Merge tag 'drm-fixes-2019-05-24-1' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Nothing too unusual here for rc2. Except the amdgpu DMCU firmware
  loading fix caused build breakage with a different set of Kconfig
  options. I've just reverted it for now until the AMD folks can rewrite
  it to avoid that problem.

  i915:
   - boosting fix
   - bump ready task fixes
   - GVT - reset fix, error return, TRTT handling fix

  amdgpu:
   - DMCU firmware loading fix
   - Polaris 10 pci id for kfd
   - picasso screen corruption fix
   - SR-IOV fixes
   - vega driver reload fixes
   - SMU locking fix
   - compute profile fix for kfd

  vmwgfx:
   - integer overflow fixes
   - dma sg fix

  sun4i:
   - HDMI phy fixes

  gma500:
   - LVDS detection fix

  panfrost:
   - devfreq selection fix"

* tag 'drm-fixes-2019-05-24-1' of git://anongit.freedesktop.org/drm/drm: (32 commits)
  Revert "drm/amd/display: Don't load DMCU for Raven 1"
  drm/panfrost: Select devfreq
  drm/gma500/cdv: Check vbt config bits when detecting lvds panels
  drm/vmwgfx: integer underflow in vmw_cmd_dx_set_shader() leading to an invalid read
  drm/vmwgfx: NULL pointer dereference from vmw_cmd_dx_view_define()
  drm/vmwgfx: Use the dma scatter-gather iterator to get dma addresses
  drm/vmwgfx: Fix compat mode shader operation
  drm/vmwgfx: Fix user space handle equal to zero
  drm/vmwgfx: Don't send drm sysfs hotplug events on initial master set
  drm/i915/gvt: Fix an error code in ppgtt_populate_spt_by_guest_entry()
  drm/i915/gvt: do not let TRTTE and 0x4dfc write passthrough to hardware
  drm/i915/gvt: add 0x4dfc to gen9 save-restore list
  drm/i915/gvt: Tiled Resources mmios are in-context mmios for gen9+
  drm/i915/gvt: use cmd to restore in-context mmios to hw for gen9 platform
  drm/i915/gvt: emit init breadcrumb for gvt request
  drm/amdkfd: Fix compute profile switching
  drm/amdgpu: skip fw pri bo alloc for SRIOV
  drm/amd/powerplay: fix locking in smu_feature_set_supported()
  drm/amdgpu/gmc9: set vram_width properly for SR-IOV
  drm/amdgpu/soc15: skip reset on init
  ...

31 files changed, 326 insertions, 263 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 05897b05766b..86cc24b2e0aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -877,13 +877,16 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (!psp->cmd)
 		return -ENOMEM;
 
-	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-					AMDGPU_GEM_DOMAIN_GTT,
-					&psp->fw_pri_bo,
-					&psp->fw_pri_mc_addr,
-					&psp->fw_pri_buf);
-	if (ret)
-		goto failed;
+	/* this fw pri bo is not used under SRIOV */
+	if (!amdgpu_sriov_vf(psp->adev)) {
+		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+					      AMDGPU_GEM_DOMAIN_GTT,
+					      &psp->fw_pri_bo,
+					      &psp->fw_pri_mc_addr,
+					      &psp->fw_pri_buf);
+		if (ret)
+			goto failed;
+	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_VRAM,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3fd79e07944d..3b7370d914a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -626,6 +626,7 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	case CHIP_VEGA10:
 		return true;
 	case CHIP_RAVEN:
+		return (adev->pdev->device == 0x15d8);
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	default:
@@ -812,8 +813,16 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 	int chansize, numchan;
 	int r;
 
-	if (amdgpu_emu_mode != 1)
+	if (amdgpu_sriov_vf(adev)) {
+		/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
+		 * and DF related registers is not readable, seems hardcord is the
+		 * only way to set the correct vram_width
+		 */
+		adev->gmc.vram_width = 2048;
+	} else if (amdgpu_emu_mode != 1) {
 		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
+	}
+
 	if (!adev->gmc.vram_width) {
 		/* hbm memory channel size */
 		if (adev->flags & AMD_IS_APU)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4900e4958dec..b7e594c2bfb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -730,6 +730,11 @@ static bool soc15_need_reset_on_init(struct amdgpu_device *adev)
 {
 	u32 sol_reg;
 
+	/* Just return false for soc15 GPUs.  Reset does not seem to
+	 * be necessary.
+	 */
+	return false;
+
 	if (adev->flags & AMD_IS_APU)
 		return false;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index c1e4d44d6137..765b58a17dc7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -355,6 +355,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x67CF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67D0, &polaris10_vf_device_info },	/* Polaris10 vf*/
 	{ 0x67DF, &polaris10_device_info },	/* Polaris10 */
+	{ 0x6FDF, &polaris10_device_info },	/* Polaris10 */
 	{ 0x67E0, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E1, &polaris11_device_info },	/* Polaris11 */
 	{ 0x67E3, &polaris11_device_info },	/* Polaris11 */
@@ -462,6 +463,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
 	kfd->pdev = pdev;
 	kfd->init_complete = false;
 	kfd->kfd2kgd = f2g;
+	atomic_set(&kfd->compute_profile, 0);
 
 	mutex_init(&kfd->doorbell_mutex);
 	memset(&kfd->doorbell_available_index, 0,
@@ -1036,6 +1038,21 @@ void kgd2kfd_set_sram_ecc_flag(struct kfd_dev *kfd)
 		atomic_inc(&kfd->sram_ecc_flag);
 }
 
+void kfd_inc_compute_active(struct kfd_dev *kfd)
+{
+	if (atomic_inc_return(&kfd->compute_profile) == 1)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, false);
+}
+
+void kfd_dec_compute_active(struct kfd_dev *kfd)
+{
+	int count = atomic_dec_return(&kfd->compute_profile);
+
+	if (count == 0)
+		amdgpu_amdkfd_set_compute_idle(kfd->kgd, true);
+	WARN_ONCE(count < 0, "Compute profile ref. count error");
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 /* This function will send a package to HIQ to hang the HWS
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index c6c9530e704e..ae381450601c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -811,8 +811,8 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	if (dqm->processes_count++ == 0)
-		amdgpu_amdkfd_set_compute_idle(dqm->dev->kgd, false);
+	dqm->processes_count++;
+	kfd_inc_compute_active(dqm->dev);
 
 	dqm_unlock(dqm);
 
@@ -835,9 +835,8 @@ static int unregister_process(struct device_queue_manager *dqm,
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			if (--dqm->processes_count == 0)
-				amdgpu_amdkfd_set_compute_idle(
-					dqm->dev->kgd, true);
+			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			goto out;
 		}
 	}
@@ -1539,6 +1538,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
@@ -1626,6 +1626,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 			list_del(&cur->list);
 			kfree(cur);
 			dqm->processes_count--;
+			kfd_dec_compute_active(dqm->dev);
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9e0230965675..487d5da337c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -279,6 +279,9 @@ struct kfd_dev {
 
 	/* SRAM ECC flag */
 	atomic_t sram_ecc_flag;
+
+	/* Compute Profile ref. count */
+	atomic_t compute_profile;
 };
 
 enum kfd_mempool {
@@ -978,6 +981,10 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
 bool kfd_is_locked(void);
 
+/* Compute profile */
+void kfd_inc_compute_active(struct kfd_dev *dev);
+void kfd_dec_compute_active(struct kfd_dev *dev);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 34d6fdcb32e2..4c8ce7938f01 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -138,13 +138,14 @@
 #endif
 #define RAVEN_UNKNOWN 0xFF
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
-#endif /* DCN1_01 */
 #define ASIC_REV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
 #define RAVEN1_F0 0xF0
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
 
+#if defined(CONFIG_DRM_AMD_DC_DCN1_01)
+#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < 0xF0))
+#endif /* DCN1_01 */
 
 #define FAMILY_RV 142 /* DCN 1*/
 
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index c058c784180e..eec329ab6037 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -280,7 +280,7 @@ int smu_feature_set_supported(struct smu_context *smu, int feature_id,
 
 	WARN_ON(feature_id > feature->feature_num);
 
-	mutex_unlock(&feature->mutex);
+	mutex_lock(&feature->mutex);
 	if (enable)
 		test_and_set_bit(feature_id, feature->supported);
 	else
diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
index de9531caaca0..9c8446184b17 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
@@ -594,6 +594,9 @@ void cdv_intel_lvds_init(struct drm_device *dev,
 	int pipe;
 	u8 pin;
 
+	if (!dev_priv->lvds_enabled_in_vbt)
+		return;
+
 	pin = GMBUS_PORT_PANEL;
 	if (!lvds_is_present_in_vbt(dev, &pin)) {
 		DRM_DEBUG_KMS("LVDS is not present in VBT\n");
diff --git a/drivers/gpu/drm/gma500/intel_bios.c b/drivers/gpu/drm/gma500/intel_bios.c
index 63bde4e86c6a..e019ea271ffc 100644
--- a/drivers/gpu/drm/gma500/intel_bios.c
+++ b/drivers/gpu/drm/gma500/intel_bios.c
@@ -436,6 +436,9 @@ parse_driver_features(struct drm_psb_private *dev_priv,
 	if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
 		dev_priv->edp.support = 1;
 
+	dev_priv->lvds_enabled_in_vbt = driver->lvds_config != 0;
+	DRM_DEBUG_KMS("LVDS VBT config bits: 0x%x\n", driver->lvds_config);
+
 	/* This bit means to use 96Mhz for DPLL_A or not */
 	if (driver->primary_lfp_id)
 		dev_priv->dplla_96mhz = true;
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 941b238bdcc9..bc608ddc3bd1 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -537,6 +537,7 @@ struct drm_psb_private {
 	int lvds_ssc_freq;
 	bool is_lvds_on;
 	bool is_mipi_on;
+	bool lvds_enabled_in_vbt;
 	u32 mipi_ctrl_display;
 
 	unsigned int core_freq;
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index ab002cfd3cab..5cb59c0b4bbe 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -896,12 +896,16 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 	}
 
 	/* TODO
-	 * Right now only scan LRI command on KBL and in inhibit context.
-	 * It's good enough to support initializing mmio by lri command in
-	 * vgpu inhibit context on KBL.
+	 * In order to let workload with inhibit context to generate
+	 * correct image data into memory, vregs values will be loaded to
+	 * hw via LRIs in the workload with inhibit context. But as
+	 * indirect context is loaded prior to LRIs in workload, we don't
+	 * want reg values specified in indirect context overwritten by
+	 * LRIs in workloads. So, when scanning an indirect context, we
+	 * update reg values in it into vregs, so LRIs in workload with
+	 * inhibit context will restore with correct values
 	 */
-	if ((IS_KABYLAKE(s->vgpu->gvt->dev_priv)
-		|| IS_COFFEELAKE(s->vgpu->gvt->dev_priv)) &&
+	if (IS_GEN(gvt->dev_priv, 9) &&
 			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
 			!strncmp(cmd, "lri", 3)) {
 		intel_gvt_hypervisor_read_gpa(s->vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 08c74e65836b..244ad1729764 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1076,8 +1076,10 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 	} else {
 		int type = get_next_pt_type(we->type);
 
-		if (!gtt_type_is_pt(type))
+		if (!gtt_type_is_pt(type)) {
+			ret = -EINVAL;
 			goto err;
+		}
 
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 90673fca792f..e09bd6e0cc4d 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1364,7 +1364,6 @@ static int dma_ctrl_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	u32 trtte = *(u32 *)p_data;
 
 	if ((trtte & 1) && (trtte & (1 << 1)) == 0) {
@@ -1373,11 +1372,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 		return -EINVAL;
 	}
 	write_vreg(vgpu, offset, p_data, bytes);
-	/* TRTTE is not per-context */
-
-	mmio_hw_access_pre(dev_priv);
-	I915_WRITE(_MMIO(offset), vgpu_vreg(vgpu, offset));
-	mmio_hw_access_post(dev_priv);
 
 	return 0;
 }
@@ -1385,15 +1379,6 @@ static int gen9_trtte_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int gen9_trtt_chicken_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	u32 val = *(u32 *)p_data;
-
-	if (val & 1) {
-		/* unblock hw logic */
-		mmio_hw_access_pre(dev_priv);
-		I915_WRITE(_MMIO(offset), val);
-		mmio_hw_access_post(dev_priv);
-	}
 	write_vreg(vgpu, offset, p_data, bytes);
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index edf6d646eb25..90bb3df0db50 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -108,12 +108,13 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
 	{RCS0, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
 	{RCS0, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
-	{RCS0, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */
-	{RCS0, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */
-	{RCS0, TRNULLDETCT, 0, false}, /* 0x4de8 */
-	{RCS0, TRINVTILEDETCT, 0, false}, /* 0x4dec */
-	{RCS0, TRVADR, 0, false}, /* 0x4df0 */
-	{RCS0, TRTTE, 0, false}, /* 0x4df4 */
+	{RCS0, TRVATTL3PTRDW(0), 0, true}, /* 0x4de0 */
+	{RCS0, TRVATTL3PTRDW(1), 0, true}, /* 0x4de4 */
+	{RCS0, TRNULLDETCT, 0, true}, /* 0x4de8 */
+	{RCS0, TRINVTILEDETCT, 0, true}, /* 0x4dec */
+	{RCS0, TRVADR, 0, true}, /* 0x4df0 */
+	{RCS0, TRTTE, 0, true}, /* 0x4df4 */
+	{RCS0, _MMIO(0x4dfc), 0, true},
 
 	{BCS0, RING_GFX_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2229c */
 	{BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
@@ -392,10 +393,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 	if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
 		return;
 
-	if (ring_id == RCS0 &&
-	    (IS_KABYLAKE(dev_priv) ||
-	     IS_BROXTON(dev_priv) ||
-	     IS_COFFEELAKE(dev_priv)))
+	if (ring_id == RCS0 && IS_GEN(dev_priv, 9))
 		return;
 
 	if (!pre && !gen9_render_mocs.initialized)
@@ -470,11 +468,10 @@ static void switch_mmio(struct intel_vgpu *pre,
 			continue;
 		/*
 		 * No need to do save or restore of the mmio which is in context
-		 * state image on kabylake, it's initialized by lri command and
+		 * state image on gen9, it's initialized by lri command and
 		 * save or restore with context together.
 		 */
-		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)
-			|| IS_COFFEELAKE(dev_priv)) && mmio->in_context)
+		if (IS_GEN(dev_priv, 9) && mmio->in_context)
 			continue;
 
 		// save
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 7c99bbc3e2b8..13632dba8b2a 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -298,12 +298,29 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	struct i915_request *req = workload->req;
 	void *shadow_ring_buffer_va;
 	u32 *cs;
+	int err;
 
-	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915)
-		|| IS_COFFEELAKE(req->i915))
-		&& is_inhibit_context(req->hw_context))
+	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
+	/*
+	 * To track whether a request has started on HW, we can emit a
+	 * breadcrumb at the beginning of the request and check its
+	 * timeline's HWSP to see if the breadcrumb has advanced past the
+	 * start of this request. Actually, the request must have the
+	 * init_breadcrumb if its timeline set has_init_bread_crumb, or the
+	 * scheduler might get a wrong state of it during reset. Since the
+	 * requests from gvt always set the has_init_breadcrumb flag, here
+	 * need to do the emit_init_breadcrumb for all the requests.
+	 */
+	if (req->engine->emit_init_breadcrumb) {
+		err = req->engine->emit_init_breadcrumb(req);
+		if (err) {
+			gvt_vgpu_err("fail to emit init breadcrumb\n");
+			return err;
+		}
+	}
+
 	/* allocate shadow ring buffer */
 	cs = intel_ring_begin(workload->req, workload->rb_len / sizeof(u32));
 	if (IS_ERR(cs)) {
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index cc44ebd3b553..49709de69875 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -20,15 +20,14 @@ enum {
 	I915_PRIORITY_INVALID = INT_MIN
 };
 
-#define I915_USER_PRIORITY_SHIFT 3
+#define I915_USER_PRIORITY_SHIFT 2
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
 #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
 #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
 
 #define I915_PRIORITY_WAIT		((u8)BIT(0))
-#define I915_PRIORITY_NEWCLIENT		((u8)BIT(1))
-#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(2))
+#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(1))
 
 #define __NO_PREEMPTION (I915_PRIORITY_WAIT)
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f6c78c0fa74b..c88e538b2ef4 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -502,15 +502,6 @@ void __i915_request_unsubmit(struct i915_request *request)
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	/*
-	 * As we do not allow WAIT to preempt inflight requests,
-	 * once we have executed a request, along with triggering
-	 * any execution callbacks, we must preserve its ordering
-	 * within the non-preemptible FIFO.
-	 */
-	BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK); /* only internal */
-	request->sched.attr.priority |= __NO_PREEMPTION;
-
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags))
 		i915_request_cancel_breadcrumb(request);
 
@@ -582,18 +573,7 @@ semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 
 	switch (state) {
 	case FENCE_COMPLETE:
-		/*
-		 * We only check a small portion of our dependencies
-		 * and so cannot guarantee that there remains no
-		 * semaphore chain across all. Instead of opting
-		 * for the full NOSEMAPHORE boost, we go for the
-		 * smaller (but still preempting) boost of
-		 * NEWCLIENT. This will be enough to boost over
-		 * a busywaiting request (as that cannot be
-		 * NEWCLIENT) without accidentally boosting
-		 * a busywait over real work elsewhere.
-		 */
-		i915_schedule_bump_priority(request, I915_PRIORITY_NEWCLIENT);
+		i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
 		break;
 
 	case FENCE_FREE:
@@ -874,12 +854,6 @@ emit_semaphore_wait(struct i915_request *to,
 	if (err < 0)
 		return err;
 
-	err = i915_sw_fence_await_dma_fence(&to->semaphore,
-					    &from->fence, 0,
-					    I915_FENCE_GFP);
-	if (err < 0)
-		return err;
-
 	/* We need to pin the signaler's HWSP until we are finished reading. */
 	err = i915_timeline_read_hwsp(from, to, &hwsp_offset);
 	if (err)
@@ -945,8 +919,18 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 						    &from->fence, 0,
 						    I915_FENCE_GFP);
 	}
+	if (ret < 0)
+		return ret;
 
-	return ret < 0 ? ret : 0;
+	if (to->sched.flags & I915_SCHED_HAS_SEMAPHORE_CHAIN) {
+		ret = i915_sw_fence_await_dma_fence(&to->semaphore,
+						    &from->fence, 0,
+						    I915_FENCE_GFP);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
 }
 
 int
@@ -1237,7 +1221,7 @@ void i915_request_add(struct i915_request *request)
 		 * the bulk clients. (FQ_CODEL)
 		 */
 		if (list_empty(&request->sched.signalers_list))
-			attr.priority |= I915_PRIORITY_NEWCLIENT;
+			attr.priority |= I915_PRIORITY_WAIT;
 
 		engine->schedule(request, &attr);
 	}
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 39bc4f54e272..108f52e1bf35 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -35,109 +35,6 @@ static inline bool node_signaled(const struct i915_sched_node *node)
 	return i915_request_completed(node_to_request(node));
 }
 
-void i915_sched_node_init(struct i915_sched_node *node)
-{
-	INIT_LIST_HEAD(&node->signalers_list);
-	INIT_LIST_HEAD(&node->waiters_list);
-	INIT_LIST_HEAD(&node->link);
-	node->attr.priority = I915_PRIORITY_INVALID;
-	node->semaphores = 0;
-	node->flags = 0;
-}
-
-static struct i915_dependency *
-i915_dependency_alloc(void)
-{
-	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
-}
-
-static void
-i915_dependency_free(struct i915_dependency *dep)
-{
-	kmem_cache_free(global.slab_dependencies, dep);
-}
-
-bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
-				      struct i915_sched_node *signal,
-				      struct i915_dependency *dep,
-				      unsigned long flags)
-{
-	bool ret = false;
-
-	spin_lock_irq(&schedule_lock);
-
-	if (!node_signaled(signal)) {
-		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
-		dep->signaler = signal;
-		dep->flags = flags;
-
-		/* Keep track of whether anyone on this chain has a semaphore */
-		if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN &&
-		    !node_started(signal))
-			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
-
-		ret = true;
-	}
-
-	spin_unlock_irq(&schedule_lock);
-
-	return ret;
-}
-
-int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal)
-{
-	struct i915_dependency *dep;
-
-	dep = i915_dependency_alloc();
-	if (!dep)
-		return -ENOMEM;
-
-	if (!__i915_sched_node_add_dependency(node, signal, dep,
-					      I915_DEPENDENCY_ALLOC))
-		i915_dependency_free(dep);
-
-	return 0;
-}
-
-void i915_sched_node_fini(struct i915_sched_node *node)
-{
-	struct i915_dependency *dep, *tmp;
-
-	GEM_BUG_ON(!list_empty(&node->link));
-
-	spin_lock_irq(&schedule_lock);
-
-	/*
-	 * Everyone we depended upon (the fences we wait to be signaled)
-	 * should retire before us and remove themselves from our list.
-	 * However, retirement is run independently on each timeline and
-	 * so we may be called out-of-order.
-	 */
-	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
-		GEM_BUG_ON(!node_signaled(dep->signaler));
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del(&dep->wait_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
-	}
-
-	/* Remove ourselves from everyone who depends upon us */
-	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
-		GEM_BUG_ON(dep->signaler != node);
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del(&dep->signal_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
-	}
-
-	spin_unlock_irq(&schedule_lock);
-}
-
 static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 {
 	return rb_entry(rb, struct i915_priolist, node);
@@ -239,6 +136,11 @@ out:
 	return &p->requests[idx];
 }
 
+void __i915_priolist_free(struct i915_priolist *p)
+{
+	kmem_cache_free(global.slab_priorities, p);
+}
+
 struct sched_cache {
 	struct list_head *priolist;
 };
@@ -273,7 +175,7 @@ static bool inflight(const struct i915_request *rq,
 	return active->hw_context == rq->hw_context;
 }
 
-static void __i915_schedule(struct i915_request *rq,
+static void __i915_schedule(struct i915_sched_node *node,
 			    const struct i915_sched_attr *attr)
 {
 	struct intel_engine_cs *engine;
@@ -287,13 +189,13 @@ static void __i915_schedule(struct i915_request *rq,
 	lockdep_assert_held(&schedule_lock);
 	GEM_BUG_ON(prio == I915_PRIORITY_INVALID);
 
-	if (i915_request_completed(rq))
+	if (node_signaled(node))
 		return;
 
-	if (prio <= READ_ONCE(rq->sched.attr.priority))
+	if (prio <= READ_ONCE(node->attr.priority))
 		return;
 
-	stack.signaler = &rq->sched;
+	stack.signaler = node;
 	list_add(&stack.dfs_link, &dfs);
 
 	/*
@@ -344,9 +246,9 @@ static void __i915_schedule(struct i915_request *rq,
 	 * execlists_submit_request()), we can set our own priority and skip
 	 * acquiring the engine locks.
 	 */
-	if (rq->sched.attr.priority == I915_PRIORITY_INVALID) {
-		GEM_BUG_ON(!list_empty(&rq->sched.link));
-		rq->sched.attr = *attr;
+	if (node->attr.priority == I915_PRIORITY_INVALID) {
+		GEM_BUG_ON(!list_empty(&node->link));
+		node->attr = *attr;
 
 		if (stack.dfs_link.next == stack.dfs_link.prev)
 			return;
@@ -355,15 +257,14 @@ static void __i915_schedule(struct i915_request *rq,
 	}
 
 	memset(&cache, 0, sizeof(cache));
-	engine = rq->engine;
+	engine = node_to_request(node)->engine;
 	spin_lock(&engine->timeline.lock);
 
 	/* Fifo and depth-first replacement ensure our deps execute before us */
 	list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
-		struct i915_sched_node *node = dep->signaler;
-
 		INIT_LIST_HEAD(&dep->dfs_link);
 
+		node = dep->signaler;
 		engine = sched_lock_engine(node, engine, &cache);
 		lockdep_assert_held(&engine->timeline.lock);
 
@@ -413,13 +314,20 @@ static void __i915_schedule(struct i915_request *rq,
 void i915_schedule(struct i915_request *rq, const struct i915_sched_attr *attr)
 {
 	spin_lock_irq(&schedule_lock);
-	__i915_schedule(rq, attr);
+	__i915_schedule(&rq->sched, attr);
 	spin_unlock_irq(&schedule_lock);
 }
 
+static void __bump_priority(struct i915_sched_node *node, unsigned int bump)
+{
+	struct i915_sched_attr attr = node->attr;
+
+	attr.priority |= bump;
+	__i915_schedule(node, &attr);
+}
+
 void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
 {
-	struct i915_sched_attr attr;
 	unsigned long flags;
 
 	GEM_BUG_ON(bump & ~I915_PRIORITY_MASK);
@@ -428,17 +336,122 @@ void i915_schedule_bump_priority(struct i915_request *rq, unsigned int bump)
 		return;
 
 	spin_lock_irqsave(&schedule_lock, flags);
+	__bump_priority(&rq->sched, bump);
+	spin_unlock_irqrestore(&schedule_lock, flags);
+}
 
-	attr = rq->sched.attr;
-	attr.priority |= bump;
-	__i915_schedule(rq, &attr);
+void i915_sched_node_init(struct i915_sched_node *node)
+{
+	INIT_LIST_HEAD(&node->signalers_list);
+	INIT_LIST_HEAD(&node->waiters_list);
+	INIT_LIST_HEAD(&node->link);
+	node->attr.priority = I915_PRIORITY_INVALID;
+	node->semaphores = 0;
+	node->flags = 0;
+}
 
-	spin_unlock_irqrestore(&schedule_lock, flags);
+static struct i915_dependency *
+i915_dependency_alloc(void)
+{
+	return kmem_cache_alloc(global.slab_dependencies, GFP_KERNEL);
 }
 
-void __i915_priolist_free(struct i915_priolist *p)
+static void
+i915_dependency_free(struct i915_dependency *dep)
 {
-	kmem_cache_free(global.slab_priorities, p);
+	kmem_cache_free(global.slab_dependencies, dep);
+}
+
+bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
+				      struct i915_sched_node *signal,
+				      struct i915_dependency *dep,
+				      unsigned long flags)
+{
+	bool ret = false;
+
+	spin_lock_irq(&schedule_lock);
+
+	if (!node_signaled(signal)) {
+		INIT_LIST_HEAD(&dep->dfs_link);
+		list_add(&dep->wait_link, &signal->waiters_list);
+		list_add(&dep->signal_link, &node->signalers_list);
+		dep->signaler = signal;
+		dep->flags = flags;
+
+		/* Keep track of whether anyone on this chain has a semaphore */
+		if (signal->flags & I915_SCHED_HAS_SEMAPHORE_CHAIN &&
+		    !node_started(signal))
+			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
+
+		/*
+		 * As we do not allow WAIT to preempt inflight requests,
+		 * once we have executed a request, along with triggering
+		 * any execution callbacks, we must preserve its ordering
+		 * within the non-preemptible FIFO.
+		 */
+		BUILD_BUG_ON(__NO_PREEMPTION & ~I915_PRIORITY_MASK);
+		if (flags & I915_DEPENDENCY_EXTERNAL)
+			__bump_priority(signal, __NO_PREEMPTION);
+
+		ret = true;
+	}
+
+	spin_unlock_irq(&schedule_lock);
+
+	return ret;
+}
+
+int i915_sched_node_add_dependency(struct i915_sched_node *node,
+				   struct i915_sched_node *signal)
+{
+	struct i915_dependency *dep;
+
+	dep = i915_dependency_alloc();
+	if (!dep)
+		return -ENOMEM;
+
+	if (!__i915_sched_node_add_dependency(node, signal, dep,
+					      I915_DEPENDENCY_EXTERNAL |
+					      I915_DEPENDENCY_ALLOC))
+		i915_dependency_free(dep);
+
+	return 0;
+}
+
+void i915_sched_node_fini(struct i915_sched_node *node)
+{
+	struct i915_dependency *dep, *tmp;
+
+	GEM_BUG_ON(!list_empty(&node->link));
+
+	spin_lock_irq(&schedule_lock);
+
+	/*
+	 * Everyone we depended upon (the fences we wait to be signaled)
+	 * should retire before us and remove themselves from our list.
+	 * However, retirement is run independently on each timeline and
+	 * so we may be called out-of-order.
+	 */
+	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
+		GEM_BUG_ON(!node_signaled(dep->signaler));
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
+		list_del(&dep->wait_link);
+		if (dep->flags & I915_DEPENDENCY_ALLOC)
+			i915_dependency_free(dep);
+	}
+
+	/* Remove ourselves from everyone who depends upon us */
+	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
+		GEM_BUG_ON(dep->signaler != node);
+		GEM_BUG_ON(!list_empty(&dep->dfs_link));
+
+		list_del(&dep->signal_link);
+		if (dep->flags & I915_DEPENDENCY_ALLOC)
+			i915_dependency_free(dep);
+	}
+
+	spin_unlock_irq(&schedule_lock);
 }
 
 static void i915_global_scheduler_shrink(void)
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index f1af3916a808..4f2b2eb7c3e5 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -66,7 +66,8 @@ struct i915_dependency {
 	struct list_head wait_link;
 	struct list_head dfs_link;
 	unsigned long flags;
-#define I915_DEPENDENCY_ALLOC BIT(0)
+#define I915_DEPENDENCY_ALLOC		BIT(0)
+#define I915_DEPENDENCY_EXTERNAL	BIT(1)
 };
 
 #endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4e0a351bfbca..11e5a86610bf 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -164,7 +164,7 @@
 #define WA_TAIL_DWORDS 2
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
-#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT | I915_PRIORITY_NOSEMAPHORE)
+#define ACTIVE_PRIORITY (I915_PRIORITY_NOSEMAPHORE)
 
 static int execlists_context_deferred_alloc(struct intel_context *ce,
 					    struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index fbee030db940..e8b0b5dbcb2c 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -99,12 +99,14 @@ static int live_busywait_preempt(void *arg)
 	ctx_hi = kernel_context(i915);
 	if (!ctx_hi)
 		goto err_unlock;
-	ctx_hi->sched.priority = INT_MAX;
+	ctx_hi->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
 	ctx_lo = kernel_context(i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority = INT_MIN;
+	ctx_lo->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
@@ -954,12 +956,14 @@ static int live_preempt_hang(void *arg)
 	ctx_hi = kernel_context(i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
-	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+	ctx_hi->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
 	ctx_lo = kernel_context(i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
-	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+	ctx_lo->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
 	for_each_engine(engine, i915, id) {
 		struct i915_request *rq;
diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig
index 591611dc4e34..81963e964b0f 100644
--- a/drivers/gpu/drm/panfrost/Kconfig
+++ b/drivers/gpu/drm/panfrost/Kconfig
@@ -9,6 +9,7 @@ config DRM_PANFROST
 	select IOMMU_SUPPORT
 	select IOMMU_IO_PGTABLE_LPAE
 	select DRM_GEM_SHMEM_HELPER
+	select PM_DEVFREQ
 	help
 	  DRM driver for ARM Mali Midgard (T6xx, T7xx, T8xx) and
 	  Bifrost (G3x, G5x, G7x) GPUs.
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 238bd1d89d43..29fcffdf2d57 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -140,8 +140,8 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 		return 0;
 
 	ret = dev_pm_opp_of_add_table(&pfdev->pdev->dev);
-	if (ret == -ENODEV) /* Optional, continue without devfreq */
-		return 0;
+	if (ret)
+		return ret;
 
 	panfrost_devfreq_reset(pfdev);
 
@@ -170,9 +170,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev)
 {
 	int i;
 
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	panfrost_devfreq_reset(pfdev);
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
 		pfdev->devfreq.slot[i].busy = false;
@@ -182,9 +179,6 @@ void panfrost_devfreq_resume(struct panfrost_device *pfdev)
 
 void panfrost_devfreq_suspend(struct panfrost_device *pfdev)
 {
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	devfreq_suspend_device(pfdev->devfreq.devfreq);
 }
 
@@ -194,9 +188,6 @@ static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, i
 	ktime_t now;
 	ktime_t last;
 
-	if (!pfdev->devfreq.devfreq)
-		return;
-
 	now = ktime_get();
 	last = pfdev->devfreq.slot[slot].time_last_update;
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 6ff585055a07..bfa7e2b146df 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -457,8 +457,9 @@ static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi,
 	u16 delay = 50 - 1;
 
 	if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
-		delay = (mode->htotal - mode->hdisplay) * 150;
-		delay /= (mode->clock / 1000) * 8;
+		u32 hsync_porch = (mode->htotal - mode->hdisplay) * 150;
+
+		delay = (hsync_porch / ((mode->clock / 1000) * 8));
 		delay -= 50;
 	}
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 66ea3a902e36..43643ad31730 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -293,7 +293,8 @@ static int sun8i_hdmi_phy_config_h3(struct dw_hdmi *hdmi,
 				 SUN8I_HDMI_PHY_ANA_CFG2_REG_BIGSW |
 				 SUN8I_HDMI_PHY_ANA_CFG2_REG_SLV(4);
 		ana_cfg3_init |= SUN8I_HDMI_PHY_ANA_CFG3_REG_AMPCK(9) |
-				 SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13);
+				 SUN8I_HDMI_PHY_ANA_CFG3_REG_AMP(13) |
+				 SUN8I_HDMI_PHY_ANA_CFG3_REG_EMP(3);
 	}
 
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_ANA_CFG1_REG,
@@ -672,22 +673,13 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 				goto err_put_clk_pll0;
 			}
 		}
-
-		ret = sun8i_phy_clk_create(phy, dev,
-					   phy->variant->has_second_pll);
-		if (ret) {
-			dev_err(dev, "Couldn't create the PHY clock\n");
-			goto err_put_clk_pll1;
-		}
-
-		clk_prepare_enable(phy->clk_phy);
 	}
 
 	phy->rst_phy = of_reset_control_get_shared(node, "phy");
 	if (IS_ERR(phy->rst_phy)) {
 		dev_err(dev, "Could not get phy reset control\n");
 		ret = PTR_ERR(phy->rst_phy);
-		goto err_disable_clk_phy;
+		goto err_put_clk_pll1;
 	}
 
 	ret = reset_control_deassert(phy->rst_phy);
@@ -708,18 +700,29 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 		goto err_disable_clk_bus;
 	}
 
+	if (phy->variant->has_phy_clk) {
+		ret = sun8i_phy_clk_create(phy, dev,
+					   phy->variant->has_second_pll);
+		if (ret) {
+			dev_err(dev, "Couldn't create the PHY clock\n");
+			goto err_disable_clk_mod;
+		}
+
+		clk_prepare_enable(phy->clk_phy);
+	}
+
 	hdmi->phy = phy;
 
 	return 0;
 
+err_disable_clk_mod:
+	clk_disable_unprepare(phy->clk_mod);
 err_disable_clk_bus:
 	clk_disable_unprepare(phy->clk_bus);
 err_deassert_rst_phy:
 	reset_control_assert(phy->rst_phy);
 err_put_rst_phy:
 	reset_control_put(phy->rst_phy);
-err_disable_clk_phy:
-	clk_disable_unprepare(phy->clk_phy);
 err_put_clk_pll1:
 	clk_put(phy->clk_pll1);
 err_put_clk_pll0:
diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c
index 36990b80e790..16077785ad47 100644
--- a/drivers/gpu/drm/vmwgfx/ttm_object.c
+++ b/drivers/gpu/drm/vmwgfx/ttm_object.c
@@ -174,7 +174,7 @@ int ttm_base_object_init(struct ttm_object_file *tfile,
 	kref_init(&base->refcount);
 	idr_preload(GFP_KERNEL);
 	spin_lock(&tdev->object_lock);
-	ret = idr_alloc(&tdev->idr, base, 0, 0, GFP_NOWAIT);
+	ret = idr_alloc(&tdev->idr, base, 1, 0, GFP_NOWAIT);
 	spin_unlock(&tdev->object_lock);
 	idr_preload_end();
 	if (ret < 0)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index bf6c3500d363..4ff11a0077e1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1239,7 +1239,13 @@ static int vmw_master_set(struct drm_device *dev,
 	}
 
 	dev_priv->active_master = vmaster;
-	drm_sysfs_hotplug_event(dev);
+
+	/*
+	 * Inform a new master that the layout may have changed while
+	 * it was gone.
+	 */
+	if (!from_open)
+		drm_sysfs_hotplug_event(dev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 96983c47fb40..366dcfc1f9bb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -296,7 +296,7 @@ struct vmw_sg_table {
 struct vmw_piter {
 	struct page **pages;
 	const dma_addr_t *addrs;
-	struct sg_page_iter iter;
+	struct sg_dma_page_iter iter;
 	unsigned long i;
 	unsigned long num_pages;
 	bool (*next)(struct vmw_piter *);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 2ff7ba04d8c8..33533d126277 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2010,6 +2010,11 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
 		return 0;
 
 	if (cmd->body.shid != SVGA3D_INVALID_ID) {
+		/*
+		 * This is the compat shader path - Per device guest-backed
+		 * shaders, but user-space thinks it's per context host-
+		 * backed shaders.
+		 */
 		res = vmw_shader_lookup(vmw_context_res_man(ctx),
 					cmd->body.shid, cmd->body.type);
 		if (!IS_ERR(res)) {
@@ -2017,6 +2022,14 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv,
 							    VMW_RES_DIRTY_NONE);
 			if (unlikely(ret != 0))
 				return ret;
+
+			ret = vmw_resource_relocation_add
+				(sw_context, res,
+				 vmw_ptr_diff(sw_context->buf_start,
+					      &cmd->body.shid),
+				 vmw_res_rel_normal);
+			if (unlikely(ret != 0))
+				return ret;
 		}
 	}
 
@@ -2193,7 +2206,8 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv,
 
 	cmd = container_of(header, typeof(*cmd), header);
 
-	if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX) {
+	if (cmd->body.type >= SVGA3D_SHADERTYPE_DX10_MAX ||
+	    cmd->body.type < SVGA3D_SHADERTYPE_MIN) {
 		VMW_DEBUG_USER("Illegal shader type %u.\n",
 			       (unsigned int) cmd->body.type);
 		return -EINVAL;
@@ -2414,6 +2428,10 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv,
 		return -EINVAL;
 
 	cmd = container_of(header, typeof(*cmd), header);
+	if (unlikely(cmd->sid == SVGA3D_INVALID_ID)) {
+		VMW_DEBUG_USER("Invalid surface id.\n");
+		return -EINVAL;
+	}
 	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				VMW_RES_DIRTY_NONE, user_surface_converter,
 				&cmd->sid, &srf);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index a3357ff7540d..a6ea75b58a83 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -266,7 +266,9 @@ static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
 
 static bool __vmw_piter_sg_next(struct vmw_piter *viter)
 {
-	return __sg_page_iter_next(&viter->iter);
+	bool ret = __vmw_piter_non_sg_next(viter);
+
+	return __sg_page_iter_dma_next(&viter->iter) && ret;
 }
 
 
@@ -284,12 +286,6 @@ static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
 	return viter->pages[viter->i];
 }
 
-static struct page *__vmw_piter_sg_page(struct vmw_piter *viter)
-{
-	return sg_page_iter_page(&viter->iter);
-}
-
-
 /**
  * Helper functions to return the DMA address of the current page.
  *
@@ -311,13 +307,7 @@ static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
 
 static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
 {
-	/*
-	 * FIXME: This driver wrongly mixes DMA and CPU SG list iteration and
-	 * needs revision. See
-	 * https://lore.kernel.org/lkml/20190104223531.GA1705@ziepe.ca/
-	 */
-	return sg_page_iter_dma_address(
-		container_of(&viter->iter, struct sg_dma_page_iter, base));
+	return sg_page_iter_dma_address(&viter->iter);
 }
 
 
@@ -336,26 +326,23 @@ void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
 {
 	viter->i = p_offset - 1;
 	viter->num_pages = vsgt->num_pages;
+	viter->page = &__vmw_piter_non_sg_page;
+	viter->pages = vsgt->pages;
 	switch (vsgt->mode) {
 	case vmw_dma_phys:
 		viter->next = &__vmw_piter_non_sg_next;
 		viter->dma_address = &__vmw_piter_phys_addr;
-		viter->page = &__vmw_piter_non_sg_page;
-		viter->pages = vsgt->pages;
 		break;
 	case vmw_dma_alloc_coherent:
 		viter->next = &__vmw_piter_non_sg_next;
 		viter->dma_address = &__vmw_piter_dma_addr;
-		viter->page = &__vmw_piter_non_sg_page;
 		viter->addrs = vsgt->addrs;
-		viter->pages = vsgt->pages;
 		break;
 	case vmw_dma_map_populate:
 	case vmw_dma_map_bind:
 		viter->next = &__vmw_piter_sg_next;
 		viter->dma_address = &__vmw_piter_sg_addr;
-		viter->page = &__vmw_piter_sg_page;
-		__sg_page_iter_start(&viter->iter, vsgt->sgt->sgl,
+		__sg_page_iter_start(&viter->iter.base, vsgt->sgt->sgl,
 				     vsgt->sgt->orig_nents, p_offset);
 		break;
 	default: