
-void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps,
-			     bool unreference);
+void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps);
 
 int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
 			     struct drm_atomic_state *state);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 5befc2719a..39949e0a49 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -147,8 +148,9 @@ static int vmw_ldu_fb_pin(struct vmw_framebuffer *vfb)
 	struct vmw_bo *buf;
 	int ret;
 
-	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
-		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.guest_memory_bo;
+	buf = vfb->bo ?
+		vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+		vmw_user_object_buffer(&vmw_framebuffer_to_vfbs(&vfb->base)->uo);
 
 	if (!buf)
 		return 0;
@@ -169,8 +171,10 @@ static int vmw_ldu_fb_unpin(struct vmw_framebuffer *vfb)
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
 	struct vmw_bo *buf;
 
-	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
-		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.guest_memory_bo;
+	buf = vfb->bo ?
+		vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+		vmw_user_object_buffer(&vmw_framebuffer_to_vfbs(&vfb->base)->uo);
+
 
 	if (WARN_ON(!buf))
 		return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index c45b4724e4..e20f64b67b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -92,7 +92,7 @@ static int vmw_overlay_send_put(struct vmw_private *dev_priv,
 {
 	struct vmw_escape_video_flush *flush;
 	size_t fifo_size;
-	bool have_so = (dev_priv->active_display_unit == vmw_du_screen_object);
+	bool have_so = (dev_priv->active_display_unit != vmw_du_legacy);
 	int i, num_items;
 	SVGAGuestPtr ptr;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index c99cad4449..598b90ac75 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2013 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2013-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -31,6 +32,7 @@
  */
 
 #include "vmwgfx_drv.h"
+#include "vmwgfx_bo.h"
 #include "ttm_object.h"
 #include <linux/dma-buf.h>
 
@@ -88,13 +90,35 @@ int vmw_prime_handle_to_fd(struct drm_device *dev,
 			   uint32_t handle, uint32_t flags,
 			   int *prime_fd)
 {
+	struct vmw_private *vmw = vmw_priv(dev);
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_bo *vbo;
 	int ret;
+	int surf_handle;
 
-	if (handle > VMWGFX_NUM_MOB)
+	if (handle > VMWGFX_NUM_MOB) {
 		ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
-	else
-		ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd);
+	} else {
+		ret = vmw_user_bo_lookup(file_priv, handle, &vbo);
+		if (ret)
+			return ret;
+		if (vbo && vbo->is_dumb) {
+			ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle,
+							 flags, prime_fd);
+		} else {
+			surf_handle = vmw_lookup_surface_handle_for_buffer(vmw,
+									   vbo,
+									   handle);
+			if (surf_handle > 0)
+				ret = ttm_prime_handle_to_fd(tfile, surf_handle,
+							     flags, prime_fd);
+			else
+				ret = drm_gem_prime_handle_to_fd(dev, file_priv,
+								 handle, flags,
+								 prime_fd);
+		}
+		vmw_user_bo_unref(&vbo);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 848dba0998..a73af8a355 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -58,6 +59,7 @@ void vmw_resource_mob_attach(struct vmw_resource *res)
 
 	rb_link_node(&res->mob_node, parent, new);
 	rb_insert_color(&res->mob_node, &gbo->res_tree);
+	vmw_bo_del_detached_resource(gbo, res);
 
 	vmw_bo_prio_add(gbo, res->used_prio);
 }
@@ -287,28 +289,35 @@ out_bad_resource:
  *
  * The pointer this pointed at by out_surf and out_buf needs to be null.
  */
-int vmw_user_lookup_handle(struct vmw_private *dev_priv,
+int vmw_user_object_lookup(struct vmw_private *dev_priv,
 			   struct drm_file *filp,
-			   uint32_t handle,
-			   struct vmw_surface **out_surf,
-			   struct vmw_bo **out_buf)
+			   u32 handle,
+			   struct vmw_user_object *uo)
 {
 	struct ttm_object_file *tfile = vmw_fpriv(filp)->tfile;
 	struct vmw_resource *res;
 	int ret;
 
-	BUG_ON(*out_surf || *out_buf);
+	WARN_ON(uo->surface || uo->buffer);
 
 	ret = vmw_user_resource_lookup_handle(dev_priv, tfile, handle,
 					      user_surface_converter,
 					      &res);
 	if (!ret) {
-		*out_surf = vmw_res_to_srf(res);
+		uo->surface = vmw_res_to_srf(res);
 		return 0;
 	}
 
-	*out_surf = NULL;
-	ret = vmw_user_bo_lookup(filp, handle, out_buf);
+	uo->surface = NULL;
+	ret = vmw_user_bo_lookup(filp, handle, &uo->buffer);
+	if (!ret && !uo->buffer->is_dumb) {
+		uo->surface = vmw_lookup_surface_for_buffer(dev_priv,
+							    uo->buffer,
+							    handle);
+		if (uo->surface)
+			vmw_user_bo_unref(&uo->buffer);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index df0039a8ef..0f4bfd9848 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2011-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2011-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -240,7 +241,7 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 		struct vmw_connector_state *vmw_conn_state;
 		int x, y;
 
-		sou->buffer = vps->bo;
+		sou->buffer = vmw_user_object_buffer(&vps->uo);
 
 		conn_state = sou->base.connector.state;
 		vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
@@ -376,10 +377,11 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane,
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
 	struct drm_crtc *crtc = plane->state->crtc ?
 		plane->state->crtc : old_state->crtc;
+	struct vmw_bo *bo = vmw_user_object_buffer(&vps->uo);
 
-	if (vps->bo)
-		vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false);
-	vmw_bo_unreference(&vps->bo);
+	if (bo)
+		vmw_bo_unpin(vmw_priv(crtc->dev), bo, false);
+	vmw_user_object_unref(&vps->uo);
 	vps->bo_size = 0;
 
 	vmw_du_plane_cleanup_fb(plane, old_state);
@@ -411,9 +413,10 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 		.bo_type = ttm_bo_type_device,
 		.pin = true
 	};
+	struct vmw_bo *bo = NULL;
 
 	if (!new_fb) {
-		vmw_bo_unreference(&vps->bo);
+		vmw_user_object_unref(&vps->uo);
 		vps->bo_size = 0;
 
 		return 0;
@@ -422,17 +425,17 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	bo_params.size = new_state->crtc_w * new_state->crtc_h * 4;
 	dev_priv = vmw_priv(crtc->dev);
 
-	if (vps->bo) {
+	bo = vmw_user_object_buffer(&vps->uo);
+	if (bo) {
 		if (vps->bo_size == bo_params.size) {
 			/*
 			 * Note that this might temporarily up the pin-count
 			 * to 2, until cleanup_fb() is called.
 			 */
-			return vmw_bo_pin_in_vram(dev_priv, vps->bo,
-						      true);
+			return vmw_bo_pin_in_vram(dev_priv, bo, true);
 		}
 
-		vmw_bo_unreference(&vps->bo);
+		vmw_user_object_unref(&vps->uo);
 		vps->bo_size = 0;
 	}
 
@@ -442,7 +445,7 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	 * resume the overlays, this is preferred to failing to alloc.
 	 */
 	vmw_overlay_pause_all(dev_priv);
-	ret = vmw_bo_create(dev_priv, &bo_params, &vps->bo);
+	ret = vmw_gem_object_create(dev_priv, &bo_params, &vps->uo.buffer);
 	vmw_overlay_resume_all(dev_priv);
 	if (ret)
 		return ret;
@@ -453,7 +456,7 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	 * TTM already thinks the buffer is pinned, but make sure the
 	 * pin_count is upped.
 	 */
-	return vmw_bo_pin_in_vram(dev_priv, vps->bo, true);
+	return vmw_bo_pin_in_vram(dev_priv, vps->uo.buffer, true);
 }
 
 static uint32_t vmw_sou_bo_fifo_size(struct vmw_du_update_plane *update,
@@ -580,6 +583,7 @@ static uint32_t vmw_sou_surface_pre_clip(struct vmw_du_update_plane *update,
 {
 	struct vmw_kms_sou_dirty_cmd *blit = cmd;
 	struct vmw_framebuffer_surface *vfbs;
+	struct vmw_surface *surf = NULL;
 
 	vfbs = container_of(update->vfb, typeof(*vfbs), base);
 
@@ -587,7 +591,8 @@ static uint32_t vmw_sou_surface_pre_clip(struct vmw_du_update_plane *update,
 	blit->header.size = sizeof(blit->body) + sizeof(SVGASignedRect) *
 		num_hits;
 
-	blit->body.srcImage.sid = vfbs->surface->res.id;
+	surf = vmw_user_object_surface(&vfbs->uo);
+	blit->body.srcImage.sid = surf->res.id;
 	blit->body.destScreenId = update->du->unit;
 
 	/* Update the source and destination bounding box later in post_clip */
@@ -1104,7 +1109,7 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 	int ret;
 
 	if (!srf)
-		srf = &vfbs->surface->res;
+		srf = &vmw_user_object_surface(&vfbs->uo)->res;
 
 	ret = vmw_validation_add_resource(&val_ctx, srf, 0, VMW_RES_DIRTY_NONE,
 					  NULL, NULL);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index a04e073631..5453f7cf0e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /******************************************************************************
  *
- * COPYRIGHT (C) 2014-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2014-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -29,6 +30,7 @@
 #include "vmwgfx_kms.h"
 #include "vmwgfx_vkms.h"
 #include "vmw_surface_cache.h"
+#include <linux/fsnotify.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -735,7 +737,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	int ret;
 
 	if (!srf)
-		srf = &vfbs->surface->res;
+		srf = &vmw_user_object_surface(&vfbs->uo)->res;
 
 	ret = vmw_validation_add_resource(&val_ctx, srf, 0, VMW_RES_DIRTY_NONE,
 					  NULL, NULL);
@@ -746,12 +748,6 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		goto out_unref;
 
-	if (vfbs->is_bo_proxy) {
-		ret = vmw_kms_update_proxy(srf, clips, num_clips, inc);
-		if (ret)
-			goto out_finish;
-	}
-
 	sdirty.base.fifo_commit = vmw_kms_stdu_surface_fifo_commit;
 	sdirty.base.clip = vmw_kms_stdu_surface_clip;
 	sdirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_surface_copy) +
@@ -765,7 +761,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips,
 				   dest_x, dest_y, num_clips, inc,
 				   &sdirty.base);
-out_finish:
+
 	vmw_kms_helper_validation_finish(dev_priv, NULL, &val_ctx, out_fence,
 					 NULL);
 
@@ -877,6 +873,32 @@ vmw_stdu_connector_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
+/*
+ * Trigger a modeset if the X,Y position of the Screen Target changes.
+ * This is needed when multi-mon is cycled. The original Screen Target will have
+ * the same mode but its relative X,Y position in the topology will change.
+ */
+static int vmw_stdu_connector_atomic_check(struct drm_connector *conn,
+					   struct drm_atomic_state *state)
+{
+	struct drm_connector_state *conn_state;
+	struct vmw_screen_target_display_unit *du;
+	struct drm_crtc_state *new_crtc_state;
+
+	conn_state = drm_atomic_get_connector_state(state, conn);
+	du = vmw_connector_to_stdu(conn);
+
+	if (!conn_state->crtc)
+		return 0;
+
+	new_crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
+	if (du->base.gui_x != du->base.set_gui_x ||
+	    du->base.gui_y != du->base.set_gui_y)
+		new_crtc_state->mode_changed = true;
+
+	return 0;
+}
+
 static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 	.dpms = vmw_du_connector_dpms,
 	.detect = vmw_du_connector_detect,
@@ -891,7 +913,8 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
 static const struct
 drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = {
 	.get_modes = vmw_connector_get_modes,
-	.mode_valid = vmw_stdu_connector_mode_valid
+	.mode_valid = vmw_stdu_connector_mode_valid,
+	.atomic_check = vmw_stdu_connector_atomic_check,
 };
 
 
@@ -918,9 +941,8 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
 {
 	struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
 
-	if (vps->surf)
+	if (vmw_user_object_surface(&vps->uo))
 		WARN_ON(!vps->pinned);
-
 	vmw_du_plane_cleanup_fb(plane, old_state);
 
 	vps->content_fb_type = SAME_AS_DISPLAY;
@@ -928,7 +950,6 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
 }
 
 
-
 /**
  * vmw_stdu_primary_plane_prepare_fb - Readies the display surface
  *
@@ -952,13 +973,15 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	enum stdu_content_type new_content_type;
 	struct vmw_framebuffer_surface *new_vfbs;
 	uint32_t hdisplay = new_state->crtc_w, vdisplay = new_state->crtc_h;
+	struct drm_plane_state *old_state = plane->state;
+	struct drm_rect rect;
 	int ret;
 
 	/* No FB to prepare */
 	if (!new_fb) {
-		if (vps->surf) {
+		if (vmw_user_object_surface(&vps->uo)) {
 			WARN_ON(vps->pinned != 0);
-			vmw_surface_unreference(&vps->surf);
+			vmw_user_object_unref(&vps->uo);
 		}
 
 		return 0;
@@ -968,8 +991,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
 
 	if (new_vfbs &&
-	    new_vfbs->surface->metadata.base_size.width == hdisplay &&
-	    new_vfbs->surface->metadata.base_size.height == vdisplay)
+	    vmw_user_object_surface(&new_vfbs->uo)->metadata.base_size.width == hdisplay &&
+	    vmw_user_object_surface(&new_vfbs->uo)->metadata.base_size.height == vdisplay)
 		new_content_type = SAME_AS_DISPLAY;
 	else if (vfb->bo)
 		new_content_type = SEPARATE_BO;
@@ -1007,29 +1030,29 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			metadata.num_sizes = 1;
 			metadata.scanout = true;
 		} else {
-			metadata = new_vfbs->surface->metadata;
+			metadata = vmw_user_object_surface(&new_vfbs->uo)->metadata;
 		}
 
 		metadata.base_size.width = hdisplay;
 		metadata.base_size.height = vdisplay;
 		metadata.base_size.depth = 1;
 
-		if (vps->surf) {
+		if (vmw_user_object_surface(&vps->uo)) {
 			struct drm_vmw_size cur_base_size =
-				vps->surf->metadata.base_size;
+				vmw_user_object_surface(&vps->uo)->metadata.base_size;
 
 			if (cur_base_size.width != metadata.base_size.width ||
 			    cur_base_size.height != metadata.base_size.height ||
-			    vps->surf->metadata.format != metadata.format) {
+			    vmw_user_object_surface(&vps->uo)->metadata.format != metadata.format) {
 				WARN_ON(vps->pinned != 0);
-				vmw_surface_unreference(&vps->surf);
+				vmw_user_object_unref(&vps->uo);
 			}
 
 		}
 
-		if (!vps->surf) {
+		if (!vmw_user_object_surface(&vps->uo)) {
 			ret = vmw_gb_surface_define(dev_priv, &metadata,
-						    &vps->surf);
+						    &vps->uo.surface);
 			if (ret != 0) {
 				DRM_ERROR("Couldn't allocate STDU surface.\n");
 				return ret;
@@ -1042,18 +1065,19 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 		 * The only time we add a reference in prepare_fb is if the
 		 * state object doesn't have a reference to begin with
 		 */
-		if (vps->surf) {
+		if (vmw_user_object_surface(&vps->uo)) {
 			WARN_ON(vps->pinned != 0);
-			vmw_surface_unreference(&vps->surf);
+			vmw_user_object_unref(&vps->uo);
 		}
 
-		vps->surf = vmw_surface_reference(new_vfbs->surface);
+		memcpy(&vps->uo, &new_vfbs->uo, sizeof(vps->uo));
+		vmw_user_object_ref(&vps->uo);
 	}
 
-	if (vps->surf) {
+	if (vmw_user_object_surface(&vps->uo)) {
 
 		/* Pin new surface before flipping */
-		ret = vmw_resource_pin(&vps->surf->res, false);
+		ret = vmw_resource_pin(&vmw_user_object_surface(&vps->uo)->res, false);
 		if (ret)
 			goto out_srf_unref;
 
@@ -1063,6 +1087,34 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	vps->content_fb_type = new_content_type;
 
 	/*
+	 * The drm fb code will do blit's via the vmap interface, which doesn't
+	 * trigger vmw_bo page dirty tracking due to being kernel side (and thus
+	 * doesn't require mmap'ing) so we have to update the surface's dirty
+	 * regions by hand but we want to be careful to not overwrite the
+	 * resource if it has been written to by the gpu (res_dirty).
+	 */
+	if (vps->uo.buffer && vps->uo.buffer->is_dumb) {
+		struct vmw_surface *surf = vmw_user_object_surface(&vps->uo);
+		struct vmw_resource *res = &surf->res;
+
+		if (!res->res_dirty && drm_atomic_helper_damage_merged(old_state,
+								       new_state,
+								       &rect)) {
+			/*
+			 * At some point it might be useful to actually translate
+			 * (rect.x1, rect.y1) => start, and (rect.x2, rect.y2) => end,
+			 * but currently the fb code will just report the entire fb
+			 * dirty so in practice it doesn't matter.
+			 */
+			pgoff_t start = res->guest_memory_offset >> PAGE_SHIFT;
+			pgoff_t end = __KERNEL_DIV_ROUND_UP(res->guest_memory_offset +
+							    res->guest_memory_size,
+							    PAGE_SIZE);
+			vmw_resource_dirty_update(res, start, end);
+		}
+	}
+
+	/*
 	 * This should only happen if the buffer object is too large to create a
 	 * proxy surface for.
 	 */
@@ -1072,7 +1124,7 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	return 0;
 
 out_srf_unref:
-	vmw_surface_unreference(&vps->surf);
+	vmw_user_object_unref(&vps->uo);
 	return ret;
 }
 
@@ -1214,14 +1266,8 @@ static uint32_t
 vmw_stdu_surface_fifo_size_same_display(struct vmw_du_update_plane *update,
 					uint32_t num_hits)
 {
-	struct vmw_framebuffer_surface *vfbs;
 	uint32_t size = 0;
 
-	vfbs = container_of(update->vfb, typeof(*vfbs), base);
-
-	if (vfbs->is_bo_proxy)
-		size += sizeof(struct vmw_stdu_update_gb_image) * num_hits;
-
 	size += sizeof(struct vmw_stdu_update);
 
 	return size;
@@ -1230,14 +1276,8 @@ vmw_stdu_surface_fifo_size_same_display(struct vmw_du_update_plane *update,
 static uint32_t vmw_stdu_surface_fifo_size(struct vmw_du_update_plane *update,
 					   uint32_t num_hits)
 {
-	struct vmw_framebuffer_surface *vfbs;
 	uint32_t size = 0;
 
-	vfbs = container_of(update->vfb, typeof(*vfbs), base);
-
-	if (vfbs->is_bo_proxy)
-		size += sizeof(struct vmw_stdu_update_gb_image) * num_hits;
-
 	size += sizeof(struct vmw_stdu_surface_copy) + sizeof(SVGA3dCopyBox) *
 		num_hits + sizeof(struct vmw_stdu_update);
 
@@ -1245,47 +1285,6 @@ static uint32_t vmw_stdu_surface_fifo_size(struct vmw_du_update_plane *update,
 }
 
 static uint32_t
-vmw_stdu_surface_update_proxy(struct vmw_du_update_plane *update, void *cmd)
-{
-	struct vmw_framebuffer_surface *vfbs;
-	struct drm_plane_state *state = update->plane->state;
-	struct drm_plane_state *old_state = update->old_state;
-	struct vmw_stdu_update_gb_image *cmd_update = cmd;
-	struct drm_atomic_helper_damage_iter iter;
-	struct drm_rect clip;
-	uint32_t copy_size = 0;
-
-	vfbs = container_of(update->vfb, typeof(*vfbs), base);
-
-	/*
-	 * proxy surface is special where a buffer object type fb is wrapped
-	 * in a surface and need an update gb image command to sync with device.
-	 */
-	drm_atomic_helper_damage_iter_init(&iter, old_state, state);
-	drm_atomic_for_each_plane_damage(&iter, &clip) {
-		SVGA3dBox *box = &cmd_update->body.box;
-
-		cmd_update->header.id = SVGA_3D_CMD_UPDATE_GB_IMAGE;
-		cmd_update->header.size = sizeof(cmd_update->body);
-		cmd_update->body.image.sid = vfbs->surface->res.id;
-		cmd_update->body.image.face = 0;
-		cmd_update->body.image.mipmap = 0;
-
-		box->x = clip.x1;
-		box->y = clip.y1;
-		box->z = 0;
-		box->w = drm_rect_width(&clip);
-		box->h = drm_rect_height(&clip);
-		box->d = 1;
-
-		copy_size += sizeof(*cmd_update);
-		cmd_update++;
-	}
-
-	return copy_size;
-}
-
-static uint32_t
 vmw_stdu_surface_populate_copy(struct vmw_du_update_plane  *update, void *cmd,
 			       uint32_t num_hits)
 {
@@ -1299,7 +1298,7 @@ vmw_stdu_surface_populate_copy(struct vmw_du_update_plane  *update, void *cmd,
 	cmd_copy->header.id = SVGA_3D_CMD_SURFACE_COPY;
 	cmd_copy->header.size = sizeof(cmd_copy->body) + sizeof(SVGA3dCopyBox) *
 		num_hits;
-	cmd_copy->body.src.sid = vfbs->surface->res.id;
+	cmd_copy->body.src.sid = vmw_user_object_surface(&vfbs->uo)->res.id;
 	cmd_copy->body.dest.sid = stdu->display_srf->res.id;
 
 	return sizeof(*cmd_copy);
@@ -1370,10 +1369,7 @@ static int vmw_stdu_plane_update_surface(struct vmw_private *dev_priv,
 	srf_update.mutex = &dev_priv->cmdbuf_mutex;
 	srf_update.intr = true;
 
-	if (vfbs->is_bo_proxy)
-		srf_update.post_prepare = vmw_stdu_surface_update_proxy;
-
-	if (vfbs->surface->res.id != stdu->display_srf->res.id) {
+	if (vmw_user_object_surface(&vfbs->uo)->res.id != stdu->display_srf->res.id) {
 		srf_update.calc_fifo_size = vmw_stdu_surface_fifo_size;
 		srf_update.pre_clip = vmw_stdu_surface_populate_copy;
 		srf_update.clip = vmw_stdu_surface_populate_clip;
@@ -1417,7 +1413,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 		stdu = vmw_crtc_to_stdu(crtc);
 		dev_priv = vmw_priv(crtc->dev);
 
-		stdu->display_srf = vps->surf;
+		stdu->display_srf = vmw_user_object_surface(&vps->uo);
 		stdu->content_fb_type = vps->content_fb_type;
 		stdu->cpp = vps->cpp;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index e7a744dfce..8ae6a761c9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
@@ -36,9 +37,6 @@
 #include <drm/ttm/ttm_placement.h>
 
 #define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
-#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32)
-#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
-	(svga3d_flags & ((uint64_t)U32_MAX))
 
 /**
  * struct vmw_user_surface - User-space visible surface resource
@@ -686,6 +684,14 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base)
 	struct vmw_resource *res = &user_srf->srf.res;
 
 	*p_base = NULL;
+
+	/*
+	 * Dumb buffers own the resource and they'll unref the
+	 * resource themselves
+	 */
+	if (res && res->guest_memory_bo && res->guest_memory_bo->is_dumb)
+		return;
+
 	vmw_resource_unreference(&res);
 }
 
@@ -812,7 +818,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 	res->guest_memory_size = cur_bo_offset;
-	if (metadata->scanout &&
+	if (!file_priv->atomic &&
+	    metadata->scanout &&
 	    metadata->num_sizes == 1 &&
 	    metadata->sizes[0].width == VMW_CURSOR_SNOOP_WIDTH &&
 	    metadata->sizes[0].height == VMW_CURSOR_SNOOP_HEIGHT &&
@@ -864,6 +871,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 			vmw_resource_unreference(&res);
 			goto out_unlock;
 		}
+		vmw_bo_add_detached_resource(res->guest_memory_bo, res);
 	}
 
 	tmp = vmw_resource_reference(&srf->res);
@@ -892,6 +900,113 @@ out_unlock:
 	return ret;
 }
 
+static struct vmw_user_surface *
+vmw_lookup_user_surface_for_buffer(struct vmw_private *vmw, struct vmw_bo *bo,
+				   u32 handle)
+{
+	struct vmw_user_surface *user_srf = NULL;
+	struct vmw_surface *surf;
+	struct ttm_base_object *base;
+
+	surf = vmw_bo_surface(bo);
+	if (surf) {
+		rcu_read_lock();
+		user_srf = container_of(surf, struct vmw_user_surface, srf);
+		base = &user_srf->prime.base;
+		if (base && !kref_get_unless_zero(&base->refcount)) {
+			drm_dbg_driver(&vmw->drm,
+				       "%s: referencing a stale surface handle %d\n",
+					__func__, handle);
+			base = NULL;
+			user_srf = NULL;
+		}
+		rcu_read_unlock();
+	}
+
+	return user_srf;
+}
+
+struct vmw_surface *vmw_lookup_surface_for_buffer(struct vmw_private *vmw,
+						  struct vmw_bo *bo,
+						  u32 handle)
+{
+	struct vmw_user_surface *user_srf =
+		vmw_lookup_user_surface_for_buffer(vmw, bo, handle);
+	struct vmw_surface *surf = NULL;
+	struct ttm_base_object *base;
+
+	if (user_srf) {
+		surf = vmw_surface_reference(&user_srf->srf);
+		base = &user_srf->prime.base;
+		ttm_base_object_unref(&base);
+	}
+	return surf;
+}
+
+u32 vmw_lookup_surface_handle_for_buffer(struct vmw_private *vmw,
+					 struct vmw_bo *bo,
+					 u32 handle)
+{
+	struct vmw_user_surface *user_srf =
+		vmw_lookup_user_surface_for_buffer(vmw, bo, handle);
+	int surf_handle = 0;
+	struct ttm_base_object *base;
+
+	if (user_srf) {
+		base = &user_srf->prime.base;
+		surf_handle = (u32)base->handle;
+		ttm_base_object_unref(&base);
+	}
+	return surf_handle;
+}
+
+static int vmw_buffer_prime_to_surface_base(struct vmw_private *dev_priv,
+					    struct drm_file *file_priv,
+					    u32 fd, u32 *handle,
+					    struct ttm_base_object **base_p)
+{
+	struct ttm_base_object *base;
+	struct vmw_bo *bo;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_user_surface *user_srf;
+	int ret;
+
+	ret = drm_gem_prime_fd_to_handle(&dev_priv->drm, file_priv, fd, handle);
+	if (ret) {
+		drm_warn(&dev_priv->drm,
+			 "Wasn't able to find user buffer for fd = %u.\n", fd);
+		return ret;
+	}
+
+	ret = vmw_user_bo_lookup(file_priv, *handle, &bo);
+	if (ret) {
+		drm_warn(&dev_priv->drm,
+			 "Wasn't able to lookup user buffer for handle = %u.\n", *handle);
+		return ret;
+	}
+
+	user_srf = vmw_lookup_user_surface_for_buffer(dev_priv, bo, *handle);
+	if (WARN_ON(!user_srf)) {
+		drm_warn(&dev_priv->drm,
+			 "User surface fd %d (handle %d) is null.\n", fd, *handle);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	base = &user_srf->prime.base;
+	ret = ttm_ref_object_add(tfile, base, NULL, false);
+	if (ret) {
+		drm_warn(&dev_priv->drm,
+			 "Couldn't add an object ref for the buffer (%d).\n", *handle);
+		goto out;
+	}
+
+	*base_p = base;
+out:
+	vmw_user_bo_unref(&bo);
+
+	return ret;
+}
 
 static int
 vmw_surface_handle_reference(struct vmw_private *dev_priv,
@@ -901,15 +1016,19 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 			     struct ttm_base_object **base_p)
 {
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_user_surface *user_srf;
+	struct vmw_user_surface *user_srf = NULL;
 	uint32_t handle;
 	struct ttm_base_object *base;
 	int ret;
 
 	if (handle_type == DRM_VMW_HANDLE_PRIME) {
 		ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
-		if (unlikely(ret != 0))
-			return ret;
+		if (ret)
+			return vmw_buffer_prime_to_surface_base(dev_priv,
+								file_priv,
+								u_handle,
+								&handle,
+								base_p);
 	} else {
 		handle = u_handle;
 	}
@@ -1503,7 +1622,12 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 		ret = vmw_user_bo_lookup(file_priv, req->base.buffer_handle,
 					 &res->guest_memory_bo);
 		if (ret == 0) {
-			if (res->guest_memory_bo->tbo.base.size < res->guest_memory_size) {
+			if (res->guest_memory_bo->is_dumb) {
+				VMW_DEBUG_USER("Can't backup surface with a dumb buffer.\n");
+				vmw_user_bo_unref(&res->guest_memory_bo);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else if (res->guest_memory_bo->tbo.base.size < res->guest_memory_size) {
 				VMW_DEBUG_USER("Surface backup buffer too small.\n");
 				vmw_user_bo_unref(&res->guest_memory_bo);
 				ret = -EINVAL;
@@ -1560,6 +1684,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 	rep->handle      = user_srf->prime.base.handle;
 	rep->backup_size = res->guest_memory_size;
 	if (res->guest_memory_bo) {
+		vmw_bo_add_detached_resource(res->guest_memory_bo, res);
 		rep->buffer_map_handle =
 			drm_vma_node_offset_addr(&res->guest_memory_bo->tbo.base.vma_node);
 		rep->buffer_size = res->guest_memory_bo->tbo.base.size;
@@ -2100,3 +2225,140 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv,
 out_unlock:
 	return ret;
 }
+
+static SVGA3dSurfaceFormat vmw_format_bpp_to_svga(struct vmw_private *vmw,
+						  int bpp)
+{
+	switch (bpp) {
+	case 8: /* DRM_FORMAT_C8 */
+		return SVGA3D_P8;
+	case 16: /* DRM_FORMAT_RGB565 */
+		return SVGA3D_R5G6B5;
+	case 32: /* DRM_FORMAT_XRGB8888 */
+		if (has_sm4_context(vmw))
+			return SVGA3D_B8G8R8X8_UNORM;
+		return SVGA3D_X8R8G8B8;
+	default:
+		drm_warn(&vmw->drm, "Unsupported format bpp: %d\n", bpp);
+		return SVGA3D_X8R8G8B8;
+	}
+}
+
+/**
+ * vmw_dumb_create - Create a dumb kms buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @args: Pointer to a struct drm_mode_create_dumb structure
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm create_dumb functionality.
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
+ * that the arguments have a different format.
+ */
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_bo *vbo = NULL;
+	struct vmw_resource *res = NULL;
+	union drm_vmw_gb_surface_create_ext_arg arg = { 0 };
+	struct drm_vmw_gb_surface_create_ext_req *req = &arg.req;
+	int ret;
+	struct drm_vmw_size drm_size = {
+		.width = args->width,
+		.height = args->height,
+		.depth = 1,
+	};
+	SVGA3dSurfaceFormat format = vmw_format_bpp_to_svga(dev_priv, args->bpp);
+	const struct SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
+	SVGA3dSurfaceAllFlags flags = SVGA3D_SURFACE_HINT_TEXTURE |
+				      SVGA3D_SURFACE_HINT_RENDERTARGET |
+				      SVGA3D_SURFACE_SCREENTARGET |
+				      SVGA3D_SURFACE_BIND_SHADER_RESOURCE |
+				      SVGA3D_SURFACE_BIND_RENDER_TARGET;
+
+	/*
+	 * Without mob support we're just going to use raw memory buffer
+	 * because we wouldn't be able to support full surface coherency
+	 * without mobs
+	 */
+	if (!dev_priv->has_mob) {
+		int cpp = DIV_ROUND_UP(args->bpp, 8);
+
+		switch (cpp) {
+		case 1: /* DRM_FORMAT_C8 */
+		case 2: /* DRM_FORMAT_RGB565 */
+		case 4: /* DRM_FORMAT_XRGB8888 */
+			break;
+		default:
+			/*
+			 * Dumb buffers don't allow anything else.
+			 * This is tested via IGT's dumb_buffers
+			 */
+			return -EINVAL;
+		}
+
+		args->pitch = args->width * cpp;
+		args->size = ALIGN(args->pitch * args->height, PAGE_SIZE);
+
+		ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
+							args->size, &args->handle,
+							&vbo);
+		/* drop reference from allocate - handle holds it now */
+		drm_gem_object_put(&vbo->tbo.base);
+		return ret;
+	}
+
+	req->version = drm_vmw_gb_surface_v1;
+	req->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	req->quality_level = SVGA3D_MS_QUALITY_NONE;
+	req->buffer_byte_stride = 0;
+	req->must_be_zero = 0;
+	req->base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(flags);
+	req->svga3d_flags_upper_32_bits = SVGA3D_FLAGS_UPPER_32(flags);
+	req->base.format = (uint32_t)format;
+	req->base.drm_surface_flags = drm_vmw_surface_flag_scanout;
+	req->base.drm_surface_flags |= drm_vmw_surface_flag_shareable;
+	req->base.drm_surface_flags |= drm_vmw_surface_flag_create_buffer;
+	req->base.drm_surface_flags |= drm_vmw_surface_flag_coherent;
+	req->base.base_size.width = args->width;
+	req->base.base_size.height = args->height;
+	req->base.base_size.depth = 1;
+	req->base.array_size = 0;
+	req->base.mip_levels = 1;
+	req->base.multisample_count = 0;
+	req->base.buffer_handle = SVGA3D_INVALID_ID;
+	req->base.autogen_filter = SVGA3D_TEX_FILTER_NONE;
+	ret = vmw_gb_surface_define_ext_ioctl(dev, &arg, file_priv);
+	if (ret) {
+		drm_warn(dev, "Unable to create a dumb buffer\n");
+		return ret;
+	}
+
+	args->handle = arg.rep.buffer_handle;
+	args->size = arg.rep.buffer_size;
+	args->pitch = vmw_surface_calculate_pitch(desc, &drm_size);
+
+	ret = vmw_user_resource_lookup_handle(dev_priv, tfile, arg.rep.handle,
+					      user_surface_converter,
+					      &res);
+	if (ret) {
+		drm_err(dev, "Created resource handle doesn't exist!\n");
+		goto err;
+	}
+
+	vbo = res->guest_memory_bo;
+	vbo->is_dumb = true;
+	vbo->dumb_surface = vmw_res_to_srf(res);
+
+err:
+	if (res)
+		vmw_resource_unreference(&res);
+	if (ret)
+		ttm_ref_object_base_unref(tfile, arg.rep.handle);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
index 7e93a45948..ac002048d8 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
@@ -76,7 +76,7 @@ done:
 	return ret;
 }
 
-static int
+static void
 compute_crc(struct drm_crtc *crtc,
 	    struct vmw_surface *surf,
 	    u32 *crc)
@@ -102,8 +102,6 @@ compute_crc(struct drm_crtc *crtc,
 	}
 
 	vmw_bo_unmap(bo);
-
-	return 0;
 }
 
 static void
@@ -117,7 +115,6 @@ crc_generate_worker(struct work_struct *work)
 	u64 frame_start, frame_end;
 	u32 crc32 = 0;
 	struct vmw_surface *surf = 0;
-	int ret;
 
 	spin_lock_irq(&du->vkms.crc_state_lock);
 	crc_pending = du->vkms.crc_pending;
@@ -131,22 +128,24 @@ crc_generate_worker(struct work_struct *work)
 		return;
 
 	spin_lock_irq(&du->vkms.crc_state_lock);
-	surf = du->vkms.surface;
+	surf = vmw_surface_reference(du->vkms.surface);
 	spin_unlock_irq(&du->vkms.crc_state_lock);
 
-	if (vmw_surface_sync(vmw, surf)) {
-		drm_warn(crtc->dev, "CRC worker wasn't able to sync the crc surface!\n");
-		return;
-	}
+	if (surf) {
+		if (vmw_surface_sync(vmw, surf)) {
+			drm_warn(
+				crtc->dev,
+				"CRC worker wasn't able to sync the crc surface!\n");
+			return;
+		}
 
-	ret = compute_crc(crtc, surf, &crc32);
-	if (ret)
-		return;
+		compute_crc(crtc, surf, &crc32);
+		vmw_surface_unreference(&surf);
+	}
 
 	spin_lock_irq(&du->vkms.crc_state_lock);
 	frame_start = du->vkms.frame_start;
 	frame_end = du->vkms.frame_end;
-	crc_pending = du->vkms.crc_pending;
 	du->vkms.frame_start = 0;
 	du->vkms.frame_end = 0;
 	du->vkms.crc_pending = false;
@@ -165,7 +164,7 @@ vmw_vkms_vblank_simulate(struct hrtimer *timer)
 	struct vmw_display_unit *du = container_of(timer, struct vmw_display_unit, vkms.timer);
 	struct drm_crtc *crtc = &du->crtc;
 	struct vmw_private *vmw = vmw_priv(crtc->dev);
-	struct vmw_surface *surf = NULL;
+	bool has_surface = false;
 	u64 ret_overrun;
 	bool locked, ret;
 
@@ -180,10 +179,10 @@ vmw_vkms_vblank_simulate(struct hrtimer *timer)
 	WARN_ON(!ret);
 	if (!locked)
 		return HRTIMER_RESTART;
-	surf = du->vkms.surface;
+	has_surface = du->vkms.surface != NULL;
 	vmw_vkms_unlock(crtc);
 
-	if (du->vkms.crc_enabled && surf) {
+	if (du->vkms.crc_enabled && has_surface) {
 		u64 frame = drm_crtc_accurate_vblank_count(crtc);
 
 		spin_lock(&du->vkms.crc_state_lock);
@@ -337,6 +336,8 @@ vmw_vkms_crtc_cleanup(struct drm_crtc *crtc)
 {
 	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
 
+	if (du->vkms.surface)
+		vmw_surface_unreference(&du->vkms.surface);
 	WARN_ON(work_pending(&du->vkms.crc_generator_work));
 	hrtimer_cancel(&du->vkms.timer);
 }
@@ -498,9 +499,12 @@ vmw_vkms_set_crc_surface(struct drm_crtc *crtc,
 	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
 	struct vmw_private *vmw = vmw_priv(crtc->dev);
 
-	if (vmw->vkms_enabled) {
+	if (vmw->vkms_enabled && du->vkms.surface != surf) {
 		WARN_ON(atomic_read(&du->vkms.atomic_lock) != VMW_VKMS_LOCK_MODESET);
-		du->vkms.surface = surf;
+		if (du->vkms.surface)
+			vmw_surface_unreference(&du->vkms.surface);
+		if (surf)
+			du->vkms.surface = vmw_surface_reference(surf);
 	}
 }
 
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
index bdb578e089..4b59687ff5 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
@@ -288,12 +288,22 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
 		mp2_ops->start(privdata, info);
 		cl_data->sensor_sts[i] = amd_sfh_wait_for_response
 						(privdata, cl_data->sensor_idx[i], SENSOR_ENABLED);
+
+		if (cl_data->sensor_sts[i] == SENSOR_ENABLED)
+			cl_data->is_any_sensor_enabled = true;
+	}
+
+	if (!cl_data->is_any_sensor_enabled ||
+	    (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) {
+		dev_warn(dev, "Failed to discover, sensors not enabled is %d\n",
+			 cl_data->is_any_sensor_enabled);
+		rc = -EOPNOTSUPP;
+		goto cleanup;
 	}
 
 	for (i = 0; i < cl_data->num_hid_devices; i++) {
 		cl_data->cur_hid_dev = i;
 		if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
-			cl_data->is_any_sensor_enabled = true;
 			rc = amdtp_hid_probe(i, cl_data);
 			if (rc)
 				goto cleanup;
@@ -305,12 +315,6 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
 			cl_data->sensor_sts[i]);
 	}
 
-	if (!cl_data->is_any_sensor_enabled ||
-	   (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) {
-		dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled);
-		rc = -EOPNOTSUPP;
-		goto cleanup;
-	}
 	schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP));
 	return 0;
 
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index a44367aef6..20de97ce0f 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -714,13 +714,12 @@ static int wacom_intuos_get_tool_type(int tool_id)
 	case 0x8e2: /* IntuosHT2 pen */
 	case 0x022:
 	case 0x200: /* Pro Pen 3 */
-	case 0x04200: /* Pro Pen 3 */
 	case 0x10842: /* MobileStudio Pro Pro Pen slim */
 	case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */
 	case 0x16802: /* Cintiq 13HD Pro Pen */
 	case 0x18802: /* DTH2242 Pen */
 	case 0x10802: /* Intuos4/5 13HD/24HD General Pen */
-	case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */
+	case 0x8842: /* Intuos Pro and Cintiq Pro 3D Pen */
 		tool_type = BTN_TOOL_PEN;
 		break;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 43952689bf..23627c973e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7491,8 +7491,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num);
 static int __bnxt_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_rings hwr = {0};
+	int rx_rings, old_rx_rings, rc;
 	int cp = bp->cp_nr_rings;
-	int rx_rings, rc;
 	int ulp_msix = 0;
 	bool sh = false;
 	int tx_cp;
@@ -7526,6 +7526,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	hwr.grp = bp->rx_nr_rings;
 	hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	hwr.stat = bnxt_get_func_stat_ctxs(bp);
+	old_rx_rings = bp->hw_resc.resv_rx_rings;
 
 	rc = bnxt_hwrm_reserve_rings(bp, &hwr);
 	if (rc)
@@ -7580,7 +7581,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	if (!bnxt_rings_ok(bp, &hwr))
 		return -ENOMEM;
 
-	if (!netif_is_rxfh_configured(bp->dev))
+	if (old_rx_rings != bp->hw_resc.resv_rx_rings &&
+	    !netif_is_rxfh_configured(bp->dev))
 		bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 
 	if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 99a75a5907..caaa101579 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
 }
 
 /**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
  */
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
 {
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	return ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
@@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5d396c1a77..1facf179a9 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 				return err;
 		}
 
-		ring->xsk_pool = ice_xsk_pool(ring);
+		ice_rx_xsk_pool(ring);
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return 0;
 		}
 
-		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
 		if (!ok) {
 			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 55a42aad92..9b075dd488 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2949,7 +2949,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
 	ice_for_each_rxq(vsi, i) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
 
-		if (rx_ring->xsk_pool)
+		if (READ_ONCE(rx_ring->xsk_pool))
 			napi_schedule(&rx_ring->q_vector->napi);
 	}
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8bb743f78f..8d25b69812 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 	if (rx_ring->vsi->type == ICE_VSI_PF)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	rx_ring->xdp_prog = NULL;
+	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
@@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
@@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
@@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a65955eb23..240a7bec24 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi)) {
-		synchronize_rcu();
+	if (ice_is_xdp_ena_vsi(vsi))
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
-	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
@@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
  * ice_qvec_cfg_msix - Enable IRQ for given queue vector
  * @vsi: the VSI that contains queue vector
  * @q_vector: queue vector
+ * @qid: queue index
  */
 static void
-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
 {
 	u16 reg_idx = q_vector->reg_idx;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
+	int q, _qid = qid;
 
 	ice_cfg_itr(hw, q_vector);
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
-				      q_vector->tx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_tx; q++) {
+		ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
+		_qid++;
+	}
+
+	_qid = qid;
 
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
-				      q_vector->rx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_rx; q++) {
+		ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
+		_qid++;
+	}
 
 	ice_flush(hw);
 }
@@ -164,6 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	struct ice_tx_ring *tx_ring;
 	struct ice_rx_ring *rx_ring;
 	int timeout = 50;
+	int fail = 0;
 	int err;
 
 	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
@@ -180,15 +183,17 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		usleep_range(1000, 2000);
 	}
 
+	synchronize_net();
+	netif_carrier_off(vsi->netdev);
+	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+
 	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 
-	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
 	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
@@ -196,17 +201,15 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
 		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
 					   &txq_meta);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 	}
-	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
-	if (err)
-		return err;
 
+	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -219,40 +222,48 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 {
 	struct ice_q_vector *q_vector;
+	int fail = 0;
+	bool link_up;
 	int err;
 
 	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
 		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 		ice_set_ring_xdp(xdp_ring);
 		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	q_vector = vsi->rx_rings[q_idx]->q_vector;
-	ice_qvec_cfg_msix(vsi, q_vector);
+	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
 
 	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
-	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
+	ice_get_link_status(vsi->port_info, &link_up);
+	if (link_up) {
+		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+		netif_carrier_on(vsi->netdev);
+	}
 	clear_bit(ICE_CFG_BUSY, vsi->state);
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -459,6 +470,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 /**
  * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Place the @count of descriptors onto Rx ring. Handle the ring wrap
@@ -467,7 +479,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
  *
  * Returns true if all allocations were successful, false if any fail.
  */
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+				   struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
@@ -479,8 +492,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	if (ntu + count >= rx_ring->count) {
-		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
-						   rx_desc,
+		nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
 						   rx_ring->count - ntu);
 		if (nb_buffs_extra != rx_ring->count - ntu) {
 			ntu += nb_buffs_extra;
@@ -493,7 +505,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+	nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
 
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count)
@@ -509,6 +521,7 @@ exit:
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Wrapper for internal allocation routine; figure out how many tail
@@ -516,7 +529,8 @@ exit:
  *
  * Returns true if all calls to internal alloc routine succeeded
  */
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
 	u16 leftover, i, tail_bumps;
@@ -525,9 +539,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
-		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
 			return false;
-	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+	return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
 }
 
 /**
@@ -596,8 +610,10 @@ out:
 /**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  */
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -648,7 +664,7 @@ skip:
 	if (xdp_ring->next_to_clean >= cnt)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		xsk_tx_completed(xsk_pool, xsk_frames);
 
 	return completed_frames;
 }
@@ -657,6 +673,7 @@ skip:
  * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
  * @xdp: XDP buffer to xmit
  * @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * note that this function works directly on xdp_buff, no need to convert
  * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
@@ -666,7 +683,8 @@ skip:
  * was not enough space on XDP ring
  */
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
-			      struct ice_tx_ring *xdp_ring)
+			      struct ice_tx_ring *xdp_ring,
+			      struct xsk_buff_pool *xsk_pool)
 {
 	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
@@ -680,7 +698,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
-		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+		free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (unlikely(!free_space))
 		goto busy;
@@ -700,7 +718,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 		dma_addr_t dma;
 
 		dma = xsk_buff_xdp_get_dma(xdp);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
 
 		tx_buf->xdp = xdp;
 		tx_buf->type = ICE_TX_BUF_XSK_TX;
@@ -742,12 +760,14 @@ busy:
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
 ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	       struct xsk_buff_pool *xsk_pool)
 {
 	int err, result = ICE_XDP_PASS;
 	u32 act;
@@ -758,7 +778,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
 		if (!err)
 			return ICE_XDP_REDIR;
-		if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+		if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
 			result = ICE_XDP_EXIT;
 		else
 			result = ICE_XDP_CONSUMED;
@@ -769,7 +789,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	case XDP_PASS:
 		break;
 	case XDP_TX:
-		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
+		result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
 		if (result == ICE_XDP_CONSUMED)
 			goto out_failure;
 		break;
@@ -821,14 +841,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
 /**
  * ice_clean_rx_irq_zc - consumes packets from the hardware ring
  * @rx_ring: AF_XDP Rx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  * @budget: NAPI budget
  *
  * Returns number of processed packets on success, remaining budget on failure.
  */
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
 	u32 ntc = rx_ring->next_to_clean;
 	u32 ntu = rx_ring->next_to_use;
 	struct xdp_buff *first = NULL;
@@ -891,7 +913,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
+					 xsk_pool);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
@@ -940,7 +963,8 @@ construct_skb:
 	rx_ring->next_to_clean = ntc;
 	entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
 	if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
-		failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
+		failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
+						 entries_to_alloc);
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -963,17 +987,19 @@ construct_skb:
 /**
  * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
  * @xdp_ring: XDP ring to produce the HW Tx descriptor on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @desc: AF_XDP descriptor to pull the DMA address and length from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
+			 struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
 			 unsigned int *total_bytes)
 {
 	struct ice_tx_desc *tx_desc;
 	dma_addr_t dma;
 
-	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
-	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
+	dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
 
 	tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
 	tx_desc->buf_addr = cpu_to_le64(dma);
@@ -986,10 +1012,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
 /**
  * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
+			       struct xsk_buff_pool *xsk_pool,
+			       struct xdp_desc *descs,
 			       unsigned int *total_bytes)
 {
 	u16 ntu = xdp_ring->next_to_use;
@@ -999,8 +1028,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
+		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
 
 		tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
 		tx_desc->buf_addr = cpu_to_le64(dma);
@@ -1016,60 +1045,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
 /**
  * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
  * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
  * @nb_pkts: count of packets to be send
  * @total_bytes: bytes accumulator that will be used for stats update
  */
-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
-				u32 nb_pkts, unsigned int *total_bytes)
+static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool,
+				struct xdp_desc *descs, u32 nb_pkts,
+				unsigned int *total_bytes)
 {
 	u32 batched, leftover, i;
 
 	batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
 	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
 	for (i = 0; i < batched; i += PKTS_PER_BATCH)
-		ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
 	for (; i < batched + leftover; i++)
-		ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+		ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
 }
 
 /**
  * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
  * @xdp_ring: XDP ring to produce the HW Tx descriptors on
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * Returns true if there is no more work that needs to be done, false otherwise
  */
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool)
 {
-	struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
+	struct xdp_desc *descs = xsk_pool->tx_descs;
 	u32 nb_pkts, nb_processed = 0;
 	unsigned int total_bytes = 0;
 	int budget;
 
-	ice_clean_xdp_irq_zc(xdp_ring);
+	ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
+
+	if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
+	    !netif_running(xdp_ring->vsi->netdev))
+		return true;
 
 	budget = ICE_DESC_UNUSED(xdp_ring);
 	budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
 
-	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
+	nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
 	if (!nb_pkts)
 		return true;
 
 	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
 		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
-		ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
+				    &total_bytes);
 		xdp_ring->next_to_use = 0;
 	}
 
-	ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
-			    &total_bytes);
+	ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
+			    nb_pkts - nb_processed, &total_bytes);
 
 	ice_set_rs_bit(xdp_ring);
 	ice_xdp_ring_update_tail(xdp_ring);
 	ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
 
-	if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
-		xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
 
 	return nb_pkts < budget;
 }
@@ -1091,7 +1129,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_tx_ring *ring;
 
-	if (test_bit(ICE_VSI_DOWN, vsi->state))
+	if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev))
 		return -ENETDOWN;
 
 	if (!ice_is_xdp_ena_vsi(vsi))
@@ -1102,7 +1140,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
 
 	ring = vsi->rx_rings[queue_id]->xdp_ring;
 
-	if (!ring->xsk_pool)
+	if (!READ_ONCE(ring->xsk_pool))
 		return -EINVAL;
 
 	/* The idea here is that if NAPI is running, mark a miss, so
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 6fa181f080..45adeb5132 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -20,16 +20,20 @@ struct ice_vsi;
 #ifdef CONFIG_XDP_SOCKETS
 int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
 		       u16 qid);
-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
+int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
+			struct xsk_buff_pool *xsk_pool,
+			int budget);
 int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count);
 bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
 void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
+bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
 #else
-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
+static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
+			       struct xsk_buff_pool __always_unused *xsk_pool)
 {
 	return false;
 }
@@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
 
 static inline int
 ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+		    struct xsk_buff_pool __always_unused *xsk_pool,
 		    int __always_unused budget)
 {
 	return 0;
@@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
 
 static inline bool
 ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
+		     struct xsk_buff_pool __always_unused *xsk_pool,
 		     u16 __always_unused count)
 {
 	return false;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 87b655b839..33069880c8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6310,21 +6310,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	size_t n;
 	int i;
 
-	switch (qopt->cmd) {
-	case TAPRIO_CMD_REPLACE:
-		break;
-	case TAPRIO_CMD_DESTROY:
-		return igc_tsn_clear_schedule(adapter);
-	case TAPRIO_CMD_STATS:
-		igc_taprio_stats(adapter->netdev, &qopt->stats);
-		return 0;
-	case TAPRIO_CMD_QUEUE_STATS:
-		igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-
 	if (qopt->base_time < 0)
 		return -ERANGE;
 
@@ -6433,7 +6418,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter,
 	if (hw->mac.type != igc_i225)
 		return -EOPNOTSUPP;
 
-	err = igc_save_qbv_schedule(adapter, qopt);
+	switch (qopt->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		err = igc_save_qbv_schedule(adapter, qopt);
+		break;
+	case TAPRIO_CMD_DESTROY:
+		err = igc_tsn_clear_schedule(adapter);
+		break;
+	case TAPRIO_CMD_STATS:
+		igc_taprio_stats(adapter->netdev, &qopt->stats);
+		return 0;
+	case TAPRIO_CMD_QUEUE_STATS:
+		igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 9adf4301c9..a40b631188 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port,
 static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en)
 {
 	struct mvpp2_port *port;
-	int i;
+	int i, j;
 
 	for (i = 0; i < priv->port_count; i++) {
 		port = priv->port_list[i];
 		if (port->priv->percpu_pools) {
-			for (i = 0; i < port->nrxqs; i++)
-				mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i],
+			for (j = 0; j < port->nrxqs; j++)
+				mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j],
 							port->tx_fc & en);
 		} else {
 			mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index fadfa8b50b..8c4e3ecef5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -920,6 +920,7 @@ err_rule:
 	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
 	mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
 err_mod_hdr:
+	*attr = *old_attr;
 	kfree(old_attr);
 err_attr:
 	kvfree(spec);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 6e00afe467..797db853de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
 		    MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
 			caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
 
-		if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
-		     MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
-		    MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
+		if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) &&
+		    ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+		      MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+		     MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)))
 			caps |= MLX5_IPSEC_CAP_PRIO;
 
 		if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3320f12ba2..58eb96a688 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1409,7 +1409,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
+	if (err) {
+		netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err);
+		goto out;
+	}
+
 	mlx5_toggle_port_link(mdev);
 
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 979c49ae6b..b43ca0b762 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
+	struct devlink *devlink = priv_to_devlink(dev);
 
 	/* if this is the driver that initiated the fw reset, devlink completed the reload */
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
@@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
 			mlx5_load_one(dev, true);
-		devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
+		devl_lock(devlink);
+		devlink_remote_reload_actions_performed(devlink, 0,
 							BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
 							BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
+		devl_unlock(devlink);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 612e666ec2..e2230c8f18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -48,6 +48,7 @@ static struct mlx5_irq *
 irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
 {
 	struct irq_affinity_desc auto_desc = {};
+	struct mlx5_irq *irq;
 	u32 irq_index;
 	int err;
 
@@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de
 		else
 			cpu_get(pool, cpumask_first(&af_desc->mask));
 	}
-	return mlx5_irq_alloc(pool, irq_index,
-			      cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
-			      NULL);
+	irq = mlx5_irq_alloc(pool, irq_index,
+			     cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+			     NULL);
+	if (IS_ERR(irq))
+		xa_erase(&pool->irqs, irq_index);
+	return irq;
 }
 
 /* Looking for the IRQ with the smallest refcount that fits req_mask.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index d0871c46b8..cf8045b926 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 		goto unlock;
 
 	for (i = 0; i < ldev->ports; i++) {
-		if (ldev->pf[MLX5_LAG_P1].netdev == slave) {
+		if (ldev->pf[i].netdev == slave) {
 			port = i;
 			break;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 459a836a5d..3e55a6c6a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -2140,7 +2140,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	/* Panic tear down fw command will stop the PCI bus communication
 	 * with the HCA, so the health poll is no longer needed.
 	 */
-	mlx5_drain_health_wq(dev);
 	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_fast_teardown_hca(dev);
@@ -2175,6 +2174,7 @@ static void shutdown(struct pci_dev *pdev)
 
 	mlx5_core_info(dev, "Shutdown was called\n");
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
+	mlx5_drain_health_wq(dev);
 	err = mlx5_try_fast_unload(dev);
 	if (err)
 		mlx5_unload_one(dev, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index b2986175d9..b706f14865 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 	struct mlx5_core_dev *mdev = sf_dev->mdev;
 
 	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_drain_health_wq(mdev);
 	mlx5_unload_one(mdev, false);
 }
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 7b9e048845..b6e89fc5a4 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4347,7 +4347,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	if (unlikely(!rtl_tx_slots_avail(tp))) {
 		if (net_ratelimit())
 			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
-		goto err_stop_0;
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
 	}
 
 	opts[1] = rtl8169_tx_vlan_tag(skb);
@@ -4403,11 +4404,6 @@ err_dma_0:
 	dev_kfree_skb_any(skb);
 	dev->stats.tx_dropped++;
 	return NETDEV_TX_OK;
-
-err_stop_0:
-	netif_stop_queue(dev);
-	dev->stats.tx_dropped++;
-	return NETDEV_TX_BUSY;
 }
 
 static unsigned int rtl_last_frag_len(struct sk_buff *skb)
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index c29809cd92..fa510f4e26 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2219,9 +2219,9 @@ static void axienet_dma_err_handler(struct work_struct *work)
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 	axienet_set_mac_address(ndev, NULL);
 	axienet_set_multicast_list(ndev);
-	axienet_setoptions(ndev, lp->options);
 	napi_enable(&lp->napi_rx);
 	napi_enable(&lp->napi_tx);
+	axienet_setoptions(ndev, lp->options);
 }
 
 /**
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index ebafedde0a..0803b6e83c 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1389,6 +1389,8 @@ static int ksz9131_config_init(struct phy_device *phydev)
 	const struct device *dev_walker;
 	int ret;
 
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
 	dev_walker = &phydev->mdio.dev;
 	do {
 		of_node = dev_walker->of_node;
@@ -1438,28 +1440,30 @@ static int ksz9131_config_init(struct phy_device *phydev)
 #define MII_KSZ9131_AUTO_MDIX		0x1C
 #define MII_KSZ9131_AUTO_MDI_SET	BIT(7)
 #define MII_KSZ9131_AUTO_MDIX_SWAP_OFF	BIT(6)
+#define MII_KSZ9131_DIG_AXAN_STS	0x14
+#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET	BIT(14)
+#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT	BIT(12)
 
 static int ksz9131_mdix_update(struct phy_device *phydev)
 {
 	int ret;
 
-	ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX);
-	if (ret < 0)
-		return ret;
-
-	if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) {
-		if (ret & MII_KSZ9131_AUTO_MDI_SET)
-			phydev->mdix_ctrl = ETH_TP_MDI;
-		else
-			phydev->mdix_ctrl = ETH_TP_MDI_X;
+	if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) {
+		phydev->mdix = phydev->mdix_ctrl;
 	} else {
-		phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
-	}
+		ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS);
+		if (ret < 0)
+			return ret;
 
-	if (ret & MII_KSZ9131_AUTO_MDI_SET)
-		phydev->mdix = ETH_TP_MDI;
-	else
-		phydev->mdix = ETH_TP_MDI_X;
+		if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) {
+			if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT)
+				phydev->mdix = ETH_TP_MDI;
+			else
+				phydev->mdix = ETH_TP_MDI_X;
+		} else {
+			phydev->mdix = ETH_TP_MDI_INVALID;
+		}
+	}
 
 	return 0;
 }
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 7ab41f95da..ffa07c3f04 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -1351,6 +1351,13 @@ static struct phy_driver realtek_drvs[] = {
 		.handle_interrupt = genphy_handle_interrupt_no_ack,
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
+	}, {
+		PHY_ID_MATCH_EXACT(0x001cc960),
+		.name		= "RTL8366S Gigabit Ethernet",
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_mmd	= genphy_read_mmd_unsupported,
+		.write_mmd	= genphy_write_mmd_unsupported,
 	},
 };
 
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 0a662e42ed..cb7d2f798f 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	struct usbnet *dev = netdev_priv(netdev);
 	__le16 res;
 	int rc = 0;
+	int err;
 
 	if (phy_id) {
 		netdev_dbg(netdev, "Only internal phy supported\n");
@@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	if (loc == MII_BMSR) {
 		u8 value;
 
-		sr_read_reg(dev, SR_NSR, &value);
+		err = sr_read_reg(dev, SR_NSR, &value);
+		if (err < 0)
+			return err;
+
 		if (value & NSR_LINKST)
 			rc = 1;
 	}
-	sr_share_read_word(dev, 1, loc, &res);
+	err = sr_share_read_word(dev, 1, loc, &res);
+	if (err < 0)
+		return err;
+
 	if (rc == 1)
 		res = le16_to_cpu(res) | BMSR_LSTATUS;
 	else
diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c
index c5e7ca793c..8fcfbde31a 100644
--- a/drivers/net/wan/fsl_qmc_hdlc.c
+++ b/drivers/net/wan/fsl_qmc_hdlc.c
@@ -18,6 +18,7 @@
 #include <linux/hdlc.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -37,7 +38,7 @@ struct qmc_hdlc {
 	struct qmc_chan *qmc_chan;
 	struct net_device *netdev;
 	struct framer *framer;
-	spinlock_t carrier_lock; /* Protect carrier detection */
+	struct mutex carrier_lock; /* Protect carrier detection */
 	struct notifier_block nb;
 	bool is_crc32;
 	spinlock_t tx_lock; /* Protect tx descriptors */
@@ -60,7 +61,7 @@ static int qmc_hdlc_framer_set_carrier(struct qmc_hdlc *qmc_hdlc)
 	if (!qmc_hdlc->framer)
 		return 0;
 
-	guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock);
+	guard(mutex)(&qmc_hdlc->carrier_lock);
 
 	ret = framer_get_status(qmc_hdlc->framer, &framer_status);
 	if (ret) {
@@ -249,6 +250,7 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
 	struct qmc_hdlc_desc *desc = context;
 	struct net_device *netdev;
 	struct qmc_hdlc *qmc_hdlc;
+	size_t crc_size;
 	int ret;
 
 	netdev = desc->netdev;
@@ -267,15 +269,26 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
 		if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */
 			netdev->stats.rx_crc_errors++;
 		kfree_skb(desc->skb);
-	} else {
-		netdev->stats.rx_packets++;
-		netdev->stats.rx_bytes += length;
+		goto re_queue;
+	}
 
-		skb_put(desc->skb, length);
-		desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
-		netif_rx(desc->skb);
+	/* Discard the CRC */
+	crc_size = qmc_hdlc->is_crc32 ? 4 : 2;
+	if (length < crc_size) {
+		netdev->stats.rx_length_errors++;
+		kfree_skb(desc->skb);
+		goto re_queue;
 	}
+	length -= crc_size;
+
+	netdev->stats.rx_packets++;
+	netdev->stats.rx_bytes += length;
+
+	skb_put(desc->skb, length);
+	desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
+	netif_rx(desc->skb);
 
+re_queue:
 	/* Re-queue a transfer using the same descriptor */
 	ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size);
 	if (ret) {
@@ -706,7 +719,7 @@ static int qmc_hdlc_probe(struct platform_device *pdev)
 
 	qmc_hdlc->dev = dev;
 	spin_lock_init(&qmc_hdlc->tx_lock);
-	spin_lock_init(&qmc_hdlc->carrier_lock);
+	mutex_init(&qmc_hdlc->carrier_lock);
 
 	qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node);
 	if (IS_ERR(qmc_hdlc->qmc_chan))
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 16af046c33..55fde0d331 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -472,7 +472,8 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
 {
 	int i;
 
-	clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+	if (!test_and_clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags))
+		return;
 
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index b1d0a1b391..9d3c249207 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -485,7 +485,9 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot,
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 
 	pci_config_pm_runtime_get(pdev);
-	pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC, status),
+
+	/* Attention and Power Indicator Control bits are supported */
+	pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC, status),
 			      PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC);
 	pci_config_pm_runtime_put(pdev);
 	return 0;
diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
index 72c2d3074c..98af97750a 100644
--- a/drivers/perf/fsl_imx9_ddr_perf.c
+++ b/drivers/perf/fsl_imx9_ddr_perf.c
@@ -476,12 +476,12 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
 	hwc->idx = counter;
 	hwc->state |= PERF_HES_STOPPED;
 
-	if (flags & PERF_EF_START)
-		ddr_perf_event_start(event, flags);
-
 	/* read trans, write trans, read beat */
 	ddr_perf_monitor_config(pmu, cfg, cfg1, cfg2);
 
+	if (flags & PERF_EF_START)
+		ddr_perf_event_start(event, flags);
+
 	return 0;
 }
 
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 4e842dcedf..11c7c85047 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -412,7 +412,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
 	 * but not in the user access mode as we want to use the other counters
 	 * that support sampling/filtering.
 	 */
-	if (hwc->flags & PERF_EVENT_FLAG_LEGACY) {
+	if ((hwc->flags & PERF_EVENT_FLAG_LEGACY) && (event->attr.type == PERF_TYPE_HARDWARE)) {
 		if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
 			cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
 			cmask = 1;
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index 945b1b15a0..f8242b8dda 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -805,9 +805,11 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev,
 	if (ret == -ENOPROTOOPT) {
 		dev_dbg(ec_dev->dev,
 			"GET_NEXT_EVENT returned invalid version error.\n");
+		mutex_lock(&ec_dev->lock);
 		ret = cros_ec_get_host_command_version_mask(ec_dev,
 							EC_CMD_GET_NEXT_EVENT,
 							&ver_mask);
+		mutex_unlock(&ec_dev->lock);
 		if (ret < 0 || ver_mask == 0)
 			/*
 			 * Do not change the MKBP supported version if we can't