Merge branch 'vmwgfx-next' of git://people.freedesktop.org/~thomash/linux into drm-next

- The coherent memory changes including mm changes.
- Some vmwgfx debug fixes.
- Removal of vmwgfx legacy security checks.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Thomas Hellstrom <VMware> <thomas@shipmail.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190619072531.4026-1-thomas@shipmail.org

MAINTAINERS

@@ -5191,6 +5191,7 @@ T:	git git://people.freedesktop.org/~thomash/linux
 S:	Supported
 F:	drivers/gpu/drm/vmwgfx/
 F:	include/uapi/drm/vmwgfx_drm.h
+F:	mm/as_dirty_helpers.c
 
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>

drivers/gpu/drm/ttm/ttm_bo.c

@@ -1739,6 +1739,7 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	mutex_lock(&ttm_global_mutex);
 	list_add_tail(&bdev->device_list, &glob->device_list);
 	mutex_unlock(&ttm_global_mutex);
+	bdev->vm_ops = &ttm_bo_vm_ops;
 
 	return 0;
 out_no_sys:

drivers/gpu/drm/ttm/ttm_bo_vm.c

@@ -42,8 +42,6 @@
 #include <linux/uaccess.h>
 #include <linux/mem_encrypt.h>
 
-#define TTM_BO_VM_NUM_PREFAULT 16
-
 static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_fault *vmf)
 {
@@ -106,25 +104,30 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
 		+ page_offset;
 }
 
-static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
+/**
+ * ttm_bo_vm_reserve - Reserve a buffer object in a retryable vm callback
+ * @bo: The buffer object
+ * @vmf: The fault structure handed to the callback
+ *
+ * vm callbacks like fault() and *_mkwrite() allow for the mm_sem to be dropped
+ * during long waits, and after the wait the callback will be restarted. This
+ * is to allow other threads using the same virtual memory space concurrent
+ * access to map(), unmap() completely unrelated buffer objects. TTM buffer
+ * object reservations sometimes wait for GPU and should therefore be
+ * considered long waits. This function reserves the buffer object interruptibly
+ * taking this into account. Starvation is avoided by the vm system not
+ * allowing too many repeated restarts.
+ * This function is intended to be used in customized fault() and _mkwrite()
+ * handlers.
+ *
+ * Return:
+ *    0 on success and the bo was reserved.
+ *    VM_FAULT_RETRY if blocking wait.
+ *    VM_FAULT_NOPAGE if blocking wait and retrying was not allowed.
+ */
+vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
+			     struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
-	    vma->vm_private_data;
-	struct ttm_bo_device *bdev = bo->bdev;
-	unsigned long page_offset;
-	unsigned long page_last;
-	unsigned long pfn;
-	struct ttm_tt *ttm = NULL;
-	struct page *page;
-	int err;
-	int i;
-	vm_fault_t ret = VM_FAULT_NOPAGE;
-	unsigned long address = vmf->address;
-	struct ttm_mem_type_manager *man =
-		&bdev->man[bo->mem.mem_type];
-	struct vm_area_struct cvma;
-
 	/*
 	 * Work around locking order reversal in fault / nopfn
 	 * between mmap_sem and bo_reserve: Perform a trylock operation
@@ -151,14 +154,55 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		return VM_FAULT_NOPAGE;
 	}
 
+	return 0;
+}
+EXPORT_SYMBOL(ttm_bo_vm_reserve);
+
+/**
+ * ttm_bo_vm_fault_reserved - TTM fault helper
+ * @vmf: The struct vm_fault given as argument to the fault callback
+ * @prot: The page protection to be used for this memory area.
+ * @num_prefault: Maximum number of prefault pages. The caller may want to
+ * specify this based on madvice settings and the size of the GPU object
+ * backed by the memory.
+ *
+ * This function inserts one or more page table entries pointing to the
+ * memory backing the buffer object, and then returns a return code
+ * instructing the caller to retry the page access.
+ *
+ * Return:
+ *   VM_FAULT_NOPAGE on success or pending signal
+ *   VM_FAULT_SIGBUS on unspecified error
+ *   VM_FAULT_OOM on out-of-memory
+ *   VM_FAULT_RETRY if retryable wait
+ */
+vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
+				    pgprot_t prot,
+				    pgoff_t num_prefault)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vm_area_struct cvma = *vma;
+	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
+	    vma->vm_private_data;
+	struct ttm_bo_device *bdev = bo->bdev;
+	unsigned long page_offset;
+	unsigned long page_last;
+	unsigned long pfn;
+	struct ttm_tt *ttm = NULL;
+	struct page *page;
+	int err;
+	pgoff_t i;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+	unsigned long address = vmf->address;
+	struct ttm_mem_type_manager *man =
+		&bdev->man[bo->mem.mem_type];
+
 	/*
 	 * Refuse to fault imported pages. This should be handled
 	 * (if at all) by redirecting mmap to the exporter.
 	 */
-	if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out_unlock;
-	}
+	if (bo->ttm && (bo->ttm->page_flags & TTM_PAGE_FLAG_SG))
+		return VM_FAULT_SIGBUS;
 
 	if (bdev->driver->fault_reserve_notify) {
 		struct dma_fence *moving = dma_fence_get(bo->moving);
@@ -169,11 +213,9 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 			break;
 		case -EBUSY:
 		case -ERESTARTSYS:
-			ret = VM_FAULT_NOPAGE;
-			goto out_unlock;
+			return VM_FAULT_NOPAGE;
 		default:
-			ret = VM_FAULT_SIGBUS;
-			goto out_unlock;
+			return VM_FAULT_SIGBUS;
 		}
 
 		if (bo->moving != moving) {
@@ -189,21 +231,12 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 	 * move.
 	 */
 	ret = ttm_bo_vm_fault_idle(bo, vmf);
-	if (unlikely(ret != 0)) {
-		if (ret == VM_FAULT_RETRY &&
-		    !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-			/* The BO has already been unreserved. */
+	if (unlikely(ret != 0))
 		return ret;
-		}
-
-		goto out_unlock;
-	}
 
 	err = ttm_mem_io_lock(man, true);
-	if (unlikely(err != 0)) {
-		ret = VM_FAULT_NOPAGE;
-		goto out_unlock;
-	}
+	if (unlikely(err != 0))
+		return VM_FAULT_NOPAGE;
 	err = ttm_mem_io_reserve_vm(bo);
 	if (unlikely(err != 0)) {
 		ret = VM_FAULT_SIGBUS;
@@ -220,18 +253,8 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		goto out_io_unlock;
 	}
 
-	/*
-	 * Make a local vma copy to modify the page_prot member
-	 * and vm_flags if necessary. The vma parameter is protected
-	 * by mmap_sem in write mode.
-	 */
-	cvma = *vma;
-	cvma.vm_page_prot = vm_get_page_prot(cvma.vm_flags);
-
-	if (bo->mem.bus.is_iomem) {
-		cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
-						cvma.vm_page_prot);
-	} else {
+	cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, prot);
+	if (!bo->mem.bus.is_iomem) {
 		struct ttm_operation_ctx ctx = {
 			.interruptible = false,
 			.no_wait_gpu = false,
@@ -240,24 +263,21 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		};
 
 		ttm = bo->ttm;
-		cvma.vm_page_prot = ttm_io_prot(bo->mem.placement,
-						cvma.vm_page_prot);
-
-		/* Allocate all page at once, most common usage */
-		if (ttm_tt_populate(ttm, &ctx)) {
+		if (ttm_tt_populate(bo->ttm, &ctx)) {
 			ret = VM_FAULT_OOM;
 			goto out_io_unlock;
 		}
+	} else {
+		/* Iomem should not be marked encrypted */
+		cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot);
 	}
 
 	/*
 	 * Speculatively prefault a number of pages. Only error on
 	 * first page.
 	 */
-	for (i = 0; i < TTM_BO_VM_NUM_PREFAULT; ++i) {
+	for (i = 0; i < num_prefault; ++i) {
 		if (bo->mem.bus.is_iomem) {
-			/* Iomem should not be marked encrypted */
-			cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot);
 			pfn = ttm_bo_io_mem_pfn(bo, page_offset);
 		} else {
 			page = ttm->pages[page_offset];
@@ -295,7 +315,26 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 	ret = VM_FAULT_NOPAGE;
 out_io_unlock:
 	ttm_mem_io_unlock(man);
-out_unlock:
+	return ret;
+}
+EXPORT_SYMBOL(ttm_bo_vm_fault_reserved);
+
+static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	pgprot_t prot;
+	struct ttm_buffer_object *bo = vma->vm_private_data;
+	vm_fault_t ret;
+
+	ret = ttm_bo_vm_reserve(bo, vmf);
+	if (ret)
+		return ret;
+
+	prot = vm_get_page_prot(vma->vm_flags);
+	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
+	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
+		return ret;
+
 	reservation_object_unlock(bo->resv);
 	return ret;
 }
@@ -395,7 +434,7 @@ static int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 	return ret;
 }
 
-static const struct vm_operations_struct ttm_bo_vm_ops = {
+const struct vm_operations_struct ttm_bo_vm_ops = {
 	.fault = ttm_bo_vm_fault,
 	.open = ttm_bo_vm_open,
 	.close = ttm_bo_vm_close,
@@ -448,7 +487,7 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 	if (unlikely(ret != 0))
 		goto out_unref;
 
-	vma->vm_ops = &ttm_bo_vm_ops;
+	vma->vm_ops = bdev->vm_ops;
 
 	/*
 	 * Note: We're transferring the bo reference to
@@ -480,7 +519,7 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 
 	ttm_bo_get(bo);
 
-	vma->vm_ops = &ttm_bo_vm_ops;
+	vma->vm_ops = bo->bdev->vm_ops;
 	vma->vm_private_data = bo;
 	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;

drivers/gpu/drm/vmwgfx/Kconfig

@@ -8,6 +8,7 @@ config DRM_VMWGFX
 	select FB_CFB_IMAGEBLIT
 	select DRM_TTM
 	select FB
+	select AS_DIRTY_HELPERS
 	# Only needed for the transitional use of drm_crtc_init - can be removed
 	# again once vmwgfx sets up the primary plane itself.
 	select DRM_KMS_HELPER

drivers/gpu/drm/vmwgfx/Makefile

@@ -8,7 +8,7 @@ vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \
 	    vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \
 	    vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \
 	    vmwgfx_simple_resource.o vmwgfx_va.o vmwgfx_blit.o \
-	    vmwgfx_validation.o \
+	    vmwgfx_validation.o vmwgfx_page_dirty.o \
 	    ttm_object.o ttm_lock.o
 
 obj-$(CONFIG_DRM_VMWGFX) := vmwgfx.o

drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h

@@ -1280,7 +1280,6 @@ svga3dsurface_get_pixel_offset(SVGA3dSurfaceFormat format,
 	return offset;
 }
 
-
 static inline u32
 svga3dsurface_get_image_offset(SVGA3dSurfaceFormat format,
 			       surf_size_struct baseLevelSize,
@@ -1375,4 +1374,236 @@ svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format)
 	return svga3dsurface_is_dx_screen_target_format(format);
 }
 
+/**
+ * struct svga3dsurface_mip - Mimpmap level information
+ * @bytes: Bytes required in the backing store of this mipmap level.
+ * @img_stride: Byte stride per image.
+ * @row_stride: Byte stride per block row.
+ * @size: The size of the mipmap.
+ */
+struct svga3dsurface_mip {
+	size_t bytes;
+	size_t img_stride;
+	size_t row_stride;
+	struct drm_vmw_size size;
+
+};
+
+/**
+ * struct svga3dsurface_cache - Cached surface information
+ * @desc: Pointer to the surface descriptor
+ * @mip: Array of mipmap level information. Valid size is @num_mip_levels.
+ * @mip_chain_bytes: Bytes required in the backing store for the whole chain
+ * of mip levels.
+ * @sheet_bytes: Bytes required in the backing store for a sheet
+ * representing a single sample.
+ * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in
+ * a chain.
+ * @num_layers: Number of slices in an array texture or number of faces in
+ * a cubemap texture.
+ */
+struct svga3dsurface_cache {
+	const struct svga3d_surface_desc *desc;
+	struct svga3dsurface_mip mip[DRM_VMW_MAX_MIP_LEVELS];
+	size_t mip_chain_bytes;
+	size_t sheet_bytes;
+	u32 num_mip_levels;
+	u32 num_layers;
+};
+
+/**
+ * struct svga3dsurface_loc - Surface location
+ * @sub_resource: Surface subresource. Defined as layer * num_mip_levels +
+ * mip_level.
+ * @x: X coordinate.
+ * @y: Y coordinate.
+ * @z: Z coordinate.
+ */
+struct svga3dsurface_loc {
+	u32 sub_resource;
+	u32 x, y, z;
+};
+
+/**
+ * svga3dsurface_subres - Compute the subresource from layer and mipmap.
+ * @cache: Surface layout data.
+ * @mip_level: The mipmap level.
+ * @layer: The surface layer (face or array slice).
+ *
+ * Return: The subresource.
+ */
+static inline u32 svga3dsurface_subres(const struct svga3dsurface_cache *cache,
+				       u32 mip_level, u32 layer)
+{
+	return cache->num_mip_levels * layer + mip_level;
+}
+
+/**
+ * svga3dsurface_setup_cache - Build a surface cache entry
+ * @size: The surface base level dimensions.
+ * @format: The surface format.
+ * @num_mip_levels: Number of mipmap levels.
+ * @num_layers: Number of layers.
+ * @cache: Pointer to a struct svga3dsurface_cach object to be filled in.
+ *
+ * Return: Zero on success, -EINVAL on invalid surface layout.
+ */
+static inline int svga3dsurface_setup_cache(const struct drm_vmw_size *size,
+					    SVGA3dSurfaceFormat format,
+					    u32 num_mip_levels,
+					    u32 num_layers,
+					    u32 num_samples,
+					    struct svga3dsurface_cache *cache)
+{
+	const struct svga3d_surface_desc *desc;
+	u32 i;
+
+	memset(cache, 0, sizeof(*cache));
+	cache->desc = desc = svga3dsurface_get_desc(format);
+	cache->num_mip_levels = num_mip_levels;
+	cache->num_layers = num_layers;
+	for (i = 0; i < cache->num_mip_levels; i++) {
+		struct svga3dsurface_mip *mip = &cache->mip[i];
+
+		mip->size = svga3dsurface_get_mip_size(*size, i);
+		mip->bytes = svga3dsurface_get_image_buffer_size
+			(desc, &mip->size, 0);
+		mip->row_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.width,
+					      desc->block_size.width) *
+			desc->bytes_per_block * num_samples;
+		if (!mip->row_stride)
+			goto invalid_dim;
+
+		mip->img_stride =
+			__KERNEL_DIV_ROUND_UP(mip->size.height,
+					      desc->block_size.height) *
+			mip->row_stride;
+		if (!mip->img_stride)
+			goto invalid_dim;
+
+		cache->mip_chain_bytes += mip->bytes;
+	}
+	cache->sheet_bytes = cache->mip_chain_bytes * num_layers;
+	if (!cache->sheet_bytes)
+		goto invalid_dim;
+
+	return 0;
+
+invalid_dim:
+	VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n");
+	return -EINVAL;
+}
+
+/**
+ * svga3dsurface_get_loc - Get a surface location from an offset into the
+ * backing store
+ * @cache: Surface layout data.
+ * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
+ * @offset: Offset into the surface backing store.
+ */
+static inline void
+svga3dsurface_get_loc(const struct svga3dsurface_cache *cache,
+		      struct svga3dsurface_loc *loc,
+		      size_t offset)
+{
+	const struct svga3dsurface_mip *mip = &cache->mip[0];
+	const struct svga3d_surface_desc *desc = cache->desc;
+	u32 layer;
+	int i;
+
+	if (offset >= cache->sheet_bytes)
+		offset %= cache->sheet_bytes;
+
+	layer = offset / cache->mip_chain_bytes;
+	offset -= layer * cache->mip_chain_bytes;
+	for (i = 0; i < cache->num_mip_levels; ++i, ++mip) {
+		if (mip->bytes > offset)
+			break;
+		offset -= mip->bytes;
+	}
+
+	loc->sub_resource = svga3dsurface_subres(cache, i, layer);
+	loc->z = offset / mip->img_stride;
+	offset -= loc->z * mip->img_stride;
+	loc->z *= desc->block_size.depth;
+	loc->y = offset / mip->row_stride;
+	offset -= loc->y * mip->row_stride;
+	loc->y *= desc->block_size.height;
+	loc->x = offset / desc->bytes_per_block;
+	loc->x *= desc->block_size.width;
+}
+
+/**
+ * svga3dsurface_inc_loc - Clamp increment a surface location with one block
+ * size
+ * in each dimension.
+ * @loc: Pointer to a struct svga3dsurface_loc to be incremented.
+ *
+ * When computing the size of a range as size = end - start, the range does not
+ * include the end element. However a location representing the last byte
+ * of a touched region in the backing store *is* included in the range.
+ * This function modifies such a location to match the end definition
+ * given as start + size which is the one used in a SVGA3dBox.
+ */
+static inline void
+svga3dsurface_inc_loc(const struct svga3dsurface_cache *cache,
+		      struct svga3dsurface_loc *loc)
+{
+	const struct svga3d_surface_desc *desc = cache->desc;
+	u32 mip = loc->sub_resource % cache->num_mip_levels;
+	const struct drm_vmw_size *size = &cache->mip[mip].size;
+
+	loc->sub_resource++;
+	loc->x += desc->block_size.width;
+	if (loc->x > size->width)
+		loc->x = size->width;
+	loc->y += desc->block_size.height;
+	if (loc->y > size->height)
+		loc->y = size->height;
+	loc->z += desc->block_size.depth;
+	if (loc->z > size->depth)
+		loc->z = size->depth;
+}
+
+/**
+ * svga3dsurface_min_loc - The start location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
+ */
+static inline void
+svga3dsurface_min_loc(const struct svga3dsurface_cache *cache,
+		      u32 sub_resource,
+		      struct svga3dsurface_loc *loc)
+{
+	loc->sub_resource = sub_resource;
+	loc->x = loc->y = loc->z = 0;
+}
+
+/**
+ * svga3dsurface_min_loc - The end location in a subresource
+ * @cache: Surface layout data.
+ * @sub_resource: The subresource.
+ * @loc: Pointer to a struct svga3dsurface_loc to be filled in.
+ *
+ * Following the end definition given in svga3dsurface_inc_loc(),
+ * Compute the end location of a surface subresource.
+ */
+static inline void
+svga3dsurface_max_loc(const struct svga3dsurface_cache *cache,
+		      u32 sub_resource,
+		      struct svga3dsurface_loc *loc)
+{
+	const struct drm_vmw_size *size;
+	u32 mip;
+
+	loc->sub_resource = sub_resource + 1;
+	mip = sub_resource % cache->num_mip_levels;
+	size = &cache->mip[mip].size;
+	loc->x = size->width;
+	loc->y = size->height;
+	loc->z = size->depth;
+}
+
 #endif /* _SVGA3D_SURFACEDEFS_H_ */

drivers/gpu/drm/vmwgfx/ttm_lock.c

@@ -29,7 +29,6 @@
  * Authors: Thomas Hellstrom <thellstrom-at-vmware-dot-com>
  */
 
-#include <drm/ttm/ttm_module.h>
 #include <linux/atomic.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
@@ -49,8 +48,6 @@ void ttm_lock_init(struct ttm_lock *lock)
 	init_waitqueue_head(&lock->queue);
 	lock->rw = 0;
 	lock->flags = 0;
-	lock->kill_takers = false;
-	lock->signal = SIGKILL;
 }
 
 void ttm_read_unlock(struct ttm_lock *lock)
@@ -66,11 +63,6 @@ static bool __ttm_read_lock(struct ttm_lock *lock)
 	bool locked = false;
 
 	spin_lock(&lock->lock);
-	if (unlikely(lock->kill_takers)) {
-		send_sig(lock->signal, current, 0);
-		spin_unlock(&lock->lock);
-		return false;
-	}
 	if (lock->rw >= 0 && lock->flags == 0) {
 		++lock->rw;
 		locked = true;
@@ -98,11 +90,6 @@ static bool __ttm_read_trylock(struct ttm_lock *lock, bool *locked)
 	*locked = false;
 
 	spin_lock(&lock->lock);
-	if (unlikely(lock->kill_takers)) {
-		send_sig(lock->signal, current, 0);
-		spin_unlock(&lock->lock);
-		return false;
-	}
 	if (lock->rw >= 0 && lock->flags == 0) {
 		++lock->rw;
 		block = false;
@@ -147,11 +134,6 @@ static bool __ttm_write_lock(struct ttm_lock *lock)
 	bool locked = false;
 
 	spin_lock(&lock->lock);
-	if (unlikely(lock->kill_takers)) {
-		send_sig(lock->signal, current, 0);
-		spin_unlock(&lock->lock);
-		return false;
-	}
 	if (lock->rw == 0 && ((lock->flags & ~TTM_WRITE_LOCK_PENDING) == 0)) {
 		lock->rw = -1;
 		lock->flags &= ~TTM_WRITE_LOCK_PENDING;
@@ -182,88 +164,6 @@ int ttm_write_lock(struct ttm_lock *lock, bool interruptible)
 	return ret;
 }
 
-static int __ttm_vt_unlock(struct ttm_lock *lock)
-{
-	int ret = 0;
-
-	spin_lock(&lock->lock);
-	if (unlikely(!(lock->flags & TTM_VT_LOCK)))
-		ret = -EINVAL;
-	lock->flags &= ~TTM_VT_LOCK;
-	wake_up_all(&lock->queue);
-	spin_unlock(&lock->lock);
-
-	return ret;
-}
-
-static void ttm_vt_lock_remove(struct ttm_base_object **p_base)
-{
-	struct ttm_base_object *base = *p_base;
-	struct ttm_lock *lock = container_of(base, struct ttm_lock, base);
-	int ret;
-
-	*p_base = NULL;
-	ret = __ttm_vt_unlock(lock);
-	BUG_ON(ret != 0);
-}
-
-static bool __ttm_vt_lock(struct ttm_lock *lock)
-{
-	bool locked = false;
-
-	spin_lock(&lock->lock);
-	if (lock->rw == 0) {
-		lock->flags &= ~TTM_VT_LOCK_PENDING;
-		lock->flags |= TTM_VT_LOCK;
-		locked = true;
-	} else {
-		lock->flags |= TTM_VT_LOCK_PENDING;
-	}
-	spin_unlock(&lock->lock);
-	return locked;
-}
-
-int ttm_vt_lock(struct ttm_lock *lock,
-		bool interruptible,
-		struct ttm_object_file *tfile)
-{
-	int ret = 0;
-
-	if (interruptible) {
-		ret = wait_event_interruptible(lock->queue,
-					       __ttm_vt_lock(lock));
-		if (unlikely(ret != 0)) {
-			spin_lock(&lock->lock);
-			lock->flags &= ~TTM_VT_LOCK_PENDING;
-			wake_up_all(&lock->queue);
-			spin_unlock(&lock->lock);
-			return ret;
-		}
-	} else
-		wait_event(lock->queue, __ttm_vt_lock(lock));
-
-	/*
-	 * Add a base-object, the destructor of which will
-	 * make sure the lock is released if the client dies
-	 * while holding it.
-	 */
-
-	ret = ttm_base_object_init(tfile, &lock->base, false,
-				   ttm_lock_type, &ttm_vt_lock_remove, NULL);
-	if (ret)
-		(void)__ttm_vt_unlock(lock);
-	else
-		lock->vt_holder = tfile;
-
-	return ret;
-}
-
-int ttm_vt_unlock(struct ttm_lock *lock)
-{
-	return ttm_ref_object_base_unref(lock->vt_holder,
-					 lock->base.handle, TTM_REF_USAGE);
-}
-
 void ttm_suspend_unlock(struct ttm_lock *lock)
 {
 	spin_lock(&lock->lock);

drivers/gpu/drm/vmwgfx/ttm_lock.h

@@ -63,8 +63,6 @@
  * @lock: Spinlock protecting some lock members.
  * @rw: Read-write lock counter. Protected by @lock.
  * @flags: Lock state. Protected by @lock.
- * @kill_takers: Boolean whether to kill takers of the lock.
- * @signal: Signal to send when kill_takers is true.
  */
 
 struct ttm_lock {
@@ -73,9 +71,6 @@ struct ttm_lock {
 	spinlock_t lock;
 	int32_t rw;
 	uint32_t flags;
-	bool kill_takers;
-	int signal;
-	struct ttm_object_file *vt_holder;
 };
 
 
@@ -220,29 +215,4 @@ extern void ttm_write_unlock(struct ttm_lock *lock);
  */
 extern int ttm_write_lock(struct ttm_lock *lock, bool interruptible);
 
-/**
- * ttm_lock_set_kill
- *
- * @lock: Pointer to a struct ttm_lock
- * @val: Boolean whether to kill processes taking the lock.
- * @signal: Signal to send to the process taking the lock.
- *
- * The kill-when-taking-lock functionality is used to kill processes that keep
- * on using the TTM functionality when its resources has been taken down, for
- * example when the X server exits. A typical sequence would look like this:
- * - X server takes lock in write mode.
- * - ttm_lock_set_kill() is called with @val set to true.
- * - As part of X server exit, TTM resources are taken down.
- * - X server releases the lock on file release.
- * - Another dri client wants to render, takes the lock and is killed.
- *
- */
-static inline void ttm_lock_set_kill(struct ttm_lock *lock, bool val,
-				     int signal)
-{
-	lock->kill_takers = val;
-	if (val)
-		lock->signal = signal;
-}
-
 #endif

drivers/gpu/drm/vmwgfx/vmwgfx_bo.c

@@ -463,6 +463,8 @@ void vmw_bo_bo_free(struct ttm_buffer_object *bo)
 {
 	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
 
+	WARN_ON(vmw_bo->dirty);
+	WARN_ON(!RB_EMPTY_ROOT(&vmw_bo->res_tree));
 	vmw_bo_unmap(vmw_bo);
 	kfree(vmw_bo);
 }
@@ -476,8 +478,11 @@ void vmw_bo_bo_free(struct ttm_buffer_object *bo)
 static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
 {
 	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
+	struct vmw_buffer_object *vbo = &vmw_user_bo->vbo;
 
-	vmw_bo_unmap(&vmw_user_bo->vbo);
+	WARN_ON(vbo->dirty);
+	WARN_ON(!RB_EMPTY_ROOT(&vbo->res_tree));
+	vmw_bo_unmap(vbo);
 	ttm_prime_object_kfree(vmw_user_bo, prime);
 }
 
@@ -510,8 +515,9 @@ int vmw_bo_init(struct vmw_private *dev_priv,
 
 	acc_size = vmw_bo_acc_size(dev_priv, size, user);
 	memset(vmw_bo, 0, sizeof(*vmw_bo));
-
-	INIT_LIST_HEAD(&vmw_bo->res_list);
+	BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3);
+	vmw_bo->base.priority = 3;
+	vmw_bo->res_tree = RB_ROOT;
 
 	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
 			  ttm_bo_type_device, placement,

drivers/gpu/drm/vmwgfx/vmwgfx_context.c

@@ -88,6 +88,8 @@ static const struct vmw_res_func vmw_gb_context_func = {
 	.res_type = vmw_res_context,
 	.needs_backup = true,
 	.may_evict = true,
+	.prio = 3,
+	.dirty_prio = 3,
 	.type_name = "guest backed contexts",
 	.backup_placement = &vmw_mob_placement,
 	.create = vmw_gb_context_create,
@@ -100,6 +102,8 @@ static const struct vmw_res_func vmw_dx_context_func = {
 	.res_type = vmw_res_dx_context,
 	.needs_backup = true,
 	.may_evict = true,
+	.prio = 3,
+	.dirty_prio = 3,
 	.type_name = "dx contexts",
 	.backup_placement = &vmw_mob_placement,
 	.create = vmw_dx_context_create,

drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c

@@ -116,6 +116,8 @@ static const struct vmw_res_func vmw_cotable_func = {
 	.res_type = vmw_res_cotable,
 	.needs_backup = true,
 	.may_evict = true,
+	.prio = 3,
+	.dirty_prio = 3,
 	.type_name = "context guest backed object tables",
 	.backup_placement = &vmw_mob_placement,
 	.create = vmw_cotable_create,
@@ -307,7 +309,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 	struct ttm_buffer_object *bo = val_buf->bo;
 	struct vmw_fence_obj *fence;
 
-	if (list_empty(&res->mob_head))
+	if (!vmw_resource_mob_attached(res))
 		return 0;
 
 	WARN_ON_ONCE(bo->mem.mem_type != VMW_PL_MOB);
@@ -453,6 +455,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 		goto out_wait;
 	}
 
+	vmw_resource_mob_detach(res);
 	res->backup = buf;
 	res->backup_size = new_size;
 	vcotbl->size_read_back = cur_size_read_back;
@@ -467,12 +470,12 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 		res->backup = old_buf;
 		res->backup_size = old_size;
 		vcotbl->size_read_back = old_size_read_back;
+		vmw_resource_mob_attach(res);
 		goto out_wait;
 	}
 
+	vmw_resource_mob_attach(res);
 	/* Let go of the old mob. */
-	list_del(&res->mob_head);
-	list_add_tail(&res->mob_head, &buf->res_list);
 	vmw_bo_unreference(&old_buf);
 	res->id = vcotbl->type;
 
@@ -496,7 +499,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
  * is called before bind() in the validation sequence is instead used for two
  * things.
  * 1) Unscrub the cotable if it is scrubbed and still attached to a backup
- *    buffer, that is, if @res->mob_head is non-empty.
+ *    buffer.
  * 2) Resize the cotable if needed.
  */
 static int vmw_cotable_create(struct vmw_resource *res)
@@ -512,7 +515,7 @@ static int vmw_cotable_create(struct vmw_resource *res)
 		new_size *= 2;
 
 	if (likely(new_size <= res->backup_size)) {
-		if (vcotbl->scrubbed && !list_empty(&res->mob_head)) {
+		if (vcotbl->scrubbed && vmw_resource_mob_attached(res)) {
 			ret = vmw_cotable_unscrub(res);
 			if (ret)
 				return ret;

drivers/gpu/drm/vmwgfx/vmwgfx_drv.c

@@ -254,7 +254,6 @@ static int vmw_restrict_dma_mask;
 static int vmw_assume_16bpp;
 
 static int vmw_probe(struct pci_dev *, const struct pci_device_id *);
-static void vmw_master_init(struct vmw_master *);
 static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
 			      void *ptr);
 
@@ -762,10 +761,6 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	DRM_INFO("MMIO at 0x%08x size is %u kiB\n",
 		 dev_priv->mmio_start, dev_priv->mmio_size / 1024);
 
-	vmw_master_init(&dev_priv->fbdev_master);
-	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
-	dev_priv->active_master = &dev_priv->fbdev_master;
-
 	dev_priv->mmio_virt = memremap(dev_priv->mmio_start,
 				       dev_priv->mmio_size, MEMREMAP_WB);
 
@@ -833,6 +828,11 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		DRM_ERROR("Failed initializing TTM buffer object driver.\n");
 		goto out_no_bdev;
 	}
+	dev_priv->vm_ops = *dev_priv->bdev.vm_ops;
+	dev_priv->vm_ops.fault = vmw_bo_vm_fault;
+	dev_priv->vm_ops.pfn_mkwrite = vmw_bo_vm_mkwrite;
+	dev_priv->vm_ops.page_mkwrite = vmw_bo_vm_mkwrite;
+	dev_priv->bdev.vm_ops = &dev_priv->vm_ops;
 
 	/*
 	 * Enable VRAM, but initially don't use it until SVGA is enabled and
@@ -1007,18 +1007,7 @@ static void vmw_driver_unload(struct drm_device *dev)
 static void vmw_postclose(struct drm_device *dev,
 			 struct drm_file *file_priv)
 {
-	struct vmw_fpriv *vmw_fp;
-
-	vmw_fp = vmw_fpriv(file_priv);
-
-	if (vmw_fp->locked_master) {
-		struct vmw_master *vmaster =
-			vmw_master(vmw_fp->locked_master);
-
-		ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
-		ttm_vt_unlock(&vmaster->lock);
-		drm_master_put(&vmw_fp->locked_master);
-	}
+	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
 
 	ttm_object_file_release(&vmw_fp->tfile);
 	kfree(vmw_fp);
@@ -1047,55 +1036,6 @@ static int vmw_driver_open(struct drm_device *dev, struct drm_file *file_priv)
 	return ret;
 }
 
-static struct vmw_master *vmw_master_check(struct drm_device *dev,
-					   struct drm_file *file_priv,
-					   unsigned int flags)
-{
-	int ret;
-	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
-	struct vmw_master *vmaster;
-
-	if (!drm_is_primary_client(file_priv) || !(flags & DRM_AUTH))
-		return NULL;
-
-	ret = mutex_lock_interruptible(&dev->master_mutex);
-	if (unlikely(ret != 0))
-		return ERR_PTR(-ERESTARTSYS);
-
-	if (drm_is_current_master(file_priv)) {
-		mutex_unlock(&dev->master_mutex);
-		return NULL;
-	}
-
-	/*
-	 * Check if we were previously master, but now dropped. In that
-	 * case, allow at least render node functionality.
-	 */
-	if (vmw_fp->locked_master) {
-		mutex_unlock(&dev->master_mutex);
-
-		if (flags & DRM_RENDER_ALLOW)
-			return NULL;
-
-		DRM_ERROR("Dropped master trying to access ioctl that "
-			  "requires authentication.\n");
-		return ERR_PTR(-EACCES);
-	}
-	mutex_unlock(&dev->master_mutex);
-
-	/*
-	 * Take the TTM lock. Possibly sleep waiting for the authenticating
-	 * master to become master again, or for a SIGTERM if the
-	 * authenticating master exits.
-	 */
-	vmaster = vmw_master(file_priv->master);
-	ret = ttm_read_lock(&vmaster->lock, true);
-	if (unlikely(ret != 0))
-		vmaster = ERR_PTR(ret);
-
-	return vmaster;
-}
-
 static long vmw_generic_ioctl(struct file *filp, unsigned int cmd,
 			      unsigned long arg,
 			      long (*ioctl_func)(struct file *, unsigned int,
@@ -1104,7 +1044,6 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd,
 	struct drm_file *file_priv = filp->private_data;
 	struct drm_device *dev = file_priv->minor->dev;
 	unsigned int nr = DRM_IOCTL_NR(cmd);
-	struct vmw_master *vmaster;
 	unsigned int flags;
 	long ret;
 
@@ -1140,21 +1079,7 @@ static long vmw_generic_ioctl(struct file *filp, unsigned int cmd,
 	} else if (!drm_ioctl_flags(nr, &flags))
 		return -EINVAL;
 
-	vmaster = vmw_master_check(dev, file_priv, flags);
-	if (IS_ERR(vmaster)) {
-		ret = PTR_ERR(vmaster);
-
-		if (ret != -ERESTARTSYS)
-			DRM_INFO("IOCTL ERROR Command %d, Error %ld.\n",
-				 nr, ret);
-		return ret;
-	}
-
-	ret = ioctl_func(filp, cmd, arg);
-	if (vmaster)
-		ttm_read_unlock(&vmaster->lock);
-
-	return ret;
+	return ioctl_func(filp, cmd, arg);
 
 out_io_encoding:
 	DRM_ERROR("Invalid command format, ioctl %d\n",
@@ -1181,65 +1106,10 @@ static void vmw_lastclose(struct drm_device *dev)
 {
 }
 
-static void vmw_master_init(struct vmw_master *vmaster)
-{
-	ttm_lock_init(&vmaster->lock);
-}
-
-static int vmw_master_create(struct drm_device *dev,
-			     struct drm_master *master)
-{
-	struct vmw_master *vmaster;
-
-	vmaster = kzalloc(sizeof(*vmaster), GFP_KERNEL);
-	if (unlikely(!vmaster))
-		return -ENOMEM;
-
-	vmw_master_init(vmaster);
-	ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
-	master->driver_priv = vmaster;
-
-	return 0;
-}
-
-static void vmw_master_destroy(struct drm_device *dev,
-			       struct drm_master *master)
-{
-	struct vmw_master *vmaster = vmw_master(master);
-
-	master->driver_priv = NULL;
-	kfree(vmaster);
-}
-
 static int vmw_master_set(struct drm_device *dev,
 			  struct drm_file *file_priv,
 			  bool from_open)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
-	struct vmw_master *active = dev_priv->active_master;
-	struct vmw_master *vmaster = vmw_master(file_priv->master);
-	int ret = 0;
-
-	if (active) {
-		BUG_ON(active != &dev_priv->fbdev_master);
-		ret = ttm_vt_lock(&active->lock, false, vmw_fp->tfile);
-		if (unlikely(ret != 0))
-			return ret;
-
-		ttm_lock_set_kill(&active->lock, true, SIGTERM);
-		dev_priv->active_master = NULL;
-	}
-
-	ttm_lock_set_kill(&vmaster->lock, false, SIGTERM);
-	if (!from_open) {
-		ttm_vt_unlock(&vmaster->lock);
-		BUG_ON(vmw_fp->locked_master != file_priv->master);
-		drm_master_put(&vmw_fp->locked_master);
-	}
-
-	dev_priv->active_master = vmaster;
-
 	/*
 	 * Inform a new master that the layout may have changed while
 	 * it was gone.
@@ -1254,31 +1124,10 @@ static void vmw_master_drop(struct drm_device *dev,
 			    struct drm_file *file_priv)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
-	struct vmw_master *vmaster = vmw_master(file_priv->master);
-	int ret;
-
-	/**
-	 * Make sure the master doesn't disappear while we have
-	 * it locked.
-	 */
 
-	vmw_fp->locked_master = drm_master_get(file_priv->master);
-	ret = ttm_vt_lock(&vmaster->lock, false, vmw_fp->tfile);
 	vmw_kms_legacy_hotspot_clear(dev_priv);
-	if (unlikely((ret != 0))) {
-		DRM_ERROR("Unable to lock TTM at VT switch.\n");
-		drm_master_put(&vmw_fp->locked_master);
-	}
-
-	ttm_lock_set_kill(&vmaster->lock, false, SIGTERM);
-
 	if (!dev_priv->enable_fb)
 		vmw_svga_disable(dev_priv);
-
-	dev_priv->active_master = &dev_priv->fbdev_master;
-	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
-	ttm_vt_unlock(&dev_priv->fbdev_master.lock);
 }
 
 /**
@@ -1557,8 +1406,6 @@ static struct drm_driver driver = {
 	.disable_vblank = vmw_disable_vblank,
 	.ioctls = vmw_ioctls,
 	.num_ioctls = ARRAY_SIZE(vmw_ioctls),
-	.master_create = vmw_master_create,
-	.master_destroy = vmw_master_destroy,
 	.master_set = vmw_master_set,
 	.master_drop = vmw_master_drop,
 	.open = vmw_driver_open,

drivers/gpu/drm/vmwgfx/vmwgfx_drv.h

@@ -44,9 +44,9 @@
 #include <linux/sync_file.h>
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20180704"
+#define VMWGFX_DRIVER_DATE "20190328"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 15
+#define VMWGFX_DRIVER_MINOR 16
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
@@ -81,19 +81,30 @@
 #define VMW_RES_SHADER ttm_driver_type4
 
 struct vmw_fpriv {
-	struct drm_master *locked_master;
 	struct ttm_object_file *tfile;
 	bool gb_aware; /* user-space is guest-backed aware */
 };
 
+/**
+ * struct vmw_buffer_object - TTM buffer object with vmwgfx additions
+ * @base: The TTM buffer object
+ * @res_tree: RB tree of resources using this buffer object as a backing MOB
+ * @pin_count: pin depth
+ * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB
+ * @map: Kmap object for semi-persistent mappings
+ * @res_prios: Eviction priority counts for attached resources
+ * @dirty: structure for user-space dirty-tracking
+ */
 struct vmw_buffer_object {
 	struct ttm_buffer_object base;
-	struct list_head res_list;
+	struct rb_root res_tree;
 	s32 pin_count;
 	/* Not ref-counted.  Protected by binding_mutex */
 	struct vmw_resource *dx_query_ctx;
 	/* Protected by reservation */
 	struct ttm_bo_kmap_obj map;
+	u32 res_prios[TTM_MAX_BO_PRIORITY];
+	struct vmw_bo_dirty *dirty;
 };
 
 /**
@@ -124,7 +135,8 @@ struct vmw_res_func;
  * @res_dirty: Resource contains data not yet in the backup buffer. Protected
  * by resource reserved.
  * @backup_dirty: Backup buffer contains data not yet in the HW resource.
- * Protecte by resource reserved.
+ * Protected by resource reserved.
+ * @coherent: Emulate coherency by tracking vm accesses.
  * @backup: The backup buffer if any. Protected by resource reserved.
  * @backup_offset: Offset into the backup buffer if any. Protected by resource
  * reserved. Note that only a few resource types can have a @backup_offset
@@ -133,28 +145,32 @@ struct vmw_res_func;
  * pin-count greater than zero. It is not on the resource LRU lists and its
  * backup buffer is pinned. Hence it can't be evicted.
  * @func: Method vtable for this resource. Immutable.
+ * @mob_node; Node for the MOB backup rbtree. Protected by @backup reserved.
  * @lru_head: List head for the LRU list. Protected by @dev_priv::resource_lock.
- * @mob_head: List head for the MOB backup list. Protected by @backup reserved.
  * @binding_head: List head for the context binding list. Protected by
  * the @dev_priv::binding_mutex
  * @res_free: The resource destructor.
  * @hw_destroy: Callback to destroy the resource on the device, as part of
  * resource destruction.
  */
+struct vmw_resource_dirty;
 struct vmw_resource {
 	struct kref kref;
 	struct vmw_private *dev_priv;
 	int id;
+	u32 used_prio;
 	unsigned long backup_size;
-	bool res_dirty;
-	bool backup_dirty;
+	u32 res_dirty : 1;
+	u32 backup_dirty : 1;
+	u32 coherent : 1;
 	struct vmw_buffer_object *backup;
 	unsigned long backup_offset;
 	unsigned long pin_count;
 	const struct vmw_res_func *func;
+	struct rb_node mob_node;
 	struct list_head lru_head;
-	struct list_head mob_head;
 	struct list_head binding_head;
+	struct vmw_resource_dirty *dirty;
 	void (*res_free) (struct vmw_resource *res);
 	void (*hw_destroy) (struct vmw_resource *res);
 };
@@ -376,10 +392,6 @@ struct vmw_sw_context{
 struct vmw_legacy_display;
 struct vmw_overlay;
 
-struct vmw_master {
-	struct ttm_lock lock;
-};
-
 struct vmw_vga_topology_state {
 	uint32_t width;
 	uint32_t height;
@@ -542,11 +554,8 @@ struct vmw_private {
 	spinlock_t svga_lock;
 
 	/**
-	 * Master management.
+	 * PM management.
 	 */
-
-	struct vmw_master *active_master;
-	struct vmw_master fbdev_master;
 	struct notifier_block pm_nb;
 	bool refuse_hibernation;
 	bool suspend_locked;
@@ -595,6 +604,9 @@ struct vmw_private {
 
 	/* Validation memory reservation */
 	struct vmw_validation_mem vvm;
+
+	/* VM operations */
+	struct vm_operations_struct vm_ops;
 };
 
 static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res)
@@ -612,11 +624,6 @@ static inline struct vmw_fpriv *vmw_fpriv(struct drm_file *file_priv)
 	return (struct vmw_fpriv *)file_priv->driver_priv;
 }
 
-static inline struct vmw_master *vmw_master(struct drm_master *master)
-{
-	return (struct vmw_master *) master->driver_priv;
-}
-
 /*
  * The locking here is fine-grained, so that it is performed once
  * for every read- and write operation. This is of course costly, but we
@@ -669,7 +676,8 @@ extern void vmw_resource_unreference(struct vmw_resource **p_res);
 extern struct vmw_resource *vmw_resource_reference(struct vmw_resource *res);
 extern struct vmw_resource *
 vmw_resource_reference_unless_doomed(struct vmw_resource *res);
-extern int vmw_resource_validate(struct vmw_resource *res, bool intr);
+extern int vmw_resource_validate(struct vmw_resource *res, bool intr,
+				 bool dirtying);
 extern int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
 				bool no_backup);
 extern bool vmw_resource_needs_backup(const struct vmw_resource *res);
@@ -709,6 +717,23 @@ extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
 extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
 extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo);
+void vmw_resource_mob_attach(struct vmw_resource *res);
+void vmw_resource_mob_detach(struct vmw_resource *res);
+void vmw_resource_dirty_update(struct vmw_resource *res, pgoff_t start,
+			       pgoff_t end);
+int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start,
+			pgoff_t end, pgoff_t *num_prefault);
+
+/**
+ * vmw_resource_mob_attached - Whether a resource currently has a mob attached
+ * @res: The resource
+ *
+ * Return: true if the resource has a mob attached, false otherwise.
+ */
+static inline bool vmw_resource_mob_attached(const struct vmw_resource *res)
+{
+	return !RB_EMPTY_NODE(&res->mob_node);
+}
 
 /**
  * vmw_user_resource_noref_release - release a user resource pointer looked up
@@ -787,6 +812,54 @@ static inline void vmw_user_bo_noref_release(void)
 	ttm_base_object_noref_release();
 }
 
+/**
+ * vmw_bo_adjust_prio - Adjust the buffer object eviction priority
+ * according to attached resources
+ * @vbo: The struct vmw_buffer_object
+ */
+static inline void vmw_bo_prio_adjust(struct vmw_buffer_object *vbo)
+{
+	int i = ARRAY_SIZE(vbo->res_prios);
+
+	while (i--) {
+		if (vbo->res_prios[i]) {
+			vbo->base.priority = i;
+			return;
+		}
+	}
+
+	vbo->base.priority = 3;
+}
+
+/**
+ * vmw_bo_prio_add - Notify a buffer object of a newly attached resource
+ * eviction priority
+ * @vbo: The struct vmw_buffer_object
+ * @prio: The resource priority
+ *
+ * After being notified, the code assigns the highest resource eviction priority
+ * to the backing buffer object (mob).
+ */
+static inline void vmw_bo_prio_add(struct vmw_buffer_object *vbo, int prio)
+{
+	if (vbo->res_prios[prio]++ == 0)
+		vmw_bo_prio_adjust(vbo);
+}
+
+/**
+ * vmw_bo_prio_del - Notify a buffer object of a resource with a certain
+ * priority being removed
+ * @vbo: The struct vmw_buffer_object
+ * @prio: The resource priority
+ *
+ * After being notified, the code assigns the highest resource eviction priority
+ * to the backing buffer object (mob).
+ */
+static inline void vmw_bo_prio_del(struct vmw_buffer_object *vbo, int prio)
+{
+	if (--vbo->res_prios[prio] == 0)
+		vmw_bo_prio_adjust(vbo);
+}
 
 /**
  * Misc Ioctl functionality - vmwgfx_ioctl.c
@@ -1016,7 +1089,6 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf,
 int vmw_kms_write_svga(struct vmw_private *vmw_priv,
 		       unsigned width, unsigned height, unsigned pitch,
 		       unsigned bpp, unsigned depth);
-void vmw_kms_idle_workqueues(struct vmw_master *vmaster);
 bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv,
 				uint32_t pitch,
 				uint32_t height);
@@ -1338,6 +1410,25 @@ int vmw_host_log(const char *log);
 #define VMW_DEBUG_USER(fmt, ...)                                              \
 	DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
 
+/**
+ * VMW_DEBUG_KMS - Debug output for kernel mode-setting
+ *
+ * This macro is for debugging vmwgfx mode-setting code.
+ */
+#define VMW_DEBUG_KMS(fmt, ...)                                               \
+	DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
+
+/* Resource dirtying - vmwgfx_page_dirty.c */
+void vmw_bo_dirty_scan(struct vmw_buffer_object *vbo);
+int vmw_bo_dirty_add(struct vmw_buffer_object *vbo);
+void vmw_bo_dirty_transfer_to_res(struct vmw_resource *res);
+void vmw_bo_dirty_clear_res(struct vmw_resource *res);
+void vmw_bo_dirty_release(struct vmw_buffer_object *vbo);
+void vmw_bo_dirty_unmap(struct vmw_buffer_object *vbo,
+			pgoff_t start, pgoff_t end);
+vm_fault_t vmw_bo_vm_fault(struct vm_fault *vmf);
+vm_fault_t vmw_bo_vm_mkwrite(struct vm_fault *vmf);
+
 /**
  * Inline helper functions
  */

drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c

@@ -2560,7 +2560,6 @@ static int vmw_cmd_dx_check_subresource(struct vmw_private *dev_priv,
 		     offsetof(typeof(*cmd), sid));
 
 	cmd = container_of(header, typeof(*cmd), header);
-
 	return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				 VMW_RES_DIRTY_NONE, user_surface_converter,
 				 &cmd->sid, NULL);

drivers/gpu/drm/vmwgfx/vmwgfx_kms.c

@@ -1462,7 +1462,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 		if (dev_priv->active_display_unit == vmw_du_screen_target &&
 		    (drm_rect_width(&rects[i]) > dev_priv->stdu_max_width ||
 		     drm_rect_height(&rects[i]) > dev_priv->stdu_max_height)) {
-			DRM_ERROR("Screen size not supported.\n");
+			VMW_DEBUG_KMS("Screen size not supported.\n");
 			return -EINVAL;
 		}
 
@@ -1486,7 +1486,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 	 * limit on primary bounding box
 	 */
 	if (pixel_mem > dev_priv->prim_bb_mem) {
-		DRM_ERROR("Combined output size too large.\n");
+		VMW_DEBUG_KMS("Combined output size too large.\n");
 		return -EINVAL;
 	}
 
@@ -1496,7 +1496,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 		bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4;
 
 		if (bb_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Topology is beyond supported limits.\n");
+			VMW_DEBUG_KMS("Topology is beyond supported limits.\n");
 			return -EINVAL;
 		}
 	}
@@ -1645,6 +1645,7 @@ static int vmw_kms_check_topology(struct drm_device *dev,
 		struct vmw_connector_state *vmw_conn_state;
 
 		if (!du->pref_active && new_crtc_state->enable) {
+			VMW_DEBUG_KMS("Enabling a disabled display unit\n");
 			ret = -EINVAL;
 			goto clean;
 		}
@@ -1701,8 +1702,10 @@ vmw_kms_atomic_check_modeset(struct drm_device *dev,
 		return ret;
 
 	ret = vmw_kms_check_implicit(dev, state);
-	if (ret)
+	if (ret) {
+		VMW_DEBUG_KMS("Invalid implicit state\n");
 		return ret;
+	}
 
 	if (!state->allow_modeset)
 		return ret;
@@ -2347,6 +2350,9 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 
 	if (!arg->num_outputs) {
 		struct drm_rect def_rect = {0, 0, 800, 600};
+		VMW_DEBUG_KMS("Default layout x1 = %d y1 = %d x2 = %d y2 = %d\n",
+			      def_rect.x1, def_rect.y1,
+			      def_rect.x2, def_rect.y2);
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
 		return 0;
 	}
@@ -2367,6 +2373,7 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 
 	drm_rects = (struct drm_rect *)rects;
 
+	VMW_DEBUG_KMS("Layout count = %u\n", arg->num_outputs);
 	for (i = 0; i < arg->num_outputs; i++) {
 		struct drm_vmw_rect curr_rect;
 
@@ -2383,6 +2390,10 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		drm_rects[i].x2 = curr_rect.x + curr_rect.w;
 		drm_rects[i].y2 = curr_rect.y + curr_rect.h;
 
+		VMW_DEBUG_KMS("  x1 = %d y1 = %d x2 = %d y2 = %d\n",
+			      drm_rects[i].x1, drm_rects[i].y1,
+			      drm_rects[i].x2, drm_rects[i].y2);
+
 		/*
 		 * Currently this check is limiting the topology within
 		 * mode_config->max (which actually is max texture size
@@ -2393,7 +2404,9 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		if (drm_rects[i].x1 < 0 ||  drm_rects[i].y1 < 0 ||
 		    drm_rects[i].x2 > mode_config->max_width ||
 		    drm_rects[i].y2 > mode_config->max_height) {
-			DRM_ERROR("Invalid GUI layout.\n");
+			VMW_DEBUG_KMS("Invalid layout %d %d %d %d\n",
+				      drm_rects[i].x1, drm_rects[i].y1,
+				      drm_rects[i].x2, drm_rects[i].y2);
 			ret = -EINVAL;
 			goto out_free;
 		}

drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h

@@ -71,6 +71,13 @@ struct vmw_user_resource_conv {
  * @commit_notify:     If the resource is a command buffer managed resource,
  *                     callback to notify that a define or remove command
  *                     has been committed to the device.
+ * @dirty_alloc:       Allocate a dirty tracker. NULL if dirty-tracking is not
+ *                     supported.
+ * @dirty_free:        Free the dirty tracker.
+ * @dirty_sync:        Upload the dirty mob contents to the resource.
+ * @dirty_add_range:   Add a sequential dirty range to the resource
+ *                     dirty tracker.
+ * @clean:             Clean the resource.
  */
 struct vmw_res_func {
 	enum vmw_res_type res_type;
@@ -78,6 +85,8 @@ struct vmw_res_func {
 	const char *type_name;
 	struct ttm_placement *backup_placement;
 	bool may_evict;
+	u32 prio;
+	u32 dirty_prio;
 
 	int (*create) (struct vmw_resource *res);
 	int (*destroy) (struct vmw_resource *res);
@@ -88,6 +97,12 @@ struct vmw_res_func {
 		       struct ttm_validate_buffer *val_buf);
 	void (*commit_notify)(struct vmw_resource *res,
 			      enum vmw_cmdbuf_res_state state);
+	int (*dirty_alloc)(struct vmw_resource *res);
+	void (*dirty_free)(struct vmw_resource *res);
+	int (*dirty_sync)(struct vmw_resource *res);
+	void (*dirty_range_add)(struct vmw_resource *res, size_t start,
+				 size_t end);
+	int (*clean)(struct vmw_resource *res);
 };
 
 /**

drivers/gpu/drm/vmwgfx/vmwgfx_shader.c

@@ -95,6 +95,8 @@ static const struct vmw_res_func vmw_gb_shader_func = {
 	.res_type = vmw_res_shader,
 	.needs_backup = true,
 	.may_evict = true,
+	.prio = 3,
+	.dirty_prio = 3,
 	.type_name = "guest backed shaders",
 	.backup_placement = &vmw_mob_placement,
 	.create = vmw_gb_shader_create,
@@ -106,7 +108,9 @@ static const struct vmw_res_func vmw_gb_shader_func = {
 static const struct vmw_res_func vmw_dx_shader_func = {
 	.res_type = vmw_res_shader,
 	.needs_backup = true,
-	.may_evict = false,
+	.may_evict = true,
+	.prio = 3,
+	.dirty_prio = 3,
 	.type_name = "dx shaders",
 	.backup_placement = &vmw_mob_placement,
 	.create = vmw_dx_shader_create,
@@ -423,7 +427,7 @@ static int vmw_dx_shader_create(struct vmw_resource *res)
 
 	WARN_ON_ONCE(!shader->committed);
 
-	if (!list_empty(&res->mob_head)) {
+	if (vmw_resource_mob_attached(res)) {
 		mutex_lock(&dev_priv->binding_mutex);
 		ret = vmw_dx_shader_unscrub(res);
 		mutex_unlock(&dev_priv->binding_mutex);

drivers/gpu/drm/vmwgfx/vmwgfx_validation.c

@@ -33,6 +33,8 @@
  * struct vmw_validation_bo_node - Buffer object validation metadata.
  * @base: Metadata used for TTM reservation- and validation.
  * @hash: A hash entry used for the duplicate detection hash table.
+ * @coherent_count: If switching backup buffers, number of new coherent
+ * resources that will have this buffer as a backup buffer.
  * @as_mob: Validate as mob.
  * @cpu_blit: Validate for cpu blit access.
  *
@@ -42,6 +44,7 @@
 struct vmw_validation_bo_node {
 	struct ttm_validate_buffer base;
 	struct drm_hash_item hash;
+	unsigned int coherent_count;
 	u32 as_mob : 1;
 	u32 cpu_blit : 1;
 };
@@ -459,6 +462,19 @@ int vmw_validation_res_reserve(struct vmw_validation_context *ctx,
 			if (ret)
 				goto out_unreserve;
 		}
+
+		if (val->switching_backup && val->new_backup &&
+		    res->coherent) {
+			struct vmw_validation_bo_node *bo_node =
+				vmw_validation_find_bo_dup(ctx,
+							   val->new_backup);
+
+			if (WARN_ON(!bo_node)) {
+				ret = -EINVAL;
+				goto out_unreserve;
+			}
+			bo_node->coherent_count++;
+		}
 	}
 
 	return 0;
@@ -562,6 +578,9 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr)
 	int ret;
 
 	list_for_each_entry(entry, &ctx->bo_list, base.head) {
+		struct vmw_buffer_object *vbo =
+			container_of(entry->base.bo, typeof(*vbo), base);
+
 		if (entry->cpu_blit) {
 			struct ttm_operation_ctx ctx = {
 				.interruptible = intr,
@@ -576,6 +595,27 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr)
 		}
 		if (ret)
 			return ret;
+
+		/*
+		 * Rather than having the resource code allocating the bo
+		 * dirty tracker in resource_unreserve() where we can't fail,
+		 * Do it here when validating the buffer object.
+		 */
+		if (entry->coherent_count) {
+			unsigned int coherent_count = entry->coherent_count;
+
+			while (coherent_count) {
+				ret = vmw_bo_dirty_add(vbo);
+				if (ret)
+					return ret;
+
+				coherent_count--;
+			}
+			entry->coherent_count -= coherent_count;
+		}
+
+		if (vbo->dirty)
+			vmw_bo_dirty_scan(vbo);
 	}
 	return 0;
 }
@@ -601,7 +641,8 @@ int vmw_validation_res_validate(struct vmw_validation_context *ctx, bool intr)
 		struct vmw_resource *res = val->res;
 		struct vmw_buffer_object *backup = res->backup;
 
-		ret = vmw_resource_validate(res, intr);
+		ret = vmw_resource_validate(res, intr, val->dirty_set &&
+					    val->dirty);
 		if (ret) {
 			if (ret != -ERESTARTSYS)
 				DRM_ERROR("Failed to validate resource.\n");
@@ -828,3 +869,34 @@ int vmw_validation_preload_res(struct vmw_validation_context *ctx,
 	ctx->mem_size_left += size;
 	return 0;
 }
+
+/**
+ * vmw_validation_bo_backoff - Unreserve buffer objects registered with a
+ * validation context
+ * @ctx: The validation context
+ *
+ * This function unreserves the buffer objects previously reserved using
+ * vmw_validation_bo_reserve. It's typically used as part of an error path
+ */
+void vmw_validation_bo_backoff(struct vmw_validation_context *ctx)
+{
+	struct vmw_validation_bo_node *entry;
+
+	/*
+	 * Switching coherent resource backup buffers failed.
+	 * Release corresponding buffer object dirty trackers.
+	 */
+	list_for_each_entry(entry, &ctx->bo_list, base.head) {
+		if (entry->coherent_count) {
+			unsigned int coherent_count = entry->coherent_count;
+			struct vmw_buffer_object *vbo =
+				container_of(entry->base.bo, typeof(*vbo),
+					     base);
+
+			while (coherent_count--)
+				vmw_bo_dirty_release(vbo);
+		}
+	}
+
+	ttm_eu_backoff_reservation(&ctx->ticket, &ctx->bo_list);
+}

drivers/gpu/drm/vmwgfx/vmwgfx_validation.h

@@ -172,20 +172,6 @@ vmw_validation_bo_reserve(struct vmw_validation_context *ctx,
 				      NULL, true);
 }
 
-/**
- * vmw_validation_bo_backoff - Unreserve buffer objects registered with a
- * validation context
- * @ctx: The validation context
- *
- * This function unreserves the buffer objects previously reserved using
- * vmw_validation_bo_reserve. It's typically used as part of an error path
- */
-static inline void
-vmw_validation_bo_backoff(struct vmw_validation_context *ctx)
-{
-	ttm_eu_backoff_reservation(&ctx->ticket, &ctx->bo_list);
-}
-
 /**
  * vmw_validation_bo_fence - Unreserve and fence buffer objects registered
  * with a validation context
@@ -268,4 +254,6 @@ int vmw_validation_preload_res(struct vmw_validation_context *ctx,
 			       unsigned int size);
 void vmw_validation_res_set_dirty(struct vmw_validation_context *ctx,
 				  void *val_private, u32 dirty);
+void vmw_validation_bo_backoff(struct vmw_validation_context *ctx);
+
 #endif

include/drm/ttm/ttm_bo_api.h

@@ -768,4 +768,14 @@ int ttm_bo_swapout(struct ttm_bo_global *glob,
 			struct ttm_operation_ctx *ctx);
 void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
 int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo);
+
+/* Default number of pre-faulted pages in the TTM fault handler */
+#define TTM_BO_VM_NUM_PREFAULT 16
+
+vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
+			     struct vm_fault *vmf);
+
+vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
+				    pgprot_t prot,
+				    pgoff_t num_prefault);
 #endif

include/drm/ttm/ttm_bo_driver.h

@@ -442,6 +442,9 @@ extern struct ttm_bo_global {
  * @driver: Pointer to a struct ttm_bo_driver struct setup by the driver.
  * @man: An array of mem_type_managers.
  * @vma_manager: Address space manager
+ * @vm_ops: Pointer to the struct vm_operations_struct used for this
+ * device's VM operations. The driver may override this before the first
+ * mmap() call.
  * lru_lock: Spinlock that protects the buffer+device lru lists and
  * ddestroy lists.
  * @dev_mapping: A pointer to the struct address_space representing the
@@ -460,6 +463,7 @@ struct ttm_bo_device {
 	struct ttm_bo_global *glob;
 	struct ttm_bo_driver *driver;
 	struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES];
+	const struct vm_operations_struct *vm_ops;
 
 	/*
 	 * Protected by internal locks.
@@ -488,6 +492,8 @@ struct ttm_bo_device {
 	bool no_retry;
 };
 
+extern const struct vm_operations_struct ttm_bo_vm_ops;
+
 /**
  * struct ttm_lru_bulk_move_pos
  *

include/linux/mm.h

@@ -2686,7 +2686,24 @@ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
 			       unsigned long size, pte_fn_t fn, void *data);
 
-
+struct pfn_range_apply;
+typedef int (*pter_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
+			 struct pfn_range_apply *closure);
+struct pfn_range_apply {
+	struct mm_struct *mm;
+	pter_fn_t ptefn;
+	unsigned int alloc;
+};
+extern int apply_to_pfn_range(struct pfn_range_apply *closure,
+			      unsigned long address, unsigned long size);
+unsigned long apply_as_wrprotect(struct address_space *mapping,
+				 pgoff_t first_index, pgoff_t nr);
+unsigned long apply_as_clean(struct address_space *mapping,
+			     pgoff_t first_index, pgoff_t nr,
+			     pgoff_t bitmap_pgoff,
+			     unsigned long *bitmap,
+			     pgoff_t *start,
+			     pgoff_t *end);
 #ifdef CONFIG_PAGE_POISONING
 extern bool page_poisoning_enabled(void);
 extern void kernel_poison_pages(struct page *page, int numpages, int enable);

include/uapi/drm/vmwgfx_drm.h

@@ -891,11 +891,13 @@ struct drm_vmw_shader_arg {
  *                                      surface.
  * @drm_vmw_surface_flag_create_buffer: Create a backup buffer if none is
  *                                      given.
+ * @drm_vmw_surface_flag_coherent:      Back surface with coherent memory.
  */
 enum drm_vmw_surface_flags {
 	drm_vmw_surface_flag_shareable = (1 << 0),
 	drm_vmw_surface_flag_scanout = (1 << 1),
-	drm_vmw_surface_flag_create_buffer = (1 << 2)
+	drm_vmw_surface_flag_create_buffer = (1 << 2),
+	drm_vmw_surface_flag_coherent = (1 << 3),
 };
 
 /**

mm/Kconfig

@@ -765,4 +765,7 @@ config GUP_BENCHMARK
 config ARCH_HAS_PTE_SPECIAL
 	bool
 
+config AS_DIRTY_HELPERS
+        bool
+
 endmenu

mm/Makefile

@@ -104,3 +104,4 @@ obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
 obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
 obj-$(CONFIG_HMM) += hmm.o
 obj-$(CONFIG_MEMFD_CREATE) += memfd.o
+obj-$(CONFIG_AS_DIRTY_HELPERS) += as_dirty_helpers.o

mm/as_dirty_helpers.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/mm_types.h>
+#include <linux/hugetlb.h>
+#include <linux/bitops.h>
+#include <linux/mmu_notifier.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+/**
+ * struct apply_as - Closure structure for apply_as_range
+ * @base: struct pfn_range_apply we derive from
+ * @start: Address of first modified pte
+ * @end: Address of last modified pte + 1
+ * @total: Total number of modified ptes
+ * @vma: Pointer to the struct vm_area_struct we're currently operating on
+ */
+struct apply_as {
+	struct pfn_range_apply base;
+	unsigned long start;
+	unsigned long end;
+	unsigned long total;
+	struct vm_area_struct *vma;
+};
+
+/**
+ * apply_pt_wrprotect - Leaf pte callback to write-protect a pte
+ * @pte: Pointer to the pte
+ * @token: Page table token, see apply_to_pfn_range()
+ * @addr: The virtual page address
+ * @closure: Pointer to a struct pfn_range_apply embedded in a
+ * struct apply_as
+ *
+ * The function write-protects a pte and records the range in
+ * virtual address space of touched ptes for efficient range TLB flushes.
+ *
+ * Return: Always zero.
+ */
+static int apply_pt_wrprotect(pte_t *pte, pgtable_t token,
+			      unsigned long addr,
+			      struct pfn_range_apply *closure)
+{
+	struct apply_as *aas = container_of(closure, typeof(*aas), base);
+	pte_t ptent = *pte;
+
+	if (pte_write(ptent)) {
+		pte_t old_pte = ptep_modify_prot_start(aas->vma, addr, pte);
+
+		ptent = pte_wrprotect(old_pte);
+		ptep_modify_prot_commit(aas->vma, addr, pte, old_pte, ptent);
+		aas->total++;
+		aas->start = min(aas->start, addr);
+		aas->end = max(aas->end, addr + PAGE_SIZE);
+	}
+
+	return 0;
+}
+
+/**
+ * struct apply_as_clean - Closure structure for apply_as_clean
+ * @base: struct apply_as we derive from
+ * @bitmap_pgoff: Address_space Page offset of the first bit in @bitmap
+ * @bitmap: Bitmap with one bit for each page offset in the address_space range
+ * covered.
+ * @start: Address_space page offset of first modified pte relative
+ * to @bitmap_pgoff
+ * @end: Address_space page offset of last modified pte relative
+ * to @bitmap_pgoff
+ */
+struct apply_as_clean {
+	struct apply_as base;
+	pgoff_t bitmap_pgoff;
+	unsigned long *bitmap;
+	pgoff_t start;
+	pgoff_t end;
+};
+
+/**
+ * apply_pt_clean - Leaf pte callback to clean a pte
+ * @pte: Pointer to the pte
+ * @token: Page table token, see apply_to_pfn_range()
+ * @addr: The virtual page address
+ * @closure: Pointer to a struct pfn_range_apply embedded in a
+ * struct apply_as_clean
+ *
+ * The function cleans a pte and records the range in
+ * virtual address space of touched ptes for efficient TLB flushes.
+ * It also records dirty ptes in a bitmap representing page offsets
+ * in the address_space, as well as the first and last of the bits
+ * touched.
+ *
+ * Return: Always zero.
+ */
+static int apply_pt_clean(pte_t *pte, pgtable_t token,
+			  unsigned long addr,
+			  struct pfn_range_apply *closure)
+{
+	struct apply_as *aas = container_of(closure, typeof(*aas), base);
+	struct apply_as_clean *clean = container_of(aas, typeof(*clean), base);
+	pte_t ptent = *pte;
+
+	if (pte_dirty(ptent)) {
+		pgoff_t pgoff = ((addr - aas->vma->vm_start) >> PAGE_SHIFT) +
+			aas->vma->vm_pgoff - clean->bitmap_pgoff;
+		pte_t old_pte = ptep_modify_prot_start(aas->vma, addr, pte);
+
+		ptent = pte_mkclean(old_pte);
+		ptep_modify_prot_commit(aas->vma, addr, pte, old_pte, ptent);
+
+		aas->total++;
+		aas->start = min(aas->start, addr);
+		aas->end = max(aas->end, addr + PAGE_SIZE);
+
+		__set_bit(pgoff, clean->bitmap);
+		clean->start = min(clean->start, pgoff);
+		clean->end = max(clean->end, pgoff + 1);
+	}
+
+	return 0;
+}
+
+/**
+ * apply_as_range - Apply a pte callback to all PTEs pointing into a range
+ * of an address_space.
+ * @mapping: Pointer to the struct address_space
+ * @aas: Closure structure
+ * @first_index: First page offset in the address_space
+ * @nr: Number of incremental page offsets to cover
+ *
+ * Return: Number of ptes touched. Note that this number might be larger
+ * than @nr if there are overlapping vmas
+ */
+static unsigned long apply_as_range(struct address_space *mapping,
+				    struct apply_as *aas,
+				    pgoff_t first_index, pgoff_t nr)
+{
+	struct vm_area_struct *vma;
+	pgoff_t vba, vea, cba, cea;
+	unsigned long start_addr, end_addr;
+	struct mmu_notifier_range range;
+
+	i_mmap_lock_read(mapping);
+	vma_interval_tree_foreach(vma, &mapping->i_mmap, first_index,
+				  first_index + nr - 1) {
+		unsigned long vm_flags = READ_ONCE(vma->vm_flags);
+
+		/*
+		 * We can only do advisory flag tests below, since we can't
+		 * require the vm's mmap_sem to be held to protect the flags.
+		 * Therefore, callers that strictly depend on specific mmap
+		 * flags to remain constant throughout the operation must
+		 * either ensure those flags are immutable for all relevant
+		 * vmas or can't use this function. Fixing this properly would
+		 * require the vma::vm_flags to be protected by a separate
+		 * lock taken after the i_mmap_lock
+		 */
+
+		/* Skip non-applicable VMAs */
+		if ((vm_flags & (VM_SHARED | VM_WRITE)) !=
+		    (VM_SHARED | VM_WRITE))
+			continue;
+
+		/* Warn on and skip VMAs whose flags indicate illegal usage */
+		if (WARN_ON((vm_flags & (VM_HUGETLB | VM_IO)) != VM_IO))
+			continue;
+
+		/* Clip to the vma */
+		vba = vma->vm_pgoff;
+		vea = vba + vma_pages(vma);
+		cba = first_index;
+		cba = max(cba, vba);
+		cea = first_index + nr;
+		cea = min(cea, vea);
+
+		/* Translate to virtual address */
+		start_addr = ((cba - vba) << PAGE_SHIFT) + vma->vm_start;
+		end_addr = ((cea - vba) << PAGE_SHIFT) + vma->vm_start;
+		if (start_addr >= end_addr)
+			continue;
+
+		aas->base.mm = vma->vm_mm;
+		aas->vma = vma;
+		aas->start = end_addr;
+		aas->end = start_addr;
+
+		mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0,
+					vma, vma->vm_mm, start_addr, end_addr);
+		mmu_notifier_invalidate_range_start(&range);
+
+		/* Needed when we only change protection? */
+		flush_cache_range(vma, start_addr, end_addr);
+
+		/*
+		 * We're not using tlb_gather_mmu() since typically
+		 * only a small subrange of PTEs are affected.
+		 */
+		inc_tlb_flush_pending(vma->vm_mm);
+
+		/* Should not error since aas->base.alloc == 0 */
+		WARN_ON(apply_to_pfn_range(&aas->base, start_addr,
+					   end_addr - start_addr));
+		if (aas->end > aas->start)
+			flush_tlb_range(vma, aas->start, aas->end);
+
+		mmu_notifier_invalidate_range_end(&range);
+		dec_tlb_flush_pending(vma->vm_mm);
+	}
+	i_mmap_unlock_read(mapping);
+
+	return aas->total;
+}
+
+/**
+ * apply_as_wrprotect - Write-protect all ptes in an address_space range
+ * @mapping: The address_space we want to write protect
+ * @first_index: The first page offset in the range
+ * @nr: Number of incremental page offsets to cover
+ *
+ * WARNING: This function should only be used for address spaces whose
+ * vmas are marked VM_IO and that do not contain huge pages.
+ * To avoid interference with COW'd pages, vmas not marked VM_SHARED are
+ * simply skipped.
+ *
+ * Return: The number of ptes actually write-protected. Note that
+ * already write-protected ptes are not counted.
+ */
+unsigned long apply_as_wrprotect(struct address_space *mapping,
+				 pgoff_t first_index, pgoff_t nr)
+{
+	struct apply_as aas = {
+		.base = {
+			.alloc = 0,
+			.ptefn = apply_pt_wrprotect,
+		},
+		.total = 0,
+	};
+
+	return apply_as_range(mapping, &aas, first_index, nr);
+}
+EXPORT_SYMBOL_GPL(apply_as_wrprotect);
+
+/**
+ * apply_as_clean - Clean all ptes in an address_space range
+ * @mapping: The address_space we want to clean
+ * @first_index: The first page offset in the range
+ * @nr: Number of incremental page offsets to cover
+ * @bitmap_pgoff: The page offset of the first bit in @bitmap
+ * @bitmap: Pointer to a bitmap of at least @nr bits. The bitmap needs to
+ * cover the whole range @first_index..@first_index + @nr.
+ * @start: Pointer to number of the first set bit in @bitmap.
+ * is modified as new bits are set by the function.
+ * @end: Pointer to the number of the last set bit in @bitmap.
+ * none set. The value is modified as new bits are set by the function.
+ *
+ * Note: When this function returns there is no guarantee that a CPU has
+ * not already dirtied new ptes. However it will not clean any ptes not
+ * reported in the bitmap.
+ *
+ * If a caller needs to make sure all dirty ptes are picked up and none
+ * additional are added, it first needs to write-protect the address-space
+ * range and make sure new writers are blocked in page_mkwrite() or
+ * pfn_mkwrite(). And then after a TLB flush following the write-protection
+ * pick up all dirty bits.
+ *
+ * WARNING: This function should only be used for address spaces whose
+ * vmas are marked VM_IO and that do not contain huge pages.
+ * To avoid interference with COW'd pages, vmas not marked VM_SHARED are
+ * simply skipped.
+ *
+ * Return: The number of dirty ptes actually cleaned.
+ */
+unsigned long apply_as_clean(struct address_space *mapping,
+			     pgoff_t first_index, pgoff_t nr,
+			     pgoff_t bitmap_pgoff,
+			     unsigned long *bitmap,
+			     pgoff_t *start,
+			     pgoff_t *end)
+{
+	bool none_set = (*start >= *end);
+	struct apply_as_clean clean = {
+		.base = {
+			.base = {
+				.alloc = 0,
+				.ptefn = apply_pt_clean,
+			},
+			.total = 0,
+		},
+		.bitmap_pgoff = bitmap_pgoff,
+		.bitmap = bitmap,
+		.start = none_set ? nr : *start,
+		.end = none_set ? 0 : *end,
+	};
+	unsigned long ret = apply_as_range(mapping, &clean.base, first_index,
+					   nr);
+
+	*start = clean.start;
+	*end = clean.end;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(apply_as_clean);

mm/memory.c

@@ -2032,18 +2032,17 @@ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long
 }
 EXPORT_SYMBOL(vm_iomap_memory);
 
-static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
-				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+static int apply_to_pte_range(struct pfn_range_apply *closure, pmd_t *pmd,
+			      unsigned long addr, unsigned long end)
 {
 	pte_t *pte;
 	int err;
 	pgtable_t token;
 	spinlock_t *uninitialized_var(ptl);
 
-	pte = (mm == &init_mm) ?
+	pte = (closure->mm == &init_mm) ?
 		pte_alloc_kernel(pmd, addr) :
-		pte_alloc_map_lock(mm, pmd, addr, &ptl);
+		pte_alloc_map_lock(closure->mm, pmd, addr, &ptl);
 	if (!pte)
 		return -ENOMEM;
 
@@ -2054,86 +2053,109 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	token = pmd_pgtable(*pmd);
 
 	do {
-		err = fn(pte++, token, addr, data);
+		err = closure->ptefn(pte++, token, addr, closure);
 		if (err)
 			break;
 	} while (addr += PAGE_SIZE, addr != end);
 
 	arch_leave_lazy_mmu_mode();
 
-	if (mm != &init_mm)
+	if (closure->mm != &init_mm)
 		pte_unmap_unlock(pte-1, ptl);
 	return err;
 }
 
-static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
-				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+static int apply_to_pmd_range(struct pfn_range_apply *closure, pud_t *pud,
+			      unsigned long addr, unsigned long end)
 {
 	pmd_t *pmd;
 	unsigned long next;
-	int err;
+	int err = 0;
 
 	BUG_ON(pud_huge(*pud));
 
-	pmd = pmd_alloc(mm, pud, addr);
+	pmd = pmd_alloc(closure->mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;
+
 	do {
 		next = pmd_addr_end(addr, end);
-		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
+		if (!closure->alloc && pmd_none_or_clear_bad(pmd))
+			continue;
+		err = apply_to_pte_range(closure, pmd, addr, next);
 		if (err)
 			break;
 	} while (pmd++, addr = next, addr != end);
 	return err;
 }
 
-static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
-				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+static int apply_to_pud_range(struct pfn_range_apply *closure, p4d_t *p4d,
+			      unsigned long addr, unsigned long end)
 {
 	pud_t *pud;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	pud = pud_alloc(mm, p4d, addr);
+	pud = pud_alloc(closure->mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
+
 	do {
 		next = pud_addr_end(addr, end);
-		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
+		if (!closure->alloc && pud_none_or_clear_bad(pud))
+			continue;
+		err = apply_to_pmd_range(closure, pud, addr, next);
 		if (err)
 			break;
 	} while (pud++, addr = next, addr != end);
 	return err;
 }
 
-static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
-				     unsigned long addr, unsigned long end,
-				     pte_fn_t fn, void *data)
+static int apply_to_p4d_range(struct pfn_range_apply *closure, pgd_t *pgd,
+			      unsigned long addr, unsigned long end)
 {
 	p4d_t *p4d;
 	unsigned long next;
-	int err;
+	int err = 0;
 
-	p4d = p4d_alloc(mm, pgd, addr);
+	p4d = p4d_alloc(closure->mm, pgd, addr);
 	if (!p4d)
 		return -ENOMEM;
+
 	do {
 		next = p4d_addr_end(addr, end);
-		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+		if (!closure->alloc && p4d_none_or_clear_bad(p4d))
+			continue;
+		err = apply_to_pud_range(closure, p4d, addr, next);
 		if (err)
 			break;
 	} while (p4d++, addr = next, addr != end);
 	return err;
 }
 
-/*
- * Scan a region of virtual memory, filling in page tables as necessary
- * and calling a provided function on each leaf page table.
+/**
+ * apply_to_pfn_range - Scan a region of virtual memory, calling a provided
+ * function on each leaf page table entry
+ * @closure: Details about how to scan and what function to apply
+ * @addr: Start virtual address
+ * @size: Size of the region
+ *
+ * If @closure->alloc is set to 1, the function will fill in the page table
+ * as necessary. Otherwise it will skip non-present parts.
+ * Note: The caller must ensure that the range does not contain huge pages.
+ * The caller must also assure that the proper mmu_notifier functions are
+ * called before and after the call to apply_to_pfn_range.
+ *
+ * WARNING: Do not use this function unless you know exactly what you are
+ * doing. It is lacking support for huge pages and transparent huge pages.
+ *
+ * Return: Zero on success. If the provided function returns a non-zero status,
+ * the page table walk will terminate and that status will be returned.
+ * If @closure->alloc is set to 1, then this function may also return memory
+ * allocation errors arising from allocating page table memory.
  */
-int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
-			unsigned long size, pte_fn_t fn, void *data)
+int apply_to_pfn_range(struct pfn_range_apply *closure,
+		       unsigned long addr, unsigned long size)
 {
 	pgd_t *pgd;
 	unsigned long next;
@@ -2143,16 +2165,65 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	if (WARN_ON(addr >= end))
 		return -EINVAL;
 
-	pgd = pgd_offset(mm, addr);
+	pgd = pgd_offset(closure->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
+		if (!closure->alloc && pgd_none_or_clear_bad(pgd))
+			continue;
+		err = apply_to_p4d_range(closure, pgd, addr, next);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
 
 	return err;
 }
+
+/**
+ * struct page_range_apply - Closure structure for apply_to_page_range()
+ * @pter: The base closure structure we derive from
+ * @fn: The leaf pte function to call
+ * @data: The leaf pte function closure
+ */
+struct page_range_apply {
+	struct pfn_range_apply pter;
+	pte_fn_t fn;
+	void *data;
+};
+
+/*
+ * Callback wrapper to enable use of apply_to_pfn_range for
+ * the apply_to_page_range interface
+ */
+static int apply_to_page_range_wrapper(pte_t *pte, pgtable_t token,
+				       unsigned long addr,
+				       struct pfn_range_apply *pter)
+{
+	struct page_range_apply *pra =
+		container_of(pter, typeof(*pra), pter);
+
+	return pra->fn(pte, token, addr, pra->data);
+}
+
+/*
+ * Scan a region of virtual memory, filling in page tables as necessary
+ * and calling a provided function on each leaf page table.
+ *
+ * WARNING: Do not use this function unless you know exactly what you are
+ * doing. It is lacking support for huge pages and transparent huge pages.
+ */
+int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+			unsigned long size, pte_fn_t fn, void *data)
+{
+	struct page_range_apply pra = {
+		.pter = {.mm = mm,
+			 .alloc = 1,
+			 .ptefn = apply_to_page_range_wrapper },
+		.fn = fn,
+		.data = data
+	};
+
+	return apply_to_pfn_range(&pra.pter, addr, size);
+}
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
 /*
@@ -2238,7 +2309,7 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf)
 	ret = vmf->vma->vm_ops->page_mkwrite(vmf);
 	/* Restore original flags so that caller is not surprised */
 	vmf->flags = old_flags;
-	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
 	if (unlikely(!(ret & VM_FAULT_LOCKED))) {
 		lock_page(page);
@@ -2515,7 +2586,7 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		vmf->flags |= FAULT_FLAG_MKWRITE;
 		ret = vma->vm_ops->pfn_mkwrite(vmf);
-		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))
+		if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))
 			return ret;
 		return finish_mkwrite_fault(vmf);
 	}
@@ -2536,7 +2607,8 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		tmp = do_page_mkwrite(vmf);
 		if (unlikely(!tmp || (tmp &
-				      (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
+				      (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
+				       VM_FAULT_RETRY)))) {
 			put_page(vmf->page);
 			return tmp;
 		}
@@ -3601,7 +3673,8 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
 		unlock_page(vmf->page);
 		tmp = do_page_mkwrite(vmf);
 		if (unlikely(!tmp ||
-				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) {
+				(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
+					VM_FAULT_RETRY)))) {
 			put_page(vmf->page);
 			return tmp;
 		}