diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 2992a49ad4a57d0c34ef0c46addf54b681f3ad2e..8ac1581a6b53b21c0c9641455f1f4356915d6d23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -945,6 +945,7 @@ struct amdgpu_device {
 
 	/* s3/s4 mask */
 	bool                            in_suspend;
+	bool				in_hibernate;
 
 	/* record last mm index being written through WREG32*/
 	unsigned long last_mm_index;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 9dff792c929036701e78af5f19f24463e9f6448b..6a5b91d23fd9b8492c02996a5af0c60ee7d717bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
 	}
 
 	/* Free the BO*/
-	amdgpu_bo_unref(&mem->bo);
+	drm_gem_object_put_unlocked(&mem->bo->tbo.base);
 	mutex_destroy(&mem->lock);
 	kfree(mem);
 
@@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 		| KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE
 		| KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE;
 
-	(*mem)->bo = amdgpu_bo_ref(bo);
+	drm_gem_object_get(&bo->tbo.base);
+	(*mem)->bo = bo;
 	(*mem)->va = va;
 	(*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
 		AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 466bfe541e455599377f6d8dcdf0948749348a8e..a735d79a717be8444a1491408d8e25f65402c168 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1181,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_dev->dev_private;
 	int r;
 
+	adev->in_hibernate = true;
 	r = amdgpu_device_suspend(drm_dev, true);
+	adev->in_hibernate = false;
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 9ae7b61f696a244c7182b06843330728ec455e47..25ddb482466a7f034196c6241e86d4ae16b232b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	u32 cpp;
 	u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 			       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS     |
-			       AMDGPU_GEM_CREATE_VRAM_CLEARED 	     |
-			       AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+			       AMDGPU_GEM_CREATE_VRAM_CLEARED;
 
 	info = drm_get_format_info(adev->ddev, mode_cmd);
 	cpp = info->cpp[0];
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f92c158d89a12ba4906014fcc6868969858c4abf..0e0daf0021b60aa9bf0b94ccecb40388f257133d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
 		/* ===  CGCG /CGLS for GFX 3D Only === */
 		gfx_v10_0_update_3d_clock_gating(adev, enable);
 		/* ===  MGCG + MGLS === */
-		/* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */
+		gfx_v10_0_update_medium_grain_clock_gating(adev, enable);
 	}
 
 	if (adev->cg_flags &
@@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else
-			amdgpu_gfx_off_ctrl(adev, true);
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
@@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
 							   ref, mask);
 }
 
+static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring,
+					 unsigned vmid)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t value = 0;
+
+	value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03);
+	value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
+	value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
+	value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid);
+	WREG32_SOC15(GC, 0, mmSQ_CMD, value);
+}
+
 static void
 gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
+	.soft_recovery = gfx_v10_0_ring_soft_recovery,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 0c390485bc106455960cfe2120d2dec47d4b7bfd..d2d9dce68c2f186fc6544e37551008c451eed06a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1236,6 +1236,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = {
 	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 },
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */
 	{ 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 },
+	/* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */
+	{ 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 },
 	{ 0, 0, 0, 0, 0 },
 };
 
@@ -5025,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
-		if (!enable) {
+		if (!enable)
 			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		}
+
 		if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) {
 			gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true);
 			gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true);
@@ -5052,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 			amdgpu_gfx_off_ctrl(adev, true);
 		break;
 	case CHIP_VEGA12:
-		if (!enable) {
-			amdgpu_gfx_off_ctrl(adev, false);
-			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
-		} else {
-			amdgpu_gfx_off_ctrl(adev, true);
-		}
+		amdgpu_gfx_off_ctrl(adev, enable);
 		break;
 	default:
 		break;
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 9c83c1303f080b80b5adae907a5763480dbb473e..28e651b173abda1f9a6861282ed0ef36f5824b87 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 
 /**
  * dm_crtc_high_irq() - Handles CRTC interrupt
- * @interrupt_params: ignored
+ * @interrupt_params: used for determining the CRTC instance
  *
  * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK
  * event handler.
@@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	unsigned long flags;
 
 	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
-	if (acrtc) {
-		acrtc_state = to_dm_crtc_state(acrtc->base.state);
-
-		DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n",
-			      acrtc->crtc_id,
-			      amdgpu_dm_vrr_active(acrtc_state));
-
-		/* Core vblank handling at start of front-porch is only possible
-		 * in non-vrr mode, as only there vblank timestamping will give
-		 * valid results while done in front-porch. Otherwise defer it
-		 * to dm_vupdate_high_irq after end of front-porch.
-		 */
-		if (!amdgpu_dm_vrr_active(acrtc_state))
-			drm_crtc_handle_vblank(&acrtc->base);
-
-		/* Following stuff must happen at start of vblank, for crc
-		 * computation and below-the-range btr support in vrr mode.
-		 */
-		amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
-
-		if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI &&
-		    acrtc_state->vrr_params.supported &&
-		    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-			spin_lock_irqsave(&adev->ddev->event_lock, flags);
-			mod_freesync_handle_v_update(
-				adev->dm.freesync_module,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params);
-
-			dc_stream_adjust_vmin_vmax(
-				adev->dm.dc,
-				acrtc_state->stream,
-				&acrtc_state->vrr_params.adjust);
-			spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
-		}
-	}
-}
-
-#if defined(CONFIG_DRM_AMD_DC_DCN)
-/**
- * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs
- * @interrupt params - interrupt parameters
- *
- * Notify DRM's vblank event handler at VSTARTUP
- *
- * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which:
- * * We are close enough to VUPDATE - the point of no return for hw
- * * We are in the fixed portion of variable front porch when vrr is enabled
- * * We are before VUPDATE, where double-buffered vrr registers are swapped
- *
- * It is therefore the correct place to signal vblank, send user flip events,
- * and update VRR.
- */
-static void dm_dcn_crtc_high_irq(void *interrupt_params)
-{
-	struct common_irq_params *irq_params = interrupt_params;
-	struct amdgpu_device *adev = irq_params->adev;
-	struct amdgpu_crtc *acrtc;
-	struct dm_crtc_state *acrtc_state;
-	unsigned long flags;
-
-	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
-
 	if (!acrtc)
 		return;
 
@@ -528,22 +464,35 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 			 amdgpu_dm_vrr_active(acrtc_state),
 			 acrtc_state->active_planes);
 
+	/**
+	 * Core vblank handling at start of front-porch is only possible
+	 * in non-vrr mode, as only there vblank timestamping will give
+	 * valid results while done in front-porch. Otherwise defer it
+	 * to dm_vupdate_high_irq after end of front-porch.
+	 */
+	if (!amdgpu_dm_vrr_active(acrtc_state))
+		drm_crtc_handle_vblank(&acrtc->base);
+
+	/**
+	 * Following stuff must happen at start of vblank, for crc
+	 * computation and below-the-range btr support in vrr mode.
+	 */
 	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
-	drm_crtc_handle_vblank(&acrtc->base);
+
+	/* BTR updates need to happen before VUPDATE on Vega and above. */
+	if (adev->family < AMDGPU_FAMILY_AI)
+		return;
 
 	spin_lock_irqsave(&adev->ddev->event_lock, flags);
 
-	if (acrtc_state->vrr_params.supported &&
+	if (acrtc_state->stream && acrtc_state->vrr_params.supported &&
 	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
-		mod_freesync_handle_v_update(
-		adev->dm.freesync_module,
-		acrtc_state->stream,
-		&acrtc_state->vrr_params);
+		mod_freesync_handle_v_update(adev->dm.freesync_module,
+					     acrtc_state->stream,
+					     &acrtc_state->vrr_params);
 
-		dc_stream_adjust_vmin_vmax(
-			adev->dm.dc,
-			acrtc_state->stream,
-			&acrtc_state->vrr_params.adjust);
+		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream,
+					   &acrtc_state->vrr_params.adjust);
 	}
 
 	/*
@@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 	 * avoid race conditions between flip programming and completion,
 	 * which could cause too early flip completion events.
 	 */
-	if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
+	if (adev->family >= AMDGPU_FAMILY_RV &&
+	    acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED &&
 	    acrtc_state->active_planes == 0) {
 		if (acrtc->event) {
 			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
@@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params)
 
 	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
 }
-#endif
 
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
@@ -2445,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 		c_irq_params->adev = adev;
 		c_irq_params->irq_src = int_params.irq_source;
 
+		amdgpu_dm_irq_register_interrupt(
+			adev, &int_params, dm_crtc_high_irq, c_irq_params);
+	}
+
+	/* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to
+	 * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx
+	 * to trigger at end of each vblank, regardless of state of the lock,
+	 * matching DCE behaviour.
+	 */
+	for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT;
+	     i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1;
+	     i++) {
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq);
+
+		if (r) {
+			DRM_ERROR("Failed to add vupdate irq id!\n");
+			return r;
+		}
+
+		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
+		int_params.irq_source =
+			dc_interrupt_to_irq_source(dc, i, 0);
+
+		c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1];
+
+		c_irq_params->adev = adev;
+		c_irq_params->irq_src = int_params.irq_source;
+
 		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_dcn_crtc_high_irq, c_irq_params);
+				dm_vupdate_high_irq, c_irq_params);
 	}
 
 	/* Use GRPH_PFLIP interrupt */
@@ -4453,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int rc;
 
-	/* Do not set vupdate for DCN hardware */
-	if (adev->family > AMDGPU_FAMILY_AI)
-		return 0;
-
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
 
 	rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY;
@@ -7882,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc,
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state;
 	struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state;
+	struct amdgpu_crtc *new_acrtc;
 	bool needs_reset;
 	int ret = 0;
 
@@ -7891,9 +7865,30 @@ static int dm_update_plane_state(struct dc *dc,
 	dm_new_plane_state = to_dm_plane_state(new_plane_state);
 	dm_old_plane_state = to_dm_plane_state(old_plane_state);
 
-	/*TODO Implement atomic check for cursor plane */
-	if (plane->type == DRM_PLANE_TYPE_CURSOR)
+	/*TODO Implement better atomic check for cursor plane */
+	if (plane->type == DRM_PLANE_TYPE_CURSOR) {
+		if (!enable || !new_plane_crtc ||
+			drm_atomic_plane_disabling(plane->state, new_plane_state))
+			return 0;
+
+		new_acrtc = to_amdgpu_crtc(new_plane_crtc);
+
+		if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) ||
+			(new_plane_state->crtc_h > new_acrtc->max_cursor_height)) {
+			DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n",
+							 new_plane_state->crtc_w, new_plane_state->crtc_h);
+			return -EINVAL;
+		}
+
+		if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width ||
+			new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) {
+			DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n",
+							 new_plane_state->crtc_x, new_plane_state->crtc_y);
+			return -EINVAL;
+		}
+
 		return 0;
+	}
 
 	needs_reset = should_reset_plane(state, plane, old_plane_state,
 					 new_plane_state);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 78e1c11d4ae544d59516dc4e17a8732c14d38bf9..dcf84a61de37f3b1254da646ec3688c00de3ecbf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
 
-	memset(display, 0, sizeof(*display));
-	memset(link, 0, sizeof(*link));
-
-	display->index = aconnector->base.index;
-
 	if (config->dpms_off) {
 		hdcp_remove_display(hdcp_work, link_index, aconnector);
 		return;
 	}
+
+	memset(display, 0, sizeof(*display));
+	memset(link, 0, sizeof(*link));
+
+	display->index = aconnector->base.index;
 	display->state = MOD_HDCP_DISPLAY_ACTIVE;
 
 	if (aconnector->dc_sink != NULL)
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index e4e5a53b2b4eafe8f655ae5f13d668ac1f55f717..8e2acb4df860b800474efd8f5fce1cdc5a1f7ca4 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr  *hwmgr,
 		if (*level & profile_mode_mask) {
 			hwmgr->saved_dpm_level = hwmgr->dpm_level;
 			hwmgr->en_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
-						AMD_IP_BLOCK_TYPE_GFX,
-						AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(hwmgr->adev,
 					AMD_IP_BLOCK_TYPE_GFX,
 					AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(hwmgr->adev,
+						AMD_IP_BLOCK_TYPE_GFX,
+						AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index e8b27fab6aa1d3eb66aa470942910c807e1fa22f..e77046931e4c6beb3c908fe2040496d73f3abba1 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu)
 	bool use_baco = !smu->is_apu &&
 		((adev->in_gpu_reset &&
 		  (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
-		 (adev->in_runpm && amdgpu_asic_supports_baco(adev)));
+		 ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
 
 	ret = smu_get_smc_version(smu, NULL, &smu_version);
 	if (ret) {
@@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle,
 		if (*level & profile_mode_mask) {
 			smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level;
 			smu_dpm_ctx->enable_umd_pstate = true;
-			amdgpu_device_ip_set_clockgating_state(smu->adev,
-							       AMD_IP_BLOCK_TYPE_GFX,
-							       AMD_CG_STATE_UNGATE);
 			amdgpu_device_ip_set_powergating_state(smu->adev,
 							       AMD_IP_BLOCK_TYPE_GFX,
 							       AMD_PG_STATE_UNGATE);
+			amdgpu_device_ip_set_clockgating_state(smu->adev,
+							       AMD_IP_BLOCK_TYPE_GFX,
+							       AMD_CG_STATE_UNGATE);
 		}
 	} else {
 		/* exit umd pstate, restore level, enable gfx cg*/
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 2e5d835a9eaa866e0a6c8c94b35ff00cbcf04db7..c125ca9ab9b3a93fa4c27da86f29140e4618e9e2 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
 	if (!ret)
 		goto err_llb;
 	else if (ret > 1) {
-		DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
-
+		DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n");
 	}
 
 	fbc->threshold = ret;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 0cc40e77bbd2fcb2bb85a01768993a57a08e9a88..4f96c8788a2ec1b396b7b11a35dc377e787260ec 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
 	if (!atomic_read(&obj->bind_count))
 		return;
 
@@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 void
 i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj = vma->obj;
-
-	assert_object_held(obj);
-
 	/* Bump the LRU to try and avoid premature eviction whilst flipping  */
-	i915_gem_object_bump_inactive_ggtt(obj);
+	i915_gem_object_bump_inactive_ggtt(vma->obj);
 
 	i915_vma_unpin(vma);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 07cb83a0d0171a48fbedee19944bb0064b142416..ca0d4f4f3615b6d7ab78392bc3e002818938d63f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -69,7 +69,13 @@ struct intel_context {
 #define CONTEXT_NOPREEMPT		7
 
 	u32 *lrc_reg_state;
-	u64 lrc_desc;
+	union {
+		struct {
+			u32 lrca;
+			u32 ccid;
+		};
+		u64 desc;
+	} lrc;
 	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	/* Time on GPU as tracked by the hw. */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index b469de0dd9b656c25ae3e76dcf086836fd1f624c..a1aa0d3e8be1d5c51badcc555dbe94c92aa78953 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
 	return intel_engine_has_preemption(engine);
 }
 
-static inline bool
-intel_engine_has_timeslices(const struct intel_engine_cs *engine)
-{
-	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
-		return false;
-
-	return intel_engine_has_semaphores(engine);
-}
-
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 3aa8a652c16dbdd092dba754fad8df057d82ba5b..883a9b7fe88d5a6a0b4398d3a3793b727b015343 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
 		drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID));
+	if (HAS_EXECLISTS(dev_priv)) {
+		drm_printf(m, "\tEL_STAT_HI: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI));
+		drm_printf(m, "\tEL_STAT_LO: 0x%08x\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO));
+	}
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   ENGINE_READ(engine, RING_START));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 80cdde7128420c21e2b5cbfb9f363d421ac997d5..0be674ae1cf63ff4a2adf665696dca8f8b9b74a1 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -156,6 +156,20 @@ struct intel_engine_execlists {
 	 */
 	struct i915_priolist default_priolist;
 
+	/**
+	 * @ccid: identifier for contexts submitted to this engine
+	 */
+	u32 ccid;
+
+	/**
+	 * @yield: CCID at the time of the last semaphore-wait interrupt.
+	 *
+	 * Instead of leaving a semaphore busy-spinning on an engine, we would
+	 * like to switch to another ready context, i.e. yielding the semaphore
+	 * timeslice.
+	 */
+	u32 yield;
+
 	/**
 	 * @error_interrupt: CS Master EIR
 	 *
@@ -295,8 +309,7 @@ struct intel_engine_cs {
 	u32 context_size;
 	u32 mmio_base;
 
-	unsigned int context_tag;
-#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS)
+	unsigned long context_tag;
 
 	struct rb_node uabi_node;
 
@@ -483,10 +496,11 @@ struct intel_engine_cs {
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
-#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
-#define I915_ENGINE_IS_VIRTUAL       BIT(5)
-#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
-#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
+#define I915_ENGINE_HAS_TIMESLICES   BIT(4)
+#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5)
+#define I915_ENGINE_IS_VIRTUAL       BIT(6)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8)
 	unsigned int flags;
 
 	/*
@@ -584,6 +598,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_HAS_SEMAPHORES;
 }
 
+static inline bool
+intel_engine_has_timeslices(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return false;
+
+	return engine->flags & I915_ENGINE_HAS_TIMESLICES;
+}
+
 static inline bool
 intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index f0e7fd95165a7d15058237e578cbb253c76c27d9..0cc7dd54f4f963ae6dc29698c3839a82e1667a0d 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		}
 	}
 
+	if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) {
+		WRITE_ONCE(engine->execlists.yield,
+			   ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI));
+		ENGINE_TRACE(engine, "semaphore yield: %08x\n",
+			     engine->execlists.yield);
+		if (del_timer(&engine->execlists.timer))
+			tasklet = true;
+	}
+
 	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
 		tasklet = true;
 
@@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	struct intel_uncore *uncore = gt->uncore;
 	const u32 dmask = irqs << 16 | irqs;
 	const u32 smask = irqs << 16;
@@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt)
 	const u32 irqs =
 		GT_CS_MASTER_ERROR_INTERRUPT |
 		GT_RENDER_USER_INTERRUPT |
-		GT_CONTEXT_SWITCH_INTERRUPT;
+		GT_CONTEXT_SWITCH_INTERRUPT |
+		GT_WAIT_SEMAPHORE_INTERRUPT;
 	const u32 gt_interrupts[] = {
 		irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT,
 		irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 683014e7bc51dfff4e68f807e2668e592059fc2d..2dfaddb8811edf863a1cec02bdefcebfd8941dd0 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev,
  * engine info, SW context ID and SW counter need to form a unique number
  * (Context ID) per lrc.
  */
-static u64
+static u32
 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 {
-	u64 desc;
+	u32 desc;
 
 	desc = INTEL_LEGACY_32B_CONTEXT;
 	if (i915_vm_is_4lvl(ce->vm))
@@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_GEN(engine->i915, 8))
 		desc |= GEN8_CTX_L3LLC_COHERENT;
 
-	desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */
-	/*
-	 * The following 32bits are copied into the OA reports (dword 2).
-	 * Consider updating oa_get_render_ctx_id in i915_perf.c when changing
-	 * anything below.
-	 */
-	if (INTEL_GEN(engine->i915) >= 11) {
-		desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT;
-								/* bits 48-53 */
-
-		desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT;
-								/* bits 61-63 */
-	}
-
-	return desc;
+	return i915_ggtt_offset(ce->state) | desc;
 }
 
 static inline unsigned int dword_in_page(void *addr)
@@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq,
 	__execlists_update_reg_state(ce, engine, head);
 
 	/* We've switched away, so this should be a no-op, but intent matters */
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static u32 intel_context_get_runtime(const struct intel_context *ce)
@@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq)
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		execlists_check_context(ce, engine);
 
-	ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
-		ce->lrc_desc |= (u64)ce->tag << 32;
+		GEM_BUG_ON(ce->tag <= BITS_PER_LONG);
+		ce->lrc.ccid = ce->tag;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		ce->lrc_desc |=
-			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
-			GEN11_SW_CTX_ID_SHIFT;
-		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
+		unsigned int tag = ffs(engine->context_tag);
+
+		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
+		clear_bit(tag - 1, &engine->context_tag);
+		ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32);
+
+		BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
+	ce->lrc.ccid |= engine->execlists.ccid;
+
 	__intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 
 static inline void
 __execlists_schedule_out(struct i915_request *rq,
-			 struct intel_engine_cs * const engine)
+			 struct intel_engine_cs * const engine,
+			 unsigned int ccid)
 {
 	struct intel_context * const ce = rq->context;
 
@@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq,
 	    i915_request_completed(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
+	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
+	ccid &= GEN12_MAX_CONTEXT_HW_ID;
+	if (ccid < BITS_PER_LONG) {
+		GEM_BUG_ON(ccid == 0);
+		GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
+		set_bit(ccid - 1, &engine->context_tag);
+	}
+
 	intel_context_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
@@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq)
 {
 	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
+	u32 ccid;
 
 	trace_i915_request_out(rq);
 
+	ccid = rq->context->lrc.ccid;
 	old = READ_ONCE(ce->inflight);
 	do
 		cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL;
 	while (!try_cmpxchg(&ce->inflight, &old, cur));
 	if (!cur)
-		__execlists_schedule_out(rq, old);
+		__execlists_schedule_out(rq, old, ccid);
 
 	i915_request_put(rq);
 }
@@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq)
 static u64 execlists_update_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->context;
-	u64 desc = ce->lrc_desc;
+	u64 desc = ce->lrc.desc;
 	u32 tail, prev;
 
 	/*
@@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 */
 	wmb();
 
-	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
 }
 
@@ -1719,6 +1721,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
+			if (p->flags & I915_DEPENDENCY_WEAK)
+				continue;
+
 			/* Leave semaphores spinning on the other engines */
 			if (w->engine != rq->engine)
 				continue;
@@ -1754,7 +1759,8 @@ static void defer_active(struct intel_engine_cs *engine)
 }
 
 static bool
-need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
+need_timeslice(const struct intel_engine_cs *engine,
+	       const struct i915_request *rq)
 {
 	int hint;
 
@@ -1768,6 +1774,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 	return hint >= effective_prio(rq);
 }
 
+static bool
+timeslice_yield(const struct intel_engine_execlists *el,
+		const struct i915_request *rq)
+{
+	/*
+	 * Once bitten, forever smitten!
+	 *
+	 * If the active context ever busy-waited on a semaphore,
+	 * it will be treated as a hog until the end of its timeslice (i.e.
+	 * until it is scheduled out and replaced by a new submission,
+	 * possibly even its own lite-restore). The HW only sends an interrupt
+	 * on the first miss, and we do know if that semaphore has been
+	 * signaled, or even if it is now stuck on another semaphore. Play
+	 * safe, yield if it might be stuck -- it will be given a fresh
+	 * timeslice in the near future.
+	 */
+	return rq->context->lrc.ccid == READ_ONCE(el->yield);
+}
+
+static bool
+timeslice_expired(const struct intel_engine_execlists *el,
+		  const struct i915_request *rq)
+{
+	return timer_expired(&el->timer) || timeslice_yield(el, rq);
+}
+
 static int
 switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
@@ -1783,8 +1815,7 @@ timeslice(const struct intel_engine_cs *engine)
 	return READ_ONCE(engine->props.timeslice_duration_ms);
 }
 
-static unsigned long
-active_timeslice(const struct intel_engine_cs *engine)
+static unsigned long active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct intel_engine_execlists *execlists = &engine->execlists;
 	const struct i915_request *rq = *execlists->active;
@@ -1946,13 +1977,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
-			   timer_expired(&engine->execlists.timer)) {
+			   timeslice_expired(execlists, last)) {
 			ENGINE_TRACE(engine,
-				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
 				     last->fence.context,
 				     last->fence.seqno,
 				     last->sched.attr.priority,
-				     execlists->queue_priority_hint);
+				     execlists->queue_priority_hint,
+				     yesno(timeslice_yield(execlists, last)));
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -2213,6 +2245,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 		clear_ports(port + 1, last_port - port);
 
+		WRITE_ONCE(execlists->yield, -1);
 		execlists_submit_ports(engine);
 		set_preempt_timeout(engine, *active);
 	} else {
@@ -3043,7 +3076,7 @@ __execlists_context_pin(struct intel_context *ce,
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 
-	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
+	ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine, ce->ring->tail);
 
@@ -3072,7 +3105,7 @@ static void execlists_context_reset(struct intel_context *ce)
 				 ce, ce->engine, ce->ring, true);
 	__execlists_update_reg_state(ce, ce->engine, ce->ring->tail);
 
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static const struct intel_context_ops execlists_context_ops = {
@@ -3541,7 +3574,7 @@ static void enable_execlists(struct intel_engine_cs *engine)
 
 	enable_error_interrupt(engine);
 
-	engine->context_tag = 0;
+	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -3753,7 +3786,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 		     head, ce->ring->tail);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine, head);
-	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
+	ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
 
 unwind:
 	/* Push back any incomplete requests for replay after the reset. */
@@ -4369,8 +4402,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->flags |= I915_ENGINE_SUPPORTS_STATS;
 	if (!intel_vgpu_active(engine->i915)) {
 		engine->flags |= I915_ENGINE_HAS_SEMAPHORES;
-		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915))
+		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) {
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
+			if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+				engine->flags |= I915_ENGINE_HAS_TIMESLICES;
+		}
 	}
 
 	if (INTEL_GEN(engine->i915) >= 12)
@@ -4449,6 +4485,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 	engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift;
 	engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift;
 	engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift;
+	engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift;
 }
 
 static void rcs_submission_override(struct intel_engine_cs *engine)
@@ -4516,6 +4553,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	else
 		execlists->csb_size = GEN11_CSB_ENTRIES;
 
+	if (INTEL_GEN(engine->i915) >= 11) {
+		execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
+		execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32);
+	}
+
 	reset_csb_pointers(engine);
 
 	/* Finally, take ownership and responsibility for cleanup! */
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 6f06ba750a0a8e2518d8ce458ad49355955cefda..f95ae15ce865c0fbad7fd7f4a85e655ba9b0c17e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce,
 			goto err;
 	}
 
-	cs = intel_ring_begin(rq, 10);
+	cs = intel_ring_begin(rq, 14);
 	if (IS_ERR(cs)) {
 		err = PTR_ERR(cs);
 		goto err;
@@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce,
 	*cs++ = MI_SEMAPHORE_WAIT |
 		MI_SEMAPHORE_GLOBAL_GTT |
 		MI_SEMAPHORE_POLL |
-		MI_SEMAPHORE_SAD_NEQ_SDD;
-	*cs++ = 0;
+		MI_SEMAPHORE_SAD_GTE_SDD;
+	*cs++ = idx;
 	*cs++ = offset;
 	*cs++ = 0;
 
@@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce,
 	*cs++ = offset + idx * sizeof(u32);
 	*cs++ = 0;
 
+	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+	*cs++ = offset;
+	*cs++ = 0;
+	*cs++ = idx + 1;
+
 	intel_ring_advance(rq, cs);
 
 	rq->sched.attr.priority = I915_PRIORITY_MASK;
@@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg)
 
 	for_each_engine(engine, gt, id) {
 		enum { A1, A2, B1 };
-		enum { X = 1, Y, Z };
+		enum { X = 1, Z, Y };
 		struct i915_request *rq[3] = {};
 		struct intel_context *ce;
 		unsigned long heartbeat;
@@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg)
 			goto err;
 		}
 
-		rq[0] = create_rewinder(ce, NULL, slot, 1);
+		rq[0] = create_rewinder(ce, NULL, slot, X);
 		if (IS_ERR(rq[0])) {
 			intel_context_put(ce);
 			goto err;
 		}
 
-		rq[1] = create_rewinder(ce, NULL, slot, 2);
+		rq[1] = create_rewinder(ce, NULL, slot, Y);
 		intel_context_put(ce);
 		if (IS_ERR(rq[1]))
 			goto err;
@@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg)
 			goto err;
 		}
 
-		rq[2] = create_rewinder(ce, rq[0], slot, 3);
+		rq[2] = create_rewinder(ce, rq[0], slot, Z);
 		intel_context_put(ce);
 		if (IS_ERR(rq[2]))
 			goto err;
@@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg)
 		GEM_BUG_ON(!timer_pending(&engine->execlists.timer));
 
 		/* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */
-		GEM_BUG_ON(!i915_request_is_active(rq[A1]));
-		GEM_BUG_ON(!i915_request_is_active(rq[A2]));
-		GEM_BUG_ON(!i915_request_is_active(rq[B1]));
-
-		/* Wait for the timeslice to kick in */
-		del_timer(&engine->execlists.timer);
-		tasklet_hi_schedule(&engine->execlists.tasklet);
-		intel_engine_flush_submission(engine);
-
+		if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */
+			/* Wait for the timeslice to kick in */
+			del_timer(&engine->execlists.timer);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+			intel_engine_flush_submission(engine);
+		}
 		/* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */
 		GEM_BUG_ON(!i915_request_is_active(rq[A1]));
 		GEM_BUG_ON(!i915_request_is_active(rq[B1]));
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index fe7778c28d2d7846c308da40668bf86dd445765c..aa6d56e25a10ae3fa6b3a5d26a16e0d45bd69917 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc,
 static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(rq->context->lrc_desc);
+	u32 ctx_desc = rq->context->lrc.ccid;
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	guc_wq_item_append(guc, engine->guc_id, ctx_desc,
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a83df2f84eb99c04a7d9aaa748cdfb9ee607b05f..a1696e9ce4b6c07c69d20b4dc65e140923bd443e 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -208,14 +208,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG0) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG1) |
 				SKL_FUSE_PG_DIST_STATUS(SKL_PG2);
-		vgpu_vreg_t(vgpu, LCPLL1_CTL) |=
-				LCPLL_PLL_ENABLE |
-				LCPLL_PLL_LOCK;
-		vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE;
-
+		/*
+		 * Only 1 PIPE enabled in current vGPU display and PIPE_A is
+		 *  tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A,
+		 *   TRANSCODER_A can be enabled. PORT_x depends on the input of
+		 *   setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x
+		 *   so we fixed to DPLL0 here.
+		 * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode
+		 */
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) =
+			DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, DPLL_CTRL1) |=
+			DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0);
+		vgpu_vreg_t(vgpu, LCPLL1_CTL) =
+			LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK;
+		vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0);
+		/*
+		 * Golden M/N are calculated based on:
+		 *   24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID),
+		 *   DP link clk 1620 MHz and non-constant_n.
+		 * TODO: calculate DP link symbol clk and stream clk m/n.
+		 */
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT;
+		vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e;
+		vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000;
+		vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e;
+		vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000;
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B);
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -236,6 +263,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
@@ -256,6 +289,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	}
 
 	if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) {
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) &=
+			~DPLL_CTRL2_DDI_CLK_OFF(PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D);
+		vgpu_vreg_t(vgpu, DPLL_CTRL2) |=
+			DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D);
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT;
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &=
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index cb11c31840857293ff2d3b7a0d7688e4ccf02e35..e92ed96c9b239422776f18b7132f818fa04162fd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -290,7 +290,7 @@ static void
 shadow_context_descriptor_update(struct intel_context *ce,
 				 struct intel_vgpu_workload *workload)
 {
-	u64 desc = ce->lrc_desc;
+	u64 desc = ce->lrc.desc;
 
 	/*
 	 * Update bits 0-11 of the context descriptor which includes flags
@@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce,
 	desc |= (u64)workload->ctx_desc.addressing_mode <<
 		GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
-	ce->lrc_desc = desc;
+	ce->lrc.desc = desc;
 }
 
 static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
@@ -379,7 +379,11 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 		for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) {
 			struct i915_page_directory * const pd =
 				i915_pd_entry(ppgtt->pd, i);
-
+			/* skip now as current i915 ppgtt alloc won't allocate
+			   top level pdp for non 4-level table, won't impact
+			   shadow ppgtt. */
+			if (!pd)
+				break;
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 4518b9b35c3d4f43aafe3f9ac004e7932bc51f1b..02ad1acd117c4dea7d9ca371996de84aee89105d 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -128,6 +128,13 @@ i915_gem_evict_something(struct i915_address_space *vm,
 	active = NULL;
 	INIT_LIST_HEAD(&eviction_list);
 	list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) {
+		if (vma == active) { /* now seen this vma twice */
+			if (flags & PIN_NONBLOCK)
+				break;
+
+			active = ERR_PTR(-EAGAIN);
+		}
+
 		/*
 		 * We keep this list in a rough least-recently scanned order
 		 * of active elements (inactive elements are cheap to reap).
@@ -143,21 +150,12 @@ i915_gem_evict_something(struct i915_address_space *vm,
 		 * To notice when we complete one full cycle, we record the
 		 * first active element seen, before moving it to the tail.
 		 */
-		if (i915_vma_is_active(vma)) {
-			if (vma == active) {
-				if (flags & PIN_NONBLOCK)
-					break;
-
-				active = ERR_PTR(-EAGAIN);
-			}
-
-			if (active != ERR_PTR(-EAGAIN)) {
-				if (!active)
-					active = vma;
+		if (active != ERR_PTR(-EAGAIN) && i915_vma_is_active(vma)) {
+			if (!active)
+				active = vma;
 
-				list_move_tail(&vma->vm_link, &vm->bound_list);
-				continue;
-			}
+			list_move_tail(&vma->vm_link, &vm->bound_list);
+			continue;
 		}
 
 		if (mark_free(&scan, vma, flags, &eviction_list))
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 2a4cd0ba546459a622536a7bed16ed4b6e014680..5c8e51d2ba5b3e139581f14f8713b5f555bb64b7 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee)
 static void record_request(const struct i915_request *request,
 			   struct i915_request_coredump *erq)
 {
-	const struct i915_gem_context *ctx;
-
 	erq->flags = request->fence.flags;
 	erq->context = request->fence.context;
 	erq->seqno = request->fence.seqno;
@@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request,
 
 	erq->pid = 0;
 	rcu_read_lock();
-	ctx = rcu_dereference(request->context->gem_context);
-	if (ctx)
-		erq->pid = pid_nr(ctx->pid);
+	if (!intel_context_is_closed(request->context)) {
+		const struct i915_gem_context *ctx;
+
+		ctx = rcu_dereference(request->context->gem_context);
+		if (ctx)
+			erq->pid = pid_nr(ctx->pid);
+	}
 	rcu_read_unlock();
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index d91557d842dcd3f796fbf61fe4927a4607e91245..8a2b83807ffcddf9190d726bee60aea57413181c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3361,7 +3361,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) |
 		GEN8_PIPE_CDCLK_CRC_DONE;
 	u32 de_pipe_enables;
-	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
+	u32 de_port_masked = gen8_de_port_aux_mask(dev_priv);
 	u32 de_port_enables;
 	u32 de_misc_masked = GEN8_DE_EDP_PSR;
 	enum pipe pipe;
@@ -3369,18 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) <= 10)
 		de_misc_masked |= GEN8_DE_MISC_GSE;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
-				  GEN9_AUX_CHANNEL_D;
-		if (IS_GEN9_LP(dev_priv))
-			de_port_masked |= BXT_DE_PORT_GMBUS;
-	}
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		de_port_masked |= ICL_AUX_CHANNEL_E;
-
-	if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11)
-		de_port_masked |= CNL_AUX_CHANNEL_F;
+	if (IS_GEN9_LP(dev_priv))
+		de_port_masked |= BXT_DE_PORT_GMBUS;
 
 	de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
 					   GEN8_PIPE_FIFO_UNDERRUN;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 66a46e41d5ef90046b9570e624244659482f9ec4..cf2c01f17da837235dd8f79e1614cf896e814299 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			 * dropped by GuC. They won't be part of the context
 			 * ID in the OA reports, so squash those lower bits.
 			 */
-			stream->specific_ctx_id =
-				lower_32_bits(ce->lrc_desc) >> 12;
+			stream->specific_ctx_id = ce->lrc.lrca >> 12;
 
 			/*
 			 * GuC uses the top bit to signal proxy submission, so
@@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
 		/*
 		 * Pick an unused context id
-		 * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts
+		 * 0 - BITS_PER_LONG are used by other contexts
 		 * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context
 		 */
 		stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
-		BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e0c6021fdaf989c96e207ec5c946a9115d144b5b..6e12000c4b6b5cd7cb181c8bd2954a8da7d2b574 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GT_BSD_CS_ERROR_INTERRUPT		(1 << 15)
 #define GT_BSD_USER_INTERRUPT			(1 << 12)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1	(1 << 11) /* hsw+; rsvd on snb, ivb, vlv */
+#define GT_WAIT_SEMAPHORE_INTERRUPT		REG_BIT(11) /* bdw+ */
 #define GT_CONTEXT_SWITCH_INTERRUPT		(1 <<  8)
 #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT	(1 <<  5) /* !snb */
 #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT	(1 <<  4)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index c0df71d7d0ff1499f53d9b98a27f7641fce87a29..e2b78db685eaecb9599dbd5b2c28f60a104e51e0 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1017,11 +1017,15 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 	GEM_BUG_ON(to == from);
 	GEM_BUG_ON(to->timeline == from->timeline);
 
-	if (i915_request_completed(from))
+	if (i915_request_completed(from)) {
+		i915_sw_fence_set_error_once(&to->submit, from->fence.error);
 		return 0;
+	}
 
 	if (to->engine->schedule) {
-		ret = i915_sched_node_add_dependency(&to->sched, &from->sched);
+		ret = i915_sched_node_add_dependency(&to->sched,
+						     &from->sched,
+						     I915_DEPENDENCY_EXTERNAL);
 		if (ret < 0)
 			return ret;
 	}
@@ -1183,7 +1187,9 @@ __i915_request_await_execution(struct i915_request *to,
 
 	/* Couple the dependency tree for PI on this exposed to->fence */
 	if (to->engine->schedule) {
-		err = i915_sched_node_add_dependency(&to->sched, &from->sched);
+		err = i915_sched_node_add_dependency(&to->sched,
+						     &from->sched,
+						     I915_DEPENDENCY_WEAK);
 		if (err < 0)
 			return err;
 	}
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 68b06a7ba667da3dfd74421aff77f5935eaf0f80..f0a9e8958ca0d64fb73fb1219e86e8607c779b12 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -456,7 +456,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 }
 
 int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal)
+				   struct i915_sched_node *signal,
+				   unsigned long flags)
 {
 	struct i915_dependency *dep;
 
@@ -465,8 +466,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 		return -ENOMEM;
 
 	if (!__i915_sched_node_add_dependency(node, signal, dep,
-					      I915_DEPENDENCY_EXTERNAL |
-					      I915_DEPENDENCY_ALLOC))
+					      flags | I915_DEPENDENCY_ALLOC))
 		i915_dependency_free(dep);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index d1dc4efef77b562f3b044050ddab332ed64ab2fe..6f0bf00fc5690d361800454029bbea703b393790 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 				      unsigned long flags);
 
 int i915_sched_node_add_dependency(struct i915_sched_node *node,
-				   struct i915_sched_node *signal);
+				   struct i915_sched_node *signal,
+				   unsigned long flags);
 
 void i915_sched_node_fini(struct i915_sched_node *node);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index d18e7055005424e67516e59f6a8a214a6978abf0..7186875088a0a285c1f05a13df5846db478f4162 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -78,6 +78,7 @@ struct i915_dependency {
 	unsigned long flags;
 #define I915_DEPENDENCY_ALLOC		BIT(0)
 #define I915_DEPENDENCY_EXTERNAL	BIT(1)
+#define I915_DEPENDENCY_WEAK		BIT(2)
 };
 
 #endif /* _I915_SCHEDULER_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 82e3bc2806224e78d10e0525fbd352bb8cf0f734..2cd7a7e87c0a750ff87db98f9bfce927af88dda6 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -1228,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma)
 
 	lockdep_assert_held(&vma->vm->mutex);
 
-	/*
-	 * First wait upon any activity as retiring the request may
-	 * have side-effects such as unpinning or even unbinding this vma.
-	 *
-	 * XXX Actually waiting under the vm->mutex is a hinderance and
-	 * should be pipelined wherever possible. In cases where that is
-	 * unavoidable, we should lift the wait to before the mutex.
-	 */
-	ret = i915_vma_sync(vma);
-	if (ret)
-		return ret;
-
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
 		return -EAGAIN;
@@ -1313,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
-	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
-		/* XXX not always required: nop_clear_range */
-		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
-
 	/* Optimistic wait before taking the mutex */
 	err = i915_vma_sync(vma);
 	if (err)
 		goto out_rpm;
 
+	if (i915_vma_is_pinned(vma)) {
+		vma_print_allocator(vma, "is pinned");
+		return -EAGAIN;
+	}
+
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+		/* XXX not always required: nop_clear_range */
+		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
 	err = mutex_lock_interruptible(&vm->mutex);
 	if (err)
 		goto out_rpm;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 8375054ba27d92b72f6b03a0e15f2703b5befdb5..a52986a9e7a68245f670746e1e3ba32ad90db042 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	 * WaIncreaseLatencyIPCEnabled: kbl,cfl
 	 * Display WA #1141: kbl,cfl
 	 */
-	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) ||
+	if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) &&
 	    dev_priv->ipc_enabled)
 		latency += 4;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 58b5f40a07dd6be16eedab36d8c52d9ff9e2e914..af89c7fc8f59340bad9d38628b0c6f751caed521 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -173,7 +173,7 @@ static int igt_vma_create(void *arg)
 		}
 
 		nc = 0;
-		for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) {
+		for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) {
 			for (; nc < num_ctx; nc++) {
 				ctx = mock_context(i915, "mock");
 				if (!ctx)
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index b5f5eb7b4bb904b311f5994750e5830026a8ae1b..8c2e1b47e81a59c582b4556ed7cde3f7c4df2452 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -412,9 +412,7 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev)
 	if (priv->afbcd.ops)
 		priv->afbcd.ops->init(priv);
 
-	drm_mode_config_helper_resume(priv->drm);
-
-	return 0;
+	return drm_mode_config_helper_resume(priv->drm);
 }
 
 static int compare_of(struct device *dev, void *data)
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index bd268028fb3d625c9c637b642a540d0e008dcfab..583cd6e0ae27faa454f32243de79b7a5d703ac8f 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt,
 
 static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 {
+	struct host1x *host1x = dev_get_drvdata(dev->dev.parent);
 	struct iommu_domain *domain;
 
 	/*
@@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev)
 	 * sufficient and whether or not the host1x is attached to an IOMMU
 	 * doesn't matter.
 	 */
-	if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32))
+	if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32))
 		return true;
 
 	return domain != NULL;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 388bcc2889aaf2e763a702e3e4c4aafd8434f080..d24344e919227251e5ab48f95662ae1dbbb38a6a 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host)
 	}
 }
 
+static bool host1x_wants_iommu(struct host1x *host1x)
+{
+	/*
+	 * If we support addressing a maximum of 32 bits of physical memory
+	 * and if the host1x firewall is enabled, there's no need to enable
+	 * IOMMU support. This can happen for example on Tegra20, Tegra30
+	 * and Tegra114.
+	 *
+	 * Tegra124 and later can address up to 34 bits of physical memory and
+	 * many platforms come equipped with more than 2 GiB of system memory,
+	 * which requires crossing the 4 GiB boundary. But there's a catch: on
+	 * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can
+	 * only address up to 32 bits of memory in GATHER opcodes, which means
+	 * that command buffers need to either be in the first 2 GiB of system
+	 * memory (which could quickly lead to memory exhaustion), or command
+	 * buffers need to be treated differently from other buffers (which is
+	 * not possible with the current ABI).
+	 *
+	 * A third option is to use the IOMMU in these cases to make sure all
+	 * buffers will be mapped into a 32-bit IOVA space that host1x can
+	 * address. This allows all of the system memory to be used and works
+	 * within the limitations of the host1x on these SoCs.
+	 *
+	 * In summary, default to enable IOMMU on Tegra124 and later. For any
+	 * of the earlier SoCs, only use the IOMMU for additional safety when
+	 * the host1x firewall is disabled.
+	 */
+	if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) {
+		if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+			return false;
+	}
+
+	return true;
+}
+
 static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev);
 	int err;
 
 	/*
-	 * If the host1x firewall is enabled, there's no need to enable IOMMU
-	 * support. Similarly, if host1x is already attached to an IOMMU (via
-	 * the DMA API), don't try to attach again.
+	 * We may not always want to enable IOMMU support (for example if the
+	 * host1x firewall is already enabled and we don't support addressing
+	 * more than 32 bits of physical memory), so check for that first.
+	 *
+	 * Similarly, if host1x is already attached to an IOMMU (via the DMA
+	 * API), don't try to attach again.
 	 */
-	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain)
+	if (!host1x_wants_iommu(host) || domain)
 		return domain;
 
 	host->group = iommu_group_get(host->dev);
@@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void)
 }
 module_exit(tegra_host1x_exit);
 
+/**
+ * host1x_get_dma_mask() - query the supported DMA mask for host1x
+ * @host1x: host1x instance
+ *
+ * Note that this returns the supported DMA mask for host1x, which can be
+ * different from the applicable DMA mask under certain circumstances.
+ */
+u64 host1x_get_dma_mask(struct host1x *host1x)
+{
+	return host1x->info->dma_mask;
+}
+EXPORT_SYMBOL(host1x_get_dma_mask);
+
 MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
 MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>");
 MODULE_DESCRIPTION("Host1x driver for Tegra products");
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 62d216ff1097940c3d28626213d4e581589637ef..c230b4e70d759283100a4e496907c3245722d235 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -17,9 +17,12 @@ enum host1x_class {
 	HOST1X_CLASS_GR3D = 0x60,
 };
 
+struct host1x;
 struct host1x_client;
 struct iommu_group;
 
+u64 host1x_get_dma_mask(struct host1x *host1x);
+
 /**
  * struct host1x_client_ops - host1x client operations
  * @init: host1x client initialization code