Merge drm/drm-next into drm-misc-next

Backmerging 5.2-rc1 to -misc-next for robher

Signed-off-by: Sean Paul <seanpaul@chromium.org>

102 files changed, 599 insertions, 306 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 13d7b321db0d..a461f078a0dd 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -207,7 +207,6 @@ config DRM_RADEON
 	select POWER_SUPPLY
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
-	select BACKLIGHT_LCD_SUPPORT
 	select INTERVAL_TREE
 	help
 	  Choose this option if you have an ATI Radeon graphics card.  There
@@ -228,7 +227,6 @@ config DRM_AMDGPU
 	select POWER_SUPPLY
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
-	select BACKLIGHT_LCD_SUPPORT
 	select INTERVAL_TREE
 	select CHASH
 	help
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 4376b17ca594..56f8ca2a3bb4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -464,8 +464,7 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 			}
 		}
 		if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
-			if ((adev->flags & AMD_IS_PX) &&
-			    amdgpu_atpx_dgpu_req_power_for_displays()) {
+			if (adev->flags & AMD_IS_PX) {
 				pm_runtime_get_sync(adev->ddev->dev);
 				/* Just fire off a uevent and let userspace tell us what to do */
 				drm_helper_hpd_irq_event(adev->ddev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b9371ec5e04f..9f282e971197 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3184,6 +3184,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 
 		/* No need to recover an evicted BO */
 		if (shadow->tbo.mem.mem_type != TTM_PL_TT ||
+		    shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET ||
 		    shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM)
 			continue;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 3e6823fdd939..58ed401c5996 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -256,14 +256,14 @@ static int amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
 	/* TODO we should be able to split locking for interval tree and
 	 * amdgpu_mn_invalidate_node
 	 */
-	if (amdgpu_mn_read_lock(amn, range->blockable))
+	if (amdgpu_mn_read_lock(amn, mmu_notifier_range_blockable(range)))
 		return -EAGAIN;
 
 	it = interval_tree_iter_first(&amn->objects, range->start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			amdgpu_mn_read_unlock(amn);
 			return -EAGAIN;
 		}
@@ -299,7 +299,7 @@ static int amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 	/* notification is exclusive, but interval is inclusive */
 	end = range->end - 1;
 
-	if (amdgpu_mn_read_lock(amn, range->blockable))
+	if (amdgpu_mn_read_lock(amn, mmu_notifier_range_blockable(range)))
 		return -EAGAIN;
 
 	it = interval_tree_iter_first(&amn->objects, range->start, end);
@@ -307,7 +307,7 @@ static int amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 		struct amdgpu_mn_node *node;
 		struct amdgpu_bo *bo;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			amdgpu_mn_read_unlock(amn);
 			return -EAGAIN;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 95144e49c7f9..34471dbaa872 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -342,6 +342,16 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	if (current_level == level)
 		return count;
 
+	/* profile_exit setting is valid only when current mode is in profile mode */
+	if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
+	    AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
+	    AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
+	    AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)) &&
+	    (level == AMD_DPM_FORCED_LEVEL_PROFILE_EXIT)) {
+		pr_err("Currently not in any profile mode!\n");
+		return -EINVAL;
+	}
+
 	if (is_support_sw_smu(adev)) {
 		mutex_lock(&adev->pm.mutex);
 		if (adev->pm.dpm.thermal_active) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 905cce1814f3..05897b05766b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -38,18 +38,10 @@ static void psp_set_funcs(struct amdgpu_device *adev);
 static int psp_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct psp_context *psp = &adev->psp;
 
 	psp_set_funcs(adev);
 
-	return 0;
-}
-
-static int psp_sw_init(void *handle)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct psp_context *psp = &adev->psp;
-	int ret;
-
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
@@ -67,6 +59,15 @@ static int psp_sw_init(void *handle)
 
 	psp->adev = adev;
 
+	return 0;
+}
+
+static int psp_sw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct psp_context *psp = &adev->psp;
+	int ret;
+
 	ret = psp_init_microcode(psp);
 	if (ret) {
 		DRM_ERROR("Failed to load psp firmware!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index 0767a93e4d91..639297250c21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -53,26 +53,25 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
 						  int fd,
 						  enum drm_sched_priority priority)
 {
-	struct file *filp = fget(fd);
+	struct fd f = fdget(fd);
 	struct amdgpu_fpriv *fpriv;
 	struct amdgpu_ctx *ctx;
 	uint32_t id;
 	int r;
 
-	if (!filp)
+	if (!f.file)
 		return -EINVAL;
 
-	r = amdgpu_file_to_fpriv(filp, &fpriv);
+	r = amdgpu_file_to_fpriv(f.file, &fpriv);
 	if (r) {
-		fput(filp);
+		fdput(f);
 		return r;
 	}
 
 	idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id)
 		amdgpu_ctx_priority_override(ctx, priority);
 
-	fput(filp);
-
+	fdput(f);
 	return 0;
 }
 
@@ -81,30 +80,30 @@ static int amdgpu_sched_context_priority_override(struct amdgpu_device *adev,
 						  unsigned ctx_id,
 						  enum drm_sched_priority priority)
 {
-	struct file *filp = fget(fd);
+	struct fd f = fdget(fd);
 	struct amdgpu_fpriv *fpriv;
 	struct amdgpu_ctx *ctx;
 	int r;
 
-	if (!filp)
+	if (!f.file)
 		return -EINVAL;
 
-	r = amdgpu_file_to_fpriv(filp, &fpriv);
+	r = amdgpu_file_to_fpriv(f.file, &fpriv);
 	if (r) {
-		fput(filp);
+		fdput(f);
 		return r;
 	}
 
 	ctx = amdgpu_ctx_get(fpriv, ctx_id);
 
 	if (!ctx) {
-		fput(filp);
+		fdput(f);
 		return -EINVAL;
 	}
 
 	amdgpu_ctx_priority_override(ctx, priority);
 	amdgpu_ctx_put(ctx);
-	fput(filp);
+	fdput(f);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index a07c85815b7a..4f10f5aba00b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2757,6 +2757,37 @@ error_free_sched_entity:
 }
 
 /**
+ * amdgpu_vm_check_clean_reserved - check if a VM is clean
+ *
+ * @adev: amdgpu_device pointer
+ * @vm: the VM to check
+ *
+ * check all entries of the root PD, if any subsequent PDs are allocated,
+ * it means there are page table creating and filling, and is no a clean
+ * VM
+ *
+ * Returns:
+ *	0 if this VM is clean
+ */
+static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
+	struct amdgpu_vm *vm)
+{
+	enum amdgpu_vm_level root = adev->vm_manager.root_level;
+	unsigned int entries = amdgpu_vm_num_entries(adev, root);
+	unsigned int i = 0;
+
+	if (!(vm->root.entries))
+		return 0;
+
+	for (i = 0; i < entries; i++) {
+		if (vm->root.entries[i].base.bo)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * amdgpu_vm_make_compute - Turn a GFX VM into a compute VM
  *
  * @adev: amdgpu_device pointer
@@ -2786,10 +2817,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, uns
 		return r;
 
 	/* Sanity checks */
-	if (!RB_EMPTY_ROOT(&vm->va.rb_root) || vm->root.entries) {
-		r = -EINVAL;
+	r = amdgpu_vm_check_clean_reserved(adev, vm);
+	if (r)
 		goto unreserve_bo;
-	}
 
 	if (pasid) {
 		unsigned long flags;
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 1741056e6af6..41a9a5779623 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -182,6 +182,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
 				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
 	}
+	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp);
 
 	tmp = mmVM_L2_CNTL4_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 8dbad496b29f..2471e7cf75ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -372,6 +372,9 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 		if (amdgpu_sriov_runtime(adev))
 			schedule_work(&adev->virt.flr_work);
 		break;
+		case IDH_QUERY_ALIVE:
+			xgpu_ai_mailbox_send_ack(adev);
+			break;
 		/* READY_TO_ACCESS_GPU is fetched by kernel polling, IRQ can ignore
 		 * it byfar since that polling thread will handle it,
 		 * other msg like flr complete is not handled here.
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
index 39d151b79153..077e91a33d62 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
@@ -49,6 +49,7 @@ enum idh_event {
 	IDH_FLR_NOTIFICATION_CMPL,
 	IDH_SUCCESS,
 	IDH_FAIL,
+	IDH_QUERY_ALIVE,
 	IDH_EVENT_MAX
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index dc461df48da0..2191d3d0a219 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -787,10 +787,13 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 							   0xFFFFFFFF, 0x00000004);
 			/* mc resume*/
 			if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
-				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
-							    lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
-				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
-							    upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i,
+							mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+							adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_lo);
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i,
+							mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+							adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_hi);
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0);
 				offset = 0;
 			} else {
 				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
@@ -798,10 +801,11 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
 							    upper_32_bits(adev->uvd.inst[i].gpu_addr));
 				offset = size;
+				MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
+							AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+
 			}
 
-			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0),
-						    AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0), size);
 
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index f3f5938430d4..c0ec27991c22 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -244,13 +244,18 @@ static int vce_v4_0_sriov_start(struct amdgpu_device *adev)
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_SWAP_CNTL1), 0);
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_LMI_VM_CTRL), 0);
 
+		offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+			uint32_t low = adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].tmr_mc_addr_lo;
+			uint32_t hi = adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].tmr_mc_addr_hi;
+			uint64_t tmr_mc_addr = (uint64_t)(hi) << 32 | low;
+
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
-						mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
-						adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 8);
+						mmVCE_LMI_VCPU_CACHE_40BIT_BAR0), tmr_mc_addr >> 8);
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
 						mmVCE_LMI_VCPU_CACHE_64BIT_BAR0),
-						(adev->firmware.ucode[AMDGPU_UCODE_ID_VCE].mc_addr >> 40) & 0xff);
+						(tmr_mc_addr >> 40) & 0xff);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0), 0);
 		} else {
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
 						mmVCE_LMI_VCPU_CACHE_40BIT_BAR0),
@@ -258,6 +263,9 @@ static int vce_v4_0_sriov_start(struct amdgpu_device *adev)
 			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
 						mmVCE_LMI_VCPU_CACHE_64BIT_BAR0),
 						(adev->vce.gpu_addr >> 40) & 0xff);
+			MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0),
+						offset & ~0x0f000000);
+
 		}
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0,
 						mmVCE_LMI_VCPU_CACHE_40BIT_BAR1),
@@ -272,10 +280,7 @@ static int vce_v4_0_sriov_start(struct amdgpu_device *adev)
 						mmVCE_LMI_VCPU_CACHE_64BIT_BAR2),
 						(adev->vce.gpu_addr >> 40) & 0xff);
 
-		offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 		size = VCE_V4_0_FW_SIZE;
-		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_OFFSET0),
-					offset & ~0x0f000000);
 		MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(VCE, 0, mmVCE_VCPU_CACHE_SIZE0), size);
 
 		offset = (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) ? offset + size : 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 1b2f69a9a24e..8d89ab7f0ae8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -31,7 +31,7 @@
 #include "soc15_common.h"
 #include "vega10_ih.h"
 
-
+#define MAX_REARM_RETRY 10
 
 static void vega10_ih_set_interrupt_funcs(struct amdgpu_device *adev);
 
@@ -382,6 +382,38 @@ static void vega10_ih_decode_iv(struct amdgpu_device *adev,
 }
 
 /**
+ * vega10_ih_irq_rearm - rearm IRQ if lost
+ *
+ * @adev: amdgpu_device pointer
+ *
+ */
+static void vega10_ih_irq_rearm(struct amdgpu_device *adev,
+			       struct amdgpu_ih_ring *ih)
+{
+	uint32_t reg_rptr = 0;
+	uint32_t v = 0;
+	uint32_t i = 0;
+
+	if (ih == &adev->irq.ih)
+		reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR);
+	else if (ih == &adev->irq.ih1)
+		reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR_RING1);
+	else if (ih == &adev->irq.ih2)
+		reg_rptr = SOC15_REG_OFFSET(OSSSYS, 0, mmIH_RB_RPTR_RING2);
+	else
+		return;
+
+	/* Rearm IRQ / re-wwrite doorbell if doorbell write is lost */
+	for (i = 0; i < MAX_REARM_RETRY; i++) {
+		v = RREG32_NO_KIQ(reg_rptr);
+		if ((v < ih->ring_size) && (v != ih->rptr))
+			WDOORBELL32(ih->doorbell_index, ih->rptr);
+		else
+			break;
+	}
+}
+
+/**
  * vega10_ih_set_rptr - set the IH ring buffer rptr
  *
  * @adev: amdgpu_device pointer
@@ -395,6 +427,9 @@ static void vega10_ih_set_rptr(struct amdgpu_device *adev,
 		/* XXX check if swapping is necessary on BE */
 		*ih->rptr_cpu = ih->rptr;
 		WDOORBELL32(ih->doorbell_index, ih->rptr);
+
+		if (amdgpu_sriov_vf(adev))
+			vega10_ih_irq_rearm(adev, ih);
 	} else if (ih == &adev->irq.ih) {
 		WREG32_SOC15(OSSSYS, 0, mmIH_RB_RPTR, ih->rptr);
 	} else if (ih == &adev->irq.ih1) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 2cb09e088dce..769dbc7be8cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1272,8 +1272,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 
 	dev->node_props.vendor_id = gpu->pdev->vendor;
 	dev->node_props.device_id = gpu->pdev->device;
-	dev->node_props.location_id = PCI_DEVID(gpu->pdev->bus->number,
-		gpu->pdev->devfn);
+	dev->node_props.location_id = pci_dev_id(gpu->pdev);
 	dev->node_props.max_engine_clk_fcompute =
 		amdgpu_amdkfd_get_max_engine_clock_in_mhz(dev->gpu->kgd);
 	dev->node_props.max_engine_clk_ccompute =
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 1854506e3e8f..995f9df66142 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5242,7 +5242,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_crtc *pcrtc,
 				    bool wait_for_vblank)
 {
-	uint32_t i, r;
+	uint32_t i;
 	uint64_t timestamp_ns;
 	struct drm_plane *plane;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
@@ -5253,6 +5253,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	struct dm_crtc_state *dm_old_crtc_state =
 			to_dm_crtc_state(drm_atomic_get_old_crtc_state(state, pcrtc));
 	int planes_count = 0, vpos, hpos;
+	long r;
 	unsigned long flags;
 	struct amdgpu_bo *abo;
 	uint64_t tiling_flags;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index dda10b1f8574..18c775a950cc 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1464,6 +1464,11 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 		return UPDATE_TYPE_FULL;
 	}
 
+	if (u->surface->force_full_update) {
+		update_flags->bits.full_update = 1;
+		return UPDATE_TYPE_FULL;
+	}
+
 	type = get_plane_info_update_type(u);
 	elevate_update_type(&overall_type, type);
 
@@ -1900,6 +1905,14 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		}
 
 		dc_resource_state_copy_construct(state, context);
+
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+			struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
+				new_pipe->plane_state->force_full_update = true;
+		}
 	}
 
 
@@ -1936,6 +1949,12 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		dc->current_state = context;
 		dc_release_state(old);
 
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (pipe_ctx->plane_state && pipe_ctx->stream == stream)
+				pipe_ctx->plane_state->force_full_update = false;
+		}
 	}
 	/*let's use current_state to update watermark etc*/
 	if (update_type >= UPDATE_TYPE_FULL)
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 70edd9ea5afe..44e4b0465587 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -612,6 +612,9 @@ struct dc_plane_state {
 	struct dc_plane_status status;
 	struct dc_context *ctx;
 
+	/* HACK: Workaround for forcing full reprogramming under some conditions */
+	bool force_full_update;
+
 	/* private to dc_surface.c */
 	enum dc_irq_source irq_source;
 	struct kref refcount;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 937b5cffd7ef..bd33c47183fc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -190,6 +190,12 @@ static void submit_channel_request(
 				AUXP_IMPCAL_OVERRIDE_ENABLE, 1,
 				AUXP_IMPCAL_OVERRIDE_ENABLE, 0);
 	}
+
+	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+
+	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+				10, aux110->timeout_period/10);
+
 	/* set the delay and the number of bytes to write */
 
 	/* The length include
@@ -242,9 +248,6 @@ static void submit_channel_request(
 		}
 	}
 
-	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
-	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
-				10, aux110->timeout_period/10);
 	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index aab5f0c34584..ce6a26d189b0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -71,11 +71,11 @@ enum {	/* This is the timeout as defined in DP 1.2a,
 	 * at most within ~240usec. That means,
 	 * increasing this timeout will not affect normal operation,
 	 * and we'll timeout after
-	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec.
 	 * This timeout is especially important for
-	 * resume from S3 and CTS.
+	 * converters, resume from S3, and CTS.
 	 */
-	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6
 };
 
 struct dce_aux {
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 8840f396a7b6..3dff9997f5e3 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -76,7 +76,6 @@ config DRM_PARADE_PS8622
 	depends on OF
 	select DRM_PANEL
 	select DRM_KMS_HELPER
-	select BACKLIGHT_LCD_SUPPORT
 	select BACKLIGHT_CLASS_DEVICE
 	---help---
 	  Parade eDP-LVDS bridge chip driver.
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index ec2ca71e1323..c532e9c9e491 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -748,11 +748,11 @@ static void adv7511_mode_set(struct adv7511 *adv7511,
 			vsync_polarity = 1;
 	}
 
-	if (mode->vrefresh <= 24000)
+	if (drm_mode_vrefresh(mode) <= 24)
 		low_refresh_rate = ADV7511_LOW_REFRESH_RATE_24HZ;
-	else if (mode->vrefresh <= 25000)
+	else if (drm_mode_vrefresh(mode) <= 25)
 		low_refresh_rate = ADV7511_LOW_REFRESH_RATE_25HZ;
-	else if (mode->vrefresh <= 30000)
+	else if (drm_mode_vrefresh(mode) <= 30)
 		low_refresh_rate = ADV7511_LOW_REFRESH_RATE_30HZ;
 	else
 		low_refresh_rate = ADV7511_LOW_REFRESH_RATE_NONE;
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index db761329a1e3..ab7968c8f6a2 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1046,6 +1046,10 @@ static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi)
 	if (hdmi->version < 0x200a)
 		return false;
 
+	/* Disable if no DDC bus */
+	if (!hdmi->ddc)
+		return false;
+
 	/* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
 	if (!display->hdmi.scdc.supported ||
 	    !display->hdmi.scdc.scrambling.supported)
@@ -1684,13 +1688,13 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			 * Source Devices compliant shall set the
 			 * Source Version = 1.
 			 */
-			drm_scdc_readb(&hdmi->i2c->adap, SCDC_SINK_VERSION,
+			drm_scdc_readb(hdmi->ddc, SCDC_SINK_VERSION,
 				       &bytes);
-			drm_scdc_writeb(&hdmi->i2c->adap, SCDC_SOURCE_VERSION,
+			drm_scdc_writeb(hdmi->ddc, SCDC_SOURCE_VERSION,
 				min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION));
 
 			/* Enabled Scrambling in the Sink */
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 1);
+			drm_scdc_set_scrambling(hdmi->ddc, 1);
 
 			/*
 			 * To activate the scrambler feature, you must ensure
@@ -1706,7 +1710,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL);
 			hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ,
 				    HDMI_MC_SWRSTZ);
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 0);
+			drm_scdc_set_scrambling(hdmi->ddc, 0);
 		}
 	}
 
@@ -1800,6 +1804,8 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 	 * iteration for others.
 	 * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing
 	 * the workaround with a single iteration.
+	 * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have
+	 * been identified as needing the workaround with a single iteration.
 	 */
 
 	switch (hdmi->version) {
@@ -1808,7 +1814,9 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 		break;
 	case 0x131a:
 	case 0x132a:
+	case 0x200a:
 	case 0x201a:
+	case 0x211a:
 	case 0x212a:
 		count = 1;
 		break;
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 2b4f373736c7..8b4cd31ce7bd 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -106,25 +106,19 @@
 static noinline void save_stack(struct drm_mm_node *node)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = STACKDEPTH,
-		.skip = 1
-	};
+	unsigned int n;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
 
 	/* May be called under spinlock, so avoid sleeping */
-	node->stack = depot_save_stack(&trace, GFP_NOWAIT);
+	node->stack = stack_depot_save(entries, n, GFP_NOWAIT);
 }
 
 static void show_leaks(struct drm_mm *mm)
 {
 	struct drm_mm_node *node;
-	unsigned long entries[STACKDEPTH];
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char *buf;
 
 	buf = kmalloc(BUFSZ, GFP_KERNEL);
@@ -132,19 +126,14 @@ static void show_leaks(struct drm_mm *mm)
 		return;
 
 	list_for_each_entry(node, drm_mm_nodes(mm), node_list) {
-		struct stack_trace trace = {
-			.entries = entries,
-			.max_entries = STACKDEPTH
-		};
-
 		if (!node->stack) {
 			DRM_ERROR("node [%08llx + %08llx]: unknown owner\n",
 				  node->start, node->size);
 			continue;
 		}
 
-		depot_fetch_stack(node->stack, &trace);
-		snprint_stack_trace(buf, BUFSZ, &trace, 0);
+		nr_entries = stack_depot_fetch(node->stack, &entries);
+		stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0);
 		DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",
 			  node->start, node->size, buf);
 	}
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index 361a01a08c18..3d400905100b 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -475,20 +475,19 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private,
 				    int fd, u32 *handle)
 {
 	struct drm_syncobj *syncobj;
-	struct file *file;
+	struct fd f = fdget(fd);
 	int ret;
 
-	file = fget(fd);
-	if (!file)
+	if (!f.file)
 		return -EINVAL;
 
-	if (file->f_op != &drm_syncobj_file_fops) {
-		fput(file);
+	if (f.file->f_op != &drm_syncobj_file_fops) {
+		fdput(f);
 		return -EINVAL;
 	}
 
 	/* take a reference to put in the idr */
-	syncobj = file->private_data;
+	syncobj = f.file->private_data;
 	drm_syncobj_get(syncobj);
 
 	idr_preload(GFP_KERNEL);
@@ -503,7 +502,7 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private,
 	} else
 		drm_syncobj_put(syncobj);
 
-	fput(file);
+	fdput(f);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/fsl-dcu/Kconfig b/drivers/gpu/drm/fsl-dcu/Kconfig
index 14a72c4c496d..dc825883400d 100644
--- a/drivers/gpu/drm/fsl-dcu/Kconfig
+++ b/drivers/gpu/drm/fsl-dcu/Kconfig
@@ -2,7 +2,6 @@ config DRM_FSL_DCU
 	tristate "DRM Support for Freescale DCU"
 	depends on DRM && OF && ARM && COMMON_CLK
 	select BACKLIGHT_CLASS_DEVICE
-	select BACKLIGHT_LCD_SUPPORT
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_PANEL
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 148be8e1a090..3d5f1cb6a76c 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -15,7 +15,6 @@ config DRM_I915
 	select IRQ_WORK
 	# i915 depends on ACPI_VIDEO when ACPI is enabled
 	# but for select to work, need to select ACPI_VIDEO's dependencies, ick
-	select BACKLIGHT_LCD_SUPPORT if ACPI
 	select BACKLIGHT_CLASS_DEVICE if ACPI
 	select INPUT if ACPI
 	select ACPI_VIDEO if ACPI
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index 2ec89bcb59f1..8a9606f91e68 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -196,9 +196,9 @@ DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops,
 int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
 {
 	struct dentry *ent;
-	char name[10] = "";
+	char name[16] = "";
 
-	sprintf(name, "vgpu%d", vgpu->id);
+	snprintf(name, 16, "vgpu%d", vgpu->id);
 	vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
 	if (!vgpu->debugfs)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 4e1e425189ba..41c8ebc60c63 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -45,6 +45,7 @@ static int vgpu_gem_get_pages(
 	int i, ret;
 	gen8_pte_t __iomem *gtt_entries;
 	struct intel_vgpu_fb_info *fb_info;
+	u32 page_num;
 
 	fb_info = (struct intel_vgpu_fb_info *)obj->gvt_info;
 	if (WARN_ON(!fb_info))
@@ -54,14 +55,15 @@ static int vgpu_gem_get_pages(
 	if (unlikely(!st))
 		return -ENOMEM;
 
-	ret = sg_alloc_table(st, fb_info->size, GFP_KERNEL);
+	page_num = obj->base.size >> PAGE_SHIFT;
+	ret = sg_alloc_table(st, page_num, GFP_KERNEL);
 	if (ret) {
 		kfree(st);
 		return ret;
 	}
 	gtt_entries = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm +
 		(fb_info->start >> PAGE_SHIFT);
-	for_each_sg(st->sgl, sg, fb_info->size, i) {
+	for_each_sg(st->sgl, sg, page_num, i) {
 		sg->offset = 0;
 		sg->length = PAGE_SIZE;
 		sg_dma_address(sg) =
@@ -158,7 +160,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 		return NULL;
 
 	drm_gem_private_object_init(dev, &obj->base,
-		info->size << PAGE_SHIFT);
+		roundup(info->size, PAGE_SIZE));
 	i915_gem_object_init(obj, &intel_vgpu_gem_ops);
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
@@ -206,11 +208,12 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		struct intel_vgpu_fb_info *info,
 		int plane_id)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_vgpu_primary_plane_format p;
 	struct intel_vgpu_cursor_plane_format c;
 	int ret, tile_height = 1;
 
+	memset(info, 0, sizeof(*info));
+
 	if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
 		ret = intel_vgpu_decode_primary_plane(vgpu, &p);
 		if (ret)
@@ -267,8 +270,7 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	info->size = (info->stride * roundup(info->height, tile_height)
-		      + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	info->size = info->stride * roundup(info->height, tile_height);
 	if (info->size == 0) {
 		gvt_vgpu_err("fb size is zero\n");
 		return -EINVAL;
@@ -278,11 +280,6 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		gvt_vgpu_err("Not aligned fb address:0x%llx\n", info->start);
 		return -EFAULT;
 	}
-	if (((info->start >> PAGE_SHIFT) + info->size) >
-		ggtt_total_entries(&dev_priv->ggtt)) {
-		gvt_vgpu_err("Invalid GTT offset or size\n");
-		return -EFAULT;
-	}
 
 	if (!intel_gvt_ggtt_validate_range(vgpu, info->start, info->size)) {
 		gvt_vgpu_err("invalid gma addr\n");
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index c2f7d20f6346..08c74e65836b 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -811,7 +811,7 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
 /* Allocate shadow page table without guest page. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
+		struct intel_vgpu *vgpu, enum intel_gvt_gtt_type type)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -861,7 +861,7 @@ err_free_spt:
 
 /* Allocate shadow page table associated with specific gfn. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
-		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+		struct intel_vgpu *vgpu, enum intel_gvt_gtt_type type,
 		unsigned long gfn, bool guest_pde_ips)
 {
 	struct intel_vgpu_ppgtt_spt *spt;
@@ -936,7 +936,7 @@ static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
 {
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *s;
-	intel_gvt_gtt_type_t cur_pt_type;
+	enum intel_gvt_gtt_type cur_pt_type;
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(e->type)));
 
@@ -1076,6 +1076,9 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 	} else {
 		int type = get_next_pt_type(we->type);
 
+		if (!gtt_type_is_pt(type))
+			goto err;
+
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
@@ -1855,7 +1858,7 @@ static void vgpu_free_mm(struct intel_vgpu_mm *mm)
  * Zero on success, negative error code in pointer if failed.
  */
 struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[])
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[])
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_vgpu_mm *mm;
@@ -2309,7 +2312,7 @@ int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu,
 }
 
 static int alloc_scratch_pages(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t type)
+		enum intel_gvt_gtt_type type)
 {
 	struct intel_vgpu_gtt *gtt = &vgpu->gtt;
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
@@ -2594,7 +2597,7 @@ struct intel_vgpu_mm *intel_vgpu_find_ppgtt_mm(struct intel_vgpu *vgpu,
  * Zero on success, negative error code if failed.
  */
 struct intel_vgpu_mm *intel_vgpu_get_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[])
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[])
 {
 	struct intel_vgpu_mm *mm;
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 32c573aea494..42d0394f0de2 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -95,8 +95,8 @@ struct intel_gvt_gtt {
 	unsigned long scratch_mfn;
 };
 
-typedef enum {
-	GTT_TYPE_INVALID = -1,
+enum intel_gvt_gtt_type {
+	GTT_TYPE_INVALID = 0,
 
 	GTT_TYPE_GGTT_PTE,
 
@@ -124,7 +124,7 @@ typedef enum {
 	GTT_TYPE_PPGTT_PML4_PT,
 
 	GTT_TYPE_MAX,
-} intel_gvt_gtt_type_t;
+};
 
 enum intel_gvt_mm_type {
 	INTEL_GVT_MM_GGTT,
@@ -148,7 +148,7 @@ struct intel_vgpu_mm {
 
 	union {
 		struct {
-			intel_gvt_gtt_type_t root_entry_type;
+			enum intel_gvt_gtt_type root_entry_type;
 			/*
 			 * The 4 PDPs in ring context. For 48bit addressing,
 			 * only PDP0 is valid and point to PML4. For 32it
@@ -169,7 +169,7 @@ struct intel_vgpu_mm {
 };
 
 struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[]);
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[]);
 
 static inline void intel_vgpu_mm_get(struct intel_vgpu_mm *mm)
 {
@@ -233,7 +233,7 @@ struct intel_vgpu_ppgtt_spt {
 	struct intel_vgpu *vgpu;
 
 	struct {
-		intel_gvt_gtt_type_t type;
+		enum intel_gvt_gtt_type type;
 		bool pde_ips; /* for 64KB PTEs */
 		void *vaddr;
 		struct page *page;
@@ -241,7 +241,7 @@ struct intel_vgpu_ppgtt_spt {
 	} shadow_page;
 
 	struct {
-		intel_gvt_gtt_type_t type;
+		enum intel_gvt_gtt_type type;
 		bool pde_ips; /* for 64KB PTEs */
 		unsigned long gfn;
 		unsigned long write_cnt;
@@ -267,7 +267,7 @@ struct intel_vgpu_mm *intel_vgpu_find_ppgtt_mm(struct intel_vgpu *vgpu,
 		u64 pdps[]);
 
 struct intel_vgpu_mm *intel_vgpu_get_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[]);
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[]);
 
 int intel_vgpu_put_ppgtt_mm(struct intel_vgpu *vgpu, u64 pdps[]);
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 18f01eeb2510..90673fca792f 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1206,7 +1206,7 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 
 static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
 {
-	intel_gvt_gtt_type_t root_entry_type = GTT_TYPE_PPGTT_ROOT_L4_ENTRY;
+	enum intel_gvt_gtt_type root_entry_type = GTT_TYPE_PPGTT_ROOT_L4_ENTRY;
 	struct intel_vgpu_mm *mm;
 	u64 *pdps;
 
@@ -3303,7 +3303,7 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt)
 /* Special MMIO blocks. */
 static struct gvt_mmio_block mmio_blocks[] = {
 	{D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL},
-	{D_ALL, MCHBAR_MIRROR_REG_BASE, 0x4000, NULL, NULL},
+	{D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL},
 	{D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE,
 		pvinfo_mmio_read, pvinfo_mmio_write},
 	{D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL},
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index e7e14c842be4..edf6d646eb25 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -132,6 +132,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 
 	{RCS0, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */
 	{RCS0, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */
+	{RCS0, _MMIO(0x20D8), 0xffff, true}, /* 0x20d8 */
 
 	{RCS0, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
 	{RCS0, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 3de5b643b266..33aaa14bfdde 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -126,7 +126,4 @@
 #define RING_GFX_MODE(base)	_MMIO((base) + 0x29c)
 #define VF_GUARDBAND		_MMIO(0x83a4)
 
-/* define the effective range of MCHBAR register on Sandybridge+ */
-#define MCHBAR_MIRROR_REG_BASE	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4000)
-
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 8998fa5ab198..7c99bbc3e2b8 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1343,7 +1343,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 	struct execlist_ctx_descriptor_format *desc = &workload->ctx_desc;
 	struct intel_vgpu_mm *mm;
 	struct intel_vgpu *vgpu = workload->vgpu;
-	intel_gvt_gtt_type_t root_entry_type;
+	enum intel_gvt_gtt_type root_entry_type;
 	u64 pdps[GVT_RING_CTX_NR_PDPS];
 
 	switch (desc->addressing_mode) {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index db88ce4d5509..ad01c92aaf74 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4199,7 +4199,7 @@ static bool discard_backing_storage(struct drm_i915_gem_object *obj)
 	 * acquiring such a reference whilst we are in the middle of
 	 * freeing the object.
 	 */
-	return atomic_long_read(&obj->base.filp->f_count) == 1;
+	return file_count(obj->base.filp) == 1;
 }
 
 static void __i915_gem_free_objects(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3d672c9edb94..c83d2a195d15 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1666,6 +1666,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 					     len)) {
 end_user:
 				user_access_end();
+end:
 				kvfree(relocs);
 				err = -EFAULT;
 				goto err;
@@ -1685,7 +1686,7 @@ end_user:
 		 * relocations were valid.
 		 */
 		if (!user_access_begin(urelocs, size))
-			goto end_user;
+			goto end;
 
 		for (copied = 0; copied < nreloc; copied++)
 			unsafe_put_user(-1,
@@ -2697,7 +2698,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		 * when we did the "copy_from_user()" above.
 		 */
 		if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
-			goto end_user;
+			goto end;
 
 		for (i = 0; i < args->buffer_count; i++) {
 			if (!(exec2_list[i].offset & UPDATE))
@@ -2711,6 +2712,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		}
 end_user:
 		user_access_end();
+end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 215bf3fef10c..8079ea3af103 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -122,7 +122,7 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	while (it) {
 		struct drm_i915_gem_object *obj;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			ret = -EAGAIN;
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index b836721d3b13..f6c78c0fa74b 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -425,6 +425,26 @@ void __i915_request_submit(struct i915_request *request)
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
+	/*
+	 * Are we using semaphores when the gpu is already saturated?
+	 *
+	 * Using semaphores incurs a cost in having the GPU poll a
+	 * memory location, busywaiting for it to change. The continual
+	 * memory reads can have a noticeable impact on the rest of the
+	 * system with the extra bus traffic, stalling the cpu as it too
+	 * tries to access memory across the bus (perf stat -e bus-cycles).
+	 *
+	 * If we installed a semaphore on this request and we only submit
+	 * the request after the signaler completed, that indicates the
+	 * system is overloaded and using semaphores at this time only
+	 * increases the amount of work we are doing. If so, we disable
+	 * further use of semaphores until we are idle again, whence we
+	 * optimistically try again.
+	 */
+	if (request->sched.semaphores &&
+	    i915_sw_fence_signaled(&request->semaphore))
+		request->hw_context->saturated |= request->sched.semaphores;
+
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
@@ -432,6 +452,7 @@ void __i915_request_submit(struct i915_request *request)
 	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
 	    !i915_request_enable_breadcrumb(request))
 		intel_engine_queue_breadcrumbs(engine);
 
@@ -799,6 +820,39 @@ err_unreserve:
 }
 
 static int
+i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
+{
+	if (list_is_first(&signal->ring_link, &signal->ring->request_list))
+		return 0;
+
+	signal = list_prev_entry(signal, ring_link);
+	if (i915_timeline_sync_is_later(rq->timeline, &signal->fence))
+		return 0;
+
+	return i915_sw_fence_await_dma_fence(&rq->submit,
+					     &signal->fence, 0,
+					     I915_FENCE_GFP);
+}
+
+static intel_engine_mask_t
+already_busywaiting(struct i915_request *rq)
+{
+	/*
+	 * Polling a semaphore causes bus traffic, delaying other users of
+	 * both the GPU and CPU. We want to limit the impact on others,
+	 * while taking advantage of early submission to reduce GPU
+	 * latency. Therefore we restrict ourselves to not using more
+	 * than one semaphore from each source, and not using a semaphore
+	 * if we have detected the engine is saturated (i.e. would not be
+	 * submitted early and cause bus traffic reading an already passed
+	 * semaphore).
+	 *
+	 * See the are-we-too-late? check in __i915_request_submit().
+	 */
+	return rq->sched.semaphores | rq->hw_context->saturated;
+}
+
+static int
 emit_semaphore_wait(struct i915_request *to,
 		    struct i915_request *from,
 		    gfp_t gfp)
@@ -811,11 +865,15 @@ emit_semaphore_wait(struct i915_request *to,
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
 
 	/* Just emit the first semaphore we see as request space is limited. */
-	if (to->sched.semaphores & from->engine->mask)
+	if (already_busywaiting(to) & from->engine->mask)
 		return i915_sw_fence_await_dma_fence(&to->submit,
 						     &from->fence, 0,
 						     I915_FENCE_GFP);
 
+	err = i915_request_await_start(to, from);
+	if (err < 0)
+		return err;
+
 	err = i915_sw_fence_await_dma_fence(&to->semaphore,
 					    &from->fence, 0,
 					    I915_FENCE_GFP);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 36726392e737..961268f66c63 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -52,11 +52,8 @@ void i915_vma_free(struct i915_vma *vma)
 
 static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 {
-	unsigned long entries[12];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char buf[512];
 
 	if (!vma->node.stack) {
@@ -65,8 +62,8 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 		return;
 	}
 
-	depot_fetch_stack(vma->node.stack, &trace);
-	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	nr_entries = stack_depot_fetch(vma->node.stack, &entries);
+	stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
 	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
 			 vma->node.start, vma->node.size, reason, buf);
 }
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 3cbffd400b1b..832cb6b1e9bd 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/kthread.h>
+#include <trace/events/dma_fence.h>
 #include <uapi/linux/sched/types.h>
 
 #include "i915_drv.h"
@@ -80,9 +81,39 @@ static inline bool __request_completed(const struct i915_request *rq)
 	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno);
 }
 
+static bool
+__dma_fence_signal(struct dma_fence *fence)
+{
+	return !test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
+}
+
+static void
+__dma_fence_signal__timestamp(struct dma_fence *fence, ktime_t timestamp)
+{
+	fence->timestamp = timestamp;
+	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
+	trace_dma_fence_signaled(fence);
+}
+
+static void
+__dma_fence_signal__notify(struct dma_fence *fence)
+{
+	struct dma_fence_cb *cur, *tmp;
+
+	lockdep_assert_held(fence->lock);
+	lockdep_assert_irqs_disabled();
+
+	list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
+		INIT_LIST_HEAD(&cur->node);
+		cur->func(fence, cur);
+	}
+	INIT_LIST_HEAD(&fence->cb_list);
+}
+
 void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
 	LIST_HEAD(signal);
@@ -104,6 +135,10 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 
 			GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_SIGNAL,
 					     &rq->fence.flags));
+			clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+
+			if (!__dma_fence_signal(&rq->fence))
+				continue;
 
 			/*
 			 * Queue for execution after dropping the signaling
@@ -111,14 +146,6 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 			 * more signalers to the same context or engine.
 			 */
 			i915_request_get(rq);
-
-			/*
-			 * We may race with direct invocation of
-			 * dma_fence_signal(), e.g. i915_request_retire(),
-			 * so we need to acquire our reference to the request
-			 * before we cancel the breadcrumb.
-			 */
-			clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
 			list_add_tail(&rq->signal_link, &signal);
 		}
 
@@ -141,7 +168,12 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 
-		dma_fence_signal(&rq->fence);
+		__dma_fence_signal__timestamp(&rq->fence, timestamp);
+
+		spin_lock(&rq->lock);
+		__dma_fence_signal__notify(&rq->fence);
+		spin_unlock(&rq->lock);
+
 		i915_request_put(rq);
 	}
 }
@@ -243,19 +275,17 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 
 bool i915_request_enable_breadcrumb(struct i915_request *rq)
 {
-	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
+	lockdep_assert_held(&rq->lock);
+	lockdep_assert_irqs_disabled();
 
-	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
-		return true;
-
-	spin_lock(&b->irq_lock);
-	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags) &&
-	    !__request_completed(rq)) {
+	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
+		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 		struct intel_context *ce = rq->hw_context;
 		struct list_head *pos;
 
+		spin_lock(&b->irq_lock);
+		GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
+
 		__intel_breadcrumbs_arm_irq(b);
 
 		/*
@@ -284,8 +314,8 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 			list_move_tail(&ce->signal_link, &b->signalers);
 
 		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+		spin_unlock(&b->irq_lock);
 	}
-	spin_unlock(&b->irq_lock);
 
 	return !__request_completed(rq);
 }
@@ -294,9 +324,15 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 {
 	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 
-	if (!test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
-		return;
+	lockdep_assert_held(&rq->lock);
+	lockdep_assert_irqs_disabled();
 
+	/*
+	 * We must wait for b->irq_lock so that we know the interrupt handler
+	 * has released its reference to the intel_context and has completed
+	 * the DMA_FENCE_FLAG_SIGNALED_BIT/I915_FENCE_FLAG_SIGNAL dance (if
+	 * required).
+	 */
 	spin_lock(&b->irq_lock);
 	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
 		struct intel_context *ce = rq->hw_context;
diff --git a/drivers/gpu/drm/i915/intel_context.c b/drivers/gpu/drm/i915/intel_context.c
index 8931e0fee873..924cc556223a 100644
--- a/drivers/gpu/drm/i915/intel_context.c
+++ b/drivers/gpu/drm/i915/intel_context.c
@@ -230,6 +230,7 @@ intel_context_init(struct intel_context *ce,
 	ce->gem_context = ctx;
 	ce->engine = engine;
 	ce->ops = engine->cops;
+	ce->saturated = 0;
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
diff --git a/drivers/gpu/drm/i915/intel_context_types.h b/drivers/gpu/drm/i915/intel_context_types.h
index 68b4ca1611e0..339c7437fe82 100644
--- a/drivers/gpu/drm/i915/intel_context_types.h
+++ b/drivers/gpu/drm/i915/intel_context_types.h
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 
 #include "i915_active_types.h"
+#include "intel_engine_types.h"
 
 struct i915_gem_context;
 struct i915_vma;
@@ -58,6 +59,8 @@ struct intel_context {
 	atomic_t pin_count;
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
 
+	intel_engine_mask_t saturated; /* submitting semaphores too late? */
+
 	/**
 	 * active_tracker: Active tracker for the external rq activity
 	 * on this intel_context object.
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5454930f6aa8..2eb62ed9e7cb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12082,6 +12082,7 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  struct intel_crtc_state *pipe_config,
 			  bool adjust)
 {
+	struct intel_crtc *crtc = to_intel_crtc(current_config->base.crtc);
 	bool ret = true;
 	bool fixup_inherited = adjust &&
 		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
@@ -12303,6 +12304,14 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 		PIPE_CONF_CHECK_X(gmch_pfit.pgm_ratios);
 	PIPE_CONF_CHECK_X(gmch_pfit.lvds_border_bits);
 
+	/*
+	 * Changing the EDP transcoder input mux
+	 * (A_ONOFF vs. A_ON) requires a full modeset.
+	 */
+	if (IS_HASWELL(dev_priv) && crtc->pipe == PIPE_A &&
+	    current_config->cpu_transcoder == TRANSCODER_EDP)
+		PIPE_CONF_CHECK_BOOL(pch_pfit.enabled);
+
 	if (!adjust) {
 		PIPE_CONF_CHECK_I(pipe_src_w);
 		PIPE_CONF_CHECK_I(pipe_src_h);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index c805a0966395..5679f2fffb7c 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -1280,6 +1280,10 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
+	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
+	if (IS_GEMINILAKE(dev_priv))
+		return 0;
+
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 37f60cb8e9e1..46cd0e70aecb 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -23,7 +23,6 @@
  */
 
 #include <linux/circ_buf.h>
-#include <trace/events/dma_fence.h>
 
 #include "intel_guc_submission.h"
 #include "intel_lrc_reg.h"
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index e1005d7b75fd..34be2cfd0ec8 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -207,7 +207,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(VIDEO_DIP_CTL, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VIDEO_DIP_DATA, *data);
 		data++;
@@ -215,7 +214,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VIDEO_DIP_DATA, 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -282,7 +280,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -290,7 +287,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -364,7 +360,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -372,7 +367,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -439,7 +433,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -447,7 +440,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -514,7 +506,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), *data);
@@ -524,7 +515,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	for (; i < data_size; i += 4)
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), 0);
-	mmiowb();
 
 	val |= hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index e94b5b1bc1b7..e7c7be4911c1 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -311,10 +311,17 @@ retry:
 	pipe_config->base.mode_changed = pipe_config->has_psr;
 	pipe_config->crc_enabled = enable;
 
-	if (IS_HASWELL(dev_priv) && crtc->pipe == PIPE_A) {
+	if (IS_HASWELL(dev_priv) &&
+	    pipe_config->base.active && crtc->pipe == PIPE_A &&
+	    pipe_config->cpu_transcoder == TRANSCODER_EDP) {
+		bool old_need_power_well = pipe_config->pch_pfit.enabled ||
+			pipe_config->pch_pfit.force_thru;
+		bool new_need_power_well = pipe_config->pch_pfit.enabled ||
+			enable;
+
 		pipe_config->pch_pfit.force_thru = enable;
-		if (pipe_config->cpu_transcoder == TRANSCODER_EDP &&
-		    pipe_config->pch_pfit.enabled != enable)
+
+		if (old_need_power_well != new_need_power_well)
 			pipe_config->base.connectors_changed = true;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d4f4262d0fee..6150e35bf7b5 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -64,31 +64,20 @@
 static noinline depot_stack_handle_t __save_depot_stack(void)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-		.skip = 1,
-	};
-
-	save_stack_trace(&trace);
-	if (trace.nr_entries &&
-	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-		trace.nr_entries--;
+	unsigned int n;
 
-	return depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
 }
 
 static void __print_depot_stack(depot_stack_handle_t stack,
 				char *buf, int sz, int indent)
 {
-	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 
-	depot_fetch_stack(stack, &trace);
-	snprint_stack_trace(buf, sz, &trace, indent);
+	nr_entries = stack_depot_fetch(stack, &entries);
+	stack_trace_snprint(buf, sz, entries, nr_entries, indent);
 }
 
 static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 311a20c942eb..9cc1d678674f 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -71,7 +71,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc,
 	if (disable_partial)
 		ipu_plane_disable(ipu_crtc->plane[1], true);
 	if (disable_full)
-		ipu_plane_disable(ipu_crtc->plane[0], false);
+		ipu_plane_disable(ipu_crtc->plane[0], true);
 }
 
 static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 9155dafae2a9..38e2cfa9cec7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -747,7 +747,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	 * will make sure that the refcounting is correct in case we need to
 	 * bring down the GX after a GMU failure
 	 */
-	if (!IS_ERR(gmu->gxpd))
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
 		pm_runtime_get(gmu->gxpd);
 
 out:
@@ -863,7 +863,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 	 * domain. Usually the GMU does this but only if the shutdown sequence
 	 * was successful
 	 */
-	if (!IS_ERR(gmu->gxpd))
+	if (!IS_ERR_OR_NULL(gmu->gxpd))
 		pm_runtime_put_sync(gmu->gxpd);
 
 	clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks);
@@ -1234,7 +1234,7 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 
 	pm_runtime_disable(gmu->dev);
 
-	if (!IS_ERR(gmu->gxpd)) {
+	if (!IS_ERR_OR_NULL(gmu->gxpd)) {
 		pm_runtime_disable(gmu->gxpd);
 		dev_pm_domain_detach(gmu->gxpd, false);
 	}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 7994de952353..d831cedb55ec 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -775,7 +775,6 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 	struct dpu_plane_state *pstate = to_dpu_plane_state(new_state);
 	struct dpu_hw_fmt_layout layout;
 	struct drm_gem_object *obj;
-	struct msm_gem_object *msm_obj;
 	struct dma_fence *fence;
 	struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base);
 	int ret;
@@ -794,8 +793,7 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 	 *       implicit fence and fb prepare by hand here.
 	 */
 	obj = msm_framebuffer_bo(new_state->fb, 0);
-	msm_obj = to_msm_bo(obj);
-	fence = reservation_object_get_excl_rcu(msm_obj->resv);
+	fence = reservation_object_get_excl_rcu(obj->resv);
 	if (fence)
 		drm_atomic_set_fence_for_plane(new_state, fence);
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index f5b1256e32b6..131c23a267ee 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -49,15 +49,13 @@ int msm_atomic_prepare_fb(struct drm_plane *plane,
 	struct msm_drm_private *priv = plane->dev->dev_private;
 	struct msm_kms *kms = priv->kms;
 	struct drm_gem_object *obj;
-	struct msm_gem_object *msm_obj;
 	struct dma_fence *fence;
 
 	if (!new_state->fb)
 		return 0;
 
 	obj = msm_framebuffer_bo(new_state->fb, 0);
-	msm_obj = to_msm_bo(obj);
-	fence = reservation_object_get_excl_rcu(msm_obj->resv);
+	fence = reservation_object_get_excl_rcu(obj->resv);
 
 	drm_atomic_set_fence_for_plane(new_state, fence);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index eb33d2d00d77..e20e6b429804 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -33,7 +33,7 @@
 #include <linux/types.h>
 #include <linux/of_graph.h>
 #include <linux/of_device.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 #include <linux/kthread.h>
 
 #include <drm/drmP.h>
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 31d5a744d84f..35f55dd25994 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -803,7 +803,8 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 		seq_puts(m, "      vmas:");
 
 		list_for_each_entry(vma, &msm_obj->vmas, list)
-			seq_printf(m, " [%s: %08llx,%s,inuse=%d]", vma->aspace->name,
+			seq_printf(m, " [%s: %08llx,%s,inuse=%d]",
+				vma->aspace != NULL ? vma->aspace->name : NULL,
 				vma->iova, vma->mapped ? "mapped" : "unmapped",
 				vma->inuse);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index c5ac781dffee..812d1b1369a5 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -86,10 +86,6 @@ struct msm_gem_object {
 
 	struct llist_node freed;
 
-	/* normally (resv == &_resv) except for imported bo's */
-	struct reservation_object *resv;
-	struct reservation_object _resv;
-
 	/* For physically contiguous buffers.  Used when we don't have
 	 * an IOMMU.  Also used for stolen/splashscreen buffer.
 	 */
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 553c7da5e8e0..1f1395148ff0 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -5,14 +5,12 @@ config DRM_NOUVEAU
 	select DRM_KMS_HELPER
 	select DRM_TTM
 	select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT
-	select BACKLIGHT_LCD_SUPPORT if DRM_NOUVEAU_BACKLIGHT
 	select ACPI_VIDEO if ACPI && X86 && BACKLIGHT_CLASS_DEVICE && INPUT
 	select X86_PLATFORM_DEVICES if ACPI && X86
 	select ACPI_WMI if ACPI && X86
 	select MXM_WMI if ACPI && X86
 	select POWER_SUPPLY
 	# Similar to i915, we need to select ACPI_VIDEO and it's dependencies
-	select BACKLIGHT_LCD_SUPPORT if ACPI && X86
 	select BACKLIGHT_CLASS_DEVICE if ACPI && X86
 	select INPUT if ACPI && X86
 	select THERMAL if ACPI && X86
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 2216c58620c2..7c41b0599d1a 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -41,6 +41,7 @@ struct nv50_disp_interlock {
 		NV50_DISP_INTERLOCK__SIZE
 	} type;
 	u32 data;
+	u32 wimm;
 };
 
 void corec37d_ntfy_init(struct nouveau_bo *, u32);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index 93754743090f..48a6485ec4e0 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -306,7 +306,7 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 			asyh->set.or = head->func->or != NULL;
 		}
 
-		if (asyh->state.mode_changed)
+		if (asyh->state.mode_changed || asyh->state.connectors_changed)
 			nv50_head_atomic_check_mode(head, asyh);
 
 		if (asyh->state.color_mgmt_changed ||
@@ -413,6 +413,7 @@ nv50_head_atomic_duplicate_state(struct drm_crtc *crtc)
 	asyh->ovly = armh->ovly;
 	asyh->dither = armh->dither;
 	asyh->procamp = armh->procamp;
+	asyh->or = armh->or;
 	asyh->dp = armh->dp;
 	asyh->clr.mask = 0;
 	asyh->set.mask = 0;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
index 9103b8494279..f7dbd965e4e7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -75,6 +75,7 @@ wimmc37b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
 		return ret;
 	}
 
+	wndw->interlock.wimm = wndw->interlock.data;
 	wndw->immd = func;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index b95181027b31..283ff690350e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -127,7 +127,7 @@ void
 nv50_wndw_flush_set(struct nv50_wndw *wndw, u32 *interlock,
 		    struct nv50_wndw_atom *asyw)
 {
-	if (interlock) {
+	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
 		asyw->image.mode = 0;
 		asyw->image.interval = 1;
 	}
@@ -149,7 +149,7 @@ nv50_wndw_flush_set(struct nv50_wndw *wndw, u32 *interlock,
 	if (asyw->set.point) {
 		if (asyw->set.point = false, asyw->set.mask)
 			interlock[wndw->interlock.type] |= wndw->interlock.data;
-		interlock[NV50_DISP_INTERLOCK_WIMM] |= wndw->interlock.data;
+		interlock[NV50_DISP_INTERLOCK_WIMM] |= wndw->interlock.wimm;
 
 		wndw->immd->point(wndw, asyw);
 		wndw->immd->update(wndw, interlock);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 22cd45845e07..7c2fcaba42d6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -631,7 +631,8 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	/* We need to check that the chipset is supported before booting
 	 * fbdev off the hardware, as there's no way to put it back.
 	 */
-	ret = nvkm_device_pci_new(pdev, NULL, "error", true, false, 0, &device);
+	ret = nvkm_device_pci_new(pdev, nouveau_config, "error",
+				  true, false, 0, &device);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 7971096b6767..10d91e8bbb94 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2540,6 +2540,41 @@ nv166_chipset = {
 	.sec2 = tu102_sec2_new,
 };
 
+static const struct nvkm_device_chip
+nv167_chipset = {
+	.name = "TU117",
+	.bar = tu102_bar_new,
+	.bios = nvkm_bios_new,
+	.bus = gf100_bus_new,
+	.devinit = tu102_devinit_new,
+	.fault = tu102_fault_new,
+	.fb = gv100_fb_new,
+	.fuse = gm107_fuse_new,
+	.gpio = gk104_gpio_new,
+	.gsp = gv100_gsp_new,
+	.i2c = gm200_i2c_new,
+	.ibus = gm200_ibus_new,
+	.imem = nv50_instmem_new,
+	.ltc = gp102_ltc_new,
+	.mc = tu102_mc_new,
+	.mmu = tu102_mmu_new,
+	.pci = gp100_pci_new,
+	.pmu = gp102_pmu_new,
+	.therm = gp100_therm_new,
+	.timer = gk20a_timer_new,
+	.top = gk104_top_new,
+	.ce[0] = tu102_ce_new,
+	.ce[1] = tu102_ce_new,
+	.ce[2] = tu102_ce_new,
+	.ce[3] = tu102_ce_new,
+	.ce[4] = tu102_ce_new,
+	.disp = tu102_disp_new,
+	.dma = gv100_dma_new,
+	.fifo = tu102_fifo_new,
+	.nvdec[0] = gp102_nvdec_new,
+	.sec2 = tu102_sec2_new,
+};
+
 static int
 nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
 		       struct nvkm_notify *notify)
@@ -2824,8 +2859,8 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	u64 mmio_base, mmio_size;
 	u32 boot0, strap;
 	void __iomem *map;
-	int ret = -EEXIST;
-	int i;
+	int ret = -EEXIST, i;
+	unsigned chipset;
 
 	mutex_lock(&nv_devices_mutex);
 	if (nvkm_device_find_locked(handle))
@@ -2870,6 +2905,26 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		strap = ioread32_native(map + 0x101000);
 		iounmap(map);
 
+		/* chipset can be overridden for devel/testing purposes */
+		chipset = nvkm_longopt(device->cfgopt, "NvChipset", 0);
+		if (chipset) {
+			u32 override_boot0;
+
+			if (chipset >= 0x10) {
+				override_boot0  = ((chipset & 0x1ff) << 20);
+				override_boot0 |= 0x000000a1;
+			} else {
+				if (chipset != 0x04)
+					override_boot0 = 0x20104000;
+				else
+					override_boot0 = 0x20004000;
+			}
+
+			nvdev_warn(device, "CHIPSET OVERRIDE: %08x -> %08x\n",
+				   boot0, override_boot0);
+			boot0 = override_boot0;
+		}
+
 		/* determine chipset and derive architecture from it */
 		if ((boot0 & 0x1f000000) > 0) {
 			device->chipset = (boot0 & 0x1ff00000) >> 20;
@@ -2996,6 +3051,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		case 0x162: device->chip = &nv162_chipset; break;
 		case 0x164: device->chip = &nv164_chipset; break;
 		case 0x166: device->chip = &nv166_chipset; break;
+		case 0x167: device->chip = &nv167_chipset; break;
 		default:
 			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
 			goto done;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 5f301e632599..818d21bd28d3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -365,8 +365,15 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps)
 	 * and it's better to have a failed modeset than that.
 	 */
 	for (cfg = nvkm_dp_rates; cfg->rate; cfg++) {
-		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw)
-			failsafe = cfg;
+		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw) {
+			/* Try to respect sink limits too when selecting
+			 * lowest link configuration.
+			 */
+			if (!failsafe ||
+			    (cfg->nr <= sink_nr && cfg->bw <= sink_bw))
+				failsafe = cfg;
+		}
+
 		if (failsafe && cfg[1].rate < dataKBps)
 			break;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmi.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmi.c
index d131cca999dd..10f2aa9f29a4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmi.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdmi.c
@@ -23,38 +23,55 @@ void pack_hdmi_infoframe(struct packed_hdmi_infoframe *packed_frame,
 		 */
 	case 17:
 		subpack1_high = (raw_frame[16] << 16);
+		/* fall through */
 	case 16:
 		subpack1_high |= (raw_frame[15] << 8);
+		/* fall through */
 	case 15:
 		subpack1_high |= raw_frame[14];
+		/* fall through */
 	case 14:
 		subpack1_low = (raw_frame[13] << 24);
+		/* fall through */
 	case 13:
 		subpack1_low |= (raw_frame[12] << 16);
+		/* fall through */
 	case 12:
 		subpack1_low |= (raw_frame[11] << 8);
+		/* fall through */
 	case 11:
 		subpack1_low |= raw_frame[10];
+		/* fall through */
 	case 10:
 		subpack0_high = (raw_frame[9] << 16);
+		/* fall through */
 	case 9:
 		subpack0_high |= (raw_frame[8] << 8);
+		/* fall through */
 	case 8:
 		subpack0_high |= raw_frame[7];
+		/* fall through */
 	case 7:
 		subpack0_low = (raw_frame[6] << 24);
+		/* fall through */
 	case 6:
 		subpack0_low |= (raw_frame[5] << 16);
+		/* fall through */
 	case 5:
 		subpack0_low |= (raw_frame[4] << 8);
+		/* fall through */
 	case 4:
 		subpack0_low |= raw_frame[3];
+		/* fall through */
 	case 3:
 		header = (raw_frame[2] << 16);
+		/* fall through */
 	case 2:
 		header |= (raw_frame[1] << 8);
+		/* fall through */
 	case 1:
 		header |= raw_frame[0];
+		/* fall through */
 	case 0:
 		break;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/dma/usernv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/dma/usernv04.c
index 49ef7e57aad4..7f1adab21a5f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/dma/usernv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/dma/usernv04.c
@@ -122,6 +122,7 @@ nv04_dmaobj_new(struct nvkm_dma *dma, const struct nvkm_oclass *oclass,
 		break;
 	case NV_MEM_ACCESS_WO:
 		dmaobj->flags0 |= 0x00008000;
+		/* fall through */
 	case NV_MEM_ACCESS_RW:
 		dmaobj->flags2 |= 0x00000002;
 		break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
index ad707ff176cc..93493b335d76 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv04.c
@@ -117,8 +117,10 @@ nv04_fifo_swmthd(struct nvkm_device *device, u32 chid, u32 addr, u32 data)
 	switch (mthd) {
 	case 0x0000 ... 0x0000: /* subchannel's engine -> software */
 		nvkm_wr32(device, 0x003280, (engine &= ~mask));
+		/* fall through */
 	case 0x0180 ... 0x01fc: /* handle -> instance */
 		data = nvkm_rd32(device, 0x003258) & 0x0000ffff;
+		/* fall through */
 	case 0x0100 ... 0x017c:
 	case 0x0200 ... 0x1ffc: /* pass method down to sw */
 		if (!(engine & mask) && sw)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv40.c
index 8c7ba32763c4..47c16821c37f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv40.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/nv40.c
@@ -81,6 +81,7 @@ nv40_fifo_init(struct nvkm_fifo *base)
 	case 0x49:
 	case 0x4b:
 		nvkm_wr32(device, 0x002230, 0x00000001);
+		/* fall through */
 	case 0x40:
 	case 0x41:
 	case 0x42:
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/perf.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/perf.c
index c3068358f695..7112992e0e38 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/perf.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/perf.c
@@ -135,6 +135,7 @@ nvbios_perfEp(struct nvkm_bios *bios, int idx,
 		break;
 	case 0x30:
 		info->script   = nvbios_rd16(bios, perf + 0x02);
+		/* fall through */
 	case 0x35:
 		info->fanspeed = nvbios_rd08(bios, perf + 0x06);
 		info->voltage  = nvbios_rd08(bios, perf + 0x07);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
index e6e804cee2bc..bda6cc9a7aaf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/pll.c
@@ -134,6 +134,7 @@ pll_map(struct nvkm_bios *bios)
 		    device->chipset == 0xaa ||
 		    device->chipset == 0xac)
 			return g84_pll_mapping;
+		/* fall through */
 	default:
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
index ba6a868d4c95..40e564524b7a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c
@@ -90,6 +90,7 @@ nvkm_cstate_valid(struct nvkm_clk *clk, struct nvkm_cstate *cstate,
 			case NVKM_CLK_BOOST_NONE:
 				if (clk->base_khz && freq > clk->base_khz)
 					return false;
+				/* fall through */
 			case NVKM_CLK_BOOST_BIOS:
 				if (clk->boost_khz && freq > clk->boost_khz)
 					return false;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/mcp77.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/mcp77.c
index 1c21b8b53b78..4f000237796f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/mcp77.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/mcp77.c
@@ -363,6 +363,7 @@ mcp77_clk_prog(struct nvkm_clk *base)
 	switch (clk->vsrc) {
 	case nv_clk_src_cclk:
 		mast |= 0x00400000;
+		/* fall through */
 	default:
 		nvkm_wr32(device, 0x4600, clk->vdiv);
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.c
index 2b12e388f47a..5f4c287d7943 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramnv40.c
@@ -131,11 +131,13 @@ nv40_ram_prog(struct nvkm_ram *base)
 		nvkm_mask(device, 0x00402c, 0xc0771100, ram->ctrl);
 		nvkm_wr32(device, 0x004048, ram->coef);
 		nvkm_wr32(device, 0x004030, ram->coef);
+		/* fall through */
 	case 0x43:
 	case 0x49:
 	case 0x4b:
 		nvkm_mask(device, 0x004038, 0xc0771100, ram->ctrl);
 		nvkm_wr32(device, 0x00403c, ram->coef);
+		/* fall through */
 	default:
 		nvkm_mask(device, 0x004020, 0xc0771100, ram->ctrl);
 		nvkm_wr32(device, 0x004024, ram->coef);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/nv50.c
index 844971e5e874..2a6150ab5611 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mxm/nv50.c
@@ -159,6 +159,7 @@ mxm_dcb_sanitise_entry(struct nvkm_bios *bios, void *data, int idx, u16 pdcb)
 		break;
 	case 0x0e: /* eDP, falls through to DPint */
 		ctx.outp[1] |= 0x00010000;
+		/* fall through */
 	case 0x07: /* DP internal, wtf is this?? HP8670w */
 		ctx.outp[1] |= 0x00000004; /* use_power_scripts? */
 		type = DCB_CONNECTOR_eDP;
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index e6b3171c7179..ccb8eb2a518c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -187,6 +187,10 @@ err_out0:
 
 void panfrost_device_fini(struct panfrost_device *pfdev)
 {
+	panfrost_job_fini(pfdev);
+	panfrost_mmu_fini(pfdev);
+	panfrost_gpu_fini(pfdev);
+	panfrost_reset_fini(pfdev);
 	panfrost_regulator_fini(pfdev);
 	panfrost_clk_fini(pfdev);
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 94b0819ad50b..d11e2281dde6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -219,7 +219,8 @@ static int panfrost_ioctl_submit(struct drm_device *dev, void *data,
 fail_job:
 	panfrost_job_put(job);
 fail_out_sync:
-	drm_syncobj_put(sync_out);
+	if (sync_out)
+		drm_syncobj_put(sync_out);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 0c5d391f0a8f..4501597f30ab 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -531,14 +531,15 @@ pl111_init_clock_divider(struct drm_device *drm)
 		dev_err(drm->dev, "CLCD: unable to get clcdclk.\n");
 		return PTR_ERR(parent);
 	}
+
+	spin_lock_init(&priv->tim2_lock);
+
 	/* If the clock divider is broken, use the parent directly */
 	if (priv->variant->broken_clockdivider) {
 		priv->clk = parent;
 		return 0;
 	}
 	parent_name = __clk_get_name(parent);
-
-	spin_lock_init(&priv->tim2_lock);
 	div->init = &init;
 
 	ret = devm_clk_hw_register(drm->dev, div);
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 578d867a81d5..f33e349c4ec5 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -255,10 +255,14 @@ static struct drm_driver qxl_driver = {
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = qxl_debugfs_init,
 #endif
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = qxl_gem_prime_pin,
 	.gem_prime_unpin = qxl_gem_prime_unpin,
+	.gem_prime_get_sg_table = qxl_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
 	.gem_prime_vmap = qxl_gem_prime_vmap,
 	.gem_prime_vunmap = qxl_gem_prime_vunmap,
 	.gem_prime_mmap = qxl_gem_prime_mmap,
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 8b448eca1cd9..114653b471c6 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -42,6 +42,18 @@ void qxl_gem_prime_unpin(struct drm_gem_object *obj)
 	qxl_bo_unpin(bo);
 }
 
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 void *qxl_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct qxl_bo *bo = gem_to_qxl_bo(obj);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index aa898c699101..433df7036f96 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -922,12 +922,12 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
 	ref_div_max = max(min(100 / post_div, ref_div_max), 1u);
 
 	/* get matching reference and feedback divider */
-	*ref_div = min(max(DIV_ROUND_CLOSEST(den, post_div), 1u), ref_div_max);
+	*ref_div = min(max(den/post_div, 1u), ref_div_max);
 	*fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den);
 
 	/* limit fb divider to its maximum */
 	if (*fb_div > fb_div_max) {
-		*ref_div = DIV_ROUND_CLOSEST(*ref_div * fb_div_max, *fb_div);
+		*ref_div = (*ref_div * fb_div_max)/(*fb_div);
 		*fb_div = fb_div_max;
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c
index b3019505065a..c9bd1278f573 100644
--- a/drivers/gpu/drm/radeon/radeon_mn.c
+++ b/drivers/gpu/drm/radeon/radeon_mn.c
@@ -133,7 +133,7 @@ static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 	/* TODO we should be able to split locking for interval tree and
 	 * the tear down.
 	 */
-	if (range->blockable)
+	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&rmn->lock);
 	else if (!mutex_trylock(&rmn->lock))
 		return -EAGAIN;
@@ -144,7 +144,7 @@ static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 		struct radeon_bo *bo;
 		long r;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			ret = -EAGAIN;
 			goto out_unlock;
 		}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index a8db758d523e..a2ebb08990e9 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -221,26 +221,13 @@ static int rockchip_drm_gem_object_mmap_iommu(struct drm_gem_object *obj,
 					      struct vm_area_struct *vma)
 {
 	struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj);
-	unsigned int i, count = obj->size >> PAGE_SHIFT;
+	unsigned int count = obj->size >> PAGE_SHIFT;
 	unsigned long user_count = vma_pages(vma);
-	unsigned long uaddr = vma->vm_start;
-	unsigned long offset = vma->vm_pgoff;
-	unsigned long end = user_count + offset;
-	int ret;
 
 	if (user_count == 0)
 		return -ENXIO;
-	if (end > count)
-		return -ENXIO;
 
-	for (i = offset; i < end; i++) {
-		ret = vm_insert_page(vma, uaddr, rk_obj->pages[i]);
-		if (ret)
-			return ret;
-		uaddr += PAGE_SIZE;
-	}
-
-	return 0;
+	return vm_map_pages(vma, rk_obj->pages, count);
 }
 
 static int rockchip_drm_gem_object_mmap_dma(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 10d1d37e644a..cf596fc0355b 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -349,10 +349,9 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 EXPORT_SYMBOL(drm_sched_increase_karma);
 
 /**
- * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ * drm_sched_stop - stop the scheduler
  *
  * @sched: scheduler instance
- * @bad: bad scheduler job
  *
  * Stop the scheduler and also removes and frees all completed jobs.
  * Note: bad job will not be freed as it might be used later and so it's
diff --git a/drivers/gpu/drm/shmobile/Kconfig b/drivers/gpu/drm/shmobile/Kconfig
index 61bbe8e8bcc5..e2a6c82c8252 100644
--- a/drivers/gpu/drm/shmobile/Kconfig
+++ b/drivers/gpu/drm/shmobile/Kconfig
@@ -4,7 +4,6 @@ config DRM_SHMOBILE
 	depends on DRM && ARM
 	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select BACKLIGHT_CLASS_DEVICE
-	select BACKLIGHT_LCD_SUPPORT
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index c8c0ab3da972..0270d7ea5651 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -16,6 +16,7 @@
 #include <linux/of_reserved_mem.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -71,6 +72,8 @@ static int sun4i_drv_bind(struct device *dev)
 		ret = -ENOMEM;
 		goto free_drm;
 	}
+
+	dev_set_drvdata(dev, drm);
 	drm->dev_private = drv;
 	INIT_LIST_HEAD(&drv->frontend_list);
 	INIT_LIST_HEAD(&drv->engine_list);
@@ -130,8 +133,12 @@ static void sun4i_drv_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
+	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
+
+	component_unbind_all(dev, NULL);
 	of_reserved_mem_device_release(dev);
+
 	drm_dev_put(drm);
 }
 
@@ -381,6 +388,8 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 static int sun4i_drv_remove(struct platform_device *pdev)
 {
+	component_master_del(&pdev->dev, &sun4i_drv_master_ops);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
index fb985ba1a176..2598741a00a6 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_tmds_clk.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/clk-provider.h>
+#include <linux/io.h>
 
 #include "sun4i_hdmi.h"
 
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 47c55974756d..d23c4bfde790 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1260,9 +1260,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 
 	hdmi->dvi = !tegra_output_is_hdmi(output);
 	if (!hdmi->dvi) {
-		err = tegra_hdmi_setup_audio(hdmi);
-		if (err < 0)
-			hdmi->dvi = true;
+		/*
+		 * Make sure that the audio format has been configured before
+		 * enabling audio, otherwise we may try to divide by zero.
+		*/
+		if (hdmi->format.sample_rate > 0) {
+			err = tegra_hdmi_setup_audio(hdmi);
+			if (err < 0)
+				hdmi->dvi = true;
+		}
 	}
 
 	if (hdmi->config->has_hda)
diff --git a/drivers/gpu/drm/tilcdc/Kconfig b/drivers/gpu/drm/tilcdc/Kconfig
index 52598049c096..cb7df2086aee 100644
--- a/drivers/gpu/drm/tilcdc/Kconfig
+++ b/drivers/gpu/drm/tilcdc/Kconfig
@@ -8,7 +8,6 @@ config DRM_TILCDC
 	select DRM_PANEL_BRIDGE
 	select VIDEOMODE_HELPERS
 	select BACKLIGHT_CLASS_DEVICE
-	select BACKLIGHT_LCD_SUPPORT
 	help
 	  Choose this option if you have an TI SoC with LCDC display
 	  controller, for example AM33xx in beagle-bone, DA8xx, or
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 988416fb8a0b..2845fceb2fbd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -49,9 +49,8 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj);
  * ttm_global_mutex - protecting the global BO state
  */
 DEFINE_MUTEX(ttm_global_mutex);
-struct ttm_bo_global ttm_bo_glob = {
-	.use_count = 0
-};
+unsigned ttm_bo_glob_use_count;
+struct ttm_bo_global ttm_bo_glob;
 
 static struct attribute ttm_bo_count = {
 	.name = "bo_count",
@@ -876,8 +875,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 		reservation_object_add_shared_fence(bo->resv, fence);
 
 		ret = reservation_object_reserve_shared(bo->resv, 1);
-		if (unlikely(ret))
+		if (unlikely(ret)) {
+			dma_fence_put(fence);
 			return ret;
+		}
 
 		dma_fence_put(bo->moving);
 		bo->moving = fence;
@@ -1529,12 +1530,13 @@ static void ttm_bo_global_release(void)
 	struct ttm_bo_global *glob = &ttm_bo_glob;
 
 	mutex_lock(&ttm_global_mutex);
-	if (--glob->use_count > 0)
+	if (--ttm_bo_glob_use_count > 0)
 		goto out;
 
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
 	ttm_mem_global_release(&ttm_mem_glob);
+	memset(glob, 0, sizeof(*glob));
 out:
 	mutex_unlock(&ttm_global_mutex);
 }
@@ -1546,7 +1548,7 @@ static int ttm_bo_global_init(void)
 	unsigned i;
 
 	mutex_lock(&ttm_global_mutex);
-	if (++glob->use_count > 1)
+	if (++ttm_bo_glob_use_count > 1)
 		goto out;
 
 	ret = ttm_mem_global_init(&ttm_mem_glob);
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index 699fed9e08ee..8617958b7ae6 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -461,8 +461,8 @@ out_no_zone:
 
 void ttm_mem_global_release(struct ttm_mem_global *glob)
 {
-	unsigned int i;
 	struct ttm_mem_zone *zone;
+	unsigned int i;
 
 	/* let the page allocator first stop the shrink work. */
 	ttm_page_alloc_fini();
@@ -475,9 +475,10 @@ void ttm_mem_global_release(struct ttm_mem_global *glob)
 		zone = glob->zones[i];
 		kobject_del(&zone->kobj);
 		kobject_put(&zone->kobj);
-			}
+	}
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
+	memset(glob, 0, sizeof(*glob));
 }
 
 static void ttm_check_swapping(struct ttm_mem_global *glob)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index f841accc2c00..627f8dc91d0e 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -730,9 +730,10 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 			}
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			if (!(flags & TTM_PAGE_FLAG_DMA32)) {
-				for (j = 0; j < HPAGE_PMD_NR; ++j)
-					if (p++ != pages[i + j])
+			if (!(flags & TTM_PAGE_FLAG_DMA32) &&
+			    (npages - i) >= HPAGE_PMD_NR) {
+				for (j = 1; j < HPAGE_PMD_NR; ++j)
+					if (++p != pages[i + j])
 					    break;
 
 				if (j == HPAGE_PMD_NR)
@@ -759,15 +760,15 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 		unsigned max_size, n2free;
 
 		spin_lock_irqsave(&huge->lock, irq_flags);
-		while (i < npages) {
+		while ((npages - i) >= HPAGE_PMD_NR) {
 			struct page *p = pages[i];
 			unsigned j;
 
 			if (!p)
 				break;
 
-			for (j = 0; j < HPAGE_PMD_NR; ++j)
-				if (p++ != pages[i + j])
+			for (j = 1; j < HPAGE_PMD_NR; ++j)
+				if (++p != pages[i + j])
 				    break;
 
 			if (j != HPAGE_PMD_NR)
diff --git a/drivers/gpu/drm/vboxvideo/Kconfig b/drivers/gpu/drm/vboxvideo/Kconfig
index fc16a5589379..56ba510f21a2 100644
--- a/drivers/gpu/drm/vboxvideo/Kconfig
+++ b/drivers/gpu/drm/vboxvideo/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config DRM_VBOXVIDEO
 	tristate "Virtual Box Graphics Card"
 	depends on DRM && X86 && PCI
diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c
index 9432c3ceec7c..e1e48ba919eb 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_mode.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c
@@ -57,8 +57,7 @@ static void vbox_do_modeset(struct drm_crtc *crtc)
 		vbox_write_ioport(VBE_DISPI_INDEX_VIRT_WIDTH, pitch * 8 / bpp);
 		vbox_write_ioport(VBE_DISPI_INDEX_BPP, bpp);
 		vbox_write_ioport(VBE_DISPI_INDEX_ENABLE, VBE_DISPI_ENABLED);
-		vbox_write_ioport(
-			VBE_DISPI_INDEX_X_OFFSET,
+		vbox_write_ioport(VBE_DISPI_INDEX_X_OFFSET,
 			vbox_crtc->fb_offset % pitch / bpp * 8 + vbox_crtc->x);
 		vbox_write_ioport(VBE_DISPI_INDEX_Y_OFFSET,
 				  vbox_crtc->fb_offset / pitch + vbox_crtc->y);
diff --git a/drivers/gpu/drm/vboxvideo/vbox_prime.c b/drivers/gpu/drm/vboxvideo/vbox_prime.c
index d61985b0c6eb..702b1aa53494 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_prime.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_prime.c
@@ -16,7 +16,7 @@
 int vbox_gem_prime_pin(struct drm_gem_object *obj)
 {
 	WARN_ONCE(1, "not implemented");
-	return -ENOSYS;
+	return -ENODEV;
 }
 
 void vbox_gem_prime_unpin(struct drm_gem_object *obj)
@@ -27,7 +27,7 @@ void vbox_gem_prime_unpin(struct drm_gem_object *obj)
 struct sg_table *vbox_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	WARN_ONCE(1, "not implemented");
-	return ERR_PTR(-ENOSYS);
+	return ERR_PTR(-ENODEV);
 }
 
 struct drm_gem_object *vbox_gem_prime_import_sg_table(
@@ -35,13 +35,13 @@ struct drm_gem_object *vbox_gem_prime_import_sg_table(
 	struct sg_table *table)
 {
 	WARN_ONCE(1, "not implemented");
-	return ERR_PTR(-ENOSYS);
+	return ERR_PTR(-ENODEV);
 }
 
 void *vbox_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	WARN_ONCE(1, "not implemented");
-	return ERR_PTR(-ENOSYS);
+	return ERR_PTR(-ENODEV);
 }
 
 void vbox_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
@@ -52,5 +52,5 @@ void vbox_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 int vbox_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *area)
 {
 	WARN_ONCE(1, "not implemented");
-	return -ENOSYS;
+	return -ENODEV;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index b2891ca0e7f4..5e09389e1514 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -1010,7 +1010,7 @@ static void
 vc4_crtc_reset(struct drm_crtc *crtc)
 {
 	if (crtc->state)
-		__drm_atomic_helper_crtc_destroy_state(crtc->state);
+		vc4_crtc_destroy_state(crtc, crtc->state);
 
 	crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
 	if (crtc->state)
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 9412709067f5..2ea4e20b7b8a 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -41,6 +41,7 @@
 #include <linux/component.h>
 #include <linux/dmaengine.h>
 #include <linux/i2c.h>
+#include <linux/io.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index 8bf3a7c23ed3..062067438f1d 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -243,7 +243,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	if (NULL == vsg->pages)
 		return -ENOMEM;
 	ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
-			vsg->num_pages, vsg->direction == DMA_FROM_DEVICE,
+			vsg->num_pages,
+			vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
 			vsg->pages);
 	if (ret != vsg->num_pages) {
 		if (ret < 0)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 7c2893181ba4..c50868753132 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -206,9 +206,11 @@ static struct drm_driver driver = {
 	.debugfs_init = virtio_gpu_debugfs_init,
 #endif
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table,
 	.gem_prime_vmap = virtgpu_gem_prime_vmap,
 	.gem_prime_vunmap = virtgpu_gem_prime_vunmap,
 	.gem_prime_mmap = virtgpu_gem_prime_mmap,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 2d3e5b1debb3..5faccf92aa15 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -375,6 +375,9 @@ int virtio_gpu_object_wait(struct virtio_gpu_object *bo, bool no_wait);
 
 /* virtgpu_prime.c */
 struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *sgt);
 void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj);
 void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int virtgpu_gem_prime_mmap(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index 22ef151410e0..8fbf71bd0c5e 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -40,6 +40,13 @@ struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 				     bo->tbo.ttm->num_pages);
 }
 
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index be25ce9440ad..bf6c3500d363 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -546,29 +546,13 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv)
 }
 
 /**
- * vmw_assume_iommu - Figure out whether coherent dma-remapping might be
- * taking place.
- * @dev: Pointer to the struct drm_device.
- *
- * Return: true if iommu present, false otherwise.
- */
-static bool vmw_assume_iommu(struct drm_device *dev)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev->dev);
-
-	return !dma_is_direct(ops) && ops &&
-		ops->map_page != dma_direct_map_page;
-}
-
-/**
  * vmw_dma_select_mode - Determine how DMA mappings should be set up for this
  * system.
  *
  * @dev_priv: Pointer to a struct vmw_private
  *
- * This functions tries to determine the IOMMU setup and what actions
- * need to be taken by the driver to make system pages visible to the
- * device.
+ * This functions tries to determine what actions need to be taken by the
+ * driver to make system pages visible to the device.
  * If this function decides that DMA is not possible, it returns -EINVAL.
  * The driver may then try to disable features of the device that require
  * DMA.
@@ -578,23 +562,16 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 	static const char *names[vmw_dma_map_max] = {
 		[vmw_dma_phys] = "Using physical TTM page addresses.",
 		[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
-		[vmw_dma_map_populate] = "Keeping DMA mappings.",
+		[vmw_dma_map_populate] = "Caching DMA mappings.",
 		[vmw_dma_map_bind] = "Giving up DMA mappings early."};
 
 	if (vmw_force_coherent)
 		dev_priv->map_mode = vmw_dma_alloc_coherent;
-	else if (vmw_assume_iommu(dev_priv->dev))
-		dev_priv->map_mode = vmw_dma_map_populate;
-	else if (!vmw_force_iommu)
-		dev_priv->map_mode = vmw_dma_phys;
-	else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl())
-		dev_priv->map_mode = vmw_dma_alloc_coherent;
+	else if (vmw_restrict_iommu)
+		dev_priv->map_mode = vmw_dma_map_bind;
 	else
 		dev_priv->map_mode = vmw_dma_map_populate;
 
-	if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu)
-		dev_priv->map_mode = vmw_dma_map_bind;
-
 	/* No TTM coherent page pool? FIXME: Ask TTM instead! */
         if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) &&
 	    (dev_priv->map_mode == vmw_dma_alloc_coherent))
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index 53c376d55fcf..a24548489dde 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -224,8 +224,7 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev,
 static int gem_mmap_obj(struct xen_gem_object *xen_obj,
 			struct vm_area_struct *vma)
 {
-	unsigned long addr = vma->vm_start;
-	int i;
+	int ret;
 
 	/*
 	 * clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the
@@ -252,18 +251,11 @@ static int gem_mmap_obj(struct xen_gem_object *xen_obj,
 	 * FIXME: as we insert all the pages now then no .fault handler must
 	 * be called, so don't provide one
 	 */
-	for (i = 0; i < xen_obj->num_pages; i++) {
-		int ret;
-
-		ret = vm_insert_page(vma, addr, xen_obj->pages[i]);
-		if (ret < 0) {
-			DRM_ERROR("Failed to insert pages into vma: %d\n", ret);
-			return ret;
-		}
+	ret = vm_map_pages(vma, xen_obj->pages, xen_obj->num_pages);
+	if (ret < 0)
+		DRM_ERROR("Failed to map pages into vma: %d\n", ret);
 
-		addr += PAGE_SIZE;
-	}
-	return 0;
+	return ret;
 }
 
 int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma)