Merge commit 'v4.16-rc4~0' into patchwork

* commit 'v4.16-rc4~0': (900 commits)
  Linux 4.16-rc4
  memremap: fix softlockup reports at teardown
  libnvdimm: re-enable deep flush for pmem devices via fsync()
  MAINTAINERS: take over Kconfig maintainership
  vfio: disable filesystem-dax page pinning
  kconfig: fix line number in recursive inclusion error message
  Coccinelle: memdup: Fix typo in warning messages
  i2c: octeon: Prevent error message on bus error
  parisc: Reduce irq overhead when run in qemu
  parisc: Use cr16 interval timers unconditionally on qemu
  parisc: Check if secondary CPUs want own PDC calls
  parisc: Hide virtual kernel memory layout
  parisc: Fix ordering of cache and TLB flushes
  kconfig: Update ncurses package names for menuconfig
  kbuild/kallsyms: trivial typo fix
  kbuild: test --build-id linker flag by ld-option instead of cc-ldoption
  kbuild: drop superfluous GCC_PLUGINS_CFLAGS assignment
  kconfig: Don't leak choice names during parsing
  sh: fix build error for empty CONFIG_BUILTIN_DTB_SOURCE
  kconfig: set SYMBOL_AUTO to the symbol marked with defconfig_list
  ...

58 files changed, 662 insertions, 336 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d5a2eefd6c3e..74edba18b159 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1156,7 +1156,7 @@ static inline void amdgpu_set_ib_value(struct amdgpu_cs_parser *p,
 /*
  * Writeback
  */
-#define AMDGPU_MAX_WB 512	/* Reserve at most 512 WB slots for amdgpu-owned rings. */
+#define AMDGPU_MAX_WB 128	/* Reserve at most 128 WB slots for amdgpu-owned rings. */
 
 struct amdgpu_wb {
 	struct amdgpu_bo	*wb_obj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index e2c3c5ec42d1..c53095b3b0fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -568,6 +568,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
 	/* HG _PR3 doesn't seem to work on this A+A weston board */
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 8ca3783f2deb..74d2efaec52f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -736,9 +736,11 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (encoder) {
 		struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
@@ -757,8 +759,12 @@ amdgpu_connector_lvds_detect(struct drm_connector *connector, bool force)
 	/* check acpi lid status ??? */
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 
@@ -868,9 +874,11 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = amdgpu_connector_best_single_encoder(connector);
 	if (!encoder)
@@ -924,8 +932,10 @@ amdgpu_connector_vga_detect(struct drm_connector *connector, bool force)
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -988,9 +998,11 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
@@ -1115,8 +1127,10 @@ out:
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 exit:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -1359,9 +1373,11 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force)
 	struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector);
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
@@ -1429,8 +1445,10 @@ amdgpu_connector_dp_detect(struct drm_connector *connector, bool force)
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 00a50cc5ec9a..af1b879a9ee9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -492,7 +492,7 @@ static int amdgpu_device_wb_init(struct amdgpu_device *adev)
 		memset(&adev->wb.used, 0, sizeof(adev->wb.used));
 
 		/* clear wb memory */
-		memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t));
+		memset((char *)adev->wb.wb, 0, AMDGPU_MAX_WB * sizeof(uint32_t) * 8);
 	}
 
 	return 0;
@@ -530,8 +530,9 @@ int amdgpu_device_wb_get(struct amdgpu_device *adev, u32 *wb)
  */
 void amdgpu_device_wb_free(struct amdgpu_device *adev, u32 wb)
 {
+	wb >>= 3;
 	if (wb < adev->wb.num_wb)
-		__clear_bit(wb >> 3, adev->wb.used);
+		__clear_bit(wb, adev->wb.used);
 }
 
 /**
@@ -1455,11 +1456,6 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.hw)
 			continue;
-		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
-			amdgpu_free_static_csa(adev);
-			amdgpu_device_wb_fini(adev);
-			amdgpu_device_vram_scratch_fini(adev);
-		}
 
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 			adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE) {
@@ -1486,6 +1482,13 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
+
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
+			amdgpu_free_static_csa(adev);
+			amdgpu_device_wb_fini(adev);
+			amdgpu_device_vram_scratch_fini(adev);
+		}
+
 		r = adev->ip_blocks[i].version->funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
 		if (r) {
@@ -2284,14 +2287,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 				drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 			}
 			drm_modeset_unlock_all(dev);
-		} else {
-			/*
-			 * There is no equivalent atomic helper to turn on
-			 * display, so we defined our own function for this,
-			 * once suspend resume is supported by the atomic
-			 * framework this will be reworked
-			 */
-			amdgpu_dm_display_resume(adev);
 		}
 	}
 
@@ -2726,7 +2721,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	if (amdgpu_device_has_dc_support(adev)) {
 		if (drm_atomic_helper_resume(adev->ddev, state))
 			dev_info(adev->dev, "drm resume failed:%d\n", r);
-		amdgpu_dm_display_resume(adev);
 	} else {
 		drm_helper_resume_force_mode(adev->ddev);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index e14ab34d8262..7c2be32c5aea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -75,7 +75,7 @@ static int amdgpu_gtt_mgr_init(struct ttm_mem_type_manager *man,
 static int amdgpu_gtt_mgr_fini(struct ttm_mem_type_manager *man)
 {
 	struct amdgpu_gtt_mgr *mgr = man->priv;
-
+	spin_lock(&mgr->lock);
 	drm_mm_takedown(&mgr->mm);
 	spin_unlock(&mgr->lock);
 	kfree(mgr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 56bcd59c3399..36483e0d3c97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -257,7 +257,8 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	r = drm_irq_install(adev->ddev, adev->ddev->pdev->irq);
 	if (r) {
 		adev->irq.installed = false;
-		flush_work(&adev->hotplug_work);
+		if (!amdgpu_device_has_dc_support(adev))
+			flush_work(&adev->hotplug_work);
 		cancel_work_sync(&adev->reset_work);
 		return r;
 	}
@@ -282,7 +283,8 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
 			pci_disable_msi(adev->pdev);
-		flush_work(&adev->hotplug_work);
+		if (!amdgpu_device_has_dc_support(adev))
+			flush_work(&adev->hotplug_work);
 		cancel_work_sync(&adev->reset_work);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 2719937e09d6..3b7e7af09ead 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -634,7 +634,7 @@ static int gmc_v9_0_late_init(void *handle)
 	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
 		BUG_ON(vm_inv_eng[i] > 16);
 
-	if (adev->asic_type == CHIP_VEGA10) {
+	if (adev->asic_type == CHIP_VEGA10 && !amdgpu_sriov_vf(adev)) {
 		r = gmc_v9_0_ecc_available(adev);
 		if (r == 1) {
 			DRM_INFO("ECC is active.\n");
@@ -682,7 +682,10 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 	adev->mc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
 	if (!adev->mc.vram_width) {
 		/* hbm memory channel size */
-		chansize = 128;
+		if (adev->flags & AMD_IS_APU)
+			chansize = 64;
+		else
+			chansize = 128;
 
 		tmp = RREG32_SOC15(DF, 0, mmDF_CS_AON0_DramBaseAddress0);
 		tmp &= DF_CS_AON0_DramBaseAddress0__IntLvNumChan_MASK;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index e92fb372bc99..91cf95a8c39c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -238,31 +238,27 @@ static uint64_t sdma_v4_0_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v4_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;
 		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-		wptr = &local_wptr;
 		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
 		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
 				me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = highbit;
+		wptr = wptr << 32;
+		wptr |= lowbit;
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index b2bfedaf57f1..9bab4842cd44 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -1618,7 +1618,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_enc_ring_vm_funcs = {
 	.set_wptr = uvd_v6_0_enc_ring_set_wptr,
 	.emit_frame_size =
 		4 + /* uvd_v6_0_enc_ring_emit_pipeline_sync */
-		6 + /* uvd_v6_0_enc_ring_emit_vm_flush */
+		5 + /* uvd_v6_0_enc_ring_emit_vm_flush */
 		5 + 5 + /* uvd_v6_0_enc_ring_emit_fence x2 vm fence */
 		1, /* uvd_v6_0_enc_ring_insert_end */
 	.emit_ib_size = 5, /* uvd_v6_0_enc_ring_emit_ib */
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 1ce4c98385e3..862835dc054e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -629,11 +629,13 @@ static int dm_resume(void *handle)
 {
 	struct amdgpu_device *adev = handle;
 	struct amdgpu_display_manager *dm = &adev->dm;
+	int ret = 0;
 
 	/* power on hardware */
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);
 
-	return 0;
+	ret = amdgpu_dm_display_resume(adev);
+	return ret;
 }
 
 int amdgpu_dm_display_resume(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 61e8c3e02d16..639421a00ab6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -718,7 +718,7 @@ static enum link_training_result perform_channel_equalization_sequence(
 	uint32_t retries_ch_eq;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = {{0}};
-	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};;
+	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};
 
 	hw_tr_pattern = get_supported_tp(link);
 
@@ -1465,7 +1465,7 @@ void decide_link_settings(struct dc_stream_state *stream,
 	/* MST doesn't perform link training for now
 	 * TODO: add MST specific link training routine
 	 */
-	if (is_mst_supported(link)) {
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
 		*link_setting = link->verified_link_cap;
 		return;
 	}
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 261811e0c094..539c3e0a6292 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -197,7 +197,8 @@ bool dc_stream_set_cursor_attributes(
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 
-		if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp))
+		if (pipe_ctx->stream != stream || (!pipe_ctx->plane_res.xfm &&
+		    !pipe_ctx->plane_res.dpp) || !pipe_ctx->plane_res.ipp)
 			continue;
 		if (pipe_ctx->top_pipe && pipe_ctx->plane_state != pipe_ctx->top_pipe->plane_state)
 			continue;
@@ -273,7 +274,8 @@ bool dc_stream_set_cursor_position(
 		if (pipe_ctx->stream != stream ||
 				(!pipe_ctx->plane_res.mi  && !pipe_ctx->plane_res.hubp) ||
 				!pipe_ctx->plane_state ||
-				(!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp))
+				(!pipe_ctx->plane_res.xfm && !pipe_ctx->plane_res.dpp) ||
+				!pipe_ctx->plane_res.ipp)
 			continue;
 
 		if (pipe_ctx->plane_state->address.type
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 4c3223a4d62b..adb6e7b9280c 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -162,7 +162,7 @@ static int pp_hw_init(void *handle)
 		if(hwmgr->smumgr_funcs->start_smu(pp_handle->hwmgr)) {
 			pr_err("smc start failed\n");
 			hwmgr->smumgr_funcs->smu_fini(pp_handle->hwmgr);
-			return -EINVAL;;
+			return -EINVAL;
 		}
 		if (ret == PP_DPM_DISABLED)
 			goto exit;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 41e42beff213..08e8a793714f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -2756,10 +2756,13 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				    PHM_PlatformCaps_DisableMclkSwitchingForFrameLock);
 
 
-	disable_mclk_switching = ((1 < info.display_count) ||
-				  disable_mclk_switching_for_frame_lock ||
-				  smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) ||
-				  (mode_info.refresh_rate > 120));
+	if (info.display_count == 0)
+		disable_mclk_switching = false;
+	else
+		disable_mclk_switching = ((1 < info.display_count) ||
+					  disable_mclk_switching_for_frame_lock ||
+					  smu7_vblank_too_short(hwmgr, mode_info.vblank_time_us) ||
+					  (mode_info.refresh_rate > 120));
 
 	sclk = smu7_ps->performance_levels[0].engine_clock;
 	mclk = smu7_ps->performance_levels[0].memory_clock;
@@ -4534,13 +4537,6 @@ static int smu7_set_power_profile_state(struct pp_hwmgr *hwmgr,
 	int tmp_result, result = 0;
 	uint32_t sclk_mask = 0, mclk_mask = 0;
 
-	if (hwmgr->chip_id == CHIP_FIJI) {
-		if (request->type == AMD_PP_GFX_PROFILE)
-			smu7_enable_power_containment(hwmgr);
-		else if (request->type == AMD_PP_COMPUTE_PROFILE)
-			smu7_disable_power_containment(hwmgr);
-	}
-
 	if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_AUTO)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 2d55dabc77d4..5f9c3efb532f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3168,10 +3168,13 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	disable_mclk_switching_for_vr = PP_CAP(PHM_PlatformCaps_DisableMclkSwitchForVR);
 	force_mclk_high = PP_CAP(PHM_PlatformCaps_ForceMclkHigh);
 
-	disable_mclk_switching = (info.display_count > 1) ||
-				    disable_mclk_switching_for_frame_lock ||
-				    disable_mclk_switching_for_vr ||
-				    force_mclk_high;
+	if (info.display_count == 0)
+		disable_mclk_switching = false;
+	else
+		disable_mclk_switching = (info.display_count > 1) ||
+			disable_mclk_switching_for_frame_lock ||
+			disable_mclk_switching_for_vr ||
+			force_mclk_high;
 
 	sclk = vega10_ps->performance_levels[0].gfx_clock;
 	mclk = vega10_ps->performance_levels[0].mem_clock;
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index cd23b1b28259..c91b9b054e3f 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -294,22 +294,7 @@ static void cirrus_crtc_prepare(struct drm_crtc *crtc)
 {
 }
 
-/*
- * This is called after a mode is programmed. It should reverse anything done
- * by the prepare function
- */
-static void cirrus_crtc_commit(struct drm_crtc *crtc)
-{
-}
-
-/*
- * The core can pass us a set of gamma values to program. We actually only
- * use this for 8-bit mode so can't perform smooth fades on deeper modes,
- * but it's a requirement that we provide the function
- */
-static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-				 u16 *blue, uint32_t size,
-				 struct drm_modeset_acquire_ctx *ctx)
+static void cirrus_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct cirrus_device *cdev = dev->dev_private;
@@ -317,7 +302,7 @@ static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
 	int i;
 
 	if (!crtc->enabled)
-		return 0;
+		return;
 
 	r = crtc->gamma_store;
 	g = r + crtc->gamma_size;
@@ -330,6 +315,27 @@ static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
 		WREG8(PALETTE_DATA, *g++ >> 8);
 		WREG8(PALETTE_DATA, *b++ >> 8);
 	}
+}
+
+/*
+ * This is called after a mode is programmed. It should reverse anything done
+ * by the prepare function
+ */
+static void cirrus_crtc_commit(struct drm_crtc *crtc)
+{
+	cirrus_crtc_load_lut(crtc);
+}
+
+/*
+ * The core can pass us a set of gamma values to program. We actually only
+ * use this for 8-bit mode so can't perform smooth fades on deeper modes,
+ * but it's a requirement that we provide the function
+ */
+static int cirrus_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
+				 u16 *blue, uint32_t size,
+				 struct drm_modeset_acquire_ctx *ctx)
+{
+	cirrus_crtc_load_lut(crtc);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index ab4032167094..ae3cbfe9e01c 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1878,6 +1878,8 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
 		new_crtc_state->event->base.completion = &commit->flip_done;
 		new_crtc_state->event->base.completion_release = release_crtc_commit;
 		drm_crtc_commit_get(commit);
+
+		commit->abort_completion = true;
 	}
 
 	for_each_oldnew_connector_in_state(state, conn, old_conn_state, new_conn_state, i) {
@@ -3421,8 +3423,21 @@ EXPORT_SYMBOL(drm_atomic_helper_crtc_duplicate_state);
 void __drm_atomic_helper_crtc_destroy_state(struct drm_crtc_state *state)
 {
 	if (state->commit) {
+		/*
+		 * In the event that a non-blocking commit returns
+		 * -ERESTARTSYS before the commit_tail work is queued, we will
+		 * have an extra reference to the commit object. Release it, if
+		 * the event has not been consumed by the worker.
+		 *
+		 * state->event may be freed, so we can't directly look at
+		 * state->event->base.completion.
+		 */
+		if (state->event && state->commit->abort_completion)
+			drm_crtc_commit_put(state->commit);
+
 		kfree(state->commit->event);
 		state->commit->event = NULL;
+
 		drm_crtc_commit_put(state->commit);
 	}
 
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index ddd537914575..4f751a9d71a3 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -113,6 +113,9 @@ static const struct edid_quirk {
 	/* AEO model 0 reports 8 bpc, but is a 6 bpc panel */
 	{ "AEO", 0, EDID_QUIRK_FORCE_6BPC },
 
+	/* CPT panel of Asus UX303LA reports 8 bpc, but is a 6 bpc panel */
+	{ "CPT", 0x17df, EDID_QUIRK_FORCE_6BPC },
+
 	/* Belinea 10 15 55 */
 	{ "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 },
 	{ "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 },
@@ -162,6 +165,24 @@ static const struct edid_quirk {
 
 	/* HTC Vive VR Headset */
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
+
+	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
+	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
+	{ "OVR", 0x0003, EDID_QUIRK_NON_DESKTOP },
+	{ "OVR", 0x0004, EDID_QUIRK_NON_DESKTOP },
+
+	/* Windows Mixed Reality Headsets */
+	{ "ACR", 0x7fce, EDID_QUIRK_NON_DESKTOP },
+	{ "HPN", 0x3515, EDID_QUIRK_NON_DESKTOP },
+	{ "LEN", 0x0408, EDID_QUIRK_NON_DESKTOP },
+	{ "LEN", 0xb800, EDID_QUIRK_NON_DESKTOP },
+	{ "FUJ", 0x1970, EDID_QUIRK_NON_DESKTOP },
+	{ "DEL", 0x7fce, EDID_QUIRK_NON_DESKTOP },
+	{ "SEC", 0x144a, EDID_QUIRK_NON_DESKTOP },
+	{ "AUS", 0xc102, EDID_QUIRK_NON_DESKTOP },
+
+	/* Sony PlayStation VR Headset */
+	{ "SNY", 0x0704, EDID_QUIRK_NON_DESKTOP },
 };
 
 /*
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index 5a13ff29f4f0..c0530a1af5e3 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -121,6 +121,10 @@ int drm_mode_addfb(struct drm_device *dev,
 	r.pixel_format = drm_mode_legacy_fb_format(or->bpp, or->depth);
 	r.handles[0] = or->handle;
 
+	if (r.pixel_format == DRM_FORMAT_XRGB2101010 &&
+	    dev->driver->driver_features & DRIVER_PREFER_XBGR_30BPP)
+		r.pixel_format = DRM_FORMAT_XBGR2101010;
+
 	ret = drm_mode_addfb2(dev, &r, file_priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 186c4e90cc1c..89eef1bb4ddc 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -836,9 +836,24 @@ struct drm_mm_node *drm_mm_scan_color_evict(struct drm_mm_scan *scan)
 	if (!mm->color_adjust)
 		return NULL;
 
-	hole = list_first_entry(&mm->hole_stack, typeof(*hole), hole_stack);
-	hole_start = __drm_mm_hole_node_start(hole);
-	hole_end = hole_start + hole->hole_size;
+	/*
+	 * The hole found during scanning should ideally be the first element
+	 * in the hole_stack list, but due to side-effects in the driver it
+	 * may not be.
+	 */
+	list_for_each_entry(hole, &mm->hole_stack, hole_stack) {
+		hole_start = __drm_mm_hole_node_start(hole);
+		hole_end = hole_start + hole->hole_size;
+
+		if (hole_start <= scan->hit_start &&
+		    hole_end >= scan->hit_end)
+			break;
+	}
+
+	/* We should only be called after we found the hole previously */
+	DRM_MM_BUG_ON(&hole->hole_stack == &mm->hole_stack);
+	if (unlikely(&hole->hole_stack == &mm->hole_stack))
+		return NULL;
 
 	DRM_MM_BUG_ON(hole_start > scan->hit_start);
 	DRM_MM_BUG_ON(hole_end < scan->hit_end);
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 555fbe54d6e2..00b8445ba819 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -654,6 +654,26 @@ out:
 }
 
 /**
+ * drm_kms_helper_is_poll_worker - is %current task an output poll worker?
+ *
+ * Determine if %current task is an output poll worker.  This can be used
+ * to select distinct code paths for output polling versus other contexts.
+ *
+ * One use case is to avoid a deadlock between the output poll worker and
+ * the autosuspend worker wherein the latter waits for polling to finish
+ * upon calling drm_kms_helper_poll_disable(), while the former waits for
+ * runtime suspend to finish upon calling pm_runtime_get_sync() in a
+ * connector ->detect hook.
+ */
+bool drm_kms_helper_is_poll_worker(void)
+{
+	struct work_struct *work = current_work();
+
+	return work && work->func == output_poll_execute;
+}
+EXPORT_SYMBOL(drm_kms_helper_is_poll_worker);
+
+/**
  * drm_kms_helper_poll_disable - disable output polling
  * @dev: drm_device
  *
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 2b8bf2dd6387..f68ef1b3a28c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -286,7 +286,6 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 
 	node = kcalloc(G2D_CMDLIST_NUM, sizeof(*node), GFP_KERNEL);
 	if (!node) {
-		dev_err(dev, "failed to allocate memory\n");
 		ret = -ENOMEM;
 		goto err;
 	}
@@ -926,7 +925,7 @@ static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no)
 	struct drm_device *drm_dev = g2d->subdrv.drm_dev;
 	struct g2d_runqueue_node *runqueue_node = g2d->runqueue_node;
 	struct drm_exynos_pending_g2d_event *e;
-	struct timeval now;
+	struct timespec64 now;
 
 	if (list_empty(&runqueue_node->event_list))
 		return;
@@ -934,9 +933,9 @@ static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no)
 	e = list_first_entry(&runqueue_node->event_list,
 			     struct drm_exynos_pending_g2d_event, base.link);
 
-	do_gettimeofday(&now);
+	ktime_get_ts64(&now);
 	e->event.tv_sec = now.tv_sec;
-	e->event.tv_usec = now.tv_usec;
+	e->event.tv_usec = now.tv_nsec / NSEC_PER_USEC;
 	e->event.cmdlist_no = cmdlist_no;
 
 	drm_send_event(drm_dev, &e->base);
@@ -1358,10 +1357,9 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 		return -EFAULT;
 
 	runqueue_node = kmem_cache_alloc(g2d->runqueue_slab, GFP_KERNEL);
-	if (!runqueue_node) {
-		dev_err(dev, "failed to allocate memory\n");
+	if (!runqueue_node)
 		return -ENOMEM;
-	}
+
 	run_cmdlist = &runqueue_node->run_cmdlist;
 	event_list = &runqueue_node->event_list;
 	INIT_LIST_HEAD(run_cmdlist);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.h b/drivers/gpu/drm/exynos/exynos_drm_rotator.h
deleted file mode 100644
index 71a0b4c0c1e8..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright (c) 2012 Samsung Electronics Co., Ltd.
- *
- * Authors:
- *	YoungJun Cho <yj44.cho@samsung.com>
- *	Eunchul Kim <chulspro.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef	_EXYNOS_DRM_ROTATOR_H_
-#define	_EXYNOS_DRM_ROTATOR_H_
-
-/* TODO */
-
-#endif
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index a4b75a46f946..abd84cbcf1c2 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1068,10 +1068,13 @@ static void hdmi_audio_config(struct hdmi_context *hdata)
 	/* Configuration I2S input ports. Configure I2S_PIN_SEL_0~4 */
 	hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_0, HDMI_I2S_SEL_SCLK(5)
 			| HDMI_I2S_SEL_LRCK(6));
-	hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_1, HDMI_I2S_SEL_SDATA1(1)
-			| HDMI_I2S_SEL_SDATA2(4));
+
+	hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_1, HDMI_I2S_SEL_SDATA1(3)
+			| HDMI_I2S_SEL_SDATA0(4));
+
 	hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_2, HDMI_I2S_SEL_SDATA3(1)
 			| HDMI_I2S_SEL_SDATA2(2));
+
 	hdmi_reg_writeb(hdata, HDMI_I2S_PIN_SEL_3, HDMI_I2S_SEL_DSD(0));
 
 	/* I2S_CON_1 & 2 */
diff --git a/drivers/gpu/drm/exynos/regs-fimc.h b/drivers/gpu/drm/exynos/regs-fimc.h
index 30496134a3d0..d7cbe53c4c01 100644
--- a/drivers/gpu/drm/exynos/regs-fimc.h
+++ b/drivers/gpu/drm/exynos/regs-fimc.h
@@ -569,7 +569,7 @@
 #define EXYNOS_CIIMGEFF_FIN_EMBOSSING		(4 << 26)
 #define EXYNOS_CIIMGEFF_FIN_SILHOUETTE		(5 << 26)
 #define EXYNOS_CIIMGEFF_FIN_MASK			(7 << 26)
-#define EXYNOS_CIIMGEFF_PAT_CBCR_MASK		((0xff < 13) | (0xff < 0))
+#define EXYNOS_CIIMGEFF_PAT_CBCR_MASK		((0xff << 13) | (0xff << 0))
 
 /* Real input DMA size register */
 #define EXYNOS_CIREAL_ISIZE_AUTOLOAD_ENABLE	(1 << 31)
diff --git a/drivers/gpu/drm/exynos/regs-hdmi.h b/drivers/gpu/drm/exynos/regs-hdmi.h
index 04be0f7e8193..4420c203ac85 100644
--- a/drivers/gpu/drm/exynos/regs-hdmi.h
+++ b/drivers/gpu/drm/exynos/regs-hdmi.h
@@ -464,7 +464,7 @@
 
 /* I2S_PIN_SEL_1 */
 #define HDMI_I2S_SEL_SDATA1(x)		(((x) & 0x7) << 4)
-#define HDMI_I2S_SEL_SDATA2(x)		((x) & 0x7)
+#define HDMI_I2S_SEL_SDATA0(x)		((x) & 0x7)
 
 /* I2S_PIN_SEL_2 */
 #define HDMI_I2S_SEL_SDATA3(x)		(((x) & 0x7) << 4)
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 909499b73d03..021f722e2481 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -733,6 +733,25 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 	return ret == 0 ? count : ret;
 }
 
+static bool gtt_entry(struct mdev_device *mdev, loff_t *ppos)
+{
+	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
+	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
+	struct intel_gvt *gvt = vgpu->gvt;
+	int offset;
+
+	/* Only allow MMIO GGTT entry access */
+	if (index != PCI_BASE_ADDRESS_0)
+		return false;
+
+	offset = (u64)(*ppos & VFIO_PCI_OFFSET_MASK) -
+		intel_vgpu_get_bar_gpa(vgpu, PCI_BASE_ADDRESS_0);
+
+	return (offset >= gvt->device_info.gtt_start_offset &&
+		offset < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt)) ?
+			true : false;
+}
+
 static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf,
 			size_t count, loff_t *ppos)
 {
@@ -742,7 +761,21 @@ static ssize_t intel_vgpu_read(struct mdev_device *mdev, char __user *buf,
 	while (count) {
 		size_t filled;
 
-		if (count >= 4 && !(*ppos % 4)) {
+		/* Only support GGTT entry 8 bytes read */
+		if (count >= 8 && !(*ppos % 8) &&
+			gtt_entry(mdev, ppos)) {
+			u64 val;
+
+			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
+					ppos, false);
+			if (ret <= 0)
+				goto read_err;
+
+			if (copy_to_user(buf, &val, sizeof(val)))
+				goto read_err;
+
+			filled = 8;
+		} else if (count >= 4 && !(*ppos % 4)) {
 			u32 val;
 
 			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
@@ -802,7 +835,21 @@ static ssize_t intel_vgpu_write(struct mdev_device *mdev,
 	while (count) {
 		size_t filled;
 
-		if (count >= 4 && !(*ppos % 4)) {
+		/* Only support GGTT entry 8 bytes write */
+		if (count >= 8 && !(*ppos % 8) &&
+			gtt_entry(mdev, ppos)) {
+			u64 val;
+
+			if (copy_from_user(&val, buf, sizeof(val)))
+				goto write_err;
+
+			ret = intel_vgpu_rw(mdev, (char *)&val, sizeof(val),
+					ppos, true);
+			if (ret <= 0)
+				goto write_err;
+
+			filled = 8;
+		} else if (count >= 4 && !(*ppos % 4)) {
 			u32 val;
 
 			if (copy_from_user(&val, buf, sizeof(val)))
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 73ad6e90e49d..256f1bb522b7 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -118,6 +118,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */
 	{RCS, GEN9_HALF_SLICE_CHICKEN5, 0xffff, true}, /* 0xe188 */
 	{RCS, GEN9_HALF_SLICE_CHICKEN7, 0xffff, true}, /* 0xe194 */
+	{RCS, GEN8_ROW_CHICKEN, 0xffff, true}, /* 0xe4f0 */
 	{RCS, TRVATTL3PTRDW(0), 0, false}, /* 0x4de0 */
 	{RCS, TRVATTL3PTRDW(1), 0, false}, /* 0x4de4 */
 	{RCS, TRNULLDETCT, 0, false}, /* 0x4de8 */
diff --git a/drivers/gpu/drm/i915/gvt/trace.h b/drivers/gpu/drm/i915/gvt/trace.h
index 7a2511538f34..736bd2bc5127 100644
--- a/drivers/gpu/drm/i915/gvt/trace.h
+++ b/drivers/gpu/drm/i915/gvt/trace.h
@@ -333,7 +333,7 @@ TRACE_EVENT(render_mmio,
 	TP_PROTO(int old_id, int new_id, char *action, unsigned int reg,
 		 unsigned int old_val, unsigned int new_val),
 
-	TP_ARGS(old_id, new_id, action, reg, new_val, old_val),
+	TP_ARGS(old_id, new_id, action, reg, old_val, new_val),
 
 	TP_STRUCT__entry(
 		__field(int, old_id)
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 173d0095e3b2..2f5209de0391 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1433,19 +1433,7 @@ void i915_driver_unload(struct drm_device *dev)
 
 	intel_modeset_cleanup(dev);
 
-	/*
-	 * free the memory space allocated for the child device
-	 * config parsed from VBT
-	 */
-	if (dev_priv->vbt.child_dev && dev_priv->vbt.child_dev_num) {
-		kfree(dev_priv->vbt.child_dev);
-		dev_priv->vbt.child_dev = NULL;
-		dev_priv->vbt.child_dev_num = 0;
-	}
-	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
-	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
-	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
-	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
+	intel_bios_cleanup(dev_priv);
 
 	vga_switcheroo_unregister_client(pdev);
 	vga_client_register(pdev, NULL, NULL, NULL);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a42deebedb0f..d307429a5ae0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1349,6 +1349,7 @@ struct intel_vbt_data {
 		u32 size;
 		u8 *data;
 		const u8 *sequence[MIPI_SEQ_MAX];
+		u8 *deassert_seq; /* Used by fixup_mipi_sequences() */
 	} dsi;
 
 	int crt_ddc_pin;
@@ -3657,6 +3658,7 @@ extern void intel_i2c_reset(struct drm_i915_private *dev_priv);
 
 /* intel_bios.c */
 void intel_bios_init(struct drm_i915_private *dev_priv);
+void intel_bios_cleanup(struct drm_i915_private *dev_priv);
 bool intel_bios_is_valid_vbt(const void *buf, size_t size);
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv);
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 648e7536ff51..0c963fcf31ff 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -803,7 +803,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 
 	case I915_CONTEXT_PARAM_PRIORITY:
 		{
-			int priority = args->value;
+			s64 priority = args->value;
 
 			if (args->size)
 				ret = -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 4401068ff468..3ab1ace2a6bd 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -505,6 +505,8 @@ eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
 		list_add_tail(&vma->exec_link, &eb->unbound);
 		if (drm_mm_node_allocated(&vma->node))
 			err = i915_vma_unbind(vma);
+		if (unlikely(err))
+			vma->exec_flags = NULL;
 	}
 	return err;
 }
@@ -2410,7 +2412,7 @@ err_request:
 	if (out_fence) {
 		if (err == 0) {
 			fd_install(out_fence_fd, out_fence->file);
-			args->rsvd2 &= GENMASK_ULL(0, 31); /* keep in-fence */
+			args->rsvd2 &= GENMASK_ULL(31, 0); /* keep in-fence */
 			args->rsvd2 |= (u64)out_fence_fd << 32;
 			out_fence_fd = -1;
 		} else {
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index e09d18df8b7f..a3e93d46316a 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -476,8 +476,6 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request)
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->timeline->lock);
 
-	trace_i915_gem_request_execute(request);
-
 	/* Transfer from per-context onto the global per-engine timeline */
 	timeline = engine->timeline;
 	GEM_BUG_ON(timeline == request->timeline);
@@ -501,6 +499,8 @@ void __i915_gem_request_submit(struct drm_i915_gem_request *request)
 	list_move_tail(&request->link, &timeline->requests);
 	spin_unlock(&request->timeline->lock);
 
+	trace_i915_gem_request_execute(request);
+
 	wake_up_all(&request->execute);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_oa_cflgt3.c b/drivers/gpu/drm/i915/i915_oa_cflgt3.c
index 42ff06fe54a3..792facdb6702 100644
--- a/drivers/gpu/drm/i915/i915_oa_cflgt3.c
+++ b/drivers/gpu/drm/i915/i915_oa_cflgt3.c
@@ -84,9 +84,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
 void
 i915_perf_load_test_config_cflgt3(struct drm_i915_private *dev_priv)
 {
-	strncpy(dev_priv->perf.oa.test_config.uuid,
+	strlcpy(dev_priv->perf.oa.test_config.uuid,
 		"577e8e2c-3fa0-4875-8743-3538d585e3b0",
-		UUID_STRING_LEN);
+		sizeof(dev_priv->perf.oa.test_config.uuid));
 	dev_priv->perf.oa.test_config.id = 1;
 
 	dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa;
diff --git a/drivers/gpu/drm/i915/i915_oa_cnl.c b/drivers/gpu/drm/i915/i915_oa_cnl.c
index ff0ac3627cc4..ba9140c87cc0 100644
--- a/drivers/gpu/drm/i915/i915_oa_cnl.c
+++ b/drivers/gpu/drm/i915/i915_oa_cnl.c
@@ -96,9 +96,9 @@ show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
 void
 i915_perf_load_test_config_cnl(struct drm_i915_private *dev_priv)
 {
-	strncpy(dev_priv->perf.oa.test_config.uuid,
+	strlcpy(dev_priv->perf.oa.test_config.uuid,
 		"db41edd4-d8e7-4730-ad11-b9a2d6833503",
-		UUID_STRING_LEN);
+		sizeof(dev_priv->perf.oa.test_config.uuid));
 	dev_priv->perf.oa.test_config.id = 1;
 
 	dev_priv->perf.oa.test_config.mux_regs = mux_config_test_oa;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 55a8a1e29424..0e9b98c32b62 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -285,26 +285,41 @@ static u64 count_interrupts(struct drm_i915_private *i915)
 	return sum;
 }
 
-static void i915_pmu_event_destroy(struct perf_event *event)
+static void engine_event_destroy(struct perf_event *event)
 {
-	WARN_ON(event->parent);
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+
+	engine = intel_engine_lookup_user(i915,
+					  engine_event_class(event),
+					  engine_event_instance(event));
+	if (WARN_ON_ONCE(!engine))
+		return;
+
+	if (engine_event_sample(event) == I915_SAMPLE_BUSY &&
+	    intel_engine_supports_stats(engine))
+		intel_disable_engine_stats(engine);
 }
 
-static int engine_event_init(struct perf_event *event)
+static void i915_pmu_event_destroy(struct perf_event *event)
 {
-	struct drm_i915_private *i915 =
-		container_of(event->pmu, typeof(*i915), pmu.base);
+	WARN_ON(event->parent);
 
-	if (!intel_engine_lookup_user(i915, engine_event_class(event),
-				      engine_event_instance(event)))
-		return -ENODEV;
+	if (is_engine_event(event))
+		engine_event_destroy(event);
+}
 
-	switch (engine_event_sample(event)) {
+static int
+engine_event_status(struct intel_engine_cs *engine,
+		    enum drm_i915_pmu_engine_sample sample)
+{
+	switch (sample) {
 	case I915_SAMPLE_BUSY:
 	case I915_SAMPLE_WAIT:
 		break;
 	case I915_SAMPLE_SEMA:
-		if (INTEL_GEN(i915) < 6)
+		if (INTEL_GEN(engine->i915) < 6)
 			return -ENODEV;
 		break;
 	default:
@@ -314,6 +329,30 @@ static int engine_event_init(struct perf_event *event)
 	return 0;
 }
 
+static int engine_event_init(struct perf_event *event)
+{
+	struct drm_i915_private *i915 =
+		container_of(event->pmu, typeof(*i915), pmu.base);
+	struct intel_engine_cs *engine;
+	u8 sample;
+	int ret;
+
+	engine = intel_engine_lookup_user(i915, engine_event_class(event),
+					  engine_event_instance(event));
+	if (!engine)
+		return -ENODEV;
+
+	sample = engine_event_sample(event);
+	ret = engine_event_status(engine, sample);
+	if (ret)
+		return ret;
+
+	if (sample == I915_SAMPLE_BUSY && intel_engine_supports_stats(engine))
+		ret = intel_enable_engine_stats(engine);
+
+	return ret;
+}
+
 static int i915_pmu_event_init(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -370,7 +409,94 @@ static int i915_pmu_event_init(struct perf_event *event)
 	return 0;
 }
 
-static u64 __i915_pmu_event_read(struct perf_event *event)
+static u64 __get_rc6(struct drm_i915_private *i915)
+{
+	u64 val;
+
+	val = intel_rc6_residency_ns(i915,
+				     IS_VALLEYVIEW(i915) ?
+				     VLV_GT_RENDER_RC6 :
+				     GEN6_GT_GFX_RC6);
+
+	if (HAS_RC6p(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+
+	if (HAS_RC6pp(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+
+	return val;
+}
+
+static u64 get_rc6(struct drm_i915_private *i915, bool locked)
+{
+#if IS_ENABLED(CONFIG_PM)
+	unsigned long flags;
+	u64 val;
+
+	if (intel_runtime_pm_get_if_in_use(i915)) {
+		val = __get_rc6(i915);
+		intel_runtime_pm_put(i915);
+
+		/*
+		 * If we are coming back from being runtime suspended we must
+		 * be careful not to report a larger value than returned
+		 * previously.
+		 */
+
+		if (!locked)
+			spin_lock_irqsave(&i915->pmu.lock, flags);
+
+		if (val >= i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+			i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0;
+			i915->pmu.sample[__I915_SAMPLE_RC6].cur = val;
+		} else {
+			val = i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+		}
+
+		if (!locked)
+			spin_unlock_irqrestore(&i915->pmu.lock, flags);
+	} else {
+		struct pci_dev *pdev = i915->drm.pdev;
+		struct device *kdev = &pdev->dev;
+		unsigned long flags2;
+
+		/*
+		 * We are runtime suspended.
+		 *
+		 * Report the delta from when the device was suspended to now,
+		 * on top of the last known real value, as the approximated RC6
+		 * counter value.
+		 */
+		if (!locked)
+			spin_lock_irqsave(&i915->pmu.lock, flags);
+
+		spin_lock_irqsave(&kdev->power.lock, flags2);
+
+		if (!i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
+			i915->pmu.suspended_jiffies_last =
+						kdev->power.suspended_jiffies;
+
+		val = kdev->power.suspended_jiffies -
+		      i915->pmu.suspended_jiffies_last;
+		val += jiffies - kdev->power.accounting_timestamp;
+
+		spin_unlock_irqrestore(&kdev->power.lock, flags2);
+
+		val = jiffies_to_nsecs(val);
+		val += i915->pmu.sample[__I915_SAMPLE_RC6].cur;
+		i915->pmu.sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+
+		if (!locked)
+			spin_unlock_irqrestore(&i915->pmu.lock, flags);
+	}
+
+	return val;
+#else
+	return __get_rc6(i915);
+#endif
+}
+
+static u64 __i915_pmu_event_read(struct perf_event *event, bool locked)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
@@ -387,7 +513,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		if (WARN_ON_ONCE(!engine)) {
 			/* Do nothing */
 		} else if (sample == I915_SAMPLE_BUSY &&
-			   engine->pmu.busy_stats) {
+			   intel_engine_supports_stats(engine)) {
 			val = ktime_to_ns(intel_engine_get_busy_time(engine));
 		} else {
 			val = engine->pmu.sample[sample].cur;
@@ -408,18 +534,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 			val = count_interrupts(i915);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
-			intel_runtime_pm_get(i915);
-			val = intel_rc6_residency_ns(i915,
-						     IS_VALLEYVIEW(i915) ?
-						     VLV_GT_RENDER_RC6 :
-						     GEN6_GT_GFX_RC6);
-			if (HAS_RC6p(i915))
-				val += intel_rc6_residency_ns(i915,
-							      GEN6_GT_GFX_RC6p);
-			if (HAS_RC6pp(i915))
-				val += intel_rc6_residency_ns(i915,
-							      GEN6_GT_GFX_RC6pp);
-			intel_runtime_pm_put(i915);
+			val = get_rc6(i915, locked);
 			break;
 		}
 	}
@@ -434,7 +549,7 @@ static void i915_pmu_event_read(struct perf_event *event)
 
 again:
 	prev = local64_read(&hwc->prev_count);
-	new = __i915_pmu_event_read(event);
+	new = __i915_pmu_event_read(event, false);
 
 	if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev)
 		goto again;
@@ -442,12 +557,6 @@ again:
 	local64_add(new - prev, &event->count);
 }
 
-static bool engine_needs_busy_stats(struct intel_engine_cs *engine)
-{
-	return intel_engine_supports_stats(engine) &&
-	       (engine->pmu.enable & BIT(I915_SAMPLE_BUSY));
-}
-
 static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -487,21 +596,7 @@ static void i915_pmu_enable(struct perf_event *event)
 
 		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
-		if (engine->pmu.enable_count[sample]++ == 0) {
-			/*
-			 * Enable engine busy stats tracking if needed or
-			 * alternatively cancel the scheduled disable.
-			 *
-			 * If the delayed disable was pending, cancel it and
-			 * in this case do not enable since it already is.
-			 */
-			if (engine_needs_busy_stats(engine) &&
-			    !engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = true;
-				if (!cancel_delayed_work(&engine->pmu.disable_busy_stats))
-					intel_enable_engine_stats(engine);
-			}
-		}
+		engine->pmu.enable_count[sample]++;
 	}
 
 	/*
@@ -509,19 +604,11 @@ static void i915_pmu_enable(struct perf_event *event)
 	 * for all listeners. Even when the event was already enabled and has
 	 * an existing non-zero value.
 	 */
-	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event));
+	local64_set(&event->hw.prev_count, __i915_pmu_event_read(event, true));
 
 	spin_unlock_irqrestore(&i915->pmu.lock, flags);
 }
 
-static void __disable_busy_stats(struct work_struct *work)
-{
-	struct intel_engine_cs *engine =
-	       container_of(work, typeof(*engine), pmu.disable_busy_stats.work);
-
-	intel_disable_engine_stats(engine);
-}
-
 static void i915_pmu_disable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -545,26 +632,8 @@ static void i915_pmu_disable(struct perf_event *event)
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
 		 */
-		if (--engine->pmu.enable_count[sample] == 0) {
+		if (--engine->pmu.enable_count[sample] == 0)
 			engine->pmu.enable &= ~BIT(sample);
-			if (!engine_needs_busy_stats(engine) &&
-			    engine->pmu.busy_stats) {
-				engine->pmu.busy_stats = false;
-				/*
-				 * We request a delayed disable to handle the
-				 * rapid on/off cycles on events, which can
-				 * happen when tools like perf stat start, in a
-				 * nicer way.
-				 *
-				 * In addition, this also helps with busy stats
-				 * accuracy with background CPU offline/online
-				 * migration events.
-				 */
-				queue_delayed_work(system_wq,
-						   &engine->pmu.disable_busy_stats,
-						   round_jiffies_up_relative(HZ));
-			}
-		}
 	}
 
 	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);
@@ -797,8 +866,6 @@ static void i915_pmu_unregister_cpuhp_state(struct drm_i915_private *i915)
 
 void i915_pmu_register(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	int ret;
 
 	if (INTEL_GEN(i915) <= 2) {
@@ -820,10 +887,6 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&i915->pmu.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	i915->pmu.timer.function = i915_sample;
 
-	for_each_engine(engine, i915, id)
-		INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats,
-				  __disable_busy_stats);
-
 	ret = perf_pmu_register(&i915->pmu.base, "i915", -1);
 	if (ret)
 		goto err;
@@ -843,9 +906,6 @@ err:
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
 	if (!i915->pmu.base.event_init)
 		return;
 
@@ -853,11 +913,6 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	hrtimer_cancel(&i915->pmu.timer);
 
-	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(engine->pmu.busy_stats);
-		flush_delayed_work(&engine->pmu.disable_busy_stats);
-	}
-
 	i915_pmu_unregister_cpuhp_state(i915);
 
 	perf_pmu_unregister(&i915->pmu.base);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 40c154d13565..bb62df15afa4 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -27,6 +27,8 @@
 enum {
 	__I915_SAMPLE_FREQ_ACT = 0,
 	__I915_SAMPLE_FREQ_REQ,
+	__I915_SAMPLE_RC6,
+	__I915_SAMPLE_RC6_ESTIMATED,
 	__I915_NUM_PMU_SAMPLERS
 };
 
@@ -94,6 +96,10 @@ struct i915_pmu {
 	 * struct intel_engine_cs.
 	 */
 	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
+	/**
+	 * @suspended_jiffies_last: Cached suspend time from PM core.
+	 */
+	unsigned long suspended_jiffies_last;
 };
 
 #ifdef CONFIG_PERF_EVENTS
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a2108e35c599..33eb0c5b1d32 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2027,7 +2027,7 @@ enum i915_power_well_id {
 #define _CNL_PORT_TX_DW5_LN0_AE		0x162454
 #define _CNL_PORT_TX_DW5_LN0_B		0x162654
 #define _CNL_PORT_TX_DW5_LN0_C		0x162C54
-#define _CNL_PORT_TX_DW5_LN0_D		0x162ED4
+#define _CNL_PORT_TX_DW5_LN0_D		0x162E54
 #define _CNL_PORT_TX_DW5_LN0_F		0x162854
 #define CNL_PORT_TX_DW5_GRP(port)	_MMIO_PORT6(port, \
 						    _CNL_PORT_TX_DW5_GRP_AE, \
@@ -2058,7 +2058,7 @@ enum i915_power_well_id {
 #define _CNL_PORT_TX_DW7_LN0_AE		0x16245C
 #define _CNL_PORT_TX_DW7_LN0_B		0x16265C
 #define _CNL_PORT_TX_DW7_LN0_C		0x162C5C
-#define _CNL_PORT_TX_DW7_LN0_D		0x162EDC
+#define _CNL_PORT_TX_DW7_LN0_D		0x162E5C
 #define _CNL_PORT_TX_DW7_LN0_F		0x16285C
 #define CNL_PORT_TX_DW7_GRP(port)	_MMIO_PORT6(port, \
 						    _CNL_PORT_TX_DW7_GRP_AE, \
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 522d54fecb53..4a01f62a392d 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -779,11 +779,11 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv,
 {
 	struct intel_encoder *encoder;
 
-	if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map)))
-		return NULL;
-
 	/* MST */
 	if (pipe >= 0) {
+		if (WARN_ON(pipe >= ARRAY_SIZE(dev_priv->av_enc_map)))
+			return NULL;
+
 		encoder = dev_priv->av_enc_map[pipe];
 		/*
 		 * when bootup, audio driver may not know it is
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index f7f771749e48..b49a2df44430 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -947,6 +947,86 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total)
 	return 0;
 }
 
+/*
+ * Get len of pre-fixed deassert fragment from a v1 init OTP sequence,
+ * skip all delay + gpio operands and stop at the first DSI packet op.
+ */
+static int get_init_otp_deassert_fragment_len(struct drm_i915_private *dev_priv)
+{
+	const u8 *data = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
+	int index, len;
+
+	if (WARN_ON(!data || dev_priv->vbt.dsi.seq_version != 1))
+		return 0;
+
+	/* index = 1 to skip sequence byte */
+	for (index = 1; data[index] != MIPI_SEQ_ELEM_END; index += len) {
+		switch (data[index]) {
+		case MIPI_SEQ_ELEM_SEND_PKT:
+			return index == 1 ? 0 : index;
+		case MIPI_SEQ_ELEM_DELAY:
+			len = 5; /* 1 byte for operand + uint32 */
+			break;
+		case MIPI_SEQ_ELEM_GPIO:
+			len = 3; /* 1 byte for op, 1 for gpio_nr, 1 for value */
+			break;
+		default:
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence.
+ * The deassert must be done before calling intel_dsi_device_ready, so for
+ * these devices we split the init OTP sequence into a deassert sequence and
+ * the actual init OTP part.
+ */
+static void fixup_mipi_sequences(struct drm_i915_private *dev_priv)
+{
+	u8 *init_otp;
+	int len;
+
+	/* Limit this to VLV for now. */
+	if (!IS_VALLEYVIEW(dev_priv))
+		return;
+
+	/* Limit this to v1 vid-mode sequences */
+	if (dev_priv->vbt.dsi.config->is_cmd_mode ||
+	    dev_priv->vbt.dsi.seq_version != 1)
+		return;
+
+	/* Only do this if there are otp and assert seqs and no deassert seq */
+	if (!dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] ||
+	    !dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET] ||
+	    dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET])
+		return;
+
+	/* The deassert-sequence ends at the first DSI packet */
+	len = get_init_otp_deassert_fragment_len(dev_priv);
+	if (!len)
+		return;
+
+	DRM_DEBUG_KMS("Using init OTP fragment to deassert reset\n");
+
+	/* Copy the fragment, update seq byte and terminate it */
+	init_otp = (u8 *)dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
+	dev_priv->vbt.dsi.deassert_seq = kmemdup(init_otp, len + 1, GFP_KERNEL);
+	if (!dev_priv->vbt.dsi.deassert_seq)
+		return;
+	dev_priv->vbt.dsi.deassert_seq[0] = MIPI_SEQ_DEASSERT_RESET;
+	dev_priv->vbt.dsi.deassert_seq[len] = MIPI_SEQ_ELEM_END;
+	/* Use the copy for deassert */
+	dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET] =
+		dev_priv->vbt.dsi.deassert_seq;
+	/* Replace the last byte of the fragment with init OTP seq byte */
+	init_otp[len - 1] = MIPI_SEQ_INIT_OTP;
+	/* And make MIPI_MIPI_SEQ_INIT_OTP point to it */
+	dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP] = init_otp + len - 1;
+}
+
 static void
 parse_mipi_sequence(struct drm_i915_private *dev_priv,
 		    const struct bdb_header *bdb)
@@ -1016,6 +1096,8 @@ parse_mipi_sequence(struct drm_i915_private *dev_priv,
 	dev_priv->vbt.dsi.size = seq_size;
 	dev_priv->vbt.dsi.seq_version = sequence->version;
 
+	fixup_mipi_sequences(dev_priv);
+
 	DRM_DEBUG_DRIVER("MIPI related VBT parsing complete\n");
 	return;
 
@@ -1589,6 +1671,29 @@ out:
 }
 
 /**
+ * intel_bios_cleanup - Free any resources allocated by intel_bios_init()
+ * @dev_priv: i915 device instance
+ */
+void intel_bios_cleanup(struct drm_i915_private *dev_priv)
+{
+	kfree(dev_priv->vbt.child_dev);
+	dev_priv->vbt.child_dev = NULL;
+	dev_priv->vbt.child_dev_num = 0;
+	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
+	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
+	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
+	dev_priv->vbt.lfp_lvds_vbt_mode = NULL;
+	kfree(dev_priv->vbt.dsi.data);
+	dev_priv->vbt.dsi.data = NULL;
+	kfree(dev_priv->vbt.dsi.pps);
+	dev_priv->vbt.dsi.pps = NULL;
+	kfree(dev_priv->vbt.dsi.config);
+	dev_priv->vbt.dsi.config = NULL;
+	kfree(dev_priv->vbt.dsi.deassert_seq);
+	dev_priv->vbt.dsi.deassert_seq = NULL;
+}
+
+/**
  * intel_bios_is_tv_present - is integrated TV present in VBT
  * @dev_priv:	i915 device instance
  *
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index bd40fea16b4f..f54ddda9fdad 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -594,29 +594,16 @@ void intel_engine_remove_wait(struct intel_engine_cs *engine,
 	spin_unlock_irq(&b->rb_lock);
 }
 
-static bool signal_valid(const struct drm_i915_gem_request *request)
-{
-	return intel_wait_check_request(&request->signaling.wait, request);
-}
-
 static bool signal_complete(const struct drm_i915_gem_request *request)
 {
 	if (!request)
 		return false;
 
-	/* If another process served as the bottom-half it may have already
-	 * signalled that this wait is already completed.
-	 */
-	if (intel_wait_complete(&request->signaling.wait))
-		return signal_valid(request);
-
-	/* Carefully check if the request is complete, giving time for the
+	/*
+	 * Carefully check if the request is complete, giving time for the
 	 * seqno to be visible or if the GPU hung.
 	 */
-	if (__i915_request_irq_complete(request))
-		return true;
-
-	return false;
+	return __i915_request_irq_complete(request);
 }
 
 static struct drm_i915_gem_request *to_signaler(struct rb_node *rb)
@@ -659,9 +646,13 @@ static int intel_breadcrumbs_signaler(void *arg)
 			request = i915_gem_request_get_rcu(request);
 		rcu_read_unlock();
 		if (signal_complete(request)) {
-			local_bh_disable();
-			dma_fence_signal(&request->fence);
-			local_bh_enable(); /* kick start the tasklets */
+			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+				      &request->fence.flags)) {
+				local_bh_disable();
+				dma_fence_signal(&request->fence);
+				GEM_BUG_ON(!i915_gem_request_completed(request));
+				local_bh_enable(); /* kick start the tasklets */
+			}
 
 			spin_lock_irq(&b->rb_lock);
 
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 5dc118f26b51..1704c8897afd 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -1952,6 +1952,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
 		min_cdclk = max(2 * 96000, min_cdclk);
 
+	/*
+	 * On Valleyview some DSI panels lose (v|h)sync when the clock is lower
+	 * than 320000KHz.
+	 */
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) &&
+	    IS_VALLEYVIEW(dev_priv))
+		min_cdclk = max(320000, min_cdclk);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index d790bdc227ff..fa960cfd2764 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1458,7 +1458,9 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	struct drm_i915_private *dev_priv = engine->i915;
 	bool idle = true;
 
-	intel_runtime_pm_get(dev_priv);
+	/* If the whole device is asleep, the engine must be idle */
+	if (!intel_runtime_pm_get_if_in_use(dev_priv))
+		return true;
 
 	/* First check that no commands are left in the ring */
 	if ((I915_READ_HEAD(engine) & HEAD_ADDR) !=
@@ -1943,16 +1945,22 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
  */
 int intel_enable_engine_stats(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists *execlists = &engine->execlists;
 	unsigned long flags;
+	int err = 0;
 
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
+	tasklet_disable(&execlists->tasklet);
 	spin_lock_irqsave(&engine->stats.lock, flags);
-	if (engine->stats.enabled == ~0)
-		goto busy;
+
+	if (unlikely(engine->stats.enabled == ~0)) {
+		err = -EBUSY;
+		goto unlock;
+	}
+
 	if (engine->stats.enabled++ == 0) {
-		struct intel_engine_execlists *execlists = &engine->execlists;
 		const struct execlist_port *port = execlists->port;
 		unsigned int num_ports = execlists_num_ports(execlists);
 
@@ -1967,14 +1975,12 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 		if (engine->stats.active)
 			engine->stats.start = engine->stats.enabled_at;
 	}
-	spin_unlock_irqrestore(&engine->stats.lock, flags);
-
-	return 0;
 
-busy:
+unlock:
 	spin_unlock_irqrestore(&engine->stats.lock, flags);
+	tasklet_enable(&execlists->tasklet);
 
-	return -EBUSY;
+	return err;
 }
 
 static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c5ff203e42d6..a0e7a6c2a57c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -366,20 +366,6 @@ struct intel_engine_cs {
 		 */
 #define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1)
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
-		/**
-		 * @busy_stats: Has enablement of engine stats tracking been
-		 * 		requested.
-		 */
-		bool busy_stats;
-		/**
-		 * @disable_busy_stats: Work item for busy stats disabling.
-		 *
-		 * Same as with @enable_busy_stats action, with the difference
-		 * that we delay it in case there are rapid enable-disable
-		 * actions, which can happen during tool startup (like perf
-		 * stat).
-		 */
-		struct delayed_work disable_busy_stats;
 	} pmu;
 
 	/*
diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c
index 5155f0179b61..05520202c967 100644
--- a/drivers/gpu/drm/meson/meson_crtc.c
+++ b/drivers/gpu/drm/meson/meson_crtc.c
@@ -36,6 +36,7 @@
 #include "meson_venc.h"
 #include "meson_vpp.h"
 #include "meson_viu.h"
+#include "meson_canvas.h"
 #include "meson_registers.h"
 
 /* CRTC definition */
@@ -192,6 +193,11 @@ void meson_crtc_irq(struct meson_drm *priv)
 		} else
 			meson_vpp_disable_interlace_vscaler_osd1(priv);
 
+		meson_canvas_setup(priv, MESON_CANVAS_ID_OSD1,
+			   priv->viu.osd1_addr, priv->viu.osd1_stride,
+			   priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE,
+			   MESON_CANVAS_BLKMODE_LINEAR);
+
 		/* Enable OSD1 */
 		writel_bits_relaxed(VPP_OSD1_POSTBLEND, VPP_OSD1_POSTBLEND,
 				    priv->io_base + _REG(VPP_MISC));
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 5e8b392b9d1f..8450d6ac8c9b 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -43,6 +43,9 @@ struct meson_drm {
 		bool osd1_commit;
 		uint32_t osd1_ctrl_stat;
 		uint32_t osd1_blk0_cfg[5];
+		uint32_t osd1_addr;
+		uint32_t osd1_stride;
+		uint32_t osd1_height;
 	} viu;
 
 	struct {
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index d0a6ac8390f3..27bd3503e1e4 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -164,10 +164,9 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	/* Update Canvas with buffer address */
 	gem = drm_fb_cma_get_gem_obj(fb, 0);
 
-	meson_canvas_setup(priv, MESON_CANVAS_ID_OSD1,
-			   gem->paddr, fb->pitches[0],
-			   fb->height, MESON_CANVAS_WRAP_NONE,
-			   MESON_CANVAS_BLKMODE_LINEAR);
+	priv->viu.osd1_addr = gem->paddr;
+	priv->viu.osd1_stride = fb->pitches[0];
+	priv->viu.osd1_height = fb->height;
 
 	spin_unlock_irqrestore(&priv->drm->event_lock, flags);
 }
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 3e9bba4d6624..6d8e3a9a6fc0 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -680,7 +680,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 	} else {
 		dev_info(&pdev->dev,
 			 "no iommu, fallback to phys contig buffers for scanout\n");
-		aspace = NULL;;
+		aspace = NULL;
 	}
 
 	pm_runtime_put_sync(&pdev->dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 69d6e61a01ec..6ed9cb053dfa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -570,9 +570,15 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		nv_connector->edid = NULL;
 	}
 
-	ret = pm_runtime_get_sync(connector->dev->dev);
-	if (ret < 0 && ret != -EACCES)
-		return conn_status;
+	/* Outputs are only polled while runtime active, so acquiring a
+	 * runtime PM ref here is unnecessary (and would deadlock upon
+	 * runtime suspend because it waits for polling to finish).
+	 */
+	if (!drm_kms_helper_is_poll_worker()) {
+		ret = pm_runtime_get_sync(connector->dev->dev);
+		if (ret < 0 && ret != -EACCES)
+			return conn_status;
+	}
 
 	nv_encoder = nouveau_connector_ddc_detect(connector);
 	if (nv_encoder && (i2c = nv_encoder->i2c) != NULL) {
@@ -647,8 +653,10 @@ detect_analog:
 
  out:
 
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return conn_status;
 }
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index dd8d4352ed99..caddce88d2d8 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -4477,6 +4477,7 @@ nv50_display_create(struct drm_device *dev)
 	nouveau_display(dev)->fini = nv50_display_fini;
 	disp->disp = &nouveau_display(dev)->disp;
 	dev->mode_config.funcs = &nv50_disp_func;
+	dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
 	if (nouveau_atomic)
 		dev->driver->driver_features |= DRIVER_ATOMIC;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
index bf62303571b3..3695cde669f8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/therm/base.c
@@ -301,7 +301,7 @@ nvkm_therm_attr_set(struct nvkm_therm *therm,
 void
 nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
 {
-	if (!therm->func->clkgate_enable || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_enable || !therm->clkgating_enabled)
 		return;
 
 	nvkm_debug(&therm->subdev,
@@ -312,7 +312,7 @@ nvkm_therm_clkgate_enable(struct nvkm_therm *therm)
 void
 nvkm_therm_clkgate_fini(struct nvkm_therm *therm, bool suspend)
 {
-	if (!therm->func->clkgate_fini || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_fini || !therm->clkgating_enabled)
 		return;
 
 	nvkm_debug(&therm->subdev,
@@ -395,7 +395,7 @@ void
 nvkm_therm_clkgate_init(struct nvkm_therm *therm,
 			const struct nvkm_therm_clkgate_pack *p)
 {
-	if (!therm->func->clkgate_init || !therm->clkgating_enabled)
+	if (!therm || !therm->func->clkgate_init || !therm->clkgating_enabled)
 		return;
 
 	therm->func->clkgate_init(therm, p);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 5012f5e47a1e..2e2ca3c6b47d 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -899,9 +899,11 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (encoder) {
 		struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
@@ -924,8 +926,12 @@ radeon_lvds_detect(struct drm_connector *connector, bool force)
 	/* check acpi lid status ??? */
 
 	radeon_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 
@@ -1039,9 +1045,11 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
@@ -1108,8 +1116,10 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 	radeon_connector_update_scratch_regs(connector, ret);
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -1173,9 +1183,11 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	if (!radeon_connector->dac_load_detect)
 		return ret;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)
@@ -1187,8 +1199,12 @@ radeon_tv_detect(struct drm_connector *connector, bool force)
 	if (ret == connector_status_connected)
 		ret = radeon_connector_analog_encoder_conflict_solve(connector, encoder, ret, false);
 	radeon_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 
@@ -1251,9 +1267,11 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (radeon_connector->detected_hpd_without_ddc) {
 		force = true;
@@ -1436,8 +1454,10 @@ out:
 	}
 
 exit:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
@@ -1688,9 +1708,11 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	if (radeon_dig_connector->is_mst)
 		return connector_status_disconnected;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;
@@ -1777,8 +1799,10 @@ radeon_dp_detect(struct drm_connector *connector, bool force)
 	}
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 8d3e3d2e0090..7828a5e10629 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1365,6 +1365,10 @@ int radeon_device_init(struct radeon_device *rdev,
 	if ((rdev->flags & RADEON_IS_PCI) &&
 	    (rdev->family <= CHIP_RS740))
 		rdev->need_dma32 = true;
+#ifdef CONFIG_PPC64
+	if (rdev->family == CHIP_CEDAR)
+		rdev->need_dma32 = true;
+#endif
 
 	dma_bits = rdev->need_dma32 ? 32 : 40;
 	r = pci_set_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits));
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 326ad068c15a..4b6542538ff9 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -47,7 +47,6 @@ static bool radeon_pm_in_vbl(struct radeon_device *rdev);
 static bool radeon_pm_debug_check_in_vbl(struct radeon_device *rdev, bool finish);
 static void radeon_pm_update_profile(struct radeon_device *rdev);
 static void radeon_pm_set_clocks(struct radeon_device *rdev);
-static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev);
 
 int radeon_pm_get_type_index(struct radeon_device *rdev,
 			     enum radeon_pm_state_type ps_type,
@@ -80,8 +79,6 @@ void radeon_pm_acpi_event_handler(struct radeon_device *rdev)
 				radeon_dpm_enable_bapm(rdev, rdev->pm.dpm.ac_power);
 		}
 		mutex_unlock(&rdev->pm.mutex);
-		/* allow new DPM state to be picked */
-		radeon_pm_compute_clocks_dpm(rdev);
 	} else if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
 		if (rdev->pm.profile == PM_PROFILE_AUTO) {
 			mutex_lock(&rdev->pm.mutex);
@@ -885,8 +882,7 @@ static struct radeon_ps *radeon_dpm_pick_power_state(struct radeon_device *rdev,
 		dpm_state = POWER_STATE_TYPE_INTERNAL_3DPERF;
 	/* balanced states don't exist at the moment */
 	if (dpm_state == POWER_STATE_TYPE_BALANCED)
-		dpm_state = rdev->pm.dpm.ac_power ?
-			POWER_STATE_TYPE_PERFORMANCE : POWER_STATE_TYPE_BATTERY;
+		dpm_state = POWER_STATE_TYPE_PERFORMANCE;
 
 restart_search:
 	/* Pick the best power state based on current conditions */
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 2c18996d59c5..0d95888ccc3e 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -461,7 +461,7 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
 {
 	struct drm_sched_job *s_job;
 	struct drm_sched_entity *entity, *tmp;
-	int i;;
+	int i;
 
 	spin_lock(&sched->job_list_lock);
 	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 3c15cf24b503..b3960118deb9 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -260,7 +260,7 @@ static void sun4i_tcon0_mode_set_common(struct sun4i_tcon *tcon,
 					const struct drm_display_mode *mode)
 {
 	/* Configure the dot clock */
-	clk_set_rate(tcon->dclk, mode->crtc_clock * 1000);
+	clk_set_rate_exclusive(tcon->dclk, mode->crtc_clock * 1000);
 
 	/* Set the resolution */
 	regmap_write(tcon->regs, SUN4I_TCON0_BASIC0_REG,
@@ -335,6 +335,9 @@ static void sun4i_tcon0_mode_set_lvds(struct sun4i_tcon *tcon,
 	regmap_update_bits(tcon->regs, SUN4I_TCON_GCTL_REG,
 			   SUN4I_TCON_GCTL_IOMAP_MASK,
 			   SUN4I_TCON_GCTL_IOMAP_TCON0);
+
+	/* Enable the output on the pins */
+	regmap_write(tcon->regs, SUN4I_TCON0_IO_TRI_REG, 0xe0000000);
 }
 
 static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
@@ -418,7 +421,7 @@ static void sun4i_tcon1_mode_set(struct sun4i_tcon *tcon,
 	WARN_ON(!tcon->quirks->has_channel_1);
 
 	/* Configure the dot clock */
-	clk_set_rate(tcon->sclk1, mode->crtc_clock * 1000);
+	clk_set_rate_exclusive(tcon->sclk1, mode->crtc_clock * 1000);
 
 	/* Adjust clock delay */
 	clk_delay = sun4i_tcon_get_clk_delay(mode, 1);
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 5720a0d4ac0a..677ac16c8a6d 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -197,6 +197,9 @@ static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data,
 	case VIRTGPU_PARAM_3D_FEATURES:
 		value = vgdev->has_virgl_3d == true ? 1 : 0;
 		break;
+	case VIRTGPU_PARAM_CAPSET_QUERY_FIX:
+		value = 1;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -472,7 +475,7 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
 {
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct drm_virtgpu_get_caps *args = data;
-	int size;
+	unsigned size, host_caps_size;
 	int i;
 	int found_valid = -1;
 	int ret;
@@ -481,6 +484,10 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
 	if (vgdev->num_capsets == 0)
 		return -ENOSYS;
 
+	/* don't allow userspace to pass 0 */
+	if (args->size == 0)
+		return -EINVAL;
+
 	spin_lock(&vgdev->display_info_lock);
 	for (i = 0; i < vgdev->num_capsets; i++) {
 		if (vgdev->capsets[i].id == args->cap_set_id) {
@@ -496,11 +503,9 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	size = vgdev->capsets[found_valid].max_size;
-	if (args->size > size) {
-		spin_unlock(&vgdev->display_info_lock);
-		return -EINVAL;
-	}
+	host_caps_size = vgdev->capsets[found_valid].max_size;
+	/* only copy to user the minimum of the host caps size or the guest caps size */
+	size = min(args->size, host_caps_size);
 
 	list_for_each_entry(cache_ent, &vgdev->cap_cache, head) {
 		if (cache_ent->id == args->cap_set_id &&