Merge tag 'drm-misc-next-2023-08-10' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v6.6:

UAPI Changes:

 * nouveau:
   * Provide several GETPARAM ioctls
   * Provide VM_BIND ioctls

Cross-subsystem Changes:

 * fbdev: Convert many drivers to fbdev I/O-memory helpers

 * media/vivid: Convert to fbdev I/O-memory helpers

 * vfio-dev/mdpy-fb: Convert to fbdev I/O-memory helpers

Core Changes:

 * Documentation fixes

 * Do not select framebuffer console for fbdev emulation, fixes Kconfig
   dependencies

 * exec:
   * Add test cases for calling drm_exec() multiple times
   * Fix memory leak in sleftests
   * Build fixes

 * gem:
   * Fix lockdep checking

 * ttm:
   * Add Kunit tests
   * Cleanups

Driver Changes:

 * atmel-hlcdc:
   * Support inverted pixclock polarity, required by several SoCs

 * bridge:
   * dw-hdmi: Update EDID on HDMI detection
   * sitronix-st7789v: Support panel orientation; Support rotation
                       property; Add support for Jasonic
 		       JT240MHQS-HWT-EK-E3 plus DT bindings; Minor
       		       fixes

 * ivpu:
   * Support VPU4
   * Refactorings

 * loongson:
   * Fixes

 * mcde:
   * Cleanups

 * nouveau:
   * Track GPU virtual memory via DRM GPUVA manager, enables Vulkan
     sparse binding/residency

 * panfrost:
   * Fix synchronization in IRQ handling

 * tve200:
   * Cleanups
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230810084505.GA14039@linux-uq9g

Documentation/devicetree/bindings/display/panel/sitronix,st7789v.yaml

@@ -18,6 +18,7 @@ properties:
     enum:
       - edt,et028013dma
       - inanbo,t28cp45tn89-v17
+      - jasonic,jt240mhqs-hwt-ek-e3
       - sitronix,st7789v
 
   reg: true
@@ -25,6 +26,7 @@ properties:
   power-supply: true
   backlight: true
   port: true
+  rotation: true
 
   spi-cpha: true
   spi-cpol: true
@@ -58,6 +60,7 @@ examples:
             reset-gpios = <&pio 6 11 GPIO_ACTIVE_LOW>;
             backlight = <&pwm_bl>;
             power-supply = <&power>;
+            rotation = <180>;
             spi-max-frequency = <100000>;
             spi-cpol;
             spi-cpha;

Documentation/devicetree/bindings/vendor-prefixes.yaml

@@ -677,6 +677,8 @@ patternProperties:
     description: iWave Systems Technologies Pvt. Ltd.
   "^jadard,.*":
     description: Jadard Technology Inc.
+  "^jasonic,.*":
+    description: Jasonic Technology Ltd.
   "^jdi,.*":
     description: Japan Display Inc.
   "^jedec,.*":

Documentation/gpu/driver-uapi.rst

@@ -6,3 +6,14 @@ drm/i915 uAPI
 =============
 
 .. kernel-doc:: include/uapi/drm/i915_drm.h
+
+drm/nouveau uAPI
+================
+
+VM_BIND / EXEC uAPI
+-------------------
+
+.. kernel-doc:: drivers/gpu/drm/nouveau/nouveau_exec.c
+    :doc: Overview
+
+.. kernel-doc:: include/uapi/drm/nouveau_drm.h

Documentation/gpu/drm-mm.rst

@@ -520,7 +520,7 @@ DRM Cache Handling and Fast WC memcpy()
 .. _drm_sync_objects:
 
 DRM Sync Objects
-===========================
+================
 
 .. kernel-doc:: drivers/gpu/drm/drm_syncobj.c
    :doc: Overview

drivers/accel/ivpu/Makefile

@@ -7,7 +7,8 @@ intel_vpu-y := \
 	ivpu_fw.o \
 	ivpu_fw_log.o \
 	ivpu_gem.o \
-	ivpu_hw_mtl.o \
+	ivpu_hw_37xx.o \
+	ivpu_hw_40xx.o \
 	ivpu_ipc.o \
 	ivpu_job.o \
 	ivpu_jsm_msg.o \

drivers/accel/ivpu/ivpu_drv.c

@@ -115,6 +115,22 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link)
 	kref_put(&file_priv->ref, file_priv_release);
 }
 
+static int ivpu_get_capabilities(struct ivpu_device *vdev, struct drm_ivpu_param *args)
+{
+	switch (args->index) {
+	case DRM_IVPU_CAP_METRIC_STREAMER:
+		args->value = 0;
+		break;
+	case DRM_IVPU_CAP_DMA_MEMORY_RANGE:
+		args->value = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
@@ -144,7 +160,7 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 		args->value = ivpu_get_context_count(vdev);
 		break;
 	case DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
-		args->value = vdev->hw->ranges.user_low.start;
+		args->value = vdev->hw->ranges.user.start;
 		break;
 	case DRM_IVPU_PARAM_CONTEXT_PRIORITY:
 		args->value = file_priv->priority;
@@ -174,6 +190,9 @@ static int ivpu_get_param_ioctl(struct drm_device *dev, void *data, struct drm_f
 	case DRM_IVPU_PARAM_SKU:
 		args->value = vdev->hw->sku;
 		break;
+	case DRM_IVPU_PARAM_CAPABILITIES:
+		ret = ivpu_get_capabilities(vdev, args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -443,8 +462,8 @@ static int ivpu_pci_init(struct ivpu_device *vdev)
 	/* Clear any pending errors */
 	pcie_capability_clear_word(pdev, PCI_EXP_DEVSTA, 0x3f);
 
-	/* VPU MTL does not require PCI spec 10m D3hot delay */
-	if (ivpu_is_mtl(vdev))
+	/* VPU 37XX does not require 10m D3hot delay */
+	if (ivpu_hw_gen(vdev) == IVPU_HW_37XX)
 		pdev->d3hot_delay = 0;
 
 	ret = pcim_enable_device(pdev);
@@ -482,8 +501,13 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	if (!vdev->pm)
 		return -ENOMEM;
 
-	vdev->hw->ops = &ivpu_hw_mtl_ops;
-	vdev->hw->dma_bits = 38;
+	if (ivpu_hw_gen(vdev) >= IVPU_HW_40XX) {
+		vdev->hw->ops = &ivpu_hw_40xx_ops;
+		vdev->hw->dma_bits = 48;
+	} else {
+		vdev->hw->ops = &ivpu_hw_37xx_ops;
+		vdev->hw->dma_bits = 38;
+	}
 
 	vdev->platform = IVPU_PLATFORM_INVALID;
 	vdev->context_xa_limit.min = IVPU_USER_CONTEXT_MIN_SSID;
@@ -610,6 +634,7 @@ static void ivpu_dev_fini(struct ivpu_device *vdev)
 
 static struct pci_device_id ivpu_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_MTL) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_LNL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, ivpu_pci_ids);

drivers/accel/ivpu/ivpu_drv.h

@@ -23,6 +23,10 @@
 #define DRIVER_DATE "20230117"
 
 #define PCI_DEVICE_ID_MTL   0x7d1d
+#define PCI_DEVICE_ID_LNL   0x643e
+
+#define IVPU_HW_37XX	37
+#define IVPU_HW_40XX	40
 
 #define IVPU_GLOBAL_CONTEXT_MMU_SSID 0
 /* SSID 1 is used by the VPU to represent invalid context */
@@ -76,6 +80,7 @@ struct ivpu_wa_table {
 	bool clear_runtime_mem;
 	bool d3hot_after_power_off;
 	bool interrupt_clear_with_0;
+	bool disable_clock_relinquish;
 };
 
 struct ivpu_hw_info;
@@ -146,11 +151,6 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link);
 int ivpu_boot(struct ivpu_device *vdev);
 int ivpu_shutdown(struct ivpu_device *vdev);
 
-static inline bool ivpu_is_mtl(struct ivpu_device *vdev)
-{
-	return to_pci_dev(vdev->drm.dev)->device == PCI_DEVICE_ID_MTL;
-}
-
 static inline u8 ivpu_revision(struct ivpu_device *vdev)
 {
 	return to_pci_dev(vdev->drm.dev)->revision;
@@ -161,6 +161,19 @@ static inline u16 ivpu_device_id(struct ivpu_device *vdev)
 	return to_pci_dev(vdev->drm.dev)->device;
 }
 
+static inline int ivpu_hw_gen(struct ivpu_device *vdev)
+{
+	switch (ivpu_device_id(vdev)) {
+	case PCI_DEVICE_ID_MTL:
+		return IVPU_HW_37XX;
+	case PCI_DEVICE_ID_LNL:
+		return IVPU_HW_40XX;
+	default:
+		ivpu_err(vdev, "Unknown VPU device\n");
+		return 0;
+	}
+}
+
 static inline struct ivpu_device *to_ivpu_device(struct drm_device *dev)
 {
 	return container_of(dev, struct ivpu_device, drm);

drivers/accel/ivpu/ivpu_fw.c

@@ -43,12 +43,20 @@ static char *ivpu_firmware;
 module_param_named_unsafe(firmware, ivpu_firmware, charp, 0644);
 MODULE_PARM_DESC(firmware, "VPU firmware binary in /lib/firmware/..");
 
+/* TODO: Remove mtl_vpu.bin from names after transition to generation based FW names */
+static struct {
+	int gen;
+	const char *name;
+} fw_names[] = {
+	{ IVPU_HW_37XX, "vpu_37xx.bin" },
+	{ IVPU_HW_37XX, "mtl_vpu.bin" },
+	{ IVPU_HW_37XX, "intel/vpu/vpu_37xx_v0.0.bin" },
+	{ IVPU_HW_40XX, "vpu_40xx.bin" },
+	{ IVPU_HW_40XX, "intel/vpu/vpu_40xx_v0.0.bin" },
+};
+
 static int ivpu_fw_request(struct ivpu_device *vdev)
 {
-	static const char * const fw_names[] = {
-		"mtl_vpu.bin",
-		"intel/vpu/mtl_vpu_v0.0.bin"
-	};
 	int ret = -ENOENT;
 	int i;
 
@@ -60,9 +68,12 @@ static int ivpu_fw_request(struct ivpu_device *vdev)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fw_names); i++) {
-		ret = firmware_request_nowarn(&vdev->fw->file, fw_names[i], vdev->drm.dev);
+		if (fw_names[i].gen != ivpu_hw_gen(vdev))
+			continue;
+
+		ret = firmware_request_nowarn(&vdev->fw->file, fw_names[i].name, vdev->drm.dev);
 		if (!ret) {
-			vdev->fw->name = fw_names[i];
+			vdev->fw->name = fw_names[i].name;
 			return 0;
 		}
 	}
@@ -195,7 +206,7 @@ static int ivpu_fw_update_global_range(struct ivpu_device *vdev)
 		return -EINVAL;
 	}
 
-	ivpu_hw_init_range(&vdev->hw->ranges.global_low, start, size);
+	ivpu_hw_init_range(&vdev->hw->ranges.global, start, size);
 	return 0;
 }
 
@@ -236,7 +247,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 	}
 
 	if (fw->shave_nn_size) {
-		fw->mem_shave_nn = ivpu_bo_alloc_internal(vdev, vdev->hw->ranges.global_high.start,
+		fw->mem_shave_nn = ivpu_bo_alloc_internal(vdev, vdev->hw->ranges.shave.start,
 							  fw->shave_nn_size, DRM_IVPU_BO_UNCACHED);
 		if (!fw->mem_shave_nn) {
 			ivpu_err(vdev, "Failed to allocate shavenn buffer\n");
@@ -434,9 +445,9 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	 * Uncached region of VPU address space, covers IPC buffers, job queues
 	 * and log buffers, programmable to L2$ Uncached by VPU MTRR
 	 */
-	boot_params->shared_region_base = vdev->hw->ranges.global_low.start;
-	boot_params->shared_region_size = vdev->hw->ranges.global_low.end -
-					  vdev->hw->ranges.global_low.start;
+	boot_params->shared_region_base = vdev->hw->ranges.global.start;
+	boot_params->shared_region_size = vdev->hw->ranges.global.end -
+					  vdev->hw->ranges.global.start;
 
 	boot_params->ipc_header_area_start = ipc_mem_rx->vpu_addr;
 	boot_params->ipc_header_area_size = ipc_mem_rx->base.size / 2;
@@ -444,10 +455,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->ipc_payload_area_start = ipc_mem_rx->vpu_addr + ipc_mem_rx->base.size / 2;
 	boot_params->ipc_payload_area_size = ipc_mem_rx->base.size / 2;
 
-	boot_params->global_aliased_pio_base =
-		vdev->hw->ranges.global_aliased_pio.start;
-	boot_params->global_aliased_pio_size =
-		ivpu_hw_range_size(&vdev->hw->ranges.global_aliased_pio);
+	boot_params->global_aliased_pio_base = vdev->hw->ranges.user.start;
+	boot_params->global_aliased_pio_size = ivpu_hw_range_size(&vdev->hw->ranges.user);
 
 	/* Allow configuration for L2C_PAGE_TABLE with boot param value */
 	boot_params->autoconfig = 1;
@@ -455,7 +464,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	/* Enable L2 cache for first 2GB of high memory */
 	boot_params->cache_defaults[VPU_BOOT_L2_CACHE_CFG_NN].use = 1;
 	boot_params->cache_defaults[VPU_BOOT_L2_CACHE_CFG_NN].cfg =
-		ADDR_TO_L2_CACHE_CFG(vdev->hw->ranges.global_high.start);
+		ADDR_TO_L2_CACHE_CFG(vdev->hw->ranges.shave.start);
 
 	if (vdev->fw->mem_shave_nn)
 		boot_params->shave_nn_fw_base = vdev->fw->mem_shave_nn->vpu_addr;

drivers/accel/ivpu/ivpu_gem.c

@@ -279,10 +279,12 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	int ret;
 
 	if (!range) {
-		if (bo->flags & DRM_IVPU_BO_HIGH_MEM)
-			range = &vdev->hw->ranges.user_high;
+		if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
+			range = &vdev->hw->ranges.shave;
+		else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
+			range = &vdev->hw->ranges.dma;
 		else
-			range = &vdev->hw->ranges.user_low;
+			range = &vdev->hw->ranges.user;
 	}
 
 	mutex_lock(&ctx->lock);
@@ -570,7 +572,7 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 		fixed_range.end = vpu_addr + size;
 		range = &fixed_range;
 	} else {
-		range = &vdev->hw->ranges.global_low;
+		range = &vdev->hw->ranges.global;
 	}
 
 	bo = ivpu_bo_alloc(vdev, &vdev->gctx, size, flags, &internal_ops, range, 0);

drivers/accel/ivpu/ivpu_hw.h

@@ -38,11 +38,10 @@ struct ivpu_addr_range {
 struct ivpu_hw_info {
 	const struct ivpu_hw_ops *ops;
 	struct {
-		struct ivpu_addr_range global_low;
-		struct ivpu_addr_range global_high;
-		struct ivpu_addr_range user_low;
-		struct ivpu_addr_range user_high;
-		struct ivpu_addr_range global_aliased_pio;
+		struct ivpu_addr_range global;
+		struct ivpu_addr_range user;
+		struct ivpu_addr_range shave;
+		struct ivpu_addr_range dma;
 	} ranges;
 	struct {
 		u8 min_ratio;
@@ -60,7 +59,8 @@ struct ivpu_hw_info {
 	int dma_bits;
 };
 
-extern const struct ivpu_hw_ops ivpu_hw_mtl_ops;
+extern const struct ivpu_hw_ops ivpu_hw_37xx_ops;
+extern const struct ivpu_hw_ops ivpu_hw_40xx_ops;
 
 static inline int ivpu_hw_info_init(struct ivpu_device *vdev)
 {

drivers/accel/ivpu/ivpu_mmu.c

@@ -7,7 +7,7 @@
 #include <linux/highmem.h>
 
 #include "ivpu_drv.h"
-#include "ivpu_hw_mtl_reg.h"
+#include "ivpu_hw_37xx_reg.h"
 #include "ivpu_hw_reg_io.h"
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
@@ -186,13 +186,13 @@
 #define IVPU_MMU_REG_TIMEOUT_US		(10 * USEC_PER_MSEC)
 #define IVPU_MMU_QUEUE_TIMEOUT_US	(100 * USEC_PER_MSEC)
 
-#define IVPU_MMU_GERROR_ERR_MASK ((REG_FLD(MTL_VPU_HOST_MMU_GERROR, CMDQ)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, EVTQ_ABT)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, PRIQ_ABT)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_CMDQ_ABT)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_EVTQ_ABT)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_PRIQ_ABT)) | \
-				  (REG_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_ABT)))
+#define IVPU_MMU_GERROR_ERR_MASK ((REG_FLD(VPU_37XX_HOST_MMU_GERROR, CMDQ)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, EVTQ_ABT)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, PRIQ_ABT)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_CMDQ_ABT)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_EVTQ_ABT)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_PRIQ_ABT)) | \
+				  (REG_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_ABT)))
 
 static char *ivpu_mmu_event_to_str(u32 cmd)
 {
@@ -250,15 +250,15 @@ static void ivpu_mmu_config_check(struct ivpu_device *vdev)
 	else
 		val_ref = IVPU_MMU_IDR0_REF;
 
-	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR0);
+	val = REGV_RD32(VPU_37XX_HOST_MMU_IDR0);
 	if (val != val_ref)
 		ivpu_dbg(vdev, MMU, "IDR0 0x%x != IDR0_REF 0x%x\n", val, val_ref);
 
-	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR1);
+	val = REGV_RD32(VPU_37XX_HOST_MMU_IDR1);
 	if (val != IVPU_MMU_IDR1_REF)
 		ivpu_dbg(vdev, MMU, "IDR1 0x%x != IDR1_REF 0x%x\n", val, IVPU_MMU_IDR1_REF);
 
-	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR3);
+	val = REGV_RD32(VPU_37XX_HOST_MMU_IDR3);
 	if (val != IVPU_MMU_IDR3_REF)
 		ivpu_dbg(vdev, MMU, "IDR3 0x%x != IDR3_REF 0x%x\n", val, IVPU_MMU_IDR3_REF);
 
@@ -269,7 +269,7 @@ static void ivpu_mmu_config_check(struct ivpu_device *vdev)
 	else
 		val_ref = IVPU_MMU_IDR5_REF;
 
-	val = REGV_RD32(MTL_VPU_HOST_MMU_IDR5);
+	val = REGV_RD32(VPU_37XX_HOST_MMU_IDR5);
 	if (val != val_ref)
 		ivpu_dbg(vdev, MMU, "IDR5 0x%x != IDR5_REF 0x%x\n", val, val_ref);
 }
@@ -396,18 +396,18 @@ static int ivpu_mmu_irqs_setup(struct ivpu_device *vdev)
 	u32 irq_ctrl = IVPU_MMU_IRQ_EVTQ_EN | IVPU_MMU_IRQ_GERROR_EN;
 	int ret;
 
-	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_IRQ_CTRL, 0);
+	ret = ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_IRQ_CTRL, 0);
 	if (ret)
 		return ret;
 
-	return ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_IRQ_CTRL, irq_ctrl);
+	return ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_IRQ_CTRL, irq_ctrl);
 }
 
 static int ivpu_mmu_cmdq_wait_for_cons(struct ivpu_device *vdev)
 {
 	struct ivpu_mmu_queue *cmdq = &vdev->mmu->cmdq;
 
-	return REGV_POLL(MTL_VPU_HOST_MMU_CMDQ_CONS, cmdq->cons, (cmdq->prod == cmdq->cons),
+	return REGV_POLL(VPU_37XX_HOST_MMU_CMDQ_CONS, cmdq->cons, (cmdq->prod == cmdq->cons),
 			 IVPU_MMU_QUEUE_TIMEOUT_US);
 }
 
@@ -447,7 +447,7 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 		return ret;
 
 	clflush_cache_range(q->base, IVPU_MMU_CMDQ_SIZE);
-	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_PROD, q->prod);
+	REGV_WR32(VPU_37XX_HOST_MMU_CMDQ_PROD, q->prod);
 
 	ret = ivpu_mmu_cmdq_wait_for_cons(vdev);
 	if (ret)
@@ -495,7 +495,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	mmu->evtq.prod = 0;
 	mmu->evtq.cons = 0;
 
-	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, 0);
+	ret = ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_CR0, 0);
 	if (ret)
 		return ret;
 
@@ -505,17 +505,17 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_SH, IVPU_MMU_SH_ISH) |
 	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_OC, IVPU_MMU_CACHE_WB) |
 	      FIELD_PREP(IVPU_MMU_CR1_QUEUE_IC, IVPU_MMU_CACHE_WB);
-	REGV_WR32(MTL_VPU_HOST_MMU_CR1, val);
+	REGV_WR32(VPU_37XX_HOST_MMU_CR1, val);
 
-	REGV_WR64(MTL_VPU_HOST_MMU_STRTAB_BASE, mmu->strtab.dma_q);
-	REGV_WR32(MTL_VPU_HOST_MMU_STRTAB_BASE_CFG, mmu->strtab.base_cfg);
+	REGV_WR64(VPU_37XX_HOST_MMU_STRTAB_BASE, mmu->strtab.dma_q);
+	REGV_WR32(VPU_37XX_HOST_MMU_STRTAB_BASE_CFG, mmu->strtab.base_cfg);
 
-	REGV_WR64(MTL_VPU_HOST_MMU_CMDQ_BASE, mmu->cmdq.dma_q);
-	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_PROD, 0);
-	REGV_WR32(MTL_VPU_HOST_MMU_CMDQ_CONS, 0);
+	REGV_WR64(VPU_37XX_HOST_MMU_CMDQ_BASE, mmu->cmdq.dma_q);
+	REGV_WR32(VPU_37XX_HOST_MMU_CMDQ_PROD, 0);
+	REGV_WR32(VPU_37XX_HOST_MMU_CMDQ_CONS, 0);
 
 	val = IVPU_MMU_CR0_CMDQEN;
-	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	ret = ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_CR0, val);
 	if (ret)
 		return ret;
 
@@ -531,17 +531,17 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 	if (ret)
 		return ret;
 
-	REGV_WR64(MTL_VPU_HOST_MMU_EVTQ_BASE, mmu->evtq.dma_q);
-	REGV_WR32(MTL_VPU_HOST_MMU_EVTQ_PROD_SEC, 0);
-	REGV_WR32(MTL_VPU_HOST_MMU_EVTQ_CONS_SEC, 0);
+	REGV_WR64(VPU_37XX_HOST_MMU_EVTQ_BASE, mmu->evtq.dma_q);
+	REGV_WR32(VPU_37XX_HOST_MMU_EVTQ_PROD_SEC, 0);
+	REGV_WR32(VPU_37XX_HOST_MMU_EVTQ_CONS_SEC, 0);
 
 	val |= IVPU_MMU_CR0_EVTQEN;
-	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	ret = ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_CR0, val);
 	if (ret)
 		return ret;
 
 	val |= IVPU_MMU_CR0_ATSCHK;
-	ret = ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	ret = ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_CR0, val);
 	if (ret)
 		return ret;
 
@@ -550,7 +550,7 @@ static int ivpu_mmu_reset(struct ivpu_device *vdev)
 		return ret;
 
 	val |= IVPU_MMU_CR0_SMMUEN;
-	return ivpu_mmu_reg_write(vdev, MTL_VPU_HOST_MMU_CR0, val);
+	return ivpu_mmu_reg_write(vdev, VPU_37XX_HOST_MMU_CR0, val);
 }
 
 static void ivpu_mmu_strtab_link_cd(struct ivpu_device *vdev, u32 sid)
@@ -801,14 +801,14 @@ static u32 *ivpu_mmu_get_event(struct ivpu_device *vdev)
 	u32 idx = IVPU_MMU_Q_IDX(evtq->cons);
 	u32 *evt = evtq->base + (idx * IVPU_MMU_EVTQ_CMD_SIZE);
 
-	evtq->prod = REGV_RD32(MTL_VPU_HOST_MMU_EVTQ_PROD_SEC);
+	evtq->prod = REGV_RD32(VPU_37XX_HOST_MMU_EVTQ_PROD_SEC);
 	if (!CIRC_CNT(IVPU_MMU_Q_IDX(evtq->prod), IVPU_MMU_Q_IDX(evtq->cons), IVPU_MMU_Q_COUNT))
 		return NULL;
 
 	clflush_cache_range(evt, IVPU_MMU_EVTQ_CMD_SIZE);
 
 	evtq->cons = (evtq->cons + 1) & IVPU_MMU_Q_WRAP_MASK;
-	REGV_WR32(MTL_VPU_HOST_MMU_EVTQ_CONS_SEC, evtq->cons);
+	REGV_WR32(VPU_37XX_HOST_MMU_EVTQ_CONS_SEC, evtq->cons);
 
 	return evt;
 }
@@ -841,35 +841,35 @@ void ivpu_mmu_irq_gerr_handler(struct ivpu_device *vdev)
 
 	ivpu_dbg(vdev, IRQ, "MMU error\n");
 
-	gerror_val = REGV_RD32(MTL_VPU_HOST_MMU_GERROR);
-	gerrorn_val = REGV_RD32(MTL_VPU_HOST_MMU_GERRORN);
+	gerror_val = REGV_RD32(VPU_37XX_HOST_MMU_GERROR);
+	gerrorn_val = REGV_RD32(VPU_37XX_HOST_MMU_GERRORN);
 
 	active = gerror_val ^ gerrorn_val;
 	if (!(active & IVPU_MMU_GERROR_ERR_MASK))
 		return;
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_ABT, active))
 		ivpu_warn_ratelimited(vdev, "MMU MSI ABT write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_PRIQ_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_PRIQ_ABT, active))
 		ivpu_warn_ratelimited(vdev, "MMU PRIQ MSI ABT write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_EVTQ_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_EVTQ_ABT, active))
 		ivpu_warn_ratelimited(vdev, "MMU EVTQ MSI ABT write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, MSI_CMDQ_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, MSI_CMDQ_ABT, active))
 		ivpu_warn_ratelimited(vdev, "MMU CMDQ MSI ABT write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, PRIQ_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, PRIQ_ABT, active))
 		ivpu_err_ratelimited(vdev, "MMU PRIQ write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, EVTQ_ABT, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, EVTQ_ABT, active))
 		ivpu_err_ratelimited(vdev, "MMU EVTQ write aborted\n");
 
-	if (REG_TEST_FLD(MTL_VPU_HOST_MMU_GERROR, CMDQ, active))
+	if (REG_TEST_FLD(VPU_37XX_HOST_MMU_GERROR, CMDQ, active))
 		ivpu_err_ratelimited(vdev, "MMU CMDQ write aborted\n");
 
-	REGV_WR32(MTL_VPU_HOST_MMU_GERRORN, gerror_val);
+	REGV_WR32(VPU_37XX_HOST_MMU_GERRORN, gerror_val);
 }
 
 int ivpu_mmu_set_pgtable(struct ivpu_device *vdev, int ssid, struct ivpu_mmu_pgtable *pgtable)

drivers/accel/ivpu/ivpu_mmu_context.c

@@ -431,11 +431,11 @@ ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u3
 		return ret;
 
 	if (!context_id) {
-		start = vdev->hw->ranges.global_low.start;
-		end = vdev->hw->ranges.global_high.end;
+		start = vdev->hw->ranges.global.start;
+		end = vdev->hw->ranges.shave.end;
 	} else {
-		start = vdev->hw->ranges.user_low.start;
-		end = vdev->hw->ranges.user_high.end;
+		start = vdev->hw->ranges.user.start;
+		end = vdev->hw->ranges.dma.end;
 	}
 
 	drm_mm_init(&ctx->mm, start, end - start);

drivers/gpu/drm/Kconfig

@@ -135,7 +135,6 @@ config DRM_DEBUG_MODESET_LOCK
 config DRM_FBDEV_EMULATION
 	bool "Enable legacy fbdev support for your modesetting driver"
 	depends on DRM
-	select FRAMEBUFFER_CONSOLE if !EXPERT
 	select FRAMEBUFFER_CONSOLE_DETECT_PRIMARY if FRAMEBUFFER_CONSOLE
 	default y
 	help
@@ -196,6 +195,21 @@ config DRM_TTM
 	  GPU memory types. Will be enabled automatically if a device driver
 	  uses it.
 
+config DRM_TTM_KUNIT_TEST
+        tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS
+        default n
+        depends on DRM && KUNIT
+        select DRM_TTM
+        select DRM_EXPORT_FOR_TESTS if m
+        select DRM_KUNIT_TEST_HELPERS
+        default KUNIT_ALL_TESTS
+        help
+          Enables unit tests for TTM, a GPU memory manager subsystem used
+          to manage memory buffers. This option is mostly useful for kernel
+          developers.
+
+          If in doubt, say "N".
+
 config DRM_EXEC
 	tristate
 	depends on DRM

drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c

@@ -68,7 +68,11 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 	struct atmel_hlcdc_crtc *crtc = drm_crtc_to_atmel_hlcdc_crtc(c);
 	struct regmap *regmap = crtc->dc->hlcdc->regmap;
 	struct drm_display_mode *adj = &c->state->adjusted_mode;
+	struct drm_encoder *encoder = NULL, *en_iter;
+	struct drm_connector *connector = NULL;
 	struct atmel_hlcdc_crtc_state *state;
+	struct drm_device *ddev = c->dev;
+	struct drm_connector_list_iter iter;
 	unsigned long mode_rate;
 	struct videomode vm;
 	unsigned long prate;
@@ -76,6 +80,23 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 	unsigned int cfg = 0;
 	int div, ret;
 
+	/* get encoder from crtc */
+	drm_for_each_encoder(en_iter, ddev) {
+		if (en_iter->crtc == c) {
+			encoder = en_iter;
+			break;
+		}
+	}
+
+	if (encoder) {
+		/* Get the connector from encoder */
+		drm_connector_list_iter_begin(ddev, &iter);
+		drm_for_each_connector_iter(connector, &iter)
+			if (connector->encoder == encoder)
+				break;
+		drm_connector_list_iter_end(&iter);
+	}
+
 	ret = clk_prepare_enable(crtc->dc->hlcdc->sys_clk);
 	if (ret)
 		return;
@@ -134,6 +155,10 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 
 	cfg |= ATMEL_HLCDC_CLKDIV(div);
 
+	if (connector &&
+	    connector->display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE)
+		cfg |= ATMEL_HLCDC_CLKPOL;
+
 	regmap_update_bits(regmap, ATMEL_HLCDC_CFG(0), mask, cfg);
 
 	state = drm_crtc_state_to_atmel_hlcdc_crtc_state(c->state);

drivers/gpu/drm/bridge/synopsys/dw-hdmi.c

@@ -2449,15 +2449,7 @@ static enum drm_connector_status dw_hdmi_detect(struct dw_hdmi *hdmi)
 	enum drm_connector_status result;
 
 	result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data);
-
-	mutex_lock(&hdmi->mutex);
-	if (result != hdmi->last_connector_result) {
-		dev_dbg(hdmi->dev, "read_hpd result: %d", result);
-		handle_plugged_change(hdmi,
-				      result == connector_status_connected);
-		hdmi->last_connector_result = result;
-	}
-	mutex_unlock(&hdmi->mutex);
+	hdmi->last_connector_result = result;
 
 	return result;
 }
@@ -2958,6 +2950,7 @@ static void dw_hdmi_bridge_atomic_disable(struct drm_bridge *bridge,
 	hdmi->curr_conn = NULL;
 	dw_hdmi_update_power(hdmi);
 	dw_hdmi_update_phy_mask(hdmi);
+	handle_plugged_change(hdmi, false);
 	mutex_unlock(&hdmi->mutex);
 }
 
@@ -2976,6 +2969,7 @@ static void dw_hdmi_bridge_atomic_enable(struct drm_bridge *bridge,
 	hdmi->curr_conn = connector;
 	dw_hdmi_update_power(hdmi);
 	dw_hdmi_update_phy_mask(hdmi);
+	handle_plugged_change(hdmi, true);
 	mutex_unlock(&hdmi->mutex);
 }
 

drivers/gpu/drm/loongson/lsdc_ttm.c

@@ -496,6 +496,8 @@ struct lsdc_bo *lsdc_bo_create_kernel_pinned(struct drm_device *ddev,
 	int ret;
 
 	lbo = lsdc_bo_create(ddev, domain, size, true, NULL, NULL);
+	if (IS_ERR(lbo))
+		return ERR_CAST(lbo);
 
 	ret = lsdc_bo_reserve(lbo);
 	if (unlikely(ret)) {

drivers/gpu/drm/mcde/mcde_dsi.c

@@ -1226,7 +1226,7 @@ static const struct of_device_id mcde_dsi_of_match[] = {
 struct platform_driver mcde_dsi_driver = {
 	.driver = {
 		.name           = "mcde-dsi",
-		.of_match_table = of_match_ptr(mcde_dsi_of_match),
+		.of_match_table = mcde_dsi_of_match,
 	},
 	.probe = mcde_dsi_probe,
 	.remove_new = mcde_dsi_remove,

drivers/gpu/drm/nouveau/Kbuild

@@ -47,6 +47,9 @@ nouveau-y += nouveau_prime.o
 nouveau-y += nouveau_sgdma.o
 nouveau-y += nouveau_ttm.o
 nouveau-y += nouveau_vmm.o
+nouveau-y += nouveau_exec.o
+nouveau-y += nouveau_sched.o
+nouveau-y += nouveau_uvmm.o
 
 # DRM - modesetting
 nouveau-$(CONFIG_DRM_NOUVEAU_BACKLIGHT) += nouveau_backlight.o

drivers/gpu/drm/nouveau/Kconfig

@@ -10,6 +10,8 @@ config DRM_NOUVEAU
 	select DRM_KMS_HELPER
 	select DRM_TTM
 	select DRM_TTM_HELPER
+	select DRM_EXEC
+	select DRM_SCHED
 	select I2C
 	select I2C_ALGOBIT
 	select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT

drivers/gpu/drm/nouveau/dispnv04/crtc.c

@@ -1122,11 +1122,18 @@ nv04_page_flip_emit(struct nouveau_channel *chan,
 	PUSH_NVSQ(push, NV_SW, NV_SW_PAGE_FLIP, 0x00000000);
 	PUSH_KICK(push);
 
-	ret = nouveau_fence_new(chan, false, pfence);
+	ret = nouveau_fence_new(pfence);
 	if (ret)
 		goto fail;
 
+	ret = nouveau_fence_emit(*pfence, chan);
+	if (ret)
+		goto fail_fence_unref;
+
 	return 0;
+
+fail_fence_unref:
+	nouveau_fence_unref(pfence);
 fail:
 	spin_lock_irqsave(&dev->event_lock, flags);
 	list_del(&s->head);

drivers/gpu/drm/nouveau/include/nvif/if000c.h

@@ -3,7 +3,10 @@
 struct nvif_vmm_v0 {
 	__u8  version;
 	__u8  page_nr;
-	__u8  managed;
+#define NVIF_VMM_V0_TYPE_UNMANAGED                                         0x00
+#define NVIF_VMM_V0_TYPE_MANAGED                                           0x01
+#define NVIF_VMM_V0_TYPE_RAW                                               0x02
+	__u8  type;
 	__u8  pad03[5];
 	__u64 addr;
 	__u64 size;
@@ -17,6 +20,7 @@ struct nvif_vmm_v0 {
 #define NVIF_VMM_V0_UNMAP                                                  0x04
 #define NVIF_VMM_V0_PFNMAP                                                 0x05
 #define NVIF_VMM_V0_PFNCLR                                                 0x06
+#define NVIF_VMM_V0_RAW                                                    0x07
 #define NVIF_VMM_V0_MTHD(i)                                         ((i) + 0x80)
 
 struct nvif_vmm_page_v0 {
@@ -66,6 +70,26 @@ struct nvif_vmm_unmap_v0 {
 	__u64 addr;
 };
 
+struct nvif_vmm_raw_v0 {
+	__u8 version;
+#define NVIF_VMM_RAW_V0_GET	0x0
+#define NVIF_VMM_RAW_V0_PUT	0x1
+#define NVIF_VMM_RAW_V0_MAP	0x2
+#define NVIF_VMM_RAW_V0_UNMAP	0x3
+#define NVIF_VMM_RAW_V0_SPARSE	0x4
+	__u8  op;
+	__u8  sparse;
+	__u8  ref;
+	__u8  shift;
+	__u32 argc;
+	__u8  pad01[7];
+	__u64 addr;
+	__u64 size;
+	__u64 offset;
+	__u64 memory;
+	__u64 argv;
+};
+
 struct nvif_vmm_pfnmap_v0 {
 	__u8  version;
 	__u8  page;

drivers/gpu/drm/nouveau/include/nvif/vmm.h

@@ -4,6 +4,12 @@
 struct nvif_mem;
 struct nvif_mmu;
 
+enum nvif_vmm_type {
+	UNMANAGED,
+	MANAGED,
+	RAW,
+};
+
 enum nvif_vmm_get {
 	ADDR,
 	PTES,
@@ -30,8 +36,9 @@ struct nvif_vmm {
 	int page_nr;
 };
 
-int nvif_vmm_ctor(struct nvif_mmu *, const char *name, s32 oclass, bool managed,
-		  u64 addr, u64 size, void *argv, u32 argc, struct nvif_vmm *);
+int nvif_vmm_ctor(struct nvif_mmu *, const char *name, s32 oclass,
+		  enum nvif_vmm_type, u64 addr, u64 size, void *argv, u32 argc,
+		  struct nvif_vmm *);
 void nvif_vmm_dtor(struct nvif_vmm *);
 int nvif_vmm_get(struct nvif_vmm *, enum nvif_vmm_get, bool sparse,
 		 u8 page, u8 align, u64 size, struct nvif_vma *);
@@ -39,4 +46,12 @@ void nvif_vmm_put(struct nvif_vmm *, struct nvif_vma *);
 int nvif_vmm_map(struct nvif_vmm *, u64 addr, u64 size, void *argv, u32 argc,
 		 struct nvif_mem *, u64 offset);
 int nvif_vmm_unmap(struct nvif_vmm *, u64);
+
+int nvif_vmm_raw_get(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift);
+int nvif_vmm_raw_put(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift);
+int nvif_vmm_raw_map(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift,
+		     void *argv, u32 argc, struct nvif_mem *mem, u64 offset);
+int nvif_vmm_raw_unmap(struct nvif_vmm *vmm, u64 addr, u64 size,
+		       u8 shift, bool sparse);
+int nvif_vmm_raw_sparse(struct nvif_vmm *vmm, u64 addr, u64 size, bool ref);
 #endif

drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h

@@ -17,6 +17,7 @@ struct nvkm_vma {
 	bool part:1; /* Region was split from an allocated region by map(). */
 	bool busy:1; /* Region busy (for temporarily preventing user access). */
 	bool mapped:1; /* Region contains valid pages. */
+	bool no_comp:1; /* Force no memory compression. */
 	struct nvkm_memory *memory; /* Memory currently mapped into VMA. */
 	struct nvkm_tags *tags; /* Compression tag reference. */
 };
@@ -27,10 +28,26 @@ struct nvkm_vmm {
 	const char *name;
 	u32 debug;
 	struct kref kref;
-	struct mutex mutex;
+
+	struct {
+		struct mutex vmm;
+		struct mutex ref;
+		struct mutex map;
+	} mutex;
 
 	u64 start;
 	u64 limit;
+	struct {
+		struct {
+			u64 addr;
+			u64 size;
+		} p;
+		struct {
+			u64 addr;
+			u64 size;
+		} n;
+		bool raw;
+	} managed;
 
 	struct nvkm_vmm_pt *pd;
 	struct list_head join;
@@ -70,6 +87,7 @@ struct nvkm_vmm_map {
 
 	const struct nvkm_vmm_page *page;
 
+	bool no_comp;
 	struct nvkm_tags *tags;
 	u64 next;
 	u64 type;

drivers/gpu/drm/nouveau/nouveau_abi16.c

@@ -35,6 +35,7 @@
 #include "nouveau_chan.h"
 #include "nouveau_abi16.h"
 #include "nouveau_vmm.h"
+#include "nouveau_sched.h"
 
 static struct nouveau_abi16 *
 nouveau_abi16(struct drm_file *file_priv)
@@ -125,6 +126,17 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 {
 	struct nouveau_abi16_ntfy *ntfy, *temp;
 
+	/* When a client exits without waiting for it's queued up jobs to
+	 * finish it might happen that we fault the channel. This is due to
+	 * drm_file_free() calling drm_gem_release() before the postclose()
+	 * callback. Hence, we can't tear down this scheduler entity before
+	 * uvmm mappings are unmapped. Currently, we can't detect this case.
+	 *
+	 * However, this should be rare and harmless, since the channel isn't
+	 * needed anymore.
+	 */
+	nouveau_sched_entity_fini(&chan->sched_entity);
+
 	/* wait for all activity to stop before cleaning up */
 	if (chan->chan)
 		nouveau_channel_idle(chan->chan);
@@ -261,6 +273,13 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	if (!drm->channel)
 		return nouveau_abi16_put(abi16, -ENODEV);
 
+	/* If uvmm wasn't initialized until now disable it completely to prevent
+	 * userspace from mixing up UAPIs.
+	 *
+	 * The client lock is already acquired by nouveau_abi16_get().
+	 */
+	__nouveau_cli_disable_uvmm_noinit(cli);
+
 	device = &abi16->device;
 	engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR;
 
@@ -304,6 +323,11 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
 	if (ret)
 		goto done;
 
+	ret = nouveau_sched_entity_init(&chan->sched_entity, &drm->sched,
+					drm->sched_wq);
+	if (ret)
+		goto done;
+
 	init->channel = chan->chan->chid;
 
 	if (device->info.family >= NV_DEVICE_INFO_V0_TESLA)

drivers/gpu/drm/nouveau/nouveau_abi16.h

@@ -26,6 +26,7 @@ struct nouveau_abi16_chan {
 	struct nouveau_bo *ntfy;
 	struct nouveau_vma *ntfy_vma;
 	struct nvkm_mm  heap;
+	struct nouveau_sched_entity sched_entity;
 };
 
 struct nouveau_abi16 {
@@ -43,28 +44,6 @@ int  nouveau_abi16_usif(struct drm_file *, void *data, u32 size);
 #define NOUVEAU_GEM_DOMAIN_VRAM      (1 << 1)
 #define NOUVEAU_GEM_DOMAIN_GART      (1 << 2)
 
-struct drm_nouveau_channel_alloc {
-	uint32_t     fb_ctxdma_handle;
-	uint32_t     tt_ctxdma_handle;
-
-	int          channel;
-	uint32_t     pushbuf_domains;
-
-	/* Notifier memory */
-	uint32_t     notifier_handle;
-
-	/* DRM-enforced subchannel assignments */
-	struct {
-		uint32_t handle;
-		uint32_t grclass;
-	} subchan[8];
-	uint32_t nr_subchan;
-};
-
-struct drm_nouveau_channel_free {
-	int channel;
-};
-
 struct drm_nouveau_grobj_alloc {
 	int      channel;
 	uint32_t handle;
@@ -83,31 +62,12 @@ struct drm_nouveau_gpuobj_free {
 	uint32_t handle;
 };
 
-#define NOUVEAU_GETPARAM_PCI_VENDOR      3
-#define NOUVEAU_GETPARAM_PCI_DEVICE      4
-#define NOUVEAU_GETPARAM_BUS_TYPE        5
-#define NOUVEAU_GETPARAM_FB_SIZE         8
-#define NOUVEAU_GETPARAM_AGP_SIZE        9
-#define NOUVEAU_GETPARAM_CHIPSET_ID      11
-#define NOUVEAU_GETPARAM_VM_VRAM_BASE    12
-#define NOUVEAU_GETPARAM_GRAPH_UNITS     13
-#define NOUVEAU_GETPARAM_PTIMER_TIME     14
-#define NOUVEAU_GETPARAM_HAS_BO_USAGE    15
-#define NOUVEAU_GETPARAM_HAS_PAGEFLIP    16
-struct drm_nouveau_getparam {
-	uint64_t param;
-	uint64_t value;
-};
-
 struct drm_nouveau_setparam {
 	uint64_t param;
 	uint64_t value;
 };
 
-#define DRM_IOCTL_NOUVEAU_GETPARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GETPARAM, struct drm_nouveau_getparam)
 #define DRM_IOCTL_NOUVEAU_SETPARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SETPARAM, struct drm_nouveau_setparam)
-#define DRM_IOCTL_NOUVEAU_CHANNEL_ALLOC      DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_ALLOC, struct drm_nouveau_channel_alloc)
-#define DRM_IOCTL_NOUVEAU_CHANNEL_FREE       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_FREE, struct drm_nouveau_channel_free)
 #define DRM_IOCTL_NOUVEAU_GROBJ_ALLOC        DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GROBJ_ALLOC, struct drm_nouveau_grobj_alloc)
 #define DRM_IOCTL_NOUVEAU_NOTIFIEROBJ_ALLOC  DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_NOTIFIEROBJ_ALLOC, struct drm_nouveau_notifierobj_alloc)
 #define DRM_IOCTL_NOUVEAU_GPUOBJ_FREE        DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GPUOBJ_FREE, struct drm_nouveau_gpuobj_free)

drivers/gpu/drm/nouveau/nouveau_bo.c

@@ -199,12 +199,12 @@ nouveau_bo_fixup_align(struct nouveau_bo *nvbo, int *align, u64 *size)
 
 struct nouveau_bo *
 nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
-		 u32 tile_mode, u32 tile_flags)
+		 u32 tile_mode, u32 tile_flags, bool internal)
 {
 	struct nouveau_drm *drm = cli->drm;
 	struct nouveau_bo *nvbo;
 	struct nvif_mmu *mmu = &cli->mmu;
-	struct nvif_vmm *vmm = cli->svm.cli ? &cli->svm.vmm : &cli->vmm.vmm;
+	struct nvif_vmm *vmm = &nouveau_cli_vmm(cli)->vmm;
 	int i, pi = -1;
 
 	if (!*size) {
@@ -215,6 +215,7 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 	nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL);
 	if (!nvbo)
 		return ERR_PTR(-ENOMEM);
+
 	INIT_LIST_HEAD(&nvbo->head);
 	INIT_LIST_HEAD(&nvbo->entry);
 	INIT_LIST_HEAD(&nvbo->vma_list);
@@ -232,68 +233,103 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain,
 			nvbo->force_coherent = true;
 	}
 
-	if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) {
-		nvbo->kind = (tile_flags & 0x0000ff00) >> 8;
-		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
-			kfree(nvbo);
-			return ERR_PTR(-EINVAL);
+	nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG);
+	if (!nouveau_cli_uvmm(cli) || internal) {
+		/* for BO noVM allocs, don't assign kinds */
+		if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) {
+			nvbo->kind = (tile_flags & 0x0000ff00) >> 8;
+			if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
+				kfree(nvbo);
+				return ERR_PTR(-EINVAL);
+			}
+
+			nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind;
+		} else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
+			nvbo->kind = (tile_flags & 0x00007f00) >> 8;
+			nvbo->comp = (tile_flags & 0x00030000) >> 16;
+			if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
+				kfree(nvbo);
+				return ERR_PTR(-EINVAL);
+			}
+		} else {
+			nvbo->zeta = (tile_flags & 0x00000007);
 		}
+		nvbo->mode = tile_mode;
+
+		/* Determine the desirable target GPU page size for the buffer. */
+		for (i = 0; i < vmm->page_nr; i++) {
+			/* Because we cannot currently allow VMM maps to fail
+			 * during buffer migration, we need to determine page
+			 * size for the buffer up-front, and pre-allocate its
+			 * page tables.
+			 *
+			 * Skip page sizes that can't support needed domains.
+			 */
+			if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE &&
+			    (domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram)
+				continue;
+			if ((domain & NOUVEAU_GEM_DOMAIN_GART) &&
+			    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
+				continue;
 
-		nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind;
-	} else
-	if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) {
-		nvbo->kind = (tile_flags & 0x00007f00) >> 8;
-		nvbo->comp = (tile_flags & 0x00030000) >> 16;
-		if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) {
+			/* Select this page size if it's the first that supports
+			 * the potential memory domains, or when it's compatible
+			 * with the requested compression settings.
+			 */
+			if (pi < 0 || !nvbo->comp || vmm->page[i].comp)
+				pi = i;
+
+			/* Stop once the buffer is larger than the current page size. */
+			if (*size >= 1ULL << vmm->page[i].shift)
+				break;
+		}
+
+		if (WARN_ON(pi < 0)) {
 			kfree(nvbo);
 			return ERR_PTR(-EINVAL);
 		}
-	} else {
-		nvbo->zeta = (tile_flags & 0x00000007);
-	}
-	nvbo->mode = tile_mode;
-	nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG);
-
-	/* Determine the desirable target GPU page size for the buffer. */
-	for (i = 0; i < vmm->page_nr; i++) {
-		/* Because we cannot currently allow VMM maps to fail
-		 * during buffer migration, we need to determine page
-		 * size for the buffer up-front, and pre-allocate its
-		 * page tables.
-		 *
-		 * Skip page sizes that can't support needed domains.
-		 */
-		if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE &&
-		    (domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram)
-			continue;
-		if ((domain & NOUVEAU_GEM_DOMAIN_GART) &&
-		    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
-			continue;
 
-		/* Select this page size if it's the first that supports
-		 * the potential memory domains, or when it's compatible
-		 * with the requested compression settings.
-		 */
-		if (pi < 0 || !nvbo->comp || vmm->page[i].comp)
-			pi = i;
-
-		/* Stop once the buffer is larger than the current page size. */
-		if (*size >= 1ULL << vmm->page[i].shift)
-			break;
-	}
+		/* Disable compression if suitable settings couldn't be found. */
+		if (nvbo->comp && !vmm->page[pi].comp) {
+			if (mmu->object.oclass >= NVIF_CLASS_MMU_GF100)
+				nvbo->kind = mmu->kind[nvbo->kind];
+			nvbo->comp = 0;
+		}
+		nvbo->page = vmm->page[pi].shift;
+	} else {
+		/* reject other tile flags when in VM mode. */
+		if (tile_mode)
+			return ERR_PTR(-EINVAL);
+		if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG)
+			return ERR_PTR(-EINVAL);
 
-	if (WARN_ON(pi < 0)) {
-		kfree(nvbo);
-		return ERR_PTR(-EINVAL);
-	}
+		/* Determine the desirable target GPU page size for the buffer. */
+		for (i = 0; i < vmm->page_nr; i++) {
+			/* Because we cannot currently allow VMM maps to fail
+			 * during buffer migration, we need to determine page
+			 * size for the buffer up-front, and pre-allocate its
+			 * page tables.
+			 *
+			 * Skip page sizes that can't support needed domains.
+			 */
+			if ((domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram)
+				continue;
+			if ((domain & NOUVEAU_GEM_DOMAIN_GART) &&
+			    (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT))
+				continue;
 
-	/* Disable compression if suitable settings couldn't be found. */
-	if (nvbo->comp && !vmm->page[pi].comp) {
-		if (mmu->object.oclass >= NVIF_CLASS_MMU_GF100)
-			nvbo->kind = mmu->kind[nvbo->kind];
-		nvbo->comp = 0;
+			if (pi < 0)
+				pi = i;
+			/* Stop once the buffer is larger than the current page size. */
+			if (*size >= 1ULL << vmm->page[i].shift)
+				break;
+		}
+		if (WARN_ON(pi < 0)) {
+			kfree(nvbo);
+			return ERR_PTR(-EINVAL);
+		}
+		nvbo->page = vmm->page[pi].shift;
 	}
-	nvbo->page = vmm->page[pi].shift;
 
 	nouveau_bo_fixup_align(nvbo, align, size);
 
@@ -306,18 +342,26 @@ nouveau_bo_init(struct nouveau_bo *nvbo, u64 size, int align, u32 domain,
 {
 	int type = sg ? ttm_bo_type_sg : ttm_bo_type_device;
 	int ret;
+	struct ttm_operation_ctx ctx = {
+		.interruptible = false,
+		.no_wait_gpu = false,
+		.resv = robj,
+	};
 
 	nouveau_bo_placement_set(nvbo, domain, 0);
 	INIT_LIST_HEAD(&nvbo->io_reserve_lru);
 
-	ret = ttm_bo_init_validate(nvbo->bo.bdev, &nvbo->bo, type,
-				   &nvbo->placement, align >> PAGE_SHIFT, false,
+	ret = ttm_bo_init_reserved(nvbo->bo.bdev, &nvbo->bo, type,
+				   &nvbo->placement, align >> PAGE_SHIFT, &ctx,
 				   sg, robj, nouveau_bo_del_ttm);
 	if (ret) {
 		/* ttm will call nouveau_bo_del_ttm if it fails.. */
 		return ret;
 	}
 
+	if (!robj)
+		ttm_bo_unreserve(&nvbo->bo);
+
 	return 0;
 }
 
@@ -331,7 +375,7 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 	int ret;
 
 	nvbo = nouveau_bo_alloc(cli, &size, &align, domain, tile_mode,
-				tile_flags);
+				tile_flags, true);
 	if (IS_ERR(nvbo))
 		return PTR_ERR(nvbo);
 
@@ -339,6 +383,11 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
 	dma_resv_init(&nvbo->bo.base._resv);
 	drm_vma_node_reset(&nvbo->bo.base.vma_node);
 
+	/* This must be called before ttm_bo_init_reserved(). Subsequent
+	 * bo_move() callbacks might already iterate the GEMs GPUVA list.
+	 */
+	drm_gem_gpuva_init(&nvbo->bo.base);
+
 	ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj);
 	if (ret)
 		return ret;
@@ -817,29 +866,39 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
 		mutex_lock(&cli->mutex);
 	else
 		mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING);
+
 	ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, ctx->interruptible);
-	if (ret == 0) {
-		ret = drm->ttm.move(chan, bo, bo->resource, new_reg);
-		if (ret == 0) {
-			ret = nouveau_fence_new(chan, false, &fence);
-			if (ret == 0) {
-				/* TODO: figure out a better solution here
-				 *
-				 * wait on the fence here explicitly as going through
-				 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
-				 *
-				 * Without this the operation can timeout and we'll fallback to a
-				 * software copy, which might take several minutes to finish.
-				 */
-				nouveau_fence_wait(fence, false, false);
-				ret = ttm_bo_move_accel_cleanup(bo,
-								&fence->base,
-								evict, false,
-								new_reg);
-				nouveau_fence_unref(&fence);
-			}
-		}
+	if (ret)
+		goto out_unlock;
+
+	ret = drm->ttm.move(chan, bo, bo->resource, new_reg);
+	if (ret)
+		goto out_unlock;
+
+	ret = nouveau_fence_new(&fence);
+	if (ret)
+		goto out_unlock;
+
+	ret = nouveau_fence_emit(fence, chan);
+	if (ret) {
+		nouveau_fence_unref(&fence);
+		goto out_unlock;
 	}
+
+	/* TODO: figure out a better solution here
+	 *
+	 * wait on the fence here explicitly as going through
+	 * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+	 *
+	 * Without this the operation can timeout and we'll fallback to a
+	 * software copy, which might take several minutes to finish.
+	 */
+	nouveau_fence_wait(fence, false, false);
+	ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false,
+					new_reg);
+	nouveau_fence_unref(&fence);
+
+out_unlock:
 	mutex_unlock(&cli->mutex);
 	return ret;
 }
@@ -935,6 +994,7 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo,
 		list_for_each_entry(vma, &nvbo->vma_list, head) {
 			nouveau_vma_map(vma, mem);
 		}
+		nouveau_uvmm_bo_map_all(nvbo, mem);
 	} else {
 		list_for_each_entry(vma, &nvbo->vma_list, head) {
 			ret = dma_resv_wait_timeout(bo->base.resv,
@@ -943,6 +1003,7 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo,
 			WARN_ON(ret <= 0);
 			nouveau_vma_unmap(vma);
 		}
+		nouveau_uvmm_bo_unmap_all(nvbo);
 	}
 
 	if (new_reg)

drivers/gpu/drm/nouveau/nouveau_bo.h

@@ -26,6 +26,7 @@ struct nouveau_bo {
 	struct list_head entry;
 	int pbbo_index;
 	bool validate_mapped;
+	bool no_share;
 
 	/* GPU address space is independent of CPU word size */
 	uint64_t offset;
@@ -73,7 +74,7 @@ extern struct ttm_device_funcs nouveau_bo_driver;
 
 void nouveau_bo_move_init(struct nouveau_drm *);
 struct nouveau_bo *nouveau_bo_alloc(struct nouveau_cli *, u64 *size, int *align,
-				    u32 domain, u32 tile_mode, u32 tile_flags);
+				    u32 domain, u32 tile_mode, u32 tile_flags, bool internal);
 int  nouveau_bo_init(struct nouveau_bo *, u64 size, int align, u32 domain,
 		     struct sg_table *sg, struct dma_resv *robj);
 int  nouveau_bo_new(struct nouveau_cli *, u64 size, int align, u32 domain,

drivers/gpu/drm/nouveau/nouveau_chan.c

@@ -40,6 +40,14 @@ MODULE_PARM_DESC(vram_pushbuf, "Create DMA push buffers in VRAM");
 int nouveau_vram_pushbuf;
 module_param_named(vram_pushbuf, nouveau_vram_pushbuf, int, 0400);
 
+void
+nouveau_channel_kill(struct nouveau_channel *chan)
+{
+	atomic_set(&chan->killed, 1);
+	if (chan->fence)
+		nouveau_fence_context_kill(chan->fence, -ENODEV);
+}
+
 static int
 nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc)
 {
@@ -47,9 +55,9 @@ nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc)
 	struct nouveau_cli *cli = (void *)chan->user.client;
 
 	NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid);
-	atomic_set(&chan->killed, 1);
-	if (chan->fence)
-		nouveau_fence_context_kill(chan->fence, -ENODEV);
+
+	if (unlikely(!atomic_read(&chan->killed)))
+		nouveau_channel_kill(chan);
 
 	return NVIF_EVENT_DROP;
 }
@@ -62,9 +70,11 @@ nouveau_channel_idle(struct nouveau_channel *chan)
 		struct nouveau_fence *fence = NULL;
 		int ret;
 
-		ret = nouveau_fence_new(chan, false, &fence);
+		ret = nouveau_fence_new(&fence);
 		if (!ret) {
-			ret = nouveau_fence_wait(fence, false, false);
+			ret = nouveau_fence_emit(fence, chan);
+			if (!ret)
+				ret = nouveau_fence_wait(fence, false, false);
 			nouveau_fence_unref(&fence);
 		}
 
@@ -149,7 +159,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device,
 
 	chan->device = device;
 	chan->drm = drm;
-	chan->vmm = cli->svm.cli ? &cli->svm : &cli->vmm;
+	chan->vmm = nouveau_cli_vmm(cli);
 	atomic_set(&chan->killed, 0);
 
 	/* allocate memory for dma push buffer */

drivers/gpu/drm/nouveau/nouveau_chan.h

@@ -66,6 +66,7 @@ int  nouveau_channel_new(struct nouveau_drm *, struct nvif_device *, bool priv,
 			 u32 vram, u32 gart, struct nouveau_channel **);
 void nouveau_channel_del(struct nouveau_channel **);
 int  nouveau_channel_idle(struct nouveau_channel *);
+void nouveau_channel_kill(struct nouveau_channel *);
 
 extern int nouveau_vram_pushbuf;
 

drivers/gpu/drm/nouveau/nouveau_debugfs.c

@@ -203,6 +203,44 @@ nouveau_debugfs_pstate_open(struct inode *inode, struct file *file)
 	return single_open(file, nouveau_debugfs_pstate_get, inode->i_private);
 }
 
+static void
+nouveau_debugfs_gpuva_regions(struct seq_file *m, struct nouveau_uvmm *uvmm)
+{
+	MA_STATE(mas, &uvmm->region_mt, 0, 0);
+	struct nouveau_uvma_region *reg;
+
+	seq_puts  (m, " VA regions  | start              | range              | end                \n");
+	seq_puts  (m, "----------------------------------------------------------------------------\n");
+	mas_for_each(&mas, reg, ULONG_MAX)
+		seq_printf(m, "             | 0x%016llx | 0x%016llx | 0x%016llx\n",
+			   reg->va.addr, reg->va.range, reg->va.addr + reg->va.range);
+}
+
+static int
+nouveau_debugfs_gpuva(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct nouveau_drm *drm = nouveau_drm(node->minor->dev);
+	struct nouveau_cli *cli;
+
+	mutex_lock(&drm->clients_lock);
+	list_for_each_entry(cli, &drm->clients, head) {
+		struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli);
+
+		if (!uvmm)
+			continue;
+
+		nouveau_uvmm_lock(uvmm);
+		drm_debugfs_gpuva_info(m, &uvmm->umgr);
+		seq_puts(m, "\n");
+		nouveau_debugfs_gpuva_regions(m, uvmm);
+		nouveau_uvmm_unlock(uvmm);
+	}
+	mutex_unlock(&drm->clients_lock);
+
+	return 0;
+}
+
 static const struct file_operations nouveau_pstate_fops = {
 	.owner = THIS_MODULE,
 	.open = nouveau_debugfs_pstate_open,
@@ -214,6 +252,7 @@ static const struct file_operations nouveau_pstate_fops = {
 static struct drm_info_list nouveau_debugfs_list[] = {
 	{ "vbios.rom",  nouveau_debugfs_vbios_image, 0, NULL },
 	{ "strap_peek", nouveau_debugfs_strap_peek, 0, NULL },
+	DRM_DEBUGFS_GPUVA_INFO(nouveau_debugfs_gpuva, NULL),
 };
 #define NOUVEAU_DEBUGFS_ENTRIES ARRAY_SIZE(nouveau_debugfs_list)
 

drivers/gpu/drm/nouveau/nouveau_dmem.c

@@ -209,7 +209,8 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 		goto done;
 	}
 
-	nouveau_fence_new(dmem->migrate.chan, false, &fence);
+	if (!nouveau_fence_new(&fence))
+		nouveau_fence_emit(fence, dmem->migrate.chan);
 	migrate_vma_pages(&args);
 	nouveau_dmem_fence_done(&fence);
 	dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
@@ -402,7 +403,8 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
 		}
 	}
 
-	nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence);
+	if (!nouveau_fence_new(&fence))
+		nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan);
 	migrate_device_pages(src_pfns, dst_pfns, npages);
 	nouveau_dmem_fence_done(&fence);
 	migrate_device_finalize(src_pfns, dst_pfns, npages);
@@ -675,7 +677,8 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm,
 		addr += PAGE_SIZE;
 	}
 
-	nouveau_fence_new(drm->dmem->migrate.chan, false, &fence);
+	if (!nouveau_fence_new(&fence))
+		nouveau_fence_emit(fence, drm->dmem->migrate.chan);
 	migrate_vma_pages(args);
 	nouveau_dmem_fence_done(&fence);
 	nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i);

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -68,6 +68,9 @@
 #include "nouveau_platform.h"
 #include "nouveau_svm.h"
 #include "nouveau_dmem.h"
+#include "nouveau_exec.h"
+#include "nouveau_uvmm.h"
+#include "nouveau_sched.h"
 
 DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0,
 			"DRM_UT_CORE",
@@ -196,6 +199,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
 	WARN_ON(!list_empty(&cli->worker));
 
 	usif_client_fini(cli);
+	nouveau_uvmm_fini(&cli->uvmm);
+	nouveau_sched_entity_fini(&cli->sched_entity);
 	nouveau_vmm_fini(&cli->svm);
 	nouveau_vmm_fini(&cli->vmm);
 	nvif_mmu_dtor(&cli->mmu);
@@ -301,6 +306,12 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
 	}
 
 	cli->mem = &mems[ret];
+
+	ret = nouveau_sched_entity_init(&cli->sched_entity, &drm->sched,
+					drm->sched_wq);
+	if (ret)
+		goto done;
+
 	return 0;
 done:
 	if (ret)
@@ -568,10 +579,14 @@ nouveau_drm_device_init(struct drm_device *dev)
 	nvif_parent_ctor(&nouveau_parent, &drm->parent);
 	drm->master.base.object.parent = &drm->parent;
 
-	ret = nouveau_cli_init(drm, "DRM-master", &drm->master);
+	ret = nouveau_sched_init(drm);
 	if (ret)
 		goto fail_alloc;
 
+	ret = nouveau_cli_init(drm, "DRM-master", &drm->master);
+	if (ret)
+		goto fail_sched;
+
 	ret = nouveau_cli_init(drm, "DRM", &drm->client);
 	if (ret)
 		goto fail_master;
@@ -628,7 +643,6 @@ nouveau_drm_device_init(struct drm_device *dev)
 	}
 
 	return 0;
-
 fail_dispinit:
 	nouveau_display_destroy(dev);
 fail_dispctor:
@@ -641,6 +655,8 @@ nouveau_drm_device_init(struct drm_device *dev)
 	nouveau_cli_fini(&drm->client);
 fail_master:
 	nouveau_cli_fini(&drm->master);
+fail_sched:
+	nouveau_sched_fini(drm);
 fail_alloc:
 	nvif_parent_dtor(&drm->parent);
 	kfree(drm);
@@ -692,6 +708,8 @@ nouveau_drm_device_fini(struct drm_device *dev)
 	}
 	mutex_unlock(&drm->clients_lock);
 
+	nouveau_sched_fini(drm);
+
 	nouveau_cli_fini(&drm->client);
 	nouveau_cli_fini(&drm->master);
 	nvif_parent_dtor(&drm->parent);
@@ -1193,6 +1211,9 @@ nouveau_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_VM_INIT, nouveau_uvmm_ioctl_vm_init, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_VM_BIND, nouveau_uvmm_ioctl_vm_bind, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(NOUVEAU_EXEC, nouveau_exec_ioctl_exec, DRM_RENDER_ALLOW),
 };
 
 long
@@ -1240,6 +1261,8 @@ nouveau_driver_fops = {
 static struct drm_driver
 driver_stub = {
 	.driver_features = DRIVER_GEM |
+			   DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE |
+			   DRIVER_GEM_GPUVA |
 			   DRIVER_MODESET |
 			   DRIVER_RENDER,
 	.open = nouveau_drm_open,

drivers/gpu/drm/nouveau/nouveau_drv.h

@@ -10,8 +10,8 @@
 #define DRIVER_DATE		"20120801"
 
 #define DRIVER_MAJOR		1
-#define DRIVER_MINOR		3
-#define DRIVER_PATCHLEVEL	1
+#define DRIVER_MINOR		4
+#define DRIVER_PATCHLEVEL	0
 
 /*
  * 1.1.1:
@@ -63,7 +63,9 @@ struct platform_device;
 
 #include "nouveau_fence.h"
 #include "nouveau_bios.h"
+#include "nouveau_sched.h"
 #include "nouveau_vmm.h"
+#include "nouveau_uvmm.h"
 
 struct nouveau_drm_tile {
 	struct nouveau_fence *fence;
@@ -91,6 +93,10 @@ struct nouveau_cli {
 	struct nvif_mmu mmu;
 	struct nouveau_vmm vmm;
 	struct nouveau_vmm svm;
+	struct nouveau_uvmm uvmm;
+
+	struct nouveau_sched_entity sched_entity;
+
 	const struct nvif_mclass *mem;
 
 	struct list_head head;
@@ -112,6 +118,59 @@ struct nouveau_cli_work {
 	struct dma_fence_cb cb;
 };
 
+static inline struct nouveau_uvmm *
+nouveau_cli_uvmm(struct nouveau_cli *cli)
+{
+	if (!cli || !cli->uvmm.vmm.cli)
+		return NULL;
+
+	return &cli->uvmm;
+}
+
+static inline struct nouveau_uvmm *
+nouveau_cli_uvmm_locked(struct nouveau_cli *cli)
+{
+	struct nouveau_uvmm *uvmm;
+
+	mutex_lock(&cli->mutex);
+	uvmm = nouveau_cli_uvmm(cli);
+	mutex_unlock(&cli->mutex);
+
+	return uvmm;
+}
+
+static inline struct nouveau_vmm *
+nouveau_cli_vmm(struct nouveau_cli *cli)
+{
+	struct nouveau_uvmm *uvmm;
+
+	uvmm = nouveau_cli_uvmm(cli);
+	if (uvmm)
+		return &uvmm->vmm;
+
+	if (cli->svm.cli)
+		return &cli->svm;
+
+	return &cli->vmm;
+}
+
+static inline void
+__nouveau_cli_disable_uvmm_noinit(struct nouveau_cli *cli)
+{
+	struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli);
+
+	if (!uvmm)
+		cli->uvmm.disabled = true;
+}
+
+static inline void
+nouveau_cli_disable_uvmm_noinit(struct nouveau_cli *cli)
+{
+	mutex_lock(&cli->mutex);
+	__nouveau_cli_disable_uvmm_noinit(cli);
+	mutex_unlock(&cli->mutex);
+}
+
 void nouveau_cli_work_queue(struct nouveau_cli *, struct dma_fence *,
 			    struct nouveau_cli_work *);
 
@@ -121,6 +180,32 @@ nouveau_cli(struct drm_file *fpriv)
 	return fpriv ? fpriv->driver_priv : NULL;
 }
 
+static inline void
+u_free(void *addr)
+{
+	kvfree(addr);
+}
+
+static inline void *
+u_memcpya(uint64_t user, unsigned int nmemb, unsigned int size)
+{
+	void *mem;
+	void __user *userptr = (void __force __user *)(uintptr_t)user;
+
+	size *= nmemb;
+
+	mem = kvmalloc(size, GFP_KERNEL);
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(mem, userptr, size)) {
+		u_free(mem);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return mem;
+}
+
 #include <nvif/object.h>
 #include <nvif/parent.h>
 
@@ -222,6 +307,10 @@ struct nouveau_drm {
 		struct mutex lock;
 		bool component_registered;
 	} audio;
+
+	struct drm_gpu_scheduler sched;
+	struct workqueue_struct *sched_wq;
+
 };
 
 static inline struct nouveau_drm *

drivers/gpu/drm/nouveau/nouveau_exec.h

+/* SPDX-License-Identifier: MIT */
+
+#ifndef __NOUVEAU_EXEC_H__
+#define __NOUVEAU_EXEC_H__
+
+#include <drm/drm_exec.h>
+
+#include "nouveau_drv.h"
+#include "nouveau_sched.h"
+
+struct nouveau_exec_job_args {
+	struct drm_file *file_priv;
+	struct nouveau_sched_entity *sched_entity;
+
+	struct drm_exec exec;
+	struct nouveau_channel *chan;
+
+	struct {
+		struct drm_nouveau_sync *s;
+		u32 count;
+	} in_sync;
+
+	struct {
+		struct drm_nouveau_sync *s;
+		u32 count;
+	} out_sync;
+
+	struct {
+		struct drm_nouveau_exec_push *s;
+		u32 count;
+	} push;
+};
+
+struct nouveau_exec_job {
+	struct nouveau_job base;
+	struct nouveau_fence *fence;
+	struct nouveau_channel *chan;
+
+	struct {
+		struct drm_nouveau_exec_push *s;
+		u32 count;
+	} push;
+};
+
+#define to_nouveau_exec_job(job)		\
+		container_of((job), struct nouveau_exec_job, base)
+
+int nouveau_exec_job_init(struct nouveau_exec_job **job,
+			  struct nouveau_exec_job_args *args);
+
+int nouveau_exec_ioctl_exec(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv);
+
+#endif

drivers/gpu/drm/nouveau/nouveau_fence.h

@@ -17,8 +17,7 @@ struct nouveau_fence {
 	unsigned long timeout;
 };
 
-int  nouveau_fence_new(struct nouveau_channel *, bool sysmem,
-		       struct nouveau_fence **);
+int  nouveau_fence_new(struct nouveau_fence **);
 void nouveau_fence_unref(struct nouveau_fence **);
 
 int  nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *);
@@ -45,7 +44,7 @@ struct nouveau_fence_chan {
 	char name[32];
 
 	struct nvif_event event;
-	int notify_ref, dead;
+	int notify_ref, dead, killed;
 };
 
 struct nouveau_fence_priv {

drivers/gpu/drm/ttm/Makefile

@@ -8,3 +8,4 @@ ttm-y := ttm_tt.o ttm_bo.o ttm_bo_util.o ttm_bo_vm.o ttm_module.o \
 ttm-$(CONFIG_AGP) += ttm_agp_backend.o
 
 obj-$(CONFIG_DRM_TTM) += ttm.o
+obj-$(CONFIG_DRM_TTM_KUNIT_TEST) += tests/