Merge tag 'drm-fixes-2020-07-17-1' of git://anongit.freedesktop.org/drm/drm into master

Pull drm fixes from Dave Airlie:
 "Weekly fixes pull, big bigger than I'd normally like, but they are
  fairly scattered and small individually.

  The vmwgfx one is a black screen regression, otherwise the largest is
  an MST encoder fix for amdgpu which results in a WARN in some cases,
  and a scattering of i915 fixes.

  I'm tracking two regressions at the moment that hopefully we get
  nailed down this week for rc7.

  dma-buf:
   - sleeping atomic fix

  amdgpu:
   - Fix a race condition with KIQ
   - Preemption fix
   - Fix handling of fake MST encoders
   - OLED panel fix
   - Handle allocation failure in stream construction
   - Renoir SMC fix
   - SDMA 5.x fix

  i915:
   - FBC w/a stride fix
   - Fix use-after-free fix on module reload
   - Ignore irq enabling on the virtual engines to fix device sleep
   - Use GTT when saving/restoring engine GPR
   - Fix selftest sort function

  vmwgfx:
   - black screen fix

  aspeed:
   - fbcon init warn fix"

* tag 'drm-fixes-2020-07-17-1' of git://anongit.freedesktop.org/drm/drm:
  drm/amdgpu/sdma5: fix wptr overwritten in ->get_wptr()
  drm/amdgpu/powerplay: Modify SMC message name for setting power profile mode
  drm/amd/display: handle failed allocation during stream construction
  drm/amd/display: OLED panel backlight adjust not work with external display connected
  drm/amdgpu/display: create fake mst encoders ahead of time (v4)
  drm/amdgpu: fix preemption unit test
  drm/amdgpu/gfx10: fix race condition for kiq
  drm/i915: Recalculate FBC w/a stride when needed
  drm/i915: Move cec_notifier to intel_hdmi_connector_unregister, v2.
  drm/i915/gt: Only swap to a random sibling once upon creation
  drm/i915/gt: Ignore irq enabling on the virtual engines
  drm/i915/perf: Use GTT when saving/restoring engine GPR
  drm/i915/selftests: Fix compare functions provided for sorting
  drm/vmwgfx: fix update of display surface when resolution changes
  dmabuf: use spinlock to access dmabuf->name
  drm/aspeed: Call drm_fbdev_generic_setup after drm_dev_register

18 files changed, 152 insertions, 99 deletions

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 412629601ad3..1ca609f66fdf 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -45,10 +45,10 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen)
 	size_t ret = 0;
 
 	dmabuf = dentry->d_fsdata;
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 
 	return dynamic_dname(dentry, buffer, buflen, "/%s:%s",
 			     dentry->d_name.name, ret > 0 ? name : "");
@@ -338,8 +338,10 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf)
 		kfree(name);
 		goto out_unlock;
 	}
+	spin_lock(&dmabuf->name_lock);
 	kfree(dmabuf->name);
 	dmabuf->name = name;
+	spin_unlock(&dmabuf->name_lock);
 
 out_unlock:
 	dma_resv_unlock(dmabuf->resv);
@@ -402,10 +404,10 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file)
 	/* Don't count the temporary reference taken inside procfs seq_show */
 	seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1);
 	seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name);
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		seq_printf(m, "name:\t%s\n", dmabuf->name);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 }
 
 static const struct file_operations dma_buf_fops = {
@@ -542,6 +544,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	dmabuf->size = exp_info->size;
 	dmabuf->exp_name = exp_info->exp_name;
 	dmabuf->owner = exp_info->owner;
+	spin_lock_init(&dmabuf->name_lock);
 	init_waitqueue_head(&dmabuf->poll);
 	dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll;
 	dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index d33cb344be69..a414da22a359 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1295,27 +1295,37 @@ static void amdgpu_ib_preempt_job_recovery(struct drm_gpu_scheduler *sched)
 static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring)
 {
 	struct amdgpu_job *job;
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	uint32_t preempt_seq;
 	struct dma_fence *fence, **ptr;
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
 	struct drm_gpu_scheduler *sched = &ring->sched;
+	bool preempted = true;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 		return;
 
 	preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2));
-	if (preempt_seq <= atomic_read(&drv->last_seq))
-		return;
+	if (preempt_seq <= atomic_read(&drv->last_seq)) {
+		preempted = false;
+		goto no_preempt;
+	}
 
 	preempt_seq &= drv->num_fences_mask;
 	ptr = &drv->fences[preempt_seq];
 	fence = rcu_dereference_protected(*ptr, 1);
 
+no_preempt:
 	spin_lock(&sched->job_list_lock);
-	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		if (dma_fence_is_signaled(&s_job->s_fence->finished)) {
+			/* remove job from ring_mirror_list */
+			list_del_init(&s_job->node);
+			sched->ops->free_job(s_job);
+			continue;
+		}
 		job = to_amdgpu_job(s_job);
-		if (job->fence == fence)
+		if (preempted && job->fence == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index bd5dd4f64311..fac77a86c04b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7513,12 +7513,17 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	unsigned long flags;
 
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
-	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size))
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		return -ENOMEM;
+	}
 
 	/* assert preemption condition */
 	amdgpu_ring_set_preempt_cond_exec(ring, false);
@@ -7529,6 +7534,8 @@ static int gfx_v10_0_ring_preempt_ib(struct amdgpu_ring *ring)
 				   ++ring->trail_seq);
 	amdgpu_ring_commit(kiq_ring);
 
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
 	/* poll the trailing fence */
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (ring->trail_seq ==
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 5d71c23e2640..8fb66e50a57b 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -314,30 +314,20 @@ static uint64_t sdma_v5_0_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u64 *wptr = NULL;
-	uint64_t local_wptr = 0;
+	u64 wptr;
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]);
-		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr);
-		*wptr = (*wptr) >> 2;
-		DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr);
+		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
-		u32 lowbit, highbit;
-
-		wptr = &local_wptr;
-		lowbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
-
-		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				ring->me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
+		wptr = wptr << 32;
+		wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
+		DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr);
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index db5e0bb0d935..86ffa0c2880f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -974,6 +974,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	/* Update the actual used number of crtc */
 	adev->mode_info.num_crtc = adev->dm.display_indexes_num;
 
+	/* create fake encoders for MST */
+	dm_dp_create_fake_mst_encoders(adev);
+
 	/* TODO: Add_display_info? */
 
 	/* TODO use dynamic cursor width */
@@ -997,6 +1000,12 @@ error:
 
 static void amdgpu_dm_fini(struct amdgpu_device *adev)
 {
+	int i;
+
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
+	}
+
 	amdgpu_dm_audio_fini(adev);
 
 	amdgpu_dm_destroy_drm_device(&adev->dm);
@@ -2010,6 +2019,7 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	struct amdgpu_display_manager *dm;
 	struct drm_connector *conn_base;
 	struct amdgpu_device *adev;
+	struct dc_link *link = NULL;
 	static const u8 pre_computed_values[] = {
 		50, 51, 52, 53, 55, 56, 57, 58, 59, 61, 62, 63, 65, 66, 68, 69,
 		71, 72, 74, 75, 77, 79, 81, 82, 84, 86, 88, 90, 92, 94, 96, 98};
@@ -2017,6 +2027,10 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	if (!aconnector || !aconnector->dc_link)
 		return;
 
+	link = aconnector->dc_link;
+	if (link->connector_signal != SIGNAL_TYPE_EDP)
+		return;
+
 	conn_base = &aconnector->base;
 	adev = conn_base->dev->dev_private;
 	dm = &adev->dm;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index d61186ff411d..648180ccdc2e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -43,6 +43,9 @@
  */
 
 #define AMDGPU_DM_MAX_DISPLAY_INDEX 31
+
+#define AMDGPU_DM_MAX_CRTC 6
+
 /*
 #include "include/amdgpu_dal_power_if.h"
 #include "amdgpu_dm_irq.h"
@@ -328,6 +331,13 @@ struct amdgpu_display_manager {
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
+
+	/**
+	 * @mst_encoders:
+	 *
+	 * fake encoders used for DP MST.
+	 */
+	struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC];
 };
 
 struct amdgpu_dm_connector {
@@ -356,7 +366,6 @@ struct amdgpu_dm_connector {
 	struct amdgpu_dm_dp_aux dm_dp_aux;
 	struct drm_dp_mst_port *port;
 	struct amdgpu_dm_connector *mst_port;
-	struct amdgpu_encoder *mst_encoder;
 	struct drm_dp_aux *dsc_aux;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index ae0a7ef1d595..e5ecc5affa1e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -95,7 +95,6 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector =
 		to_amdgpu_dm_connector(connector);
-	struct amdgpu_encoder *amdgpu_encoder = aconnector->mst_encoder;
 
 	if (aconnector->dc_sink) {
 		dc_link_remove_remote_sink(aconnector->dc_link,
@@ -105,8 +104,6 @@ dm_dp_mst_connector_destroy(struct drm_connector *connector)
 
 	kfree(aconnector->edid);
 
-	drm_encoder_cleanup(&amdgpu_encoder->base);
-	kfree(amdgpu_encoder);
 	drm_connector_cleanup(connector);
 	drm_dp_mst_put_port_malloc(aconnector->port);
 	kfree(aconnector);
@@ -243,7 +240,11 @@ static struct drm_encoder *
 dm_mst_atomic_best_encoder(struct drm_connector *connector,
 			   struct drm_connector_state *connector_state)
 {
-	return &to_amdgpu_dm_connector(connector)->mst_encoder->base;
+	struct drm_device *dev = connector->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(connector_state->crtc);
+
+	return &adev->dm.mst_encoders[acrtc->crtc_id].base;
 }
 
 static int
@@ -306,31 +307,27 @@ static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = {
 	.destroy = amdgpu_dm_encoder_destroy,
 };
 
-static struct amdgpu_encoder *
-dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector)
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = connector->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_encoder *amdgpu_encoder;
-	struct drm_encoder *encoder;
-
-	amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL);
-	if (!amdgpu_encoder)
-		return NULL;
+	struct drm_device *dev = adev->ddev;
+	int i;
 
-	encoder = &amdgpu_encoder->base;
-	encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		struct amdgpu_encoder *amdgpu_encoder = &adev->dm.mst_encoders[i];
+		struct drm_encoder *encoder = &amdgpu_encoder->base;
 
-	drm_encoder_init(
-		dev,
-		&amdgpu_encoder->base,
-		&amdgpu_dm_encoder_funcs,
-		DRM_MODE_ENCODER_DPMST,
-		NULL);
+		encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
 
-	drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
+		drm_encoder_init(
+			dev,
+			&amdgpu_encoder->base,
+			&amdgpu_dm_encoder_funcs,
+			DRM_MODE_ENCODER_DPMST,
+			NULL);
 
-	return amdgpu_encoder;
+		drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
+	}
 }
 
 static struct drm_connector *
@@ -343,6 +340,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	int i;
 
 	aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL);
 	if (!aconnector)
@@ -369,9 +367,10 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		master->dc_link,
 		master->connector_id);
 
-	aconnector->mst_encoder = dm_dp_create_fake_mst_encoder(master);
-	drm_connector_attach_encoder(&aconnector->base,
-				     &aconnector->mst_encoder->base);
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_connector_attach_encoder(&aconnector->base,
+					     &adev->dm.mst_encoders[i].base);
+	}
 
 	connector->max_bpc_property = master->base.max_bpc_property;
 	if (connector->max_bpc_property)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index d2c56579a2cc..b38bd68121ce 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -35,6 +35,9 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector,
 				       int link_index);
 
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev);
+
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 				       struct dc_state *dc_state);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 4f0e7203dba4..470c82794f6f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -56,7 +56,7 @@ void update_stream_signal(struct dc_stream_state *stream, struct dc_sink *sink)
 	}
 }
 
-static void dc_stream_construct(struct dc_stream_state *stream,
+static bool dc_stream_construct(struct dc_stream_state *stream,
 	struct dc_sink *dc_sink_data)
 {
 	uint32_t i = 0;
@@ -118,11 +118,17 @@ static void dc_stream_construct(struct dc_stream_state *stream,
 	update_stream_signal(stream, dc_sink_data);
 
 	stream->out_transfer_func = dc_create_transfer_func();
+	if (stream->out_transfer_func == NULL) {
+		dc_sink_release(dc_sink_data);
+		return false;
+	}
 	stream->out_transfer_func->type = TF_TYPE_BYPASS;
 	stream->out_transfer_func->ctx = stream->ctx;
 
 	stream->stream_id = stream->ctx->dc_stream_id_count;
 	stream->ctx->dc_stream_id_count++;
+
+	return true;
 }
 
 static void dc_stream_destruct(struct dc_stream_state *stream)
@@ -164,13 +170,20 @@ struct dc_stream_state *dc_create_stream_for_sink(
 
 	stream = kzalloc(sizeof(struct dc_stream_state), GFP_KERNEL);
 	if (stream == NULL)
-		return NULL;
+		goto alloc_fail;
 
-	dc_stream_construct(stream, sink);
+	if (dc_stream_construct(stream, sink) == false)
+		goto construct_fail;
 
 	kref_init(&stream->refcount);
 
 	return stream;
+
+construct_fail:
+	kfree(stream);
+
+alloc_fail:
+	return NULL;
 }
 
 struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 67476047c067..fbb3f3a0dff7 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -689,7 +689,7 @@ static int renoir_set_power_profile_mode(struct smu_context *smu, long *input, u
 		return -EINVAL;
 	}
 
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
+	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
 				    1 << workload_type,
 				    NULL);
 	if (ret) {
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
index 6b27242b9ee3..bca3fcff16ec 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
@@ -173,8 +173,6 @@ static int aspeed_gfx_load(struct drm_device *drm)
 
 	drm_mode_config_reset(drm);
 
-	drm_fbdev_generic_setup(drm, 32);
-
 	return 0;
 }
 
@@ -225,6 +223,7 @@ static int aspeed_gfx_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unload;
 
+	drm_fbdev_generic_setup(&priv->drm, 32);
 	return 0;
 
 err_unload:
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index a65d9d8b79a7..412572f88b67 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -719,6 +719,25 @@ static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
 		fbc->compressed_fb.size * fbc->threshold;
 }
 
+static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+	    cache->fb.modifier != I915_FORMAT_MOD_X_TILED)
+		return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+	else
+		return 0;
+}
+
+static bool intel_fbc_gen9_wa_cfb_stride_changed(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	return fbc->params.gen9_wa_cfb_stride != intel_fbc_gen9_wa_cfb_stride(dev_priv);
+}
+
 static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
@@ -877,6 +896,7 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 	params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane;
 
 	params->fb.format = cache->fb.format;
+	params->fb.modifier = cache->fb.modifier;
 	params->fb.stride = cache->fb.stride;
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
@@ -906,6 +926,9 @@ static bool intel_fbc_can_flip_nuke(const struct intel_crtc_state *crtc_state)
 	if (params->fb.format != cache->fb.format)
 		return false;
 
+	if (params->fb.modifier != cache->fb.modifier)
+		return false;
+
 	if (params->fb.stride != cache->fb.stride)
 		return false;
 
@@ -1185,7 +1208,8 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 
 	if (fbc->crtc) {
 		if (fbc->crtc != crtc ||
-		    !intel_fbc_cfb_size_changed(dev_priv))
+		    (!intel_fbc_cfb_size_changed(dev_priv) &&
+		     !intel_fbc_gen9_wa_cfb_stride_changed(dev_priv)))
 			goto out;
 
 		__intel_fbc_disable(dev_priv);
@@ -1207,12 +1231,7 @@ void intel_fbc_enable(struct intel_atomic_state *state,
 		goto out;
 	}
 
-	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
-	    plane_state->hw.fb->modifier != I915_FORMAT_MOD_X_TILED)
-		cache->gen9_wa_cfb_stride =
-			DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
-	else
-		cache->gen9_wa_cfb_stride = 0;
+	cache->gen9_wa_cfb_stride = intel_fbc_gen9_wa_cfb_stride(dev_priv);
 
 	drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n",
 		    pipe_name(crtc->pipe));
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 010f37240710..95b6d9457910 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2867,19 +2867,13 @@ intel_hdmi_connector_register(struct drm_connector *connector)
 	return ret;
 }
 
-static void intel_hdmi_destroy(struct drm_connector *connector)
+static void intel_hdmi_connector_unregister(struct drm_connector *connector)
 {
 	struct cec_notifier *n = intel_attached_hdmi(to_intel_connector(connector))->cec_notifier;
 
 	cec_notifier_conn_unregister(n);
 
-	intel_connector_destroy(connector);
-}
-
-static void intel_hdmi_connector_unregister(struct drm_connector *connector)
-{
 	intel_hdmi_remove_i2c_symlink(connector);
-
 	intel_connector_unregister(connector);
 }
 
@@ -2891,7 +2885,7 @@ static const struct drm_connector_funcs intel_hdmi_connector_funcs = {
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
 	.late_register = intel_hdmi_connector_register,
 	.early_unregister = intel_hdmi_connector_unregister,
-	.destroy = intel_hdmi_destroy,
+	.destroy = intel_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
 };
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7c3d8ef4a47c..cb07e1d2a353 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -5396,13 +5396,8 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 	 * typically be the first we inspect for submission.
 	 */
 	swp = prandom_u32_max(ve->num_siblings);
-	if (!swp)
-		return;
-
-	swap(ve->siblings[swp], ve->siblings[0]);
-	if (!intel_engine_has_relative_mmio(ve->siblings[0]))
-		virtual_update_register_offsets(ve->context.lrc_reg_state,
-						ve->siblings[0]);
+	if (swp)
+		swap(ve->siblings[swp], ve->siblings[0]);
 }
 
 static int virtual_context_alloc(struct intel_context *ce)
@@ -5415,15 +5410,9 @@ static int virtual_context_alloc(struct intel_context *ce)
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
-	int err;
 
 	/* Note: we must use a real engine class for setting up reg state */
-	err = __execlists_context_pin(ce, ve->siblings[0]);
-	if (err)
-		return err;
-
-	virtual_engine_initial_hint(ve);
-	return 0;
+	return __execlists_context_pin(ce, ve->siblings[0]);
 }
 
 static void virtual_context_enter(struct intel_context *ce)
@@ -5688,6 +5677,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
 	intel_engine_init_execlists(&ve->base);
+	ve->base.breadcrumbs.irq_armed = true; /* fake HW, used for irq_work */
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
@@ -5769,6 +5759,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
+	virtual_engine_initial_hint(ve);
 	return &ve->context;
 
 err_put:
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 5049c3dd08a6..c91981e75ebf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -44,9 +44,9 @@ static int cmp_u64(const void *A, const void *B)
 {
 	const u64 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
@@ -56,9 +56,9 @@ static int cmp_u32(const void *A, const void *B)
 {
 	const u32 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f79f118bf192..ae99a9190200 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -440,6 +440,7 @@ struct intel_fbc {
 		struct {
 			const struct drm_format_info *format;
 			unsigned int stride;
+			u64 modifier;
 		} fb;
 
 		int cfb_size;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 25329b7600c9..014f34c047d5 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1592,6 +1592,7 @@ static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
 	u32 d;
 
 	cmd = save ? MI_STORE_REGISTER_MEM : MI_LOAD_REGISTER_MEM;
+	cmd |= MI_SRM_LRM_GLOBAL_GTT;
 	if (INTEL_GEN(stream->perf->i915) >= 8)
 		cmd++;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 9ffa9c75a5da..16b385629688 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1069,10 +1069,6 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	if (new_content_type != SAME_AS_DISPLAY) {
 		struct vmw_surface_metadata metadata = {0};
 
-		metadata.base_size.width = hdisplay;
-		metadata.base_size.height = vdisplay;
-		metadata.base_size.depth = 1;
-
 		/*
 		 * If content buffer is a buffer object, then we have to
 		 * construct surface info
@@ -1104,6 +1100,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			metadata = new_vfbs->surface->metadata;
 		}
 
+		metadata.base_size.width = hdisplay;
+		metadata.base_size.height = vdisplay;
+		metadata.base_size.depth = 1;
+
 		if (vps->surf) {
 			struct drm_vmw_size cur_base_size =
 				vps->surf->metadata.base_size;