Merge 35219bc5c7 ("Merge tag 'vfs-6.12.netfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs") into android-mainline

Steps on the way to 6.12-rc1

Bug: 367265496
Change-Id: I37a904f83857c7847142c7273b3c2771b5125cfc
Signed-off-by: Matthias Maennich <maennich@google.com>

Documentation/admin-guide/kernel-parameters.txt

@@ -4792,6 +4792,16 @@
 	printk.time=	Show timing data prefixed to each printk message line
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 
+	proc_mem.force_override= [KNL]
+			Format: {always | ptrace | never}
+			Traditionally /proc/pid/mem allows memory permissions to be
+			overridden without restrictions. This option may be set to
+			restrict that. Can be one of:
+			- 'always': traditional behavior always allows mem overrides.
+			- 'ptrace': only allow mem overrides for active ptracers.
+			- 'never':  never allow mem overrides.
+			If not specified, default is the CONFIG_PROC_MEM_* choice.
+
 	processor.max_cstate=	[HW,ACPI]
 			Limit processor to maximum C-state
 			max_cstate=9 overrides any DMI blacklist limit.

Documentation/filesystems/idmappings.rst

@@ -821,7 +821,7 @@ the same idmapping to the mount. We now perform three steps:
       /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
       make_kuid(u0:k20000:r10000, u1000) = k21000
 
-2. Verify that the caller's kernel ids can be mapped to userspace ids in the
+3. Verify that the caller's kernel ids can be mapped to userspace ids in the
    filesystem's idmapping::
 
     from_kuid(u0:k20000:r10000, k21000) = u1000
@@ -854,10 +854,10 @@ The same translation algorithm works with the third example.
        /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
        make_kuid(u0:k0:r4294967295, u1000) = k1000
 
-2. Verify that the caller's kernel ids can be mapped to userspace ids in the
+3. Verify that the caller's kernel ids can be mapped to userspace ids in the
    filesystem's idmapping::
 
-    from_kuid(u0:k0:r4294967295, k21000) = u1000
+    from_kuid(u0:k0:r4294967295, k1000) = u1000
 
 So the ownership that lands on disk will be ``u1000``.
 
@@ -994,7 +994,7 @@ from above:::
       /* Map the userspace id down into a kernel id in the filesystem's idmapping. */
       make_kuid(u0:k0:r4294967295, u1000) = k1000
 
-2. Verify that the caller's filesystem ids can be mapped to userspace ids in the
+3. Verify that the caller's filesystem ids can be mapped to userspace ids in the
    filesystem's idmapping::
 
     from_kuid(u0:k0:r4294967295, k1000) = u1000

Documentation/filesystems/iomap/design.rst

@@ -142,9 +142,9 @@ Definitions
  * **pure overwrite**: A write operation that does not require any
    metadata or zeroing operations to perform during either submission
    or completion.
-   This implies that the fileystem must have already allocated space
+   This implies that the filesystem must have already allocated space
    on disk as ``IOMAP_MAPPED`` and the filesystem must not place any
-   constaints on IO alignment or size.
+   constraints on IO alignment or size.
    The only constraints on I/O alignment are device level (minimum I/O
    size and alignment, typically sector size).
 
@@ -394,7 +394,7 @@ iomap is concerned:
 
  * The **upper** level primitive is provided by the filesystem to
    coordinate access to different iomap operations.
-   The exact primitive is specifc to the filesystem and operation,
+   The exact primitive is specific to the filesystem and operation,
    but is often a VFS inode, pagecache invalidation, or folio lock.
    For example, a filesystem might take ``i_rwsem`` before calling
    ``iomap_file_buffered_write`` and ``iomap_file_unshare`` to prevent

Documentation/filesystems/locking.rst

@@ -251,10 +251,10 @@ prototypes::
 	void (*readahead)(struct readahead_control *);
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata);
+				struct folio **foliop, void **fsdata);
 	int (*write_end)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata);
+				struct folio *folio, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
@@ -280,7 +280,7 @@ read_folio:		yes, unlocks				shared
 writepages:
 dirty_folio:		maybe
 readahead:		yes, unlocks				shared
-write_begin:		locks the page		 exclusive
+write_begin:		locks the folio		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
 invalidate_folio:	yes					exclusive

Documentation/filesystems/netfs_library.rst

@@ -116,7 +116,7 @@ The following services are provided:
  * Handle local caching, allowing cached data and server-read data to be
    interleaved for a single request.
 
- * Handle clearing of bufferage that aren't on the server.
+ * Handle clearing of bufferage that isn't on the server.
 
  * Handle retrying of reads that failed, switching reads from the cache to the
    server as necessary.

Documentation/filesystems/vfs.rst

@@ -810,7 +810,7 @@ cache in your filesystem.  The following members are defined:
 				struct page **pagep, void **fsdata);
 		int (*write_end)(struct file *, struct address_space *mapping,
 				 loff_t pos, unsigned len, unsigned copied,
-				 struct page *page, void *fsdata);
+				 struct folio *folio, void *fsdata);
 		sector_t (*bmap)(struct address_space *, sector_t);
 		void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 		bool (*release_folio)(struct folio *, gfp_t);
@@ -926,12 +926,12 @@ cache in your filesystem.  The following members are defined:
 	(if they haven't been read already) so that the updated blocks
 	can be written out properly.
 
-	The filesystem must return the locked pagecache page for the
-	specified offset, in ``*pagep``, for the caller to write into.
+	The filesystem must return the locked pagecache folio for the
+	specified offset, in ``*foliop``, for the caller to write into.
 
 	It must be able to cope with short writes (where the length
 	passed to write_begin is greater than the number of bytes copied
-	into the page).
+	into the folio).
 
 	A void * may be returned in fsdata, which then gets passed into
 	write_end.
@@ -944,8 +944,8 @@ cache in your filesystem.  The following members are defined:
 	called.  len is the original len passed to write_begin, and
 	copied is the amount that was able to be copied.
 
-	The filesystem must take care of unlocking the page and
-	releasing it refcount, and updating i_size.
+	The filesystem must take care of unlocking the folio,
+	decrementing its refcount, and updating i_size.
 
 	Returns < 0 on failure, otherwise the number of bytes (<=
 	'copied') that were able to be copied into pagecache.

MAINTAINERS

@@ -8635,6 +8635,7 @@ M:	Christian Brauner <brauner@kernel.org>
 R:	Jan Kara <jack@suse.cz>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
+T:	git https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git
 F:	fs/*
 F:	include/linux/fs.h
 F:	include/linux/fs_types.h

block/fops.c

@@ -451,20 +451,20 @@ static void blkdev_readahead(struct readahead_control *rac)
 }
 
 static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
-	return block_write_begin(mapping, pos, len, pagep, blkdev_get_block);
+	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
 }
 
 static int blkdev_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct page *page,
+		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
 		void *fsdata)
 {
 	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return ret;
 }
@@ -771,7 +771,7 @@ reexpand:
 
 #define	BLKDEV_FALLOC_FL_SUPPORTED					\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
-		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
+		 FALLOC_FL_ZERO_RANGE)
 
 static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
@@ -830,14 +830,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 					     len >> SECTOR_SHIFT, GFP_KERNEL,
 					     BLKDEV_ZERO_NOFALLBACK);
 		break;
-	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
-		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
-		if (error)
-			goto fail;
-
-		error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
-					     len >> SECTOR_SHIFT, GFP_KERNEL);
-		break;
 	default:
 		error = -EOPNOTSUPP;
 	}

drivers/char/adi.c

@@ -14,12 +14,6 @@
 
 #define MAX_BUF_SZ	PAGE_SIZE
 
-static int adi_open(struct inode *inode, struct file *file)
-{
-	file->f_mode |= FMODE_UNSIGNED_OFFSET;
-	return 0;
-}
-
 static int read_mcd_tag(unsigned long addr)
 {
 	long err;
@@ -196,7 +190,6 @@ static loff_t adi_llseek(struct file *file, loff_t offset, int whence)
 
 	if (offset != file->f_pos) {
 		file->f_pos = offset;
-		file->f_version = 0;
 		ret = offset;
 	}
 
@@ -206,9 +199,9 @@ static loff_t adi_llseek(struct file *file, loff_t offset, int whence)
 static const struct file_operations adi_fops = {
 	.owner		= THIS_MODULE,
 	.llseek		= adi_llseek,
-	.open		= adi_open,
 	.read		= adi_read,
 	.write		= adi_write,
+	.fop_flags	= FOP_UNSIGNED_OFFSET,
 };
 
 static struct miscdevice adi_miscdev = {

drivers/char/mem.c

@@ -643,6 +643,7 @@ static const struct file_operations __maybe_unused mem_fops = {
 	.get_unmapped_area = get_unmapped_area_mem,
 	.mmap_capabilities = memory_mmap_capabilities,
 #endif
+	.fop_flags	= FOP_UNSIGNED_OFFSET,
 };
 
 static const struct file_operations null_fops = {
@@ -693,7 +694,7 @@ static const struct memdev {
 	umode_t mode;
 } devlist[] = {
 #ifdef CONFIG_DEVMEM
-	[DEVMEM_MINOR] = { "mem", &mem_fops, FMODE_UNSIGNED_OFFSET, 0 },
+	[DEVMEM_MINOR] = { "mem", &mem_fops, 0, 0 },
 #endif
 	[3] = { "null", &null_fops, FMODE_NOWAIT, 0666 },
 #ifdef CONFIG_DEVPORT

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

@@ -2908,6 +2908,7 @@ static const struct file_operations amdgpu_driver_kms_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo = drm_show_fdinfo,
 #endif
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv)

drivers/gpu/drm/drm_file.c

@@ -318,6 +318,8 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	if (dev->switch_power_state != DRM_SWITCH_POWER_ON &&
 	    dev->switch_power_state != DRM_SWITCH_POWER_DYNAMIC_OFF)
 		return -EINVAL;
+	if (WARN_ON_ONCE(!(filp->f_op->fop_flags & FOP_UNSIGNED_OFFSET)))
+		return -EINVAL;
 
 	drm_dbg_core(dev, "comm=\"%s\", pid=%d, minor=%d\n",
 		     current->comm, task_pid_nr(current), minor->index);
@@ -335,7 +337,6 @@ int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	}
 
 	filp->private_data = priv;
-	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
 	priv->filp = filp;
 
 	mutex_lock(&dev->filelist_mutex);

drivers/gpu/drm/gma500/psb_drv.c

@@ -498,6 +498,7 @@ static const struct file_operations psb_gem_fops = {
 	.mmap = drm_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static const struct drm_driver driver = {

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -424,7 +424,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 	struct address_space *mapping = obj->base.filp->f_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
 	char __user *user_data = u64_to_user_ptr(arg->data_ptr);
-	u64 remain, offset;
+	u64 remain;
+	loff_t pos;
 	unsigned int pg;
 
 	/* Caller already validated user args */
@@ -457,12 +458,12 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 	 */
 
 	remain = arg->size;
-	offset = arg->offset;
-	pg = offset_in_page(offset);
+	pos = arg->offset;
+	pg = offset_in_page(pos);
 
 	do {
 		unsigned int len, unwritten;
-		struct page *page;
+		struct folio *folio;
 		void *data, *vaddr;
 		int err;
 		char __maybe_unused c;
@@ -480,21 +481,19 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 		if (err)
 			return err;
 
-		err = aops->write_begin(obj->base.filp, mapping, offset, len,
-					&page, &data);
+		err = aops->write_begin(obj->base.filp, mapping, pos, len,
+					&folio, &data);
 		if (err < 0)
 			return err;
 
-		vaddr = kmap_local_page(page);
+		vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos));
 		pagefault_disable();
-		unwritten = __copy_from_user_inatomic(vaddr + pg,
-						      user_data,
-						      len);
+		unwritten = __copy_from_user_inatomic(vaddr, user_data, len);
 		pagefault_enable();
 		kunmap_local(vaddr);
 
-		err = aops->write_end(obj->base.filp, mapping, offset, len,
-				      len - unwritten, page, data);
+		err = aops->write_end(obj->base.filp, mapping, pos, len,
+				      len - unwritten, folio, data);
 		if (err < 0)
 			return err;
 
@@ -504,7 +503,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 
 		remain -= len;
 		user_data += len;
-		offset += len;
+		pos += len;
 		pg = 0;
 	} while (remain);
 
@@ -660,7 +659,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 	struct drm_i915_gem_object *obj;
 	struct file *file;
 	const struct address_space_operations *aops;
-	resource_size_t offset;
+	loff_t pos;
 	int err;
 
 	GEM_WARN_ON(IS_DGFX(i915));
@@ -672,29 +671,27 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 
 	file = obj->base.filp;
 	aops = file->f_mapping->a_ops;
-	offset = 0;
+	pos = 0;
 	do {
 		unsigned int len = min_t(typeof(size), size, PAGE_SIZE);
-		struct page *page;
-		void *pgdata, *vaddr;
+		struct folio *folio;
+		void *fsdata;
 
-		err = aops->write_begin(file, file->f_mapping, offset, len,
-					&page, &pgdata);
+		err = aops->write_begin(file, file->f_mapping, pos, len,
+					&folio, &fsdata);
 		if (err < 0)
 			goto fail;
 
-		vaddr = kmap(page);
-		memcpy(vaddr, data, len);
-		kunmap(page);
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len);
 
-		err = aops->write_end(file, file->f_mapping, offset, len, len,
-				      page, pgdata);
+		err = aops->write_end(file, file->f_mapping, pos, len, len,
+				      folio, fsdata);
 		if (err < 0)
 			goto fail;
 
 		size -= len;
 		data += len;
-		offset += len;
+		pos += len;
 	} while (size);
 
 	return obj;

drivers/gpu/drm/i915/i915_driver.c

@@ -1671,6 +1671,7 @@ static const struct file_operations i915_driver_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo = drm_show_fdinfo,
 #endif
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static int

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -1274,6 +1274,7 @@ nouveau_driver_fops = {
 	.compat_ioctl = nouveau_compat_ioctl,
 #endif
 	.llseek = noop_llseek,
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static struct drm_driver

drivers/gpu/drm/radeon/radeon_drv.c

@@ -520,6 +520,7 @@ static const struct file_operations radeon_driver_kms_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = radeon_kms_compat_ioctl,
 #endif
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static const struct drm_ioctl_desc radeon_ioctls_kms[] = {

drivers/gpu/drm/tegra/drm.c

@@ -801,6 +801,7 @@ static const struct file_operations tegra_drm_fops = {
 	.read = drm_read,
 	.compat_ioctl = drm_compat_ioctl,
 	.llseek = noop_llseek,
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static int tegra_drm_context_cleanup(int id, void *p, void *data)

drivers/gpu/drm/vmwgfx/vmwgfx_drv.c

@@ -1609,6 +1609,7 @@ static const struct file_operations vmwgfx_driver_fops = {
 	.compat_ioctl = vmw_compat_ioctl,
 #endif
 	.llseek = noop_llseek,
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static const struct drm_driver driver = {

drivers/gpu/drm/xe/xe_device.c

@@ -241,6 +241,7 @@ static const struct file_operations xe_driver_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo = drm_show_fdinfo,
 #endif
+	.fop_flags = FOP_UNSIGNED_OFFSET,
 };
 
 static struct drm_driver driver = {

drivers/input/input.c

@@ -1079,33 +1079,31 @@ static inline void input_wakeup_procfs_readers(void)
 	wake_up(&input_devices_poll_wait);
 }
 
+struct input_seq_state {
+	unsigned short pos;
+	bool mutex_acquired;
+	int input_devices_state;
+};
+
 static __poll_t input_proc_devices_poll(struct file *file, poll_table *wait)
 {
+	struct seq_file *seq = file->private_data;
+	struct input_seq_state *state = seq->private;
+
 	poll_wait(file, &input_devices_poll_wait, wait);
-	if (file->f_version != input_devices_state) {
-		file->f_version = input_devices_state;
+	if (state->input_devices_state != input_devices_state) {
+		state->input_devices_state = input_devices_state;
 		return EPOLLIN | EPOLLRDNORM;
 	}
 
 	return 0;
 }
 
-union input_seq_state {
-	struct {
-		unsigned short pos;
-		bool mutex_acquired;
-	};
-	void *p;
-};
-
 static void *input_devices_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	union input_seq_state *state = (union input_seq_state *)&seq->private;
+	struct input_seq_state *state = seq->private;
 	int error;
 
-	/* We need to fit into seq->private pointer */
-	BUILD_BUG_ON(sizeof(union input_seq_state) != sizeof(seq->private));
-
 	error = mutex_lock_interruptible(&input_mutex);
 	if (error) {
 		state->mutex_acquired = false;
@@ -1124,7 +1122,7 @@ static void *input_devices_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 static void input_seq_stop(struct seq_file *seq, void *v)
 {
-	union input_seq_state *state = (union input_seq_state *)&seq->private;
+	struct input_seq_state *state = seq->private;
 
 	if (state->mutex_acquired)
 		mutex_unlock(&input_mutex);
@@ -1210,7 +1208,8 @@ static const struct seq_operations input_devices_seq_ops = {
 
 static int input_proc_devices_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &input_devices_seq_ops);
+	return seq_open_private(file, &input_devices_seq_ops,
+				sizeof(struct input_seq_state));
 }
 
 static const struct proc_ops input_devices_proc_ops = {
@@ -1218,17 +1217,14 @@ static const struct proc_ops input_devices_proc_ops = {
 	.proc_poll	= input_proc_devices_poll,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
-	.proc_release	= seq_release,
+	.proc_release	= seq_release_private,
 };
 
 static void *input_handlers_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	union input_seq_state *state = (union input_seq_state *)&seq->private;
+	struct input_seq_state *state = seq->private;
 	int error;
 
-	/* We need to fit into seq->private pointer */
-	BUILD_BUG_ON(sizeof(union input_seq_state) != sizeof(seq->private));
-
 	error = mutex_lock_interruptible(&input_mutex);
 	if (error) {
 		state->mutex_acquired = false;
@@ -1243,7 +1239,7 @@ static void *input_handlers_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *input_handlers_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
-	union input_seq_state *state = (union input_seq_state *)&seq->private;
+	struct input_seq_state *state = seq->private;
 
 	state->pos = *pos + 1;
 	return seq_list_next(v, &input_handler_list, pos);
@@ -1252,7 +1248,7 @@ static void *input_handlers_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 static int input_handlers_seq_show(struct seq_file *seq, void *v)
 {
 	struct input_handler *handler = container_of(v, struct input_handler, node);
-	union input_seq_state *state = (union input_seq_state *)&seq->private;
+	struct input_seq_state *state = seq->private;
 
 	seq_printf(seq, "N: Number=%u Name=%s", state->pos, handler->name);
 	if (handler->filter)
@@ -1273,14 +1269,15 @@ static const struct seq_operations input_handlers_seq_ops = {
 
 static int input_proc_handlers_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &input_handlers_seq_ops);
+	return seq_open_private(file, &input_handlers_seq_ops,
+				sizeof(struct input_seq_state));
 }
 
 static const struct proc_ops input_handlers_proc_ops = {
 	.proc_open	= input_proc_handlers_open,
 	.proc_read	= seq_read,
 	.proc_lseek	= seq_lseek,
-	.proc_release	= seq_release,
+	.proc_release	= seq_release_private,
 };
 
 static int __init input_proc_init(void)

drivers/md/md-bitmap.c

@@ -360,7 +360,7 @@ static int read_file_page(struct file *file, unsigned long index,
 	pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE,
 		 (unsigned long long)index << PAGE_SHIFT);
 
-	bh = alloc_page_buffers(page, blocksize, false);
+	bh = alloc_page_buffers(page, blocksize);
 	if (!bh) {
 		ret = -ENOMEM;
 		goto out;

drivers/net/tun.c

@@ -3452,6 +3452,12 @@ static int tun_chr_fasync(int fd, struct file *file, int on)
 	struct tun_file *tfile = file->private_data;
 	int ret;
 
+	if (on) {
+		ret = file_f_owner_allocate(file);
+		if (ret)
+			goto out;
+	}
+
 	if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
 		goto out;
 

drivers/s390/char/hmcdrv_dev.c

@@ -186,9 +186,6 @@ static loff_t hmcdrv_dev_seek(struct file *fp, loff_t pos, int whence)
 	if (pos < 0)
 		return -EINVAL;
 
-	if (fp->f_pos != pos)
-		++fp->f_version;
-
 	fp->f_pos = pos;
 	return pos;
 }

drivers/tty/tty_io.c

@@ -2225,6 +2225,12 @@ static int __tty_fasync(int fd, struct file *filp, int on)
 	if (tty_paranoia_check(tty, file_inode(filp), "tty_fasync"))
 		goto out;
 
+	if (on) {
+		retval = file_f_owner_allocate(filp);
+		if (retval)
+			goto out;
+	}
+
 	retval = fasync_helper(fd, filp, on, &tty->fasync);
 	if (retval <= 0)
 		goto out;

fs/9p/vfs_addr.c

@@ -68,17 +68,22 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 	struct p9_fid *fid = rreq->netfs_priv;
+	unsigned long long pos = subreq->start + subreq->transferred;
 	int total, err;
 
-	total = p9_client_read(fid, subreq->start + subreq->transferred,
-			       &subreq->io_iter, &err);
+	total = p9_client_read(fid, pos, &subreq->io_iter, &err);
 
 	/* if we just extended the file size, any portion not in
 	 * cache won't be on server and is zeroes */
 	if (subreq->rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (pos + total >= i_size_read(rreq->inode))
+		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
 
-	netfs_subreq_terminated(subreq, err ?: total, false);
+	if (!err)
+		subreq->transferred += total;
+
+	netfs_read_subreq_terminated(subreq, err, false);
 }
 
 /**

fs/adfs/inode.c

@@ -55,12 +55,11 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int adfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))

fs/affs/dir.c

@@ -17,13 +17,44 @@
 #include <linux/iversion.h>
 #include "affs.h"
 
+struct affs_dir_data {
+	unsigned long ino;
+	u64 cookie;
+};
+
 static int affs_readdir(struct file *, struct dir_context *);
 
+static loff_t affs_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct affs_dir_data *data = file->private_data;
+
+	return generic_llseek_cookie(file, offset, whence, &data->cookie);
+}
+
+static int affs_dir_open(struct inode *inode, struct file *file)
+{
+	struct affs_dir_data	*data;
+
+	data = kzalloc(sizeof(struct affs_dir_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+	file->private_data = data;
+	return 0;
+}
+
+static int affs_dir_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
 const struct file_operations affs_dir_operations = {
+	.open		= affs_dir_open,
 	.read		= generic_read_dir,
-	.llseek		= generic_file_llseek,
+	.llseek		= affs_dir_llseek,
 	.iterate_shared	= affs_readdir,
 	.fsync		= affs_file_fsync,
+	.release	= affs_dir_release,
 };
 
 /*
@@ -45,6 +76,7 @@ static int
 affs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct inode		*inode = file_inode(file);
+	struct affs_dir_data	*data = file->private_data;
 	struct super_block	*sb = inode->i_sb;
 	struct buffer_head	*dir_bh = NULL;
 	struct buffer_head	*fh_bh = NULL;
@@ -59,7 +91,7 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	pr_debug("%s(ino=%lu,f_pos=%llx)\n", __func__, inode->i_ino, ctx->pos);
 
 	if (ctx->pos < 2) {
-		file->private_data = (void *)0;
+		data->ino = 0;
 		if (!dir_emit_dots(file, ctx))
 			return 0;
 	}
@@ -80,8 +112,8 @@ affs_readdir(struct file *file, struct dir_context *ctx)
 	/* If the directory hasn't changed since the last call to readdir(),
 	 * we can jump directly to where we left off.
 	 */
-	ino = (u32)(long)file->private_data;
-	if (ino && inode_eq_iversion(inode, file->f_version)) {
+	ino = data->ino;
+	if (ino && inode_eq_iversion(inode, data->cookie)) {
 		pr_debug("readdir() left off=%d\n", ino);
 		goto inside;
 	}
@@ -131,8 +163,8 @@ inside:
 		} while (ino);
 	}
 done:
-	file->f_version = inode_query_iversion(inode);
-	file->private_data = (void *)(long)ino;
+	data->cookie = inode_query_iversion(inode);
+	data->ino = ino;
 	affs_brelse(fh_bh);
 
 out_brelse_dir:

fs/affs/file.c

@@ -417,12 +417,11 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static int affs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -433,12 +432,12 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 
 static int affs_write_end(struct file *file, struct address_space *mapping,
 			  loff_t pos, unsigned int len, unsigned int copied,
-			  struct page *page, void *fsdata)
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
 	/* Clear Archived bit on file writes, as AmigaOS would do */
 	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
@@ -648,7 +647,7 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio)
 
 static int affs_write_begin_ofs(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata)
+				struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct folio *folio;
@@ -671,7 +670,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 			mapping_gfp_mask(mapping));
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
-	*pagep = &folio->page;
+	*foliop = folio;
 
 	if (folio_test_uptodate(folio))
 		return 0;
@@ -687,9 +686,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 
 static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *bh, *prev_bh;
@@ -882,14 +880,14 @@ affs_truncate(struct inode *inode)
 
 	if (inode->i_size > AFFS_I(inode)->mmu_private) {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page;
+		struct folio *folio;
 		void *fsdata = NULL;
 		loff_t isize = inode->i_size;
 		int res;
 
-		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata);
+		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &folio, &fsdata);
 		if (!res)
-			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata);
+			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, folio, fsdata);
 		else
 			inode->i_size = AFFS_I(inode)->mmu_private;
 		mark_inode_dirty(inode);

fs/afs/file.c

@@ -16,6 +16,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 #include "internal.h"
 
 static int afs_file_mmap(struct file *file, struct vm_area_struct *vma);
@@ -242,9 +243,10 @@ static void afs_fetch_data_notify(struct afs_operation *op)
 
 	req->error = error;
 	if (subreq) {
-		if (subreq->rreq->origin != NETFS_DIO_READ)
-			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
-		netfs_subreq_terminated(subreq, error ?: req->actual_len, false);
+		subreq->rreq->i_size = req->file_size;
+		if (req->pos + req->actual_len >= req->file_size)
+			__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
+		netfs_read_subreq_terminated(subreq, error, false);
 		req->subreq = NULL;
 	} else if (req->done) {
 		req->done(req);
@@ -262,6 +264,12 @@ static void afs_fetch_data_success(struct afs_operation *op)
 	afs_fetch_data_notify(op);
 }
 
+static void afs_fetch_data_aborted(struct afs_operation *op)
+{
+	afs_check_for_remote_deletion(op);
+	afs_fetch_data_notify(op);
+}
+
 static void afs_fetch_data_put(struct afs_operation *op)
 {
 	op->fetch.req->error = afs_op_error(op);
@@ -272,7 +280,7 @@ static const struct afs_operation_ops afs_fetch_data_operation = {
 	.issue_afs_rpc	= afs_fs_fetch_data,
 	.issue_yfs_rpc	= yfs_fs_fetch_data,
 	.success	= afs_fetch_data_success,
-	.aborted	= afs_check_for_remote_deletion,
+	.aborted	= afs_fetch_data_aborted,
 	.failed		= afs_fetch_data_notify,
 	.put		= afs_fetch_data_put,
 };
@@ -294,7 +302,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req)
 	op = afs_alloc_operation(req->key, vnode->volume);
 	if (IS_ERR(op)) {
 		if (req->subreq)
-			netfs_subreq_terminated(req->subreq, PTR_ERR(op), false);
+			netfs_read_subreq_terminated(req->subreq, PTR_ERR(op), false);
 		return PTR_ERR(op);
 	}
 
@@ -305,14 +313,15 @@ int afs_fetch_data(struct afs_vnode *vnode, struct afs_read *req)
 	return afs_do_sync_operation(op);
 }
 
-static void afs_issue_read(struct netfs_io_subrequest *subreq)
+static void afs_read_worker(struct work_struct *work)
 {
+	struct netfs_io_subrequest *subreq = container_of(work, struct netfs_io_subrequest, work);
 	struct afs_vnode *vnode = AFS_FS_I(subreq->rreq->inode);
 	struct afs_read *fsreq;
 
 	fsreq = afs_alloc_read(GFP_NOFS);
 	if (!fsreq)
-		return netfs_subreq_terminated(subreq, -ENOMEM, false);
+		return netfs_read_subreq_terminated(subreq, -ENOMEM, false);
 
 	fsreq->subreq	= subreq;
 	fsreq->pos	= subreq->start + subreq->transferred;
@@ -321,10 +330,17 @@ static void afs_issue_read(struct netfs_io_subrequest *subreq)
 	fsreq->vnode	= vnode;
 	fsreq->iter	= &subreq->io_iter;
 
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	afs_fetch_data(fsreq->vnode, fsreq);
 	afs_put_read(fsreq);
 }
 
+static void afs_issue_read(struct netfs_io_subrequest *subreq)
+{
+	INIT_WORK(&subreq->work, afs_read_worker);
+	queue_work(system_long_wq, &subreq->work);
+}
+
 static int afs_symlink_read_folio(struct file *file, struct folio *folio)
 {
 	struct afs_vnode *vnode = AFS_FS_I(folio->mapping->host);

fs/afs/fsclient.c

@@ -304,6 +304,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 	struct afs_vnode_param *vp = &op->file[0];
 	struct afs_read *req = op->fetch.req;
 	const __be32 *bp;
+	size_t count_before;
 	int ret;
 
 	_enter("{%u,%zu,%zu/%llu}",
@@ -345,10 +346,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 
 		/* extract the returned data */
 	case 2:
-		_debug("extract data %zu/%llu",
-		       iov_iter_count(call->iter), req->actual_len);
+		count_before = call->iov_len;
+		_debug("extract data %zu/%llu", count_before, req->actual_len);
 
 		ret = afs_extract_data(call, true);
+		if (req->subreq) {
+			req->subreq->transferred += count_before - call->iov_len;
+			netfs_read_subreq_progress(req->subreq, false);
+		}
 		if (ret < 0)
 			return ret;
 

fs/afs/write.c

@@ -89,10 +89,12 @@ static const struct afs_operation_ops afs_store_data_operation = {
  */
 void afs_prepare_write(struct netfs_io_subrequest *subreq)
 {
+	struct netfs_io_stream *stream = &subreq->rreq->io_streams[subreq->stream_nr];
+
 	//if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags))
 	//	subreq->max_len = 512 * 1024;
 	//else
-	subreq->max_len = 256 * 1024 * 1024;
+	stream->sreq_max_len = 256 * 1024 * 1024;
 }
 
 /*

fs/afs/yfsclient.c

@@ -355,6 +355,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 	struct afs_vnode_param *vp = &op->file[0];
 	struct afs_read *req = op->fetch.req;
 	const __be32 *bp;
+	size_t count_before;
 	int ret;
 
 	_enter("{%u,%zu, %zu/%llu}",
@@ -391,10 +392,14 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call)
 
 		/* extract the returned data */
 	case 2:
-		_debug("extract data %zu/%llu",
-		       iov_iter_count(call->iter), req->actual_len);
+		count_before = call->iov_len;
+		_debug("extract data %zu/%llu", count_before, req->actual_len);
 
 		ret = afs_extract_data(call, true);
+		if (req->subreq) {
+			req->subreq->transferred += count_before - call->iov_len;
+			netfs_read_subreq_progress(req->subreq, false);
+		}
 		if (ret < 0)
 			return ret;
 

fs/aio.c

@@ -100,7 +100,7 @@ struct kioctx {
 
 	unsigned long		user_id;
 
-	struct __percpu kioctx_cpu *cpu;
+	struct kioctx_cpu __percpu *cpu;
 
 	/*
 	 * For percpu reqs_available, number of slots we move to/from global

fs/autofs/autofs_i.h

@@ -62,6 +62,7 @@ struct autofs_info {
 	struct list_head expiring;
 
 	struct autofs_sb_info *sbi;
+	unsigned long exp_timeout;
 	unsigned long last_used;
 	int count;
 
@@ -81,6 +82,9 @@ struct autofs_info {
 					*/
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
+#define AUTOFS_INF_EXPIRE_SET	(1<<3) /* per-dentry expire timeout set for
+					  this mount point.
+					*/
 struct autofs_wait_queue {
 	wait_queue_head_t queue;
 	struct autofs_wait_queue *next;

fs/autofs/dev-ioctl.c

@@ -128,7 +128,13 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 			goto out;
 		}
 
+		/* Setting the per-dentry expire timeout requires a trailing
+		 * path component, ie. no '/', so invert the logic of the
+		 * check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD.
+		 */
 		err = check_name(param->path);
+		if (cmd == AUTOFS_DEV_IOCTL_TIMEOUT_CMD)
+			err = err ? 0 : -EINVAL;
 		if (err) {
 			pr_warn("invalid path supplied for cmd(0x%08x)\n",
 				cmd);
@@ -396,16 +402,97 @@ static int autofs_dev_ioctl_catatonic(struct file *fp,
 	return 0;
 }
 
-/* Set the autofs mount timeout */
+/*
+ * Set the autofs mount expire timeout.
+ *
+ * There are two places an expire timeout can be set, in the autofs
+ * super block info. (this is all that's needed for direct and offset
+ * mounts because there's a distinct mount corresponding to each of
+ * these) and per-dentry within within the dentry info. If a per-dentry
+ * timeout is set it will override the expire timeout set in the parent
+ * autofs super block info.
+ *
+ * If setting the autofs super block expire timeout the autofs_dev_ioctl
+ * size field will be equal to the autofs_dev_ioctl structure size. If
+ * setting the per-dentry expire timeout the mount point name is passed
+ * in the autofs_dev_ioctl path field and the size field updated to
+ * reflect this.
+ *
+ * Setting the autofs mount expire timeout sets the timeout in the super
+ * block info. struct. Setting the per-dentry timeout does a little more.
+ * If the timeout is equal to -1 the per-dentry timeout (and flag) is
+ * cleared which reverts to using the super block timeout, otherwise if
+ * timeout is 0 the timeout is set to this value and the flag is left
+ * set which disables expiration for the mount point, lastly the flag
+ * and the timeout are set enabling the dentry to use this timeout.
+ */
 static int autofs_dev_ioctl_timeout(struct file *fp,
 				    struct autofs_sb_info *sbi,
 				    struct autofs_dev_ioctl *param)
 {
-	unsigned long timeout;
+	unsigned long timeout = param->timeout.timeout;
+
+	/* If setting the expire timeout for an individual indirect
+	 * mount point dentry the mount trailing component path is
+	 * placed in param->path and param->size adjusted to account
+	 * for it otherwise param->size it is set to the structure
+	 * size.
+	 */
+	if (param->size == AUTOFS_DEV_IOCTL_SIZE) {
+		param->timeout.timeout = sbi->exp_timeout / HZ;
+		sbi->exp_timeout = timeout * HZ;
+	} else {
+		struct dentry *base = fp->f_path.dentry;
+		struct inode *inode = base->d_inode;
+		int path_len = param->size - AUTOFS_DEV_IOCTL_SIZE - 1;
+		struct dentry *dentry;
+		struct autofs_info *ino;
+
+		if (!autofs_type_indirect(sbi->type))
+			return -EINVAL;
+
+		/* An expire timeout greater than the superblock timeout
+		 * could be a problem at shutdown but the super block
+		 * timeout itself can change so all we can really do is
+		 * warn the user.
+		 */
+		if (timeout >= sbi->exp_timeout)
+			pr_warn("per-mount expire timeout is greater than "
+				"the parent autofs mount timeout which could "
+				"prevent shutdown\n");
+
+		inode_lock_shared(inode);
+		dentry = try_lookup_one_len(param->path, base, path_len);
+		inode_unlock_shared(inode);
+		if (IS_ERR_OR_NULL(dentry))
+			return dentry ? PTR_ERR(dentry) : -ENOENT;
+		ino = autofs_dentry_ino(dentry);
+		if (!ino) {
+			dput(dentry);
+			return -ENOENT;
+		}
+
+		if (ino->exp_timeout && ino->flags & AUTOFS_INF_EXPIRE_SET)
+			param->timeout.timeout = ino->exp_timeout / HZ;
+		else
+			param->timeout.timeout = sbi->exp_timeout / HZ;
+
+		if (timeout == -1) {
+			/* Revert to using the super block timeout */
+			ino->flags &= ~AUTOFS_INF_EXPIRE_SET;
+			ino->exp_timeout = 0;
+		} else {
+			/* Set the dentry expire flag and timeout.
+			 *
+			 * If timeout is 0 it will prevent the expire
+			 * of this particular automount.
+			 */
+			ino->flags |= AUTOFS_INF_EXPIRE_SET;
+			ino->exp_timeout = timeout * HZ;
+		}
+		dput(dentry);
+	}
 
-	timeout = param->timeout.timeout;
-	param->timeout.timeout = sbi->exp_timeout / HZ;
-	sbi->exp_timeout = timeout * HZ;
 	return 0;
 }
 

fs/autofs/expire.c

@@ -429,8 +429,6 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb,
 	if (!root)
 		return NULL;
 
-	timeout = sbi->exp_timeout;
-
 	dentry = NULL;
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
@@ -441,6 +439,11 @@ static struct dentry *autofs_expire_indirect(struct super_block *sb,
 		}
 		spin_unlock(&sbi->fs_lock);
 
+		if (ino->flags & AUTOFS_INF_EXPIRE_SET)
+			timeout = ino->exp_timeout;
+		else
+			timeout = sbi->exp_timeout;
+
 		expired = should_expire(dentry, mnt, timeout, how);
 		if (!expired)
 			continue;

fs/autofs/inode.c

@@ -19,6 +19,7 @@ struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi)
 		INIT_LIST_HEAD(&ino->expiring);
 		ino->last_used = jiffies;
 		ino->sbi = sbi;
+		ino->exp_timeout = -1;
 		ino->count = 1;
 	}
 	return ino;
@@ -28,6 +29,7 @@ void autofs_clean_ino(struct autofs_info *ino)
 {
 	ino->uid = GLOBAL_ROOT_UID;
 	ino->gid = GLOBAL_ROOT_GID;
+	ino->exp_timeout = -1;
 	ino->last_used = jiffies;
 }
 
@@ -172,8 +174,7 @@ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi,
 	ret = autofs_check_pipe(pipe);
 	if (ret < 0) {
 		errorf(fc, "Invalid/unusable pipe");
-		if (param->type != fs_value_is_file)
-			fput(pipe);
+		fput(pipe);
 		return -EBADF;
 	}
 

fs/bcachefs/fs-io-buffered.c

@@ -659,7 +659,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc
 
 int bch2_write_begin(struct file *file, struct address_space *mapping,
 		     loff_t pos, unsigned len,
-		     struct page **pagep, void **fsdata)
+		     struct folio **foliop, void **fsdata)
 {
 	struct bch_inode_info *inode = to_bch_ei(mapping->host);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
@@ -728,12 +728,11 @@ out:
 		goto err;
 	}
 
-	*pagep = &folio->page;
+	*foliop = folio;
 	return 0;
 err:
 	folio_unlock(folio);
 	folio_put(folio);
-	*pagep = NULL;
 err_unlock:
 	bch2_pagecache_add_put(inode);
 	kfree(res);
@@ -743,12 +742,11 @@ err_unlock:
 
 int bch2_write_end(struct file *file, struct address_space *mapping,
 		   loff_t pos, unsigned len, unsigned copied,
-		   struct page *page, void *fsdata)
+		   struct folio *folio, void *fsdata)
 {
 	struct bch_inode_info *inode = to_bch_ei(mapping->host);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
 	struct bch2_folio_reservation *res = fsdata;
-	struct folio *folio = page_folio(page);
 	unsigned offset = pos - folio_pos(folio);
 
 	lockdep_assert_held(&inode->v.i_rwsem);

fs/bcachefs/fs-io-buffered.h

@@ -10,10 +10,10 @@ int bch2_read_folio(struct file *, struct folio *);
 int bch2_writepages(struct address_space *, struct writeback_control *);
 void bch2_readahead(struct readahead_control *);
 
-int bch2_write_begin(struct file *, struct address_space *, loff_t,
-		     unsigned, struct page **, void **);
+int bch2_write_begin(struct file *, struct address_space *, loff_t pos,
+		     unsigned len, struct folio **, void **);
 int bch2_write_end(struct file *, struct address_space *, loff_t,
-		   unsigned, unsigned, struct page *, void *);
+		   unsigned len, unsigned copied, struct folio *, void *);
 
 ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *);
 

fs/bcachefs/fs.c

@@ -1652,14 +1652,16 @@ again:
 				break;
 			}
 		} else if (clean_pass && this_pass_clean) {
-			wait_queue_head_t *wq = bit_waitqueue(&inode->v.i_state, __I_NEW);
-			DEFINE_WAIT_BIT(wait, &inode->v.i_state, __I_NEW);
+			struct wait_bit_queue_entry wqe;
+			struct wait_queue_head *wq_head;
 
-			prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+			wq_head = inode_bit_waitqueue(&wqe, &inode->v, __I_NEW);
+			prepare_to_wait_event(wq_head, &wqe.wq_entry,
+					      TASK_UNINTERRUPTIBLE);
 			mutex_unlock(&c->vfs_inodes_lock);
 
 			schedule();
-			finish_wait(wq, &wait.wq_entry);
+			finish_wait(wq_head, &wqe.wq_entry);
 			goto again;
 		}
 	}

fs/bfs/file.c

@@ -172,11 +172,11 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int bfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, bfs_get_block);
 	if (unlikely(ret))
 		bfs_write_failed(mapping, pos + len);
 

fs/buffer.c

@@ -774,12 +774,11 @@ EXPORT_SYMBOL(block_dirty_folio);
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list)
 {
 	struct buffer_head *bh;
-	struct list_head tmp;
 	struct address_space *mapping;
 	int err = 0, err2;
 	struct blk_plug plug;
+	LIST_HEAD(tmp);
 
-	INIT_LIST_HEAD(&tmp);
 	blk_start_plug(&plug);
 
 	spin_lock(lock);
@@ -958,12 +957,9 @@ no_grow:
 }
 EXPORT_SYMBOL_GPL(folio_alloc_buffers);
 
-struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
-				       bool retry)
+struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size)
 {
 	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
-	if (retry)
-		gfp |= __GFP_NOFAIL;
 
 	return folio_alloc_buffers(page_folio(page), size, gfp);
 }
@@ -2168,11 +2164,10 @@ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len,
 	return err;
 }
 
-int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block)
 {
-	return __block_write_begin_int(page_folio(page), pos, len, get_block,
-				       NULL);
+	return __block_write_begin_int(folio, pos, len, get_block, NULL);
 }
 EXPORT_SYMBOL(__block_write_begin);
 
@@ -2222,33 +2217,33 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
  * The filesystem needs to handle block truncation upon failure.
  */
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-		struct page **pagep, get_block_t *get_block)
+		struct folio **foliop, get_block_t *get_block)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
-	struct page *page;
+	struct folio *folio;
 	int status;
 
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
-		return -ENOMEM;
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
 
-	status = __block_write_begin(page, pos, len, get_block);
+	status = __block_write_begin_int(folio, pos, len, get_block, NULL);
 	if (unlikely(status)) {
-		unlock_page(page);
-		put_page(page);
-		page = NULL;
+		folio_unlock(folio);
+		folio_put(folio);
+		folio = NULL;
 	}
 
-	*pagep = page;
+	*foliop = folio;
 	return status;
 }
 EXPORT_SYMBOL(block_write_begin);
 
 int block_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	size_t start = pos - folio_pos(folio);
 
 	if (unlikely(copied < len)) {
@@ -2280,19 +2275,19 @@ EXPORT_SYMBOL(block_write_end);
 
 int generic_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
 	bool i_size_changed = false;
 
-	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
 	/*
 	 * No need to use i_size_read() here, the i_size cannot change under us
 	 * because we hold i_rwsem.
 	 *
-	 * But it's important to update i_size while still holding page lock:
+	 * But it's important to update i_size while still holding folio lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
 	if (pos + copied > inode->i_size) {
@@ -2300,8 +2295,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 		i_size_changed = true;
 	}
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
@@ -2467,7 +2462,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 {
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	int err;
 
@@ -2475,11 +2470,11 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 	if (err)
 		goto out;
 
-	err = aops->write_begin(NULL, mapping, size, 0, &page, &fsdata);
+	err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata);
 	if (err)
 		goto out;
 
-	err = aops->write_end(NULL, mapping, size, 0, 0, page, fsdata);
+	err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata);
 	BUG_ON(err > 0);
 
 out:
@@ -2493,7 +2488,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	const struct address_space_operations *aops = mapping->a_ops;
 	unsigned int blocksize = i_blocksize(inode);
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	pgoff_t index, curidx;
 	loff_t curpos;
@@ -2512,12 +2507,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		len = PAGE_SIZE - zerofrom;
 
 		err = aops->write_begin(file, mapping, curpos, len,
-					    &page, &fsdata);
+					    &folio, &fsdata);
 		if (err)
 			goto out;
-		zero_user(page, zerofrom, len);
+		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
 		err = aops->write_end(file, mapping, curpos, len, len,
-						page, fsdata);
+						folio, fsdata);
 		if (err < 0)
 			goto out;
 		BUG_ON(err != len);
@@ -2545,12 +2540,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		len = offset - zerofrom;
 
 		err = aops->write_begin(file, mapping, curpos, len,
-					    &page, &fsdata);
+					    &folio, &fsdata);
 		if (err)
 			goto out;
-		zero_user(page, zerofrom, len);
+		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
 		err = aops->write_end(file, mapping, curpos, len, len,
-						page, fsdata);
+						folio, fsdata);
 		if (err < 0)
 			goto out;
 		BUG_ON(err != len);
@@ -2566,7 +2561,7 @@ out:
  */
 int cont_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata,
+			struct folio **foliop, void **fsdata,
 			get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
@@ -2584,7 +2579,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 		(*bytes)++;
 	}
 
-	return block_write_begin(mapping, pos, len, pagep, get_block);
+	return block_write_begin(mapping, pos, len, foliop, get_block);
 }
 EXPORT_SYMBOL(cont_write_begin);
 

fs/cachefiles/io.c

@@ -627,11 +627,12 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *wreq = subreq->rreq;
 	struct netfs_cache_resources *cres = &wreq->cache_resources;
+	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 
 	_enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start);
 
-	subreq->max_len = MAX_RW_COUNT;
-	subreq->max_nr_segs = BIO_MAX_VECS;
+	stream->sreq_max_len = MAX_RW_COUNT;
+	stream->sreq_max_segs = BIO_MAX_VECS;
 
 	if (!cachefiles_cres_file(cres)) {
 		if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE))
@@ -647,6 +648,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 	struct netfs_cache_resources *cres = &wreq->cache_resources;
 	struct cachefiles_object *object = cachefiles_cres_object(cres);
 	struct cachefiles_cache *cache = object->volume->cache;
+	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 	const struct cred *saved_cred;
 	size_t off, pre, post, len = subreq->len;
 	loff_t start = subreq->start;
@@ -660,6 +662,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 	if (off) {
 		pre = CACHEFILES_DIO_BLOCK_SIZE - off;
 		if (pre >= len) {
+			fscache_count_dio_misfit();
 			netfs_write_subrequest_terminated(subreq, len, false);
 			return;
 		}
@@ -670,10 +673,22 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 	}
 
 	/* We also need to end on the cache granularity boundary */
+	if (start + len == wreq->i_size) {
+		size_t part = len % CACHEFILES_DIO_BLOCK_SIZE;
+		size_t need = CACHEFILES_DIO_BLOCK_SIZE - part;
+
+		if (part && stream->submit_extendable_to >= need) {
+			len += need;
+			subreq->len += need;
+			subreq->io_iter.count += need;
+		}
+	}
+
 	post = len & (CACHEFILES_DIO_BLOCK_SIZE - 1);
 	if (post) {
 		len -= post;
 		if (len == 0) {
+			fscache_count_dio_misfit();
 			netfs_write_subrequest_terminated(subreq, post, false);
 			return;
 		}

fs/cachefiles/xattr.c

@@ -64,9 +64,15 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object)
 		memcpy(buf->data, fscache_get_aux(object->cookie), len);
 
 	ret = cachefiles_inject_write_error();
-	if (ret == 0)
-		ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache,
-				   buf, sizeof(struct cachefiles_xattr) + len, 0);
+	if (ret == 0) {
+		ret = mnt_want_write_file(file);
+		if (ret == 0) {
+			ret = vfs_setxattr(&nop_mnt_idmap, dentry,
+					   cachefiles_xattr_cache, buf,
+					   sizeof(struct cachefiles_xattr) + len, 0);
+			mnt_drop_write_file(file);
+		}
+	}
 	if (ret < 0) {
 		trace_cachefiles_vfs_error(object, file_inode(file), ret,
 					   cachefiles_trace_setxattr_error);
@@ -151,8 +157,14 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
 	int ret;
 
 	ret = cachefiles_inject_remove_error();
-	if (ret == 0)
-		ret = vfs_removexattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache);
+	if (ret == 0) {
+		ret = mnt_want_write(cache->mnt);
+		if (ret == 0) {
+			ret = vfs_removexattr(&nop_mnt_idmap, dentry,
+					      cachefiles_xattr_cache);
+			mnt_drop_write(cache->mnt);
+		}
+	}
 	if (ret < 0) {
 		trace_cachefiles_vfs_error(object, d_inode(dentry), ret,
 					   cachefiles_trace_remxattr_error);
@@ -208,9 +220,15 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume)
 	memcpy(buf->data, p, volume->vcookie->coherency_len);
 
 	ret = cachefiles_inject_write_error();
-	if (ret == 0)
-		ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache,
-				   buf, len, 0);
+	if (ret == 0) {
+		ret = mnt_want_write(volume->cache->mnt);
+		if (ret == 0) {
+			ret = vfs_setxattr(&nop_mnt_idmap, dentry,
+					   cachefiles_xattr_cache,
+					   buf, len, 0);
+			mnt_drop_write(volume->cache->mnt);
+		}
+	}
 	if (ret < 0) {
 		trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret,
 					   cachefiles_trace_setxattr_error);

fs/ceph/addr.c

@@ -13,6 +13,7 @@
 #include <linux/iversion.h>
 #include <linux/ktime.h>
 #include <linux/netfs.h>
+#include <trace/events/netfs.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -205,21 +206,6 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq)
 	}
 }
 
-static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)
-{
-	struct inode *inode = subreq->rreq->inode;
-	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	u64 objno, objoff;
-	u32 xlen;
-
-	/* Truncate the extent at the end of the current block */
-	ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
-				      &objno, &objoff, &xlen);
-	subreq->len = min(xlen, fsc->mount_options->rsize);
-	return true;
-}
-
 static void finish_netfs_read(struct ceph_osd_request *req)
 {
 	struct inode *inode = req->r_inode;
@@ -264,7 +250,12 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 				     calc_pages_for(osd_data->alignment,
 					osd_data->length), false);
 	}
-	netfs_subreq_terminated(subreq, err, false);
+	if (err > 0) {
+		subreq->transferred = err;
+		err = 0;
+	}
+	trace_netfs_sreq(subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(subreq, err, false);
 	iput(req->r_inode);
 	ceph_dec_osd_stopping_blocker(fsc->mdsc);
 }
@@ -278,7 +269,6 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	struct ceph_mds_request *req;
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct iov_iter iter;
 	ssize_t err = 0;
 	size_t len;
 	int mode;
@@ -301,6 +291,7 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INLINE_DATA);
 	req->r_num_caps = 2;
 
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	if (err < 0)
 		goto out;
@@ -314,17 +305,36 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	}
 
 	len = min_t(size_t, iinfo->inline_len - subreq->start, subreq->len);
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &iter);
-	if (err == 0)
+	err = copy_to_iter(iinfo->inline_data + subreq->start, len, &subreq->io_iter);
+	if (err == 0) {
 		err = -EFAULT;
+	} else {
+		subreq->transferred += err;
+		err = 0;
+	}
 
 	ceph_mdsc_put_request(req);
 out:
-	netfs_subreq_terminated(subreq, err, false);
+	netfs_read_subreq_terminated(subreq, err, false);
 	return true;
 }
 
+static int ceph_netfs_prepare_read(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct inode *inode = rreq->inode;
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
+	u64 objno, objoff;
+	u32 xlen;
+
+	/* Truncate the extent at the end of the current block */
+	ceph_calc_file_object_mapping(&ci->i_layout, subreq->start, subreq->len,
+				      &objno, &objoff, &xlen);
+	rreq->io_streams[0].sreq_max_len = umin(xlen, fsc->mount_options->rsize);
+	return 0;
+}
+
 static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
@@ -334,9 +344,8 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	struct ceph_client *cl = fsc->client;
 	struct ceph_osd_request *req = NULL;
 	struct ceph_vino vino = ceph_vino(inode);
-	struct iov_iter iter;
-	int err = 0;
-	u64 len = subreq->len;
+	int err;
+	u64 len;
 	bool sparse = IS_ENCRYPTED(inode) || ceph_test_mount_opt(fsc, SPARSEREAD);
 	u64 off = subreq->start;
 	int extent_cnt;
@@ -349,6 +358,12 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq))
 		return;
 
+	// TODO: This rounding here is slightly dodgy.  It *should* work, for
+	// now, as the cache only deals in blocks that are a multiple of
+	// PAGE_SIZE and fscrypt blocks are at most PAGE_SIZE.  What needs to
+	// happen is for the fscrypt driving to be moved into netfslib and the
+	// data in the cache also to be stored encrypted.
+	len = subreq->len;
 	ceph_fscrypt_adjust_off_and_len(inode, &off, &len);
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino,
@@ -371,8 +386,6 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	doutc(cl, "%llx.%llx pos=%llu orig_len=%zu len=%llu\n",
 	      ceph_vinop(inode), subreq->start, subreq->len, len);
 
-	iov_iter_xarray(&iter, ITER_DEST, &rreq->mapping->i_pages, subreq->start, len);
-
 	/*
 	 * FIXME: For now, use CEPH_OSD_DATA_TYPE_PAGES instead of _ITER for
 	 * encrypted inodes. We'd need infrastructure that handles an iov_iter
@@ -384,7 +397,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 		struct page **pages;
 		size_t page_off;
 
-		err = iov_iter_get_pages_alloc2(&iter, &pages, len, &page_off);
+		err = iov_iter_get_pages_alloc2(&subreq->io_iter, &pages, len, &page_off);
 		if (err < 0) {
 			doutc(cl, "%llx.%llx failed to allocate pages, %d\n",
 			      ceph_vinop(inode), err);
@@ -399,7 +412,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false,
 						 false);
 	} else {
-		osd_req_op_extent_osd_iter(req, 0, &iter);
+		osd_req_op_extent_osd_iter(req, 0, &subreq->io_iter);
 	}
 	if (!ceph_inc_osd_stopping_blocker(fsc->mdsc)) {
 		err = -EIO;
@@ -410,17 +423,19 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq)
 	req->r_inode = inode;
 	ihold(inode);
 
+	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	ceph_osdc_start_request(req->r_osdc, req);
 out:
 	ceph_osdc_put_request(req);
 	if (err)
-		netfs_subreq_terminated(subreq, err, false);
+		netfs_read_subreq_terminated(subreq, err, false);
 	doutc(cl, "%llx.%llx result %d\n", ceph_vinop(inode), err);
 }
 
 static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 {
 	struct inode *inode = rreq->inode;
+	struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
 	struct ceph_client *cl = ceph_inode_to_client(inode);
 	int got = 0, want = CEPH_CAP_FILE_CACHE;
 	struct ceph_netfs_request_data *priv;
@@ -472,6 +487,7 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 
 	priv->caps = got;
 	rreq->netfs_priv = priv;
+	rreq->io_streams[0].sreq_max_len = fsc->mount_options->rsize;
 
 out:
 	if (ret < 0)
@@ -496,9 +512,9 @@ static void ceph_netfs_free_request(struct netfs_io_request *rreq)
 const struct netfs_request_ops ceph_netfs_ops = {
 	.init_request		= ceph_init_request,
 	.free_request		= ceph_netfs_free_request,
+	.prepare_read		= ceph_netfs_prepare_read,
 	.issue_read		= ceph_netfs_issue_read,
 	.expand_readahead	= ceph_netfs_expand_readahead,
-	.clamp_length		= ceph_netfs_clamp_length,
 	.check_write_begin	= ceph_netfs_check_write_begin,
 };
 
@@ -1508,20 +1524,18 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  */
 static int ceph_write_begin(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len,
-			    struct page **pagep, void **fsdata)
+			    struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct folio *folio = NULL;
 	int r;
 
-	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, &folio, NULL);
+	r = netfs_write_begin(&ci->netfs, file, inode->i_mapping, pos, len, foliop, NULL);
 	if (r < 0)
 		return r;
 
-	folio_wait_private_2(folio); /* [DEPRECATED] */
-	WARN_ON_ONCE(!folio_test_locked(folio));
-	*pagep = &folio->page;
+	folio_wait_private_2(*foliop); /* [DEPRECATED] */
+	WARN_ON_ONCE(!folio_test_locked(*foliop));
 	return 0;
 }
 
@@ -1531,9 +1545,8 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
  */
 static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *subpage, void *fsdata)
+			  struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(subpage);
 	struct inode *inode = file_inode(file);
 	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool check_cap = false;

fs/ceph/dir.c

@@ -707,7 +707,6 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int whence)
 
 		if (offset != file->f_pos) {
 			file->f_pos = offset;
-			file->f_version = 0;
 			dfi->file_info.flags &= ~CEPH_F_ATEND;
 		}
 		retval = offset;

fs/coda/inode.c

@@ -119,31 +119,43 @@ static const struct fs_parameter_spec coda_param_specs[] = {
 	{}
 };
 
-static int coda_parse_fd(struct fs_context *fc, int fd)
+static int coda_set_idx(struct fs_context *fc, struct file *file)
 {
 	struct coda_fs_context *ctx = fc->fs_private;
-	struct fd f;
 	struct inode *inode;
 	int idx;
 
-	f = fdget(fd);
-	if (!f.file)
-		return -EBADF;
-	inode = file_inode(f.file);
+	inode = file_inode(file);
 	if (!S_ISCHR(inode->i_mode) || imajor(inode) != CODA_PSDEV_MAJOR) {
-		fdput(f);
-		return invalf(fc, "code: Not coda psdev");
+		return invalf(fc, "coda: Not coda psdev");
 	}
-
 	idx = iminor(inode);
-	fdput(f);
-
 	if (idx < 0 || idx >= MAX_CODADEVS)
 		return invalf(fc, "coda: Bad minor number");
 	ctx->idx = idx;
 	return 0;
 }
 
+static int coda_parse_fd(struct fs_context *fc, struct fs_parameter *param,
+			 struct fs_parse_result *result)
+{
+	struct file *file;
+	int err;
+
+	if (param->type == fs_value_is_file) {
+		file = param->file;
+		param->file = NULL;
+	} else {
+		file = fget(result->uint_32);
+	}
+	if (!file)
+		return -EBADF;
+
+	err = coda_set_idx(fc, file);
+	fput(file);
+	return err;
+}
+
 static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct fs_parse_result result;
@@ -155,7 +167,7 @@ static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param)
 
 	switch (opt) {
 	case Opt_fd:
-		return coda_parse_fd(fc, result.uint_32);
+		return coda_parse_fd(fc, param, &result);
 	}
 
 	return 0;
@@ -167,6 +179,7 @@ static int coda_parse_param(struct fs_context *fc, struct fs_parameter *param)
  */
 static int coda_parse_monolithic(struct fs_context *fc, void *_data)
 {
+	struct file *file;
 	struct coda_mount_data *data = _data;
 
 	if (!data)
@@ -175,7 +188,11 @@ static int coda_parse_monolithic(struct fs_context *fc, void *_data)
 	if (data->version != CODA_MOUNT_VERSION)
 		return invalf(fc, "coda: Bad mount version");
 
-	coda_parse_fd(fc, data->fd);
+	file = fget(data->fd);
+	if (file) {
+		coda_set_idx(fc, file);
+		fput(file);
+	}
 	return 0;
 }
 

fs/dcache.c

@@ -1913,8 +1913,13 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 	__d_instantiate(entry, inode);
 	WARN_ON(!(inode->i_state & I_NEW));
 	inode->i_state &= ~I_NEW & ~I_CREATING;
+	/*
+	 * Pairs with the barrier in prepare_to_wait_event() to make sure
+	 * ___wait_var_event() either sees the bit cleared or
+	 * waitqueue_active() check in wake_up_var() sees the waiter.
+	 */
 	smp_mb();
-	wake_up_bit(&inode->i_state, __I_NEW);
+	inode_wake_up_bit(inode, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(d_instantiate_new);
@@ -2168,9 +2173,6 @@ seqretry:
  * without taking d_lock and checking d_seq sequence count against @seq
  * returned here.
  *
- * A refcount may be taken on the found dentry with the d_rcu_to_refcount
- * function.
- *
  * Alternatively, __d_lookup_rcu may be called again to look up the child of
  * the returned dentry, so long as its parent's seqlock is checked after the
  * child is looked up. Thus, an interlocking stepping of sequence lock checks

fs/debugfs/inode.c

@@ -89,12 +89,14 @@ enum {
 	Opt_uid,
 	Opt_gid,
 	Opt_mode,
+	Opt_source,
 };
 
 static const struct fs_parameter_spec debugfs_param_specs[] = {
 	fsparam_gid	("gid",		Opt_gid),
 	fsparam_u32oct	("mode",	Opt_mode),
 	fsparam_uid	("uid",		Opt_uid),
+	fsparam_string	("source",	Opt_source),
 	{}
 };
 
@@ -126,6 +128,12 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param
 	case Opt_mode:
 		opts->mode = result.uint_32 & S_IALLUGO;
 		break;
+	case Opt_source:
+		if (fc->source)
+			return invalfc(fc, "Multiple sources specified");
+		fc->source = param->string;
+		param->string = NULL;
+		break;
 	/*
 	 * We might like to report bad mount options here;
 	 * but traditionally debugfs has ignored all mount options

fs/direct-io.c

@@ -37,7 +37,6 @@
 #include <linux/rwsem.h>
 #include <linux/uio.h>
 #include <linux/atomic.h>
-#include <linux/prefetch.h>
 
 #include "internal.h"
 
@@ -1121,11 +1120,6 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	struct blk_plug plug;
 	unsigned long align = offset | iov_iter_alignment(iter);
 
-	/*
-	 * Avoid references to bdev if not absolutely needed to give
-	 * the early prefetch in the caller enough time.
-	 */
-
 	/* watch out for a 0 len io from a tricksy fs */
 	if (iov_iter_rw(iter) == READ && !count)
 		return 0;

fs/ecryptfs/mmap.c

@@ -234,17 +234,17 @@ out:
 /*
  * Called with lower inode mutex held.
  */
-static int fill_zeros_to_end_of_page(struct page *page, unsigned int to)
+static int fill_zeros_to_end_of_page(struct folio *folio, unsigned int to)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 	int end_byte_in_page;
 
-	if ((i_size_read(inode) / PAGE_SIZE) != page->index)
+	if ((i_size_read(inode) / PAGE_SIZE) != folio->index)
 		goto out;
 	end_byte_in_page = i_size_read(inode) % PAGE_SIZE;
 	if (to > end_byte_in_page)
 		end_byte_in_page = to;
-	zero_user_segment(page, end_byte_in_page, PAGE_SIZE);
+	folio_zero_segment(folio, end_byte_in_page, PAGE_SIZE);
 out:
 	return 0;
 }
@@ -255,7 +255,7 @@ out:
  * @mapping: The eCryptfs object
  * @pos: The file offset at which to start writing
  * @len: Length of the write
- * @pagep: Pointer to return the page
+ * @foliop: Pointer to return the folio
  * @fsdata: Pointer to return fs data (unused)
  *
  * This function must zero any hole we create
@@ -265,38 +265,39 @@ out:
 static int ecryptfs_write_begin(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
-	struct page *page;
+	struct folio *folio;
 	loff_t prev_page_end_size;
 	int rc = 0;
 
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
-		return -ENOMEM;
-	*pagep = page;
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	*foliop = folio;
 
 	prev_page_end_size = ((loff_t)index << PAGE_SHIFT);
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		struct ecryptfs_crypt_stat *crypt_stat =
 			&ecryptfs_inode_to_private(mapping->host)->crypt_stat;
 
 		if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
 			rc = ecryptfs_read_lower_page_segment(
-				page, index, 0, PAGE_SIZE, mapping->host);
+				&folio->page, index, 0, PAGE_SIZE, mapping->host);
 			if (rc) {
 				printk(KERN_ERR "%s: Error attempting to read "
 				       "lower page segment; rc = [%d]\n",
 				       __func__, rc);
-				ClearPageUptodate(page);
+				folio_clear_uptodate(folio);
 				goto out;
 			} else
-				SetPageUptodate(page);
+				folio_mark_uptodate(folio);
 		} else if (crypt_stat->flags & ECRYPTFS_VIEW_AS_ENCRYPTED) {
 			if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
 				rc = ecryptfs_copy_up_encrypted_with_header(
-					page, crypt_stat);
+					&folio->page, crypt_stat);
 				if (rc) {
 					printk(KERN_ERR "%s: Error attempting "
 					       "to copy the encrypted content "
@@ -304,46 +305,46 @@ static int ecryptfs_write_begin(struct file *file,
 					       "inserting the metadata from "
 					       "the xattr into the header; rc "
 					       "= [%d]\n", __func__, rc);
-					ClearPageUptodate(page);
+					folio_clear_uptodate(folio);
 					goto out;
 				}
-				SetPageUptodate(page);
+				folio_mark_uptodate(folio);
 			} else {
 				rc = ecryptfs_read_lower_page_segment(
-					page, index, 0, PAGE_SIZE,
+					&folio->page, index, 0, PAGE_SIZE,
 					mapping->host);
 				if (rc) {
 					printk(KERN_ERR "%s: Error reading "
 					       "page; rc = [%d]\n",
 					       __func__, rc);
-					ClearPageUptodate(page);
+					folio_clear_uptodate(folio);
 					goto out;
 				}
-				SetPageUptodate(page);
+				folio_mark_uptodate(folio);
 			}
 		} else {
 			if (prev_page_end_size
-			    >= i_size_read(page->mapping->host)) {
-				zero_user(page, 0, PAGE_SIZE);
-				SetPageUptodate(page);
+			    >= i_size_read(mapping->host)) {
+				folio_zero_range(folio, 0, PAGE_SIZE);
+				folio_mark_uptodate(folio);
 			} else if (len < PAGE_SIZE) {
-				rc = ecryptfs_decrypt_page(page);
+				rc = ecryptfs_decrypt_page(&folio->page);
 				if (rc) {
 					printk(KERN_ERR "%s: Error decrypting "
 					       "page at index [%ld]; "
 					       "rc = [%d]\n",
-					       __func__, page->index, rc);
-					ClearPageUptodate(page);
+					       __func__, folio->index, rc);
+					folio_clear_uptodate(folio);
 					goto out;
 				}
-				SetPageUptodate(page);
+				folio_mark_uptodate(folio);
 			}
 		}
 	}
 	/* If creating a page or more of holes, zero them out via truncate.
 	 * Note, this will increase i_size. */
 	if (index != 0) {
-		if (prev_page_end_size > i_size_read(page->mapping->host)) {
+		if (prev_page_end_size > i_size_read(mapping->host)) {
 			rc = ecryptfs_truncate(file->f_path.dentry,
 					       prev_page_end_size);
 			if (rc) {
@@ -359,12 +360,11 @@ static int ecryptfs_write_begin(struct file *file,
 	 * of page?  Zero it out. */
 	if ((i_size_read(mapping->host) == prev_page_end_size)
 	    && (pos != 0))
-		zero_user(page, 0, PAGE_SIZE);
+		folio_zero_range(folio, 0, PAGE_SIZE);
 out:
 	if (unlikely(rc)) {
-		unlock_page(page);
-		put_page(page);
-		*pagep = NULL;
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 	return rc;
 }
@@ -457,13 +457,13 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
  * @pos: The file position
  * @len: The length of the data (unused)
  * @copied: The amount of data copied
- * @page: The eCryptfs page
+ * @folio: The eCryptfs folio
  * @fsdata: The fsdata (unused)
  */
 static int ecryptfs_write_end(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 	unsigned from = pos & (PAGE_SIZE - 1);
@@ -476,8 +476,8 @@ static int ecryptfs_write_end(struct file *file,
 	ecryptfs_printk(KERN_DEBUG, "Calling fill_zeros_to_end_of_page"
 			"(page w/ index = [0x%.16lx], to = [%d])\n", index, to);
 	if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
-		rc = ecryptfs_write_lower_page_segment(ecryptfs_inode, page, 0,
-						       to);
+		rc = ecryptfs_write_lower_page_segment(ecryptfs_inode,
+				&folio->page, 0, to);
 		if (!rc) {
 			rc = copied;
 			fsstack_copy_inode_size(ecryptfs_inode,
@@ -485,21 +485,21 @@ static int ecryptfs_write_end(struct file *file,
 		}
 		goto out;
 	}
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		if (copied < PAGE_SIZE) {
 			rc = 0;
 			goto out;
 		}
-		SetPageUptodate(page);
+		folio_mark_uptodate(folio);
 	}
 	/* Fills in zeros if 'to' goes beyond inode size */
-	rc = fill_zeros_to_end_of_page(page, to);
+	rc = fill_zeros_to_end_of_page(folio, to);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error attempting to fill "
 			"zeros in page with index = [0x%.16lx]\n", index);
 		goto out;
 	}
-	rc = ecryptfs_encrypt_page(page);
+	rc = ecryptfs_encrypt_page(&folio->page);
 	if (rc) {
 		ecryptfs_printk(KERN_WARNING, "Error encrypting page (upper "
 				"index [0x%.16lx])\n", index);
@@ -518,8 +518,8 @@ static int ecryptfs_write_end(struct file *file,
 	else
 		rc = copied;
 out:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 	return rc;
 }
 

fs/eventpoll.c

@@ -420,7 +420,7 @@ static bool busy_loop_ep_timeout(unsigned long start_time,
 
 static bool ep_busy_loop_on(struct eventpoll *ep)
 {
-	return !!ep->busy_poll_usecs || net_busy_loop_on();
+	return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on();
 }
 
 static bool ep_busy_loop_end(void *p, unsigned long start_time)
@@ -2200,11 +2200,6 @@ static int do_epoll_create(int flags)
 		error = PTR_ERR(file);
 		goto out_free_fd;
 	}
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	ep->busy_poll_usecs = 0;
-	ep->busy_poll_budget = 0;
-	ep->prefer_busy_poll = false;
-#endif
 	ep->file = file;
 	fd_install(fd, file);
 	return fd;

fs/exec.c

@@ -145,13 +145,11 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
 		goto out;
 
 	/*
-	 * may_open() has already checked for this, so it should be
-	 * impossible to trip now. But we need to be extra cautious
-	 * and check again at the very end too.
+	 * Check do_open_execat() for an explanation.
 	 */
 	error = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
-			 path_noexec(&file->f_path)))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
+	    path_noexec(&file->f_path))
 		goto exit;
 
 	error = -ENOEXEC;
@@ -971,28 +969,26 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 
 	file = do_filp_open(fd, name, &open_exec_flags);
 	if (IS_ERR(file))
-		goto out;
+		return file;
 
 	/*
-	 * may_open() has already checked for this, so it should be
-	 * impossible to trip now. But we need to be extra cautious
-	 * and check again at the very end too.
+	 * In the past the regular type check was here. It moved to may_open() in
+	 * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is
+	 * an invariant that all non-regular files error out before we get here.
 	 */
-	err = -EACCES;
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) ||
-			 path_noexec(&file->f_path)))
-		goto exit;
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
+	    path_noexec(&file->f_path)) {
+		fput(file);
+		return ERR_PTR(-EACCES);
+	}
 
 	err = deny_write_access(file);
-	if (err)
-		goto exit;
+	if (err) {
+		fput(file);
+		return ERR_PTR(err);
+	}
 
-out:
 	return file;
-
-exit:
-	fput(file);
-	return ERR_PTR(err);
 }
 
 /**

fs/exfat/file.c

@@ -535,20 +535,20 @@ static int exfat_file_zeroed_range(struct file *file, loff_t start, loff_t end)
 
 	while (start < end) {
 		u32 zerofrom, len;
-		struct page *page = NULL;
+		struct folio *folio;
 
 		zerofrom = start & (PAGE_SIZE - 1);
 		len = PAGE_SIZE - zerofrom;
 		if (start + len > end)
 			len = end - start;
 
-		err = ops->write_begin(file, mapping, start, len, &page, NULL);
+		err = ops->write_begin(file, mapping, start, len, &folio, NULL);
 		if (err)
 			goto out;
 
-		zero_user_segment(page, zerofrom, zerofrom + len);
+		folio_zero_range(folio, offset_in_folio(folio, start), len);
 
-		err = ops->write_end(file, mapping, start, len, len, page, NULL);
+		err = ops->write_end(file, mapping, start, len, len, folio, NULL);
 		if (err < 0)
 			goto out;
 		start += len;

fs/exfat/inode.c

@@ -448,12 +448,11 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to)
 
 static int exfat_write_begin(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned int len,
-		struct page **pagep, void **fsdata)
+		struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = block_write_begin(mapping, pos, len, pagep, exfat_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, exfat_get_block);
 
 	if (ret < 0)
 		exfat_write_failed(mapping, pos+len);
@@ -463,13 +462,13 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 
 static int exfat_write_end(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned int len, unsigned int copied,
-		struct page *pagep, void *fsdata)
+		struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	int err;
 
-	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
+	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
 	if (ei->i_size_aligned < i_size_read(inode)) {
 		exfat_fs_error(inode->i_sb,

fs/ext2/dir.c

@@ -87,7 +87,7 @@ static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 
 	inode_inc_iversion(dir);
-	block_write_end(NULL, mapping, pos, len, len, &folio->page, NULL);
+	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
@@ -263,7 +263,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 	unsigned long n = pos >> PAGE_SHIFT;
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
-	bool need_revalidate = !inode_eq_iversion(inode, file->f_version);
+	bool need_revalidate = !inode_eq_iversion(inode, *(u64 *)file->private_data);
 	bool has_filetype;
 
 	if (pos > inode->i_size - EXT2_DIR_REC_LEN(1))
@@ -290,7 +290,7 @@ ext2_readdir(struct file *file, struct dir_context *ctx)
 				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
 				ctx->pos = (n<<PAGE_SHIFT) + offset;
 			}
-			file->f_version = inode_query_iversion(inode);
+			*(u64 *)file->private_data = inode_query_iversion(inode);
 			need_revalidate = false;
 		}
 		de = (ext2_dirent *)(kaddr+offset);
@@ -434,7 +434,7 @@ int ext2_inode_by_name(struct inode *dir, const struct qstr *child, ino_t *ino)
 
 static int ext2_prepare_chunk(struct folio *folio, loff_t pos, unsigned len)
 {
-	return __block_write_begin(&folio->page, pos, len, ext2_get_block);
+	return __block_write_begin(folio, pos, len, ext2_get_block);
 }
 
 static int ext2_handle_dirsync(struct inode *dir)
@@ -703,8 +703,30 @@ not_empty:
 	return 0;
 }
 
+static int ext2_dir_open(struct inode *inode, struct file *file)
+{
+	file->private_data = kzalloc(sizeof(u64), GFP_KERNEL);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+static int ext2_dir_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static loff_t ext2_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+	return generic_llseek_cookie(file, offset, whence,
+				     (u64 *)file->private_data);
+}
+
 const struct file_operations ext2_dir_operations = {
-	.llseek		= generic_file_llseek,
+	.open		= ext2_dir_open,
+	.release	= ext2_dir_release,
+	.llseek		= ext2_dir_llseek,
 	.read		= generic_read_dir,
 	.iterate_shared	= ext2_readdir,
 	.unlocked_ioctl = ext2_ioctl,

fs/ext2/inode.c

@@ -916,11 +916,11 @@ static void ext2_readahead(struct readahead_control *rac)
 
 static int
 ext2_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, pagep, ext2_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, ext2_get_block);
 	if (ret < 0)
 		ext2_write_failed(mapping, pos + len);
 	return ret;
@@ -928,11 +928,11 @@ ext2_write_begin(struct file *file, struct address_space *mapping,
 
 static int ext2_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		ext2_write_failed(mapping, pos + len);
 	return ret;

fs/ext4/dir.c

@@ -133,6 +133,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *bh = NULL;
 	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
+	struct dir_private_info *info = file->private_data;
 
 	err = fscrypt_prepare_readdir(inode);
 	if (err)
@@ -229,7 +230,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 		 * readdir(2), then we might be pointing to an invalid
 		 * dirent right now.  Scan from the start of the block
 		 * to make sure. */
-		if (!inode_eq_iversion(inode, file->f_version)) {
+		if (!inode_eq_iversion(inode, info->cookie)) {
 			for (i = 0; i < sb->s_blocksize && i < offset; ) {
 				de = (struct ext4_dir_entry_2 *)
 					(bh->b_data + i);
@@ -249,7 +250,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			offset = i;
 			ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
 				| offset;
-			file->f_version = inode_query_iversion(inode);
+			info->cookie = inode_query_iversion(inode);
 		}
 
 		while (ctx->pos < inode->i_size
@@ -384,6 +385,7 @@ static inline loff_t ext4_get_htree_eof(struct file *filp)
 static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file->f_mapping->host;
+	struct dir_private_info *info = file->private_data;
 	int dx_dir = is_dx_dir(inode);
 	loff_t ret, htree_max = ext4_get_htree_eof(file);
 
@@ -392,7 +394,7 @@ static loff_t ext4_dir_llseek(struct file *file, loff_t offset, int whence)
 						    htree_max, htree_max);
 	else
 		ret = ext4_llseek(file, offset, whence);
-	file->f_version = inode_peek_iversion(inode) - 1;
+	info->cookie = inode_peek_iversion(inode) - 1;
 	return ret;
 }
 
@@ -429,18 +431,15 @@ static void free_rb_tree_fname(struct rb_root *root)
 	*root = RB_ROOT;
 }
 
-
-static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp,
-							   loff_t pos)
+static void ext4_htree_init_dir_info(struct file *filp, loff_t pos)
 {
-	struct dir_private_info *p;
+	struct dir_private_info *p = filp->private_data;
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return NULL;
-	p->curr_hash = pos2maj_hash(filp, pos);
-	p->curr_minor_hash = pos2min_hash(filp, pos);
-	return p;
+	if (is_dx_dir(file_inode(filp)) && !p->initialized) {
+		p->curr_hash = pos2maj_hash(filp, pos);
+		p->curr_minor_hash = pos2min_hash(filp, pos);
+		p->initialized = true;
+	}
 }
 
 void ext4_htree_free_dir_info(struct dir_private_info *p)
@@ -552,12 +551,7 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 	struct fname *fname;
 	int ret = 0;
 
-	if (!info) {
-		info = ext4_htree_create_dir_info(file, ctx->pos);
-		if (!info)
-			return -ENOMEM;
-		file->private_data = info;
-	}
+	ext4_htree_init_dir_info(file, ctx->pos);
 
 	if (ctx->pos == ext4_get_htree_eof(file))
 		return 0;	/* EOF */
@@ -590,10 +584,10 @@ static int ext4_dx_readdir(struct file *file, struct dir_context *ctx)
 		 * cached entries.
 		 */
 		if ((!info->curr_node) ||
-		    !inode_eq_iversion(inode, file->f_version)) {
+		    !inode_eq_iversion(inode, info->cookie)) {
 			info->curr_node = NULL;
 			free_rb_tree_fname(&info->root);
-			file->f_version = inode_query_iversion(inode);
+			info->cookie = inode_query_iversion(inode);
 			ret = ext4_htree_fill_tree(file, info->curr_hash,
 						   info->curr_minor_hash,
 						   &info->next_hash);
@@ -664,7 +658,19 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
 	return 0;
 }
 
+static int ext4_dir_open(struct inode *inode, struct file *file)
+{
+	struct dir_private_info *info;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+	file->private_data = info;
+	return 0;
+}
+
 const struct file_operations ext4_dir_operations = {
+	.open		= ext4_dir_open,
 	.llseek		= ext4_dir_llseek,
 	.read		= generic_read_dir,
 	.iterate_shared	= ext4_readdir,

fs/ext4/ext4.h

@@ -2553,6 +2553,8 @@ struct dir_private_info {
 	__u32		curr_hash;
 	__u32		curr_minor_hash;
 	__u32		next_hash;
+	u64		cookie;
+	bool		initialized;
 };
 
 /* calculate the first block number of the group */
@@ -3563,13 +3565,13 @@ int ext4_readpage_inline(struct inode *inode, struct folio *folio);
 extern int ext4_try_to_write_inline_data(struct address_space *mapping,
 					 struct inode *inode,
 					 loff_t pos, unsigned len,
-					 struct page **pagep);
+					 struct folio **foliop);
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct folio *folio);
 extern int ext4_da_write_inline_data_begin(struct address_space *mapping,
 					   struct inode *inode,
 					   loff_t pos, unsigned len,
-					   struct page **pagep,
+					   struct folio **foliop,
 					   void **fsdata);
 extern int ext4_try_add_inline_entry(handle_t *handle,
 				     struct ext4_filename *fname,

fs/ext4/inline.c

@@ -601,10 +601,10 @@ retry:
 		goto out;
 
 	if (ext4_should_dioread_nolock(inode)) {
-		ret = __block_write_begin(&folio->page, from, to,
+		ret = __block_write_begin(folio, from, to,
 					  ext4_get_block_unwritten);
 	} else
-		ret = __block_write_begin(&folio->page, from, to, ext4_get_block);
+		ret = __block_write_begin(folio, from, to, ext4_get_block);
 
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
@@ -660,7 +660,7 @@ out_nofolio:
 int ext4_try_to_write_inline_data(struct address_space *mapping,
 				  struct inode *inode,
 				  loff_t pos, unsigned len,
-				  struct page **pagep)
+				  struct folio **foliop)
 {
 	int ret;
 	handle_t *handle;
@@ -708,7 +708,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 		goto out;
 	}
 
-	*pagep = &folio->page;
+	*foliop = folio;
 	down_read(&EXT4_I(inode)->xattr_sem);
 	if (!ext4_has_inline_data(inode)) {
 		ret = 0;
@@ -856,7 +856,7 @@ static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
 			goto out;
 	}
 
-	ret = __block_write_begin(&folio->page, 0, inline_size,
+	ret = __block_write_begin(folio, 0, inline_size,
 				  ext4_da_get_block_prep);
 	if (ret) {
 		up_read(&EXT4_I(inode)->xattr_sem);
@@ -891,7 +891,7 @@ out:
 int ext4_da_write_inline_data_begin(struct address_space *mapping,
 				    struct inode *inode,
 				    loff_t pos, unsigned len,
-				    struct page **pagep,
+				    struct folio **foliop,
 				    void **fsdata)
 {
 	int ret;
@@ -954,7 +954,7 @@ retry_journal:
 		goto out_release_page;
 
 	up_read(&EXT4_I(inode)->xattr_sem);
-	*pagep = &folio->page;
+	*foliop = folio;
 	brelse(iloc.bh);
 	return 1;
 out_release_page:
@@ -1460,6 +1460,7 @@ int ext4_read_inline_dir(struct file *file,
 	struct ext4_iloc iloc;
 	void *dir_buf = NULL;
 	int dotdot_offset, dotdot_size, extra_offset, extra_size;
+	struct dir_private_info *info = file->private_data;
 
 	ret = ext4_get_inode_loc(inode, &iloc);
 	if (ret)
@@ -1503,12 +1504,12 @@ int ext4_read_inline_dir(struct file *file,
 	extra_size = extra_offset + inline_size;
 
 	/*
-	 * If the version has changed since the last call to
+	 * If the cookie has changed since the last call to
 	 * readdir(2), then we might be pointing to an invalid
 	 * dirent right now.  Scan from the start of the inline
 	 * dir to make sure.
 	 */
-	if (!inode_eq_iversion(inode, file->f_version)) {
+	if (!inode_eq_iversion(inode, info->cookie)) {
 		for (i = 0; i < extra_size && i < offset;) {
 			/*
 			 * "." is with offset 0 and
@@ -1540,7 +1541,7 @@ int ext4_read_inline_dir(struct file *file,
 		}
 		offset = i;
 		ctx->pos = offset;
-		file->f_version = inode_query_iversion(inode);
+		info->cookie = inode_query_iversion(inode);
 	}
 
 	while (ctx->pos < extra_size) {

fs/ext4/inode.c

@@ -1145,7 +1145,7 @@ static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len,
  */
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len,
-			    struct page **pagep, void **fsdata)
+			    struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret, needed_blocks;
@@ -1170,7 +1170,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
 		ret = ext4_try_to_write_inline_data(mapping, inode, pos, len,
-						    pagep);
+						    foliop);
 		if (ret < 0)
 			return ret;
 		if (ret == 1)
@@ -1224,10 +1224,10 @@ retry_journal:
 		ret = ext4_block_write_begin(folio, pos, len, ext4_get_block);
 #else
 	if (ext4_should_dioread_nolock(inode))
-		ret = __block_write_begin(&folio->page, pos, len,
+		ret = __block_write_begin(folio, pos, len,
 					  ext4_get_block_unwritten);
 	else
-		ret = __block_write_begin(&folio->page, pos, len, ext4_get_block);
+		ret = __block_write_begin(folio, pos, len, ext4_get_block);
 #endif
 	if (!ret && ext4_should_journal_data(inode)) {
 		ret = ext4_walk_page_buffers(handle, inode,
@@ -1270,7 +1270,7 @@ retry_journal:
 		folio_put(folio);
 		return ret;
 	}
-	*pagep = &folio->page;
+	*foliop = folio;
 	return ret;
 }
 
@@ -1298,9 +1298,8 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 static int ext4_write_end(struct file *file,
 			  struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *page, void *fsdata)
+			  struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -1315,7 +1314,7 @@ static int ext4_write_end(struct file *file,
 		return ext4_write_inline_data_end(inode, pos, len, copied,
 						  folio);
 
-	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
 	/*
 	 * it's important to update i_size while still holding folio lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
@@ -1402,9 +1401,8 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle,
 static int ext4_journalled_write_end(struct file *file,
 				     struct address_space *mapping,
 				     loff_t pos, unsigned len, unsigned copied,
-				     struct page *page, void *fsdata)
+				     struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -2926,7 +2924,7 @@ static int ext4_nonda_switch(struct super_block *sb)
 
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 			       loff_t pos, unsigned len,
-			       struct page **pagep, void **fsdata)
+			       struct folio **foliop, void **fsdata)
 {
 	int ret, retries = 0;
 	struct folio *folio;
@@ -2941,14 +2939,14 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
 		return ext4_write_begin(file, mapping, pos,
-					len, pagep, fsdata);
+					len, foliop, fsdata);
 	}
 	*fsdata = (void *)0;
 	trace_ext4_da_write_begin(inode, pos, len);
 
 	if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
 		ret = ext4_da_write_inline_data_begin(mapping, inode, pos, len,
-						      pagep, fsdata);
+						      foliop, fsdata);
 		if (ret < 0)
 			return ret;
 		if (ret == 1)
@@ -2964,7 +2962,7 @@ retry:
 #ifdef CONFIG_FS_ENCRYPTION
 	ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
 #else
-	ret = __block_write_begin(&folio->page, pos, len, ext4_da_get_block_prep);
+	ret = __block_write_begin(folio, pos, len, ext4_da_get_block_prep);
 #endif
 	if (ret < 0) {
 		folio_unlock(folio);
@@ -2983,7 +2981,7 @@ retry:
 		return ret;
 	}
 
-	*pagep = &folio->page;
+	*foliop = folio;
 	return ret;
 }
 
@@ -3029,7 +3027,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	 * flag, which all that's needed to trigger page writeback.
 	 */
 	copied = block_write_end(NULL, mapping, pos, len, copied,
-			&folio->page, NULL);
+			folio, NULL);
 	new_i_size = pos + copied;
 
 	/*
@@ -3080,15 +3078,14 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 static int ext4_da_write_end(struct file *file,
 			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned copied,
-			     struct page *page, void *fsdata)
+			     struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int write_mode = (int)(unsigned long)fsdata;
-	struct folio *folio = page_folio(page);
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC)
 		return ext4_write_end(file, mapping, pos,
-				      len, copied, &folio->page, fsdata);
+				      len, copied, folio, fsdata);
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
 
@@ -6219,7 +6216,7 @@ retry_alloc:
 		if (folio_pos(folio) + len > size)
 			len = size - folio_pos(folio);
 
-		err = __block_write_begin(&folio->page, 0, len, ext4_get_block);
+		err = __block_write_begin(folio, 0, len, ext4_get_block);
 		if (!err) {
 			ret = VM_FAULT_SIGBUS;
 			if (ext4_journal_folio_buffers(handle, folio, len))

fs/ext4/verity.c

@@ -76,17 +76,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
 	while (count) {
 		size_t n = min_t(size_t, count,
 				 PAGE_SIZE - offset_in_page(pos));
-		struct page *page;
+		struct folio *folio;
 		void *fsdata = NULL;
 		int res;
 
-		res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata);
+		res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata);
 		if (res)
 			return res;
 
-		memcpy_to_page(page, offset_in_page(pos), buf, n);
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n);
 
-		res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata);
+		res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata);
 		if (res < 0)
 			return res;
 		if (res != n)

fs/f2fs/data.c

@@ -3556,12 +3556,12 @@ reserve_block:
 }
 
 static int f2fs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct page *page = NULL;
-	pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
+	struct folio *folio;
+	pgoff_t index = pos >> PAGE_SHIFT;
 	bool need_balance = false;
 	bool use_cow = false;
 	block_t blkaddr = NULL_ADDR;
@@ -3577,7 +3577,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	/*
 	 * We should check this at this moment to avoid deadlock on inode page
 	 * and #0 page. The locking rule for inline_data conversion should be:
-	 * lock_page(page #0) -> lock_page(inode_page)
+	 * folio_lock(folio #0) -> folio_lock(inode_page)
 	 */
 	if (index != 0) {
 		err = f2fs_convert_inline_inode(inode);
@@ -3588,18 +3588,20 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	if (f2fs_compressed_file(inode)) {
 		int ret;
+		struct page *page;
 
 		*fsdata = NULL;
 
 		if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode)))
 			goto repeat;
 
-		ret = f2fs_prepare_compress_overwrite(inode, pagep,
+		ret = f2fs_prepare_compress_overwrite(inode, &page,
 							index, fsdata);
 		if (ret < 0) {
 			err = ret;
 			goto fail;
 		} else if (ret) {
+			*foliop = page_folio(page);
 			return 0;
 		}
 	}
@@ -3607,81 +3609,85 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 
 repeat:
 	/*
-	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
-	 * wait_for_stable_page. Will wait that below with our IO control.
+	 * Do not use FGP_STABLE to avoid deadlock.
+	 * Will wait that below with our IO control.
 	 */
-	page = f2fs_pagecache_get_page(mapping, index,
+	folio = __filemap_get_folio(mapping, index,
 				FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
-	if (!page) {
-		err = -ENOMEM;
+	if (IS_ERR(folio)) {
+		err = PTR_ERR(folio);
 		goto fail;
 	}
 
 	/* TODO: cluster can be compressed due to race with .writepage */
 
-	*pagep = page;
+	*foliop = folio;
 
 	if (f2fs_is_atomic_file(inode))
-		err = prepare_atomic_write_begin(sbi, page, pos, len,
+		err = prepare_atomic_write_begin(sbi, &folio->page, pos, len,
 					&blkaddr, &need_balance, &use_cow);
 	else
-		err = prepare_write_begin(sbi, page, pos, len,
+		err = prepare_write_begin(sbi, &folio->page, pos, len,
 					&blkaddr, &need_balance);
 	if (err)
-		goto fail;
+		goto put_folio;
 
 	if (need_balance && !IS_NOQUOTA(inode) &&
 			has_not_enough_free_secs(sbi, 0, 0)) {
-		unlock_page(page);
+		folio_unlock(folio);
 		f2fs_balance_fs(sbi, true);
-		lock_page(page);
-		if (page->mapping != mapping) {
-			/* The page got truncated from under us */
-			f2fs_put_page(page, 1);
+		folio_lock(folio);
+		if (folio->mapping != mapping) {
+			/* The folio got truncated from under us */
+			folio_unlock(folio);
+			folio_put(folio);
 			goto repeat;
 		}
 	}
 
-	f2fs_wait_on_page_writeback(page, DATA, false, true);
+	f2fs_wait_on_page_writeback(&folio->page, DATA, false, true);
 
-	if (len == PAGE_SIZE || PageUptodate(page))
+	if (len == folio_size(folio) || folio_test_uptodate(folio))
 		return 0;
 
 	if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
 	    !f2fs_verity_in_progress(inode)) {
-		zero_user_segment(page, len, PAGE_SIZE);
+		folio_zero_segment(folio, len, PAGE_SIZE);
 		return 0;
 	}
 
 	if (blkaddr == NEW_ADDR) {
-		zero_user_segment(page, 0, PAGE_SIZE);
-		SetPageUptodate(page);
+		folio_zero_segment(folio, 0, folio_size(folio));
+		folio_mark_uptodate(folio);
 	} else {
 		if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
 				DATA_GENERIC_ENHANCE_READ)) {
 			err = -EFSCORRUPTED;
-			goto fail;
+			goto put_folio;
 		}
 		err = f2fs_submit_page_read(use_cow ?
-				F2FS_I(inode)->cow_inode : inode, page,
+				F2FS_I(inode)->cow_inode : inode, &folio->page,
 				blkaddr, 0, true);
 		if (err)
-			goto fail;
+			goto put_folio;
 
-		lock_page(page);
-		if (unlikely(page->mapping != mapping)) {
-			f2fs_put_page(page, 1);
+		folio_lock(folio);
+		if (unlikely(folio->mapping != mapping)) {
+			folio_unlock(folio);
+			folio_put(folio);
 			goto repeat;
 		}
-		if (unlikely(!PageUptodate(page))) {
+		if (unlikely(!folio_test_uptodate(folio))) {
 			err = -EIO;
-			goto fail;
+			goto put_folio;
 		}
 	}
 	return 0;
 
+put_folio:
+	folio_unlock(folio);
+	folio_put(folio);
 fail:
-	f2fs_put_page(page, 1);
 	f2fs_write_failed(inode, pos + len);
 	return err;
 }
@@ -3689,9 +3695,9 @@ fail:
 static int f2fs_write_end(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 
 	trace_f2fs_write_end(inode, pos, len, copied);
 
@@ -3700,17 +3706,17 @@ static int f2fs_write_end(struct file *file,
 	 * should be PAGE_SIZE. Otherwise, we treat it with zero copied and
 	 * let generic_perform_write() try to copy data again through copied=0.
 	 */
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		if (unlikely(copied != len))
 			copied = 0;
 		else
-			SetPageUptodate(page);
+			folio_mark_uptodate(folio);
 	}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 	/* overwrite compressed file */
 	if (f2fs_compressed_file(inode) && fsdata) {
-		f2fs_compress_write_end(inode, fsdata, page->index, copied);
+		f2fs_compress_write_end(inode, fsdata, folio->index, copied);
 		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
 		if (pos + copied > i_size_read(inode) &&
@@ -3723,7 +3729,7 @@ static int f2fs_write_end(struct file *file,
 	if (!copied)
 		goto unlock_out;
 
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 
 	if (pos + copied > i_size_read(inode) &&
 	    !f2fs_verity_in_progress(inode)) {
@@ -3733,7 +3739,8 @@ static int f2fs_write_end(struct file *file,
 					pos + copied);
 	}
 unlock_out:
-	f2fs_put_page(page, 1);
+	folio_unlock(folio);
+	folio_put(folio);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return copied;
 }

fs/f2fs/super.c

@@ -2677,7 +2677,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	int offset = off & (sb->s_blocksize - 1);
 	size_t towrite = len;
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	int err = 0;
 	int tocopy;
@@ -2687,7 +2687,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
 								towrite);
 retry:
 		err = a_ops->write_begin(NULL, mapping, off, tocopy,
-							&page, &fsdata);
+							&folio, &fsdata);
 		if (unlikely(err)) {
 			if (err == -ENOMEM) {
 				f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
@@ -2697,10 +2697,10 @@ retry:
 			break;
 		}
 
-		memcpy_to_page(page, offset, data, tocopy);
+		memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy);
 
 		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
-						page, fsdata);
+						folio, fsdata);
 		offset = 0;
 		towrite -= tocopy;
 		off += tocopy;

fs/f2fs/verity.c

@@ -80,17 +80,17 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
 	while (count) {
 		size_t n = min_t(size_t, count,
 				 PAGE_SIZE - offset_in_page(pos));
-		struct page *page;
+		struct folio *folio;
 		void *fsdata = NULL;
 		int res;
 
-		res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata);
+		res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata);
 		if (res)
 			return res;
 
-		memcpy_to_page(page, offset_in_page(pos), buf, n);
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n);
 
-		res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata);
+		res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata);
 		if (res < 0)
 			return res;
 		if (res != n)

fs/fat/inode.c

@@ -221,13 +221,12 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
 
 static int fat_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int err;
 
-	*pagep = NULL;
 	err = cont_write_begin(file, mapping, pos, len,
-				pagep, fsdata, fat_get_block,
+				foliop, fsdata, fat_get_block,
 				&MSDOS_I(mapping->host)->mmu_private);
 	if (err < 0)
 		fat_write_failed(mapping, pos + len);
@@ -236,11 +235,11 @@ static int fat_write_begin(struct file *file, struct address_space *mapping,
 
 static int fat_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *pagep, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
+	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		fat_write_failed(mapping, pos + len);
 	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {

fs/fcntl.c

@@ -33,6 +33,8 @@
 #include <asm/siginfo.h>
 #include <linux/uaccess.h>
 
+#include "internal.h"
+
 #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME)
 
 static int setfl(int fd, struct file * filp, unsigned int arg)
@@ -87,22 +89,64 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
 	return error;
 }
 
+/*
+ * Allocate an file->f_owner struct if it doesn't exist, handling racing
+ * allocations correctly.
+ */
+int file_f_owner_allocate(struct file *file)
+{
+	struct fown_struct *f_owner;
+
+	f_owner = file_f_owner(file);
+	if (f_owner)
+		return 0;
+
+	f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL);
+	if (!f_owner)
+		return -ENOMEM;
+
+	rwlock_init(&f_owner->lock);
+	f_owner->file = file;
+	/* If someone else raced us, drop our allocation. */
+	if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner)))
+		kfree(f_owner);
+	return 0;
+}
+EXPORT_SYMBOL(file_f_owner_allocate);
+
+void file_f_owner_release(struct file *file)
+{
+	struct fown_struct *f_owner;
+
+	f_owner = file_f_owner(file);
+	if (f_owner) {
+		put_pid(f_owner->pid);
+		kfree(f_owner);
+	}
+}
+
 static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
                      int force)
 {
-	write_lock_irq(&filp->f_owner.lock);
-	if (force || !filp->f_owner.pid) {
-		put_pid(filp->f_owner.pid);
-		filp->f_owner.pid = get_pid(pid);
-		filp->f_owner.pid_type = type;
+	struct fown_struct *f_owner;
+
+	f_owner = file_f_owner(filp);
+	if (WARN_ON_ONCE(!f_owner))
+		return;
+
+	write_lock_irq(&f_owner->lock);
+	if (force || !f_owner->pid) {
+		put_pid(f_owner->pid);
+		f_owner->pid = get_pid(pid);
+		f_owner->pid_type = type;
 
 		if (pid) {
 			const struct cred *cred = current_cred();
-			filp->f_owner.uid = cred->uid;
-			filp->f_owner.euid = cred->euid;
+			f_owner->uid = cred->uid;
+			f_owner->euid = cred->euid;
 		}
 	}
-	write_unlock_irq(&filp->f_owner.lock);
+	write_unlock_irq(&f_owner->lock);
 }
 
 void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
@@ -119,6 +163,8 @@ int f_setown(struct file *filp, int who, int force)
 	struct pid *pid = NULL;
 	int ret = 0;
 
+	might_sleep();
+
 	type = PIDTYPE_TGID;
 	if (who < 0) {
 		/* avoid overflow below */
@@ -129,6 +175,10 @@ int f_setown(struct file *filp, int who, int force)
 		who = -who;
 	}
 
+	ret = file_f_owner_allocate(filp);
+	if (ret)
+		return ret;
+
 	rcu_read_lock();
 	if (who) {
 		pid = find_vpid(who);
@@ -152,16 +202,21 @@ void f_delown(struct file *filp)
 pid_t f_getown(struct file *filp)
 {
 	pid_t pid = 0;
+	struct fown_struct *f_owner;
 
-	read_lock_irq(&filp->f_owner.lock);
+	f_owner = file_f_owner(filp);
+	if (!f_owner)
+		return pid;
+
+	read_lock_irq(&f_owner->lock);
 	rcu_read_lock();
-	if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) {
-		pid = pid_vnr(filp->f_owner.pid);
-		if (filp->f_owner.pid_type == PIDTYPE_PGID)
+	if (pid_task(f_owner->pid, f_owner->pid_type)) {
+		pid = pid_vnr(f_owner->pid);
+		if (f_owner->pid_type == PIDTYPE_PGID)
 			pid = -pid;
 	}
 	rcu_read_unlock();
-	read_unlock_irq(&filp->f_owner.lock);
+	read_unlock_irq(&f_owner->lock);
 	return pid;
 }
 
@@ -194,6 +249,10 @@ static int f_setown_ex(struct file *filp, unsigned long arg)
 		return -EINVAL;
 	}
 
+	ret = file_f_owner_allocate(filp);
+	if (ret)
+		return ret;
+
 	rcu_read_lock();
 	pid = find_vpid(owner.pid);
 	if (owner.pid && !pid)
@@ -210,13 +269,20 @@ static int f_getown_ex(struct file *filp, unsigned long arg)
 	struct f_owner_ex __user *owner_p = (void __user *)arg;
 	struct f_owner_ex owner = {};
 	int ret = 0;
+	struct fown_struct *f_owner;
+	enum pid_type pid_type = PIDTYPE_PID;
 
-	read_lock_irq(&filp->f_owner.lock);
-	rcu_read_lock();
-	if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type))
-		owner.pid = pid_vnr(filp->f_owner.pid);
-	rcu_read_unlock();
-	switch (filp->f_owner.pid_type) {
+	f_owner = file_f_owner(filp);
+	if (f_owner) {
+		read_lock_irq(&f_owner->lock);
+		rcu_read_lock();
+		if (pid_task(f_owner->pid, f_owner->pid_type))
+			owner.pid = pid_vnr(f_owner->pid);
+		rcu_read_unlock();
+		pid_type = f_owner->pid_type;
+	}
+
+	switch (pid_type) {
 	case PIDTYPE_PID:
 		owner.type = F_OWNER_TID;
 		break;
@@ -234,7 +300,8 @@ static int f_getown_ex(struct file *filp, unsigned long arg)
 		ret = -EINVAL;
 		break;
 	}
-	read_unlock_irq(&filp->f_owner.lock);
+	if (f_owner)
+		read_unlock_irq(&f_owner->lock);
 
 	if (!ret) {
 		ret = copy_to_user(owner_p, &owner, sizeof(owner));
@@ -248,14 +315,18 @@ static int f_getown_ex(struct file *filp, unsigned long arg)
 static int f_getowner_uids(struct file *filp, unsigned long arg)
 {
 	struct user_namespace *user_ns = current_user_ns();
+	struct fown_struct *f_owner;
 	uid_t __user *dst = (void __user *)arg;
-	uid_t src[2];
+	uid_t src[2] = {0, 0};
 	int err;
 
-	read_lock_irq(&filp->f_owner.lock);
-	src[0] = from_kuid(user_ns, filp->f_owner.uid);
-	src[1] = from_kuid(user_ns, filp->f_owner.euid);
-	read_unlock_irq(&filp->f_owner.lock);
+	f_owner = file_f_owner(filp);
+	if (f_owner) {
+		read_lock_irq(&f_owner->lock);
+		src[0] = from_kuid(user_ns, f_owner->uid);
+		src[1] = from_kuid(user_ns, f_owner->euid);
+		read_unlock_irq(&f_owner->lock);
+	}
 
 	err  = put_user(src[0], &dst[0]);
 	err |= put_user(src[1], &dst[1]);
@@ -343,6 +414,36 @@ static long f_dupfd_query(int fd, struct file *filp)
 	return f.file == filp;
 }
 
+/* Let the caller figure out whether a given file was just created. */
+static long f_created_query(const struct file *filp)
+{
+	return !!(filp->f_mode & FMODE_CREATED);
+}
+
+static int f_owner_sig(struct file *filp, int signum, bool setsig)
+{
+	int ret = 0;
+	struct fown_struct *f_owner;
+
+	might_sleep();
+
+	if (setsig) {
+		if (!valid_signal(signum))
+			return -EINVAL;
+
+		ret = file_f_owner_allocate(filp);
+		if (ret)
+			return ret;
+	}
+
+	f_owner = file_f_owner(filp);
+	if (setsig)
+		f_owner->signum = signum;
+	else if (f_owner)
+		ret = f_owner->signum;
+	return ret;
+}
+
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		struct file *filp)
 {
@@ -352,6 +453,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	long err = -EINVAL;
 
 	switch (cmd) {
+	case F_CREATED_QUERY:
+		err = f_created_query(filp);
+		break;
 	case F_DUPFD:
 		err = f_dupfd(argi, filp, 0);
 		break;
@@ -421,15 +525,10 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = f_getowner_uids(filp, arg);
 		break;
 	case F_GETSIG:
-		err = filp->f_owner.signum;
+		err = f_owner_sig(filp, 0, false);
 		break;
 	case F_SETSIG:
-		/* arg == 0 restores default behaviour. */
-		if (!valid_signal(argi)) {
-			break;
-		}
-		err = 0;
-		filp->f_owner.signum = argi;
+		err = f_owner_sig(filp, argi, true);
 		break;
 	case F_GETLEASE:
 		err = fcntl_getlease(filp);
@@ -463,6 +562,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 static int check_fcntl_cmd(unsigned cmd)
 {
 	switch (cmd) {
+	case F_CREATED_QUERY:
 	case F_DUPFD:
 	case F_DUPFD_CLOEXEC:
 	case F_DUPFD_QUERY:
@@ -844,14 +944,19 @@ static void send_sigurg_to_task(struct task_struct *p,
 		do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type);
 }
 
-int send_sigurg(struct fown_struct *fown)
+int send_sigurg(struct file *file)
 {
+	struct fown_struct *fown;
 	struct task_struct *p;
 	enum pid_type type;
 	struct pid *pid;
 	unsigned long flags;
 	int ret = 0;
 	
+	fown = file_f_owner(file);
+	if (!fown)
+		return 0;
+
 	read_lock_irqsave(&fown->lock, flags);
 
 	type = fown->pid_type;
@@ -1027,13 +1132,16 @@ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band)
 		}
 		read_lock_irqsave(&fa->fa_lock, flags);
 		if (fa->fa_file) {
-			fown = &fa->fa_file->f_owner;
+			fown = file_f_owner(fa->fa_file);
+			if (!fown)
+				goto next;
 			/* Don't send SIGURG to processes which have not set a
 			   queued signum: SIGURG has its own default signalling
 			   mechanism. */
 			if (!(sig == SIGURG && fown->signum == 0))
 				send_sigio(fown, fa->fa_fd, band);
 		}
+next:
 		read_unlock_irqrestore(&fa->fa_lock, flags);
 		fa = rcu_dereference(fa->fa_next);
 	}

fs/fhandle.c

@@ -16,7 +16,8 @@
 
 static long do_sys_name_to_handle(const struct path *path,
 				  struct file_handle __user *ufh,
-				  int __user *mnt_id, int fh_flags)
+				  void __user *mnt_id, bool unique_mntid,
+				  int fh_flags)
 {
 	long retval;
 	struct file_handle f_handle;
@@ -69,9 +70,19 @@ static long do_sys_name_to_handle(const struct path *path,
 	} else
 		retval = 0;
 	/* copy the mount id */
-	if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) ||
-	    copy_to_user(ufh, handle,
-			 struct_size(handle, f_handle, handle_bytes)))
+	if (unique_mntid) {
+		if (put_user(real_mount(path->mnt)->mnt_id_unique,
+			     (u64 __user *) mnt_id))
+			retval = -EFAULT;
+	} else {
+		if (put_user(real_mount(path->mnt)->mnt_id,
+			     (int __user *) mnt_id))
+			retval = -EFAULT;
+	}
+	/* copy the handle */
+	if (retval != -EFAULT &&
+		copy_to_user(ufh, handle,
+			     struct_size(handle, f_handle, handle_bytes)))
 		retval = -EFAULT;
 	kfree(handle);
 	return retval;
@@ -83,6 +94,7 @@ static long do_sys_name_to_handle(const struct path *path,
  * @name: name that should be converted to handle.
  * @handle: resulting file handle
  * @mnt_id: mount id of the file system containing the file
+ *          (u64 if AT_HANDLE_MNT_ID_UNIQUE, otherwise int)
  * @flag: flag value to indicate whether to follow symlink or not
  *        and whether a decodable file handle is required.
  *
@@ -92,7 +104,7 @@ static long do_sys_name_to_handle(const struct path *path,
  * value required.
  */
 SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
-		struct file_handle __user *, handle, int __user *, mnt_id,
+		struct file_handle __user *, handle, void __user *, mnt_id,
 		int, flag)
 {
 	struct path path;
@@ -100,7 +112,8 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 	int fh_flags;
 	int err;
 
-	if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID))
+	if (flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH | AT_HANDLE_FID |
+		     AT_HANDLE_MNT_ID_UNIQUE))
 		return -EINVAL;
 
 	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
@@ -109,7 +122,9 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 		lookup_flags |= LOOKUP_EMPTY;
 	err = user_path_at(dfd, name, lookup_flags, &path);
 	if (!err) {
-		err = do_sys_name_to_handle(&path, handle, mnt_id, fh_flags);
+		err = do_sys_name_to_handle(&path, handle, mnt_id,
+					    flag & AT_HANDLE_MNT_ID_UNIQUE,
+					    fh_flags);
 		path_put(&path);
 	}
 	return err;

fs/file.c

@@ -672,7 +672,7 @@ int close_fd(unsigned fd)
 
 	return filp_close(file, files);
 }
-EXPORT_SYMBOL(close_fd); /* for ksys_close() */
+EXPORT_SYMBOL(close_fd);
 
 /**
  * last_fd - return last valid index into fd table

fs/file_table.c

@@ -136,6 +136,7 @@ static int __init init_fs_stat_sysctls(void)
 	register_sysctl_init("fs", fs_stat_sysctls);
 	if (IS_ENABLED(CONFIG_BINFMT_MISC)) {
 		struct ctl_table_header *hdr;
+
 		hdr = register_sysctl_mount_point("fs/binfmt_misc");
 		kmemleak_not_leak(hdr);
 	}
@@ -155,8 +156,14 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 		return error;
 	}
 
-	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
+	/*
+	 * Note that f_pos_lock is only used for files raising
+	 * FMODE_ATOMIC_POS and directories. Other files such as pipes
+	 * don't need it and since f_pos_lock is in a union may reuse
+	 * the space for other purposes. They are expected to initialize
+	 * the respective member when opening the file.
+	 */
 	mutex_init(&f->f_pos_lock);
 	f->f_flags = flags;
 	f->f_mode = OPEN_FMODE(flags);
@@ -383,7 +390,9 @@ EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
 struct file *alloc_file_clone(struct file *base, int flags,
 				const struct file_operations *fops)
 {
-	struct file *f = alloc_file(&base->f_path, flags, fops);
+	struct file *f;
+
+	f = alloc_file(&base->f_path, flags, fops);
 	if (!IS_ERR(f)) {
 		path_get(&f->f_path);
 		f->f_mapping = base->f_mapping;
@@ -425,7 +434,7 @@ static void __fput(struct file *file)
 		cdev_put(inode->i_cdev);
 	}
 	fops_put(file->f_op);
-	put_pid(file->f_owner.pid);
+	file_f_owner_release(file);
 	put_file_access(file);
 	dput(dentry);
 	if (unlikely(mode & FMODE_NEED_UNMOUNT))
@@ -512,9 +521,9 @@ EXPORT_SYMBOL(__fput_sync);
 
 void __init files_init(void)
 {
-	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
-				SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN |
-				SLAB_PANIC | SLAB_ACCOUNT, NULL);
+	filp_cachep = kmem_cache_create_rcu("filp", sizeof(struct file),
+				offsetof(struct file, f_freeptr),
+				SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 }
 

fs/fs-writeback.c

@@ -1132,6 +1132,7 @@ out_bdi_put:
 
 /**
  * cgroup_writeback_umount - flush inode wb switches for umount
+ * @sb: target super_block
  *
  * This function is called when a super_block is about to be destroyed and
  * flushes in-flight inode wb switches.  An inode wb switch goes through
@@ -1140,8 +1141,12 @@ out_bdi_put:
  * rare occurrences and synchronize_rcu() can take a while, perform
  * flushing iff wb switches are in flight.
  */
-void cgroup_writeback_umount(void)
+void cgroup_writeback_umount(struct super_block *sb)
 {
+
+	if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK))
+		return;
+
 	/*
 	 * SB_ACTIVE should be reliably cleared before checking
 	 * isw_nr_in_flight, see generic_shutdown_super().
@@ -1381,12 +1386,13 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 
 static void inode_sync_complete(struct inode *inode)
 {
+	assert_spin_locked(&inode->i_lock);
+
 	inode->i_state &= ~I_SYNC;
 	/* If inode is clean an unused, put it into LRU now... */
 	inode_add_lru(inode);
-	/* Waiters must see I_SYNC cleared before being woken up */
-	smp_mb();
-	wake_up_bit(&inode->i_state, __I_SYNC);
+	/* Called with inode->i_lock which ensures memory ordering. */
+	inode_wake_up_bit(inode, __I_SYNC);
 }
 
 static bool inode_dirtied_after(struct inode *inode, unsigned long t)
@@ -1505,30 +1511,27 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc)
  * Wait for writeback on an inode to complete. Called with i_lock held.
  * Caller must make sure inode cannot go away when we drop i_lock.
  */
-static void __inode_wait_for_writeback(struct inode *inode)
-	__releases(inode->i_lock)
-	__acquires(inode->i_lock)
-{
-	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
-	wait_queue_head_t *wqh;
-
-	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	while (inode->i_state & I_SYNC) {
-		spin_unlock(&inode->i_lock);
-		__wait_on_bit(wqh, &wq, bit_wait,
-			      TASK_UNINTERRUPTIBLE);
-		spin_lock(&inode->i_lock);
-	}
-}
-
-/*
- * Wait for writeback on an inode to complete. Caller must have inode pinned.
- */
 void inode_wait_for_writeback(struct inode *inode)
 {
-	spin_lock(&inode->i_lock);
-	__inode_wait_for_writeback(inode);
-	spin_unlock(&inode->i_lock);
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
+
+	assert_spin_locked(&inode->i_lock);
+
+	if (!(inode->i_state & I_SYNC))
+		return;
+
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
+	for (;;) {
+		prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
+		/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
+		if (!(inode->i_state & I_SYNC))
+			break;
+		spin_unlock(&inode->i_lock);
+		schedule();
+		spin_lock(&inode->i_lock);
+	}
+	finish_wait(wq_head, &wqe.wq_entry);
 }
 
 /*
@@ -1539,16 +1542,20 @@ void inode_wait_for_writeback(struct inode *inode)
 static void inode_sleep_on_writeback(struct inode *inode)
 	__releases(inode->i_lock)
 {
-	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	int sleep;
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
+	bool sleep;
 
-	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
-	sleep = inode->i_state & I_SYNC;
+	assert_spin_locked(&inode->i_lock);
+
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC);
+	prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
+	/* Checking I_SYNC with inode->i_lock guarantees memory ordering. */
+	sleep = !!(inode->i_state & I_SYNC);
 	spin_unlock(&inode->i_lock);
 	if (sleep)
 		schedule();
-	finish_wait(wqh, &wait);
+	finish_wait(wq_head, &wqe.wq_entry);
 }
 
 /*
@@ -1752,7 +1759,7 @@ static int writeback_single_inode(struct inode *inode,
 		 */
 		if (wbc->sync_mode != WB_SYNC_ALL)
 			goto out;
-		__inode_wait_for_writeback(inode);
+		inode_wait_for_writeback(inode);
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*

fs/fuse/file.c

@@ -2393,76 +2393,77 @@ out:
  * but how to implement it without killing performance need more thinking.
  */
 static int fuse_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
-	struct page *page;
+	struct folio *folio;
 	loff_t fsize;
 	int err = -ENOMEM;
 
 	WARN_ON(!fc->writeback_cache);
 
-	page = grab_cache_page_write_begin(mapping, index);
-	if (!page)
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (IS_ERR(folio))
 		goto error;
 
-	fuse_wait_on_page_writeback(mapping->host, page->index);
+	fuse_wait_on_page_writeback(mapping->host, folio->index);
 
-	if (PageUptodate(page) || len == PAGE_SIZE)
+	if (folio_test_uptodate(folio) || len >= folio_size(folio))
 		goto success;
 	/*
-	 * Check if the start this page comes after the end of file, in which
-	 * case the readpage can be optimized away.
+	 * Check if the start of this folio comes after the end of file,
+	 * in which case the readpage can be optimized away.
 	 */
 	fsize = i_size_read(mapping->host);
-	if (fsize <= (pos & PAGE_MASK)) {
-		size_t off = pos & ~PAGE_MASK;
+	if (fsize <= folio_pos(folio)) {
+		size_t off = offset_in_folio(folio, pos);
 		if (off)
-			zero_user_segment(page, 0, off);
+			folio_zero_segment(folio, 0, off);
 		goto success;
 	}
-	err = fuse_do_readpage(file, page);
+	err = fuse_do_readpage(file, &folio->page);
 	if (err)
 		goto cleanup;
 success:
-	*pagep = page;
+	*foliop = folio;
 	return 0;
 
 cleanup:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 error:
 	return err;
 }
 
 static int fuse_write_end(struct file *file, struct address_space *mapping,
 		loff_t pos, unsigned len, unsigned copied,
-		struct page *page, void *fsdata)
+		struct folio *folio, void *fsdata)
 {
-	struct inode *inode = page->mapping->host;
+	struct inode *inode = folio->mapping->host;
 
 	/* Haven't copied anything?  Skip zeroing, size extending, dirtying. */
 	if (!copied)
 		goto unlock;
 
 	pos += copied;
-	if (!PageUptodate(page)) {
+	if (!folio_test_uptodate(folio)) {
 		/* Zero any unwritten bytes at the end of the page */
 		size_t endoff = pos & ~PAGE_MASK;
 		if (endoff)
-			zero_user_segment(page, endoff, PAGE_SIZE);
-		SetPageUptodate(page);
+			folio_zero_segment(folio, endoff, PAGE_SIZE);
+		folio_mark_uptodate(folio);
 	}
 
 	if (pos > inode->i_size)
 		i_size_write(inode, pos);
 
-	set_page_dirty(page);
+	folio_mark_dirty(folio);
 
 unlock:
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return copied;
 }

fs/hfs/extent.c

@@ -487,15 +487,15 @@ void hfs_file_truncate(struct inode *inode)
 	if (inode->i_size > HFS_I(inode)->phys_size) {
 		struct address_space *mapping = inode->i_mapping;
 		void *fsdata = NULL;
-		struct page *page;
+		struct folio *folio;
 
 		/* XXX: Can use generic_cont_expand? */
 		size = inode->i_size - 1;
-		res = hfs_write_begin(NULL, mapping, size + 1, 0, &page,
+		res = hfs_write_begin(NULL, mapping, size + 1, 0, &folio,
 				&fsdata);
 		if (!res) {
 			res = generic_write_end(NULL, mapping, size + 1, 0, 0,
-					page, fsdata);
+					folio, fsdata);
 		}
 		if (res)
 			inode->i_size = HFS_I(inode)->phys_size;

fs/hfs/hfs_fs.h

@@ -202,7 +202,7 @@ extern const struct address_space_operations hfs_aops;
 extern const struct address_space_operations hfs_btree_aops;
 
 int hfs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata);
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
 extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t);
 extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *);
 extern int hfs_write_inode(struct inode *, struct writeback_control *);

fs/hfs/inode.c

@@ -45,12 +45,11 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 int hfs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				hfs_get_block,
 				&HFS_I(mapping->host)->phys_size);
 	if (unlikely(ret))

fs/hfsplus/extents.c

@@ -554,16 +554,16 @@ void hfsplus_file_truncate(struct inode *inode)
 
 	if (inode->i_size > hip->phys_size) {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page;
+		struct folio *folio;
 		void *fsdata = NULL;
 		loff_t size = inode->i_size;
 
 		res = hfsplus_write_begin(NULL, mapping, size, 0,
-					  &page, &fsdata);
+					  &folio, &fsdata);
 		if (res)
 			return;
 		res = generic_write_end(NULL, mapping, size, 0, 0,
-					page, fsdata);
+					folio, fsdata);
 		if (res < 0)
 			return;
 		mark_inode_dirty(inode);

fs/hfsplus/hfsplus_fs.h

@@ -472,7 +472,7 @@ extern const struct address_space_operations hfsplus_btree_aops;
 extern const struct dentry_operations hfsplus_dentry_operations;
 
 int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata);
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
 struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir,
 				umode_t mode);
 void hfsplus_delete_inode(struct inode *inode);

fs/hfsplus/inode.c

@@ -39,12 +39,11 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
 }
 
 int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				hfsplus_get_block,
 				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret))

fs/hostfs/hostfs_kern.c

@@ -465,31 +465,32 @@ static int hostfs_read_folio(struct file *file, struct folio *folio)
 
 static int hostfs_write_begin(struct file *file, struct address_space *mapping,
 			      loff_t pos, unsigned len,
-			      struct page **pagep, void **fsdata)
+			      struct folio **foliop, void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
 
-	*pagep = grab_cache_page_write_begin(mapping, index);
-	if (!*pagep)
+	*foliop = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (!*foliop)
 		return -ENOMEM;
 	return 0;
 }
 
 static int hostfs_write_end(struct file *file, struct address_space *mapping,
 			    loff_t pos, unsigned len, unsigned copied,
-			    struct page *page, void *fsdata)
+			    struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	void *buffer;
-	unsigned from = pos & (PAGE_SIZE - 1);
+	size_t from = offset_in_folio(folio, pos);
 	int err;
 
-	buffer = kmap_local_page(page);
-	err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer + from, copied);
+	buffer = kmap_local_folio(folio, from);
+	err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer, copied);
 	kunmap_local(buffer);
 
-	if (!PageUptodate(page) && err == PAGE_SIZE)
-		SetPageUptodate(page);
+	if (!folio_test_uptodate(folio) && err == folio_size(folio))
+		folio_mark_uptodate(folio);
 
 	/*
 	 * If err > 0, write_file has added err to pos, so we are comparing
@@ -497,8 +498,8 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 	 */
 	if (err > 0 && (pos > inode->i_size))
 		inode->i_size = pos;
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return err;
 }

fs/hpfs/file.c

@@ -190,12 +190,11 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				hpfs_get_block,
 				&hpfs_i(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -206,11 +205,11 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 
 static int hpfs_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *pagep, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
+	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		hpfs_write_failed(mapping, pos + len);
 	if (!(err < 0)) {

fs/hugetlbfs/inode.c

@@ -388,14 +388,14 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 static int hugetlbfs_write_begin(struct file *file,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	return -EINVAL;
 }
 
 static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	BUG();
 	return -EINVAL;

fs/inode.c

@@ -472,6 +472,17 @@ static void __inode_add_lru(struct inode *inode, bool rotate)
 		inode->i_state |= I_REFERENCED;
 }
 
+struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe,
+					    struct inode *inode, u32 bit)
+{
+        void *bit_address;
+
+        bit_address = inode_state_wait_address(inode, bit);
+        init_wait_var_entry(wqe, bit_address, 0);
+        return __var_waitqueue(bit_address);
+}
+EXPORT_SYMBOL(inode_bit_waitqueue);
+
 /*
  * Add inode to LRU if needed (inode is unused and clean).
  *
@@ -500,25 +511,35 @@ static void inode_unpin_lru_isolating(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_LRU_ISOLATING));
 	inode->i_state &= ~I_LRU_ISOLATING;
-	smp_mb();
-	wake_up_bit(&inode->i_state, __I_LRU_ISOLATING);
+	/* Called with inode->i_lock which ensures memory ordering. */
+	inode_wake_up_bit(inode, __I_LRU_ISOLATING);
 	spin_unlock(&inode->i_lock);
 }
 
 static void inode_wait_for_lru_isolating(struct inode *inode)
 {
-	spin_lock(&inode->i_lock);
-	if (inode->i_state & I_LRU_ISOLATING) {
-		DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING);
-		wait_queue_head_t *wqh;
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
 
-		wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING);
+	lockdep_assert_held(&inode->i_lock);
+	if (!(inode->i_state & I_LRU_ISOLATING))
+		return;
+
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_LRU_ISOLATING);
+	for (;;) {
+		prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
+		/*
+		 * Checking I_LRU_ISOLATING with inode->i_lock guarantees
+		 * memory ordering.
+		 */
+		if (!(inode->i_state & I_LRU_ISOLATING))
+			break;
 		spin_unlock(&inode->i_lock);
-		__wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE);
+		schedule();
 		spin_lock(&inode->i_lock);
-		WARN_ON(inode->i_state & I_LRU_ISOLATING);
 	}
-	spin_unlock(&inode->i_lock);
+	finish_wait(wq_head, &wqe.wq_entry);
+	WARN_ON(inode->i_state & I_LRU_ISOLATING);
 }
 
 /**
@@ -595,6 +616,7 @@ void dump_mapping(const struct address_space *mapping)
 	struct hlist_node *dentry_first;
 	struct dentry *dentry_ptr;
 	struct dentry dentry;
+	char fname[64] = {};
 	unsigned long ino;
 
 	/*
@@ -631,11 +653,14 @@ void dump_mapping(const struct address_space *mapping)
 		return;
 	}
 
+	if (strncpy_from_kernel_nofault(fname, dentry.d_name.name, 63) < 0)
+		strscpy(fname, "<invalid>");
 	/*
-	 * if dentry is corrupted, the %pd handler may still crash,
-	 * but it's unlikely that we reach here with a corrupt mapping
+	 * Even if strncpy_from_kernel_nofault() succeeded,
+	 * the fname could be unreliable
 	 */
-	pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry);
+	pr_warn("aops:%ps ino:%lx dentry name(?):\"%s\"\n",
+		a_ops, ino, fname);
 }
 
 void clear_inode(struct inode *inode)
@@ -690,6 +715,7 @@ static void evict(struct inode *inode)
 
 	inode_sb_list_del(inode);
 
+	spin_lock(&inode->i_lock);
 	inode_wait_for_lru_isolating(inode);
 
 	/*
@@ -699,6 +725,7 @@ static void evict(struct inode *inode)
 	 * the inode.  We just have to wait for running writeback to finish.
 	 */
 	inode_wait_for_writeback(inode);
+	spin_unlock(&inode->i_lock);
 
 	if (op->evict_inode) {
 		op->evict_inode(inode);
@@ -722,7 +749,13 @@ static void evict(struct inode *inode)
 	 * used as an indicator whether blocking on it is safe.
 	 */
 	spin_lock(&inode->i_lock);
-	wake_up_bit(&inode->i_state, __I_NEW);
+	/*
+	 * Pairs with the barrier in prepare_to_wait_event() to make sure
+	 * ___wait_var_event() either sees the bit cleared or
+	 * waitqueue_active() check in wake_up_var() sees the waiter.
+	 */
+	smp_mb();
+	inode_wake_up_bit(inode, __I_NEW);
 	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
 	spin_unlock(&inode->i_lock);
 
@@ -770,6 +803,10 @@ again:
 			continue;
 
 		spin_lock(&inode->i_lock);
+		if (atomic_read(&inode->i_count)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
 			spin_unlock(&inode->i_lock);
 			continue;
@@ -1130,8 +1167,13 @@ void unlock_new_inode(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
 	inode->i_state &= ~I_NEW & ~I_CREATING;
+	/*
+	 * Pairs with the barrier in prepare_to_wait_event() to make sure
+	 * ___wait_var_event() either sees the bit cleared or
+	 * waitqueue_active() check in wake_up_var() sees the waiter.
+	 */
 	smp_mb();
-	wake_up_bit(&inode->i_state, __I_NEW);
+	inode_wake_up_bit(inode, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(unlock_new_inode);
@@ -1142,8 +1184,13 @@ void discard_new_inode(struct inode *inode)
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
 	inode->i_state &= ~I_NEW;
+	/*
+	 * Pairs with the barrier in prepare_to_wait_event() to make sure
+	 * ___wait_var_event() either sees the bit cleared or
+	 * waitqueue_active() check in wake_up_var() sees the waiter.
+	 */
 	smp_mb();
-	wake_up_bit(&inode->i_state, __I_NEW);
+	inode_wake_up_bit(inode, __I_NEW);
 	spin_unlock(&inode->i_lock);
 	iput(inode);
 }
@@ -1570,9 +1617,7 @@ struct inode *ilookup(struct super_block *sb, unsigned long ino)
 	struct hlist_head *head = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
 again:
-	spin_lock(&inode_hash_lock);
-	inode = find_inode_fast(sb, head, ino, true);
-	spin_unlock(&inode_hash_lock);
+	inode = find_inode_fast(sb, head, ino, false);
 
 	if (inode) {
 		if (IS_ERR(inode))
@@ -2334,8 +2379,8 @@ EXPORT_SYMBOL(inode_needs_sync);
  */
 static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_locked)
 {
-	wait_queue_head_t *wq;
-	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
+	struct wait_bit_queue_entry wqe;
+	struct wait_queue_head *wq_head;
 
 	/*
 	 * Handle racing against evict(), see that routine for more details.
@@ -2346,14 +2391,14 @@ static void __wait_on_freeing_inode(struct inode *inode, bool is_inode_hash_lock
 		return;
 	}
 
-	wq = bit_waitqueue(&inode->i_state, __I_NEW);
-	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+	wq_head = inode_bit_waitqueue(&wqe, inode, __I_NEW);
+	prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE);
 	spin_unlock(&inode->i_lock);
 	rcu_read_unlock();
 	if (is_inode_hash_locked)
 		spin_unlock(&inode_hash_lock);
 	schedule();
-	finish_wait(wq, &wait.wq_entry);
+	finish_wait(wq_head, &wqe.wq_entry);
 	if (is_inode_hash_locked)
 		spin_lock(&inode_hash_lock);
 	rcu_read_lock();
@@ -2502,18 +2547,11 @@ EXPORT_SYMBOL(inode_owner_or_capable);
 /*
  * Direct i/o helper functions
  */
-static void __inode_dio_wait(struct inode *inode)
+bool inode_dio_finished(const struct inode *inode)
 {
-	wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
-	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
-
-	do {
-		prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE);
-		if (atomic_read(&inode->i_dio_count))
-			schedule();
-	} while (atomic_read(&inode->i_dio_count));
-	finish_wait(wq, &q.wq_entry);
+	return atomic_read(&inode->i_dio_count) == 0;
 }
+EXPORT_SYMBOL(inode_dio_finished);
 
 /**
  * inode_dio_wait - wait for outstanding DIO requests to finish
@@ -2527,11 +2565,17 @@ static void __inode_dio_wait(struct inode *inode)
  */
 void inode_dio_wait(struct inode *inode)
 {
-	if (atomic_read(&inode->i_dio_count))
-		__inode_dio_wait(inode);
+	wait_var_event(&inode->i_dio_count, inode_dio_finished(inode));
 }
 EXPORT_SYMBOL(inode_dio_wait);
 
+void inode_dio_wait_interruptible(struct inode *inode)
+{
+	wait_var_event_interruptible(&inode->i_dio_count,
+				     inode_dio_finished(inode));
+}
+EXPORT_SYMBOL(inode_dio_wait_interruptible);
+
 /*
  * inode_set_flags - atomically set some inode flags
  *

fs/internal.h

@@ -337,3 +337,4 @@ static inline bool path_mounted(const struct path *path)
 {
 	return path->mnt->mnt_root == path->dentry;
 }
+void file_f_owner_release(struct file *file);

fs/iomap/buffered-io.c

@@ -900,7 +900,7 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 		size_t bh_written;
 
 		bh_written = block_write_end(NULL, iter->inode->i_mapping, pos,
-					len, copied, &folio->page, NULL);
+					len, copied, folio, NULL);
 		WARN_ON_ONCE(bh_written != copied && bh_written != 0);
 		return bh_written == copied;
 	}

fs/jffs2/file.c

@@ -23,10 +23,10 @@
 
 static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *pg, void *fsdata);
+			struct folio *folio, void *fsdata);
 static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata);
+			struct folio **foliop, void **fsdata);
 static int jffs2_read_folio(struct file *filp, struct folio *folio);
 
 int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
@@ -77,29 +77,27 @@ const struct address_space_operations jffs2_file_address_operations =
 	.write_end =	jffs2_write_end,
 };
 
-static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
+static int jffs2_do_readpage_nolock(struct inode *inode, struct folio *folio)
 {
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
-	unsigned char *pg_buf;
+	unsigned char *kaddr;
 	int ret;
 
 	jffs2_dbg(2, "%s(): ino #%lu, page at offset 0x%lx\n",
-		  __func__, inode->i_ino, pg->index << PAGE_SHIFT);
+		  __func__, inode->i_ino, folio->index << PAGE_SHIFT);
 
-	BUG_ON(!PageLocked(pg));
+	BUG_ON(!folio_test_locked(folio));
 
-	pg_buf = kmap(pg);
-	/* FIXME: Can kmap fail? */
-
-	ret = jffs2_read_inode_range(c, f, pg_buf, pg->index << PAGE_SHIFT,
+	kaddr = kmap_local_folio(folio, 0);
+	ret = jffs2_read_inode_range(c, f, kaddr, folio->index << PAGE_SHIFT,
 				     PAGE_SIZE);
+	kunmap_local(kaddr);
 
 	if (!ret)
-		SetPageUptodate(pg);
+		folio_mark_uptodate(folio);
 
-	flush_dcache_page(pg);
-	kunmap(pg);
+	flush_dcache_folio(folio);
 
 	jffs2_dbg(2, "readpage finished\n");
 	return ret;
@@ -107,7 +105,7 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 
 int __jffs2_read_folio(struct file *file, struct folio *folio)
 {
-	int ret = jffs2_do_readpage_nolock(folio->mapping->host, &folio->page);
+	int ret = jffs2_do_readpage_nolock(folio->mapping->host, folio);
 	folio_unlock(folio);
 	return ret;
 }
@@ -125,9 +123,9 @@ static int jffs2_read_folio(struct file *file, struct folio *folio)
 
 static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
-	struct page *pg;
+	struct folio *folio;
 	struct inode *inode = mapping->host;
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
 	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
@@ -206,29 +204,30 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 	 * page in read_cache_page(), which causes a deadlock.
 	 */
 	mutex_lock(&c->alloc_sem);
-	pg = grab_cache_page_write_begin(mapping, index);
-	if (!pg) {
-		ret = -ENOMEM;
+	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+			mapping_gfp_mask(mapping));
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
 		goto release_sem;
 	}
-	*pagep = pg;
+	*foliop = folio;
 
 	/*
-	 * Read in the page if it wasn't already present. Cannot optimize away
-	 * the whole page write case until jffs2_write_end can handle the
+	 * Read in the folio if it wasn't already present. Cannot optimize away
+	 * the whole folio write case until jffs2_write_end can handle the
 	 * case of a short-copy.
 	 */
-	if (!PageUptodate(pg)) {
+	if (!folio_test_uptodate(folio)) {
 		mutex_lock(&f->sem);
-		ret = jffs2_do_readpage_nolock(inode, pg);
+		ret = jffs2_do_readpage_nolock(inode, folio);
 		mutex_unlock(&f->sem);
 		if (ret) {
-			unlock_page(pg);
-			put_page(pg);
+			folio_unlock(folio);
+			folio_put(folio);
 			goto release_sem;
 		}
 	}
-	jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags);
+	jffs2_dbg(1, "end write_begin(). folio->flags %lx\n", folio->flags);
 
 release_sem:
 	mutex_unlock(&c->alloc_sem);
@@ -238,7 +237,7 @@ out_err:
 
 static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *pg, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
 	/* Actually commit the write from the page cache page we're looking at.
 	 * For now, we write the full page out each time. It sucks, but it's simple
@@ -252,16 +251,17 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	unsigned aligned_start = start & ~3;
 	int ret = 0;
 	uint32_t writtenlen = 0;
+	void *buf;
 
-	jffs2_dbg(1, "%s(): ino #%lu, page at 0x%lx, range %d-%d, flags %lx\n",
-		  __func__, inode->i_ino, pg->index << PAGE_SHIFT,
-		  start, end, pg->flags);
+	jffs2_dbg(1, "%s(): ino #%lu, page at 0x%llx, range %d-%d, flags %lx\n",
+		  __func__, inode->i_ino, folio_pos(folio),
+		  start, end, folio->flags);
 
 	/* We need to avoid deadlock with page_cache_read() in
-	   jffs2_garbage_collect_pass(). So the page must be
+	   jffs2_garbage_collect_pass(). So the folio must be
 	   up to date to prevent page_cache_read() from trying
 	   to re-lock it. */
-	BUG_ON(!PageUptodate(pg));
+	BUG_ON(!folio_test_uptodate(folio));
 
 	if (end == PAGE_SIZE) {
 		/* When writing out the end of a page, write out the
@@ -276,8 +276,8 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	if (!ri) {
 		jffs2_dbg(1, "%s(): Allocation of raw inode failed\n",
 			  __func__);
-		unlock_page(pg);
-		put_page(pg);
+		folio_unlock(folio);
+		folio_put(folio);
 		return -ENOMEM;
 	}
 
@@ -289,15 +289,11 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	ri->isize = cpu_to_je32((uint32_t)inode->i_size);
 	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(JFFS2_NOW());
 
-	/* In 2.4, it was already kmapped by generic_file_write(). Doesn't
-	   hurt to do it again. The alternative is ifdefs, which are ugly. */
-	kmap(pg);
-
-	ret = jffs2_write_inode_range(c, f, ri, page_address(pg) + aligned_start,
-				      (pg->index << PAGE_SHIFT) + aligned_start,
+	buf = kmap_local_folio(folio, aligned_start);
+	ret = jffs2_write_inode_range(c, f, ri, buf,
+				      folio_pos(folio) + aligned_start,
 				      end - aligned_start, &writtenlen);
-
-	kunmap(pg);
+	kunmap_local(buf);
 
 	if (ret)
 		mapping_set_error(mapping, ret);
@@ -323,12 +319,12 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 		   it gets reread */
 		jffs2_dbg(1, "%s(): Not all bytes written. Marking page !uptodate\n",
 			__func__);
-		ClearPageUptodate(pg);
+		folio_clear_uptodate(folio);
 	}
 
 	jffs2_dbg(1, "%s() returning %d\n",
 		  __func__, writtenlen > 0 ? writtenlen : ret);
-	unlock_page(pg);
-	put_page(pg);
+	folio_unlock(folio);
+	folio_put(folio);
 	return writtenlen > 0 ? writtenlen : ret;
 }

fs/jffs2/gc.c

@@ -1171,7 +1171,7 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 	uint32_t alloclen, offset, orig_end, orig_start;
 	int ret = 0;
 	unsigned char *comprbuf = NULL, *writebuf;
-	struct page *page;
+	struct folio *folio;
 	unsigned char *pg_ptr;
 
 	memset(&ri, 0, sizeof(ri));
@@ -1317,25 +1317,25 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		BUG_ON(start > orig_start);
 	}
 
-	/* The rules state that we must obtain the page lock *before* f->sem, so
+	/* The rules state that we must obtain the folio lock *before* f->sem, so
 	 * drop f->sem temporarily. Since we also hold c->alloc_sem, nothing's
 	 * actually going to *change* so we're safe; we only allow reading.
 	 *
 	 * It is important to note that jffs2_write_begin() will ensure that its
-	 * page is marked Uptodate before allocating space. That means that if we
-	 * end up here trying to GC the *same* page that jffs2_write_begin() is
-	 * trying to write out, read_cache_page() will not deadlock. */
+	 * folio is marked uptodate before allocating space. That means that if we
+	 * end up here trying to GC the *same* folio that jffs2_write_begin() is
+	 * trying to write out, read_cache_folio() will not deadlock. */
 	mutex_unlock(&f->sem);
-	page = read_cache_page(inode->i_mapping, start >> PAGE_SHIFT,
+	folio = read_cache_folio(inode->i_mapping, start >> PAGE_SHIFT,
 			       __jffs2_read_folio, NULL);
-	if (IS_ERR(page)) {
-		pr_warn("read_cache_page() returned error: %ld\n",
-			PTR_ERR(page));
+	if (IS_ERR(folio)) {
+		pr_warn("read_cache_folio() returned error: %ld\n",
+			PTR_ERR(folio));
 		mutex_lock(&f->sem);
-		return PTR_ERR(page);
+		return PTR_ERR(folio);
 	}
 
-	pg_ptr = kmap(page);
+	pg_ptr = kmap_local_folio(folio, 0);
 	mutex_lock(&f->sem);
 
 	offset = start;
@@ -1400,7 +1400,6 @@ static int jffs2_garbage_collect_dnode(struct jffs2_sb_info *c, struct jffs2_era
 		}
 	}
 
-	kunmap(page);
-	put_page(page);
+	folio_release_kmap(folio, pg_ptr);
 	return ret;
 }

fs/jfs/inode.c

@@ -292,11 +292,11 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int jfs_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata)
+				struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, pagep, jfs_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, jfs_get_block);
 	if (unlikely(ret))
 		jfs_write_failed(mapping, pos + len);
 
@@ -304,12 +304,12 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping,
 }
 
 static int jfs_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct page *page,
+		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
 		void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		jfs_write_failed(mapping, pos + len);
 	return ret;

fs/libfs.c

@@ -914,7 +914,7 @@ static int simple_read_folio(struct file *file, struct folio *folio)
 
 int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	struct folio *folio;
 
@@ -923,7 +923,7 @@ int simple_write_begin(struct file *file, struct address_space *mapping,
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	*pagep = &folio->page;
+	*foliop = folio;
 
 	if (!folio_test_uptodate(folio) && (len != folio_size(folio))) {
 		size_t from = offset_in_folio(folio, pos);
@@ -942,11 +942,11 @@ EXPORT_SYMBOL(simple_write_begin);
  * @pos: 		"
  * @len: 		"
  * @copied: 		"
- * @page: 		"
+ * @folio: 		"
  * @fsdata: 		"
  *
- * simple_write_end does the minimum needed for updating a page after writing is
- * done. It has the same API signature as the .write_end of
+ * simple_write_end does the minimum needed for updating a folio after
+ * writing is done. It has the same API signature as the .write_end of
  * address_space_operations vector. So it can just be set onto .write_end for
  * FSes that don't need any other processing. i_mutex is assumed to be held.
  * Block based filesystems should use generic_write_end().
@@ -959,9 +959,8 @@ EXPORT_SYMBOL(simple_write_begin);
  */
 static int simple_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
+			struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
 
@@ -2003,13 +2002,19 @@ bool inode_maybe_inc_iversion(struct inode *inode, bool force)
 	 * information, but the legacy inode_inc_iversion code used a spinlock
 	 * to serialize increments.
 	 *
-	 * Here, we add full memory barriers to ensure that any de-facto
-	 * ordering with other info is preserved.
+	 * We add a full memory barrier to ensure that any de facto ordering
+	 * with other state is preserved (either implicitly coming from cmpxchg
+	 * or explicitly from smp_mb if we don't know upfront if we will execute
+	 * the former).
 	 *
-	 * This barrier pairs with the barrier in inode_query_iversion()
+	 * These barriers pair with inode_query_iversion().
 	 */
-	smp_mb();
 	cur = inode_peek_iversion_raw(inode);
+	if (!force && !(cur & I_VERSION_QUERIED)) {
+		smp_mb();
+		cur = inode_peek_iversion_raw(inode);
+	}
+
 	do {
 		/* If flag is clear then we needn't do anything */
 		if (!force && !(cur & I_VERSION_QUERIED))
@@ -2038,20 +2043,22 @@ EXPORT_SYMBOL(inode_maybe_inc_iversion);
 u64 inode_query_iversion(struct inode *inode)
 {
 	u64 cur, new;
+	bool fenced = false;
 
+	/*
+	 * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with
+	 * inode_maybe_inc_iversion(), see that routine for more details.
+	 */
 	cur = inode_peek_iversion_raw(inode);
 	do {
 		/* If flag is already set, then no need to swap */
 		if (cur & I_VERSION_QUERIED) {
-			/*
-			 * This barrier (and the implicit barrier in the
-			 * cmpxchg below) pairs with the barrier in
-			 * inode_maybe_inc_iversion().
-			 */
-			smp_mb();
+			if (!fenced)
+				smp_mb();
 			break;
 		}
 
+		fenced = true;
 		new = cur | I_VERSION_QUERIED;
 	} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
 	return cur >> I_VERSION_QUERIED_SHIFT;

fs/locks.c

@@ -1451,7 +1451,7 @@ int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose)
 		struct file *filp = fl->c.flc_file;
 
 		f_delown(filp);
-		filp->f_owner.signum = 0;
+		file_f_owner(filp)->signum = 0;
 		fasync_helper(0, fl->c.flc_file, 0, &fl->fl_fasync);
 		if (fl->fl_fasync != NULL) {
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
@@ -1783,6 +1783,10 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
 
+	error = file_f_owner_allocate(filp);
+	if (error)
+		return error;
+
 	/* Note that arg is never F_UNLCK here */
 	ctx = locks_get_lock_context(inode, arg);
 	if (!ctx)

fs/minix/dir.c

@@ -40,18 +40,18 @@ minix_last_byte(struct inode *inode, unsigned long page_nr)
 	return last_byte;
 }
 
-static void dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
+static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping = folio->mapping;
 	struct inode *dir = mapping->host;
 
-	block_write_end(NULL, mapping, pos, len, len, page, NULL);
+	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
 		mark_inode_dirty(dir);
 	}
-	unlock_page(page);
+	folio_unlock(folio);
 }
 
 static int minix_handle_dirsync(struct inode *dir)
@@ -64,14 +64,15 @@ static int minix_handle_dirsync(struct inode *dir)
 	return err;
 }
 
-static void *dir_get_page(struct inode *dir, unsigned long n, struct page **p)
+static void *dir_get_folio(struct inode *dir, unsigned long n,
+		struct folio **foliop)
 {
-	struct address_space *mapping = dir->i_mapping;
-	struct page *page = read_mapping_page(mapping, n, NULL);
-	if (IS_ERR(page))
-		return ERR_CAST(page);
-	*p = page;
-	return kmap_local_page(page);
+	struct folio *folio = read_mapping_folio(dir->i_mapping, n, NULL);
+
+	if (IS_ERR(folio))
+		return ERR_CAST(folio);
+	*foliop = folio;
+	return kmap_local_folio(folio, 0);
 }
 
 static inline void *minix_next_entry(void *de, struct minix_sb_info *sbi)
@@ -99,9 +100,9 @@ static int minix_readdir(struct file *file, struct dir_context *ctx)
 
 	for ( ; n < npages; n++, offset = 0) {
 		char *p, *kaddr, *limit;
-		struct page *page;
+		struct folio *folio;
 
-		kaddr = dir_get_page(inode, n, &page);
+		kaddr = dir_get_folio(inode, n, &folio);
 		if (IS_ERR(kaddr))
 			continue;
 		p = kaddr+offset;
@@ -122,13 +123,13 @@ static int minix_readdir(struct file *file, struct dir_context *ctx)
 				unsigned l = strnlen(name, sbi->s_namelen);
 				if (!dir_emit(ctx, name, l,
 					      inumber, DT_UNKNOWN)) {
-					unmap_and_put_page(page, p);
+					folio_release_kmap(folio, p);
 					return 0;
 				}
 			}
 			ctx->pos += chunk_size;
 		}
-		unmap_and_put_page(page, kaddr);
+		folio_release_kmap(folio, kaddr);
 	}
 	return 0;
 }
@@ -144,12 +145,13 @@ static inline int namecompare(int len, int maxlen,
 /*
  *	minix_find_entry()
  *
- * finds an entry in the specified directory with the wanted name. It
- * returns the cache buffer in which the entry was found, and the entry
- * itself (as a parameter - res_dir). It does NOT read the inode of the
+ * finds an entry in the specified directory with the wanted name.
+ * It does NOT read the inode of the
  * entry - you'll have to do that yourself if you want to.
+ * 
+ * On Success folio_release_kmap() should be called on *foliop.
  */
-minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page)
+minix_dirent *minix_find_entry(struct dentry *dentry, struct folio **foliop)
 {
 	const char * name = dentry->d_name.name;
 	int namelen = dentry->d_name.len;
@@ -158,17 +160,15 @@ minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page)
 	struct minix_sb_info * sbi = minix_sb(sb);
 	unsigned long n;
 	unsigned long npages = dir_pages(dir);
-	struct page *page = NULL;
 	char *p;
 
 	char *namx;
 	__u32 inumber;
-	*res_page = NULL;
 
 	for (n = 0; n < npages; n++) {
 		char *kaddr, *limit;
 
-		kaddr = dir_get_page(dir, n, &page);
+		kaddr = dir_get_folio(dir, n, foliop);
 		if (IS_ERR(kaddr))
 			continue;
 
@@ -188,12 +188,11 @@ minix_dirent *minix_find_entry(struct dentry *dentry, struct page **res_page)
 			if (namecompare(namelen, sbi->s_namelen, name, namx))
 				goto found;
 		}
-		unmap_and_put_page(page, kaddr);
+		folio_release_kmap(*foliop, kaddr);
 	}
 	return NULL;
 
 found:
-	*res_page = page;
 	return (minix_dirent *)p;
 }
 
@@ -204,7 +203,7 @@ int minix_add_link(struct dentry *dentry, struct inode *inode)
 	int namelen = dentry->d_name.len;
 	struct super_block * sb = dir->i_sb;
 	struct minix_sb_info * sbi = minix_sb(sb);
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 	unsigned long npages = dir_pages(dir);
 	unsigned long n;
 	char *kaddr, *p;
@@ -223,10 +222,10 @@ int minix_add_link(struct dentry *dentry, struct inode *inode)
 	for (n = 0; n <= npages; n++) {
 		char *limit, *dir_end;
 
-		kaddr = dir_get_page(dir, n, &page);
+		kaddr = dir_get_folio(dir, n, &folio);
 		if (IS_ERR(kaddr))
 			return PTR_ERR(kaddr);
-		lock_page(page);
+		folio_lock(folio);
 		dir_end = kaddr + minix_last_byte(dir, n);
 		limit = kaddr + PAGE_SIZE - sbi->s_dirsize;
 		for (p = kaddr; p <= limit; p = minix_next_entry(p, sbi)) {
@@ -253,15 +252,15 @@ int minix_add_link(struct dentry *dentry, struct inode *inode)
 			if (namecompare(namelen, sbi->s_namelen, name, namx))
 				goto out_unlock;
 		}
-		unlock_page(page);
-		unmap_and_put_page(page, kaddr);
+		folio_unlock(folio);
+		folio_release_kmap(folio, kaddr);
 	}
 	BUG();
 	return -EINVAL;
 
 got_it:
-	pos = page_offset(page) + offset_in_page(p);
-	err = minix_prepare_chunk(page, pos, sbi->s_dirsize);
+	pos = folio_pos(folio) + offset_in_folio(folio, p);
+	err = minix_prepare_chunk(folio, pos, sbi->s_dirsize);
 	if (err)
 		goto out_unlock;
 	memcpy (namx, name, namelen);
@@ -272,37 +271,37 @@ got_it:
 		memset (namx + namelen, 0, sbi->s_dirsize - namelen - 2);
 		de->inode = inode->i_ino;
 	}
-	dir_commit_chunk(page, pos, sbi->s_dirsize);
+	dir_commit_chunk(folio, pos, sbi->s_dirsize);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 	mark_inode_dirty(dir);
 	err = minix_handle_dirsync(dir);
 out_put:
-	unmap_and_put_page(page, kaddr);
+	folio_release_kmap(folio, kaddr);
 	return err;
 out_unlock:
-	unlock_page(page);
+	folio_unlock(folio);
 	goto out_put;
 }
 
-int minix_delete_entry(struct minix_dir_entry *de, struct page *page)
+int minix_delete_entry(struct minix_dir_entry *de, struct folio *folio)
 {
-	struct inode *inode = page->mapping->host;
-	loff_t pos = page_offset(page) + offset_in_page(de);
+	struct inode *inode = folio->mapping->host;
+	loff_t pos = folio_pos(folio) + offset_in_folio(folio, de);
 	struct minix_sb_info *sbi = minix_sb(inode->i_sb);
 	unsigned len = sbi->s_dirsize;
 	int err;
 
-	lock_page(page);
-	err = minix_prepare_chunk(page, pos, len);
+	folio_lock(folio);
+	err = minix_prepare_chunk(folio, pos, len);
 	if (err) {
-		unlock_page(page);
+		folio_unlock(folio);
 		return err;
 	}
 	if (sbi->s_version == MINIX_V3)
 		((minix3_dirent *)de)->inode = 0;
 	else
 		de->inode = 0;
-	dir_commit_chunk(page, pos, len);
+	dir_commit_chunk(folio, pos, len);
 	inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
 	mark_inode_dirty(inode);
 	return minix_handle_dirsync(inode);
@@ -310,21 +309,21 @@ int minix_delete_entry(struct minix_dir_entry *de, struct page *page)
 
 int minix_make_empty(struct inode *inode, struct inode *dir)
 {
-	struct page *page = grab_cache_page(inode->i_mapping, 0);
+	struct folio *folio = filemap_grab_folio(inode->i_mapping, 0);
 	struct minix_sb_info *sbi = minix_sb(inode->i_sb);
 	char *kaddr;
 	int err;
 
-	if (!page)
-		return -ENOMEM;
-	err = minix_prepare_chunk(page, 0, 2 * sbi->s_dirsize);
+	if (IS_ERR(folio))
+		return PTR_ERR(folio);
+	err = minix_prepare_chunk(folio, 0, 2 * sbi->s_dirsize);
 	if (err) {
-		unlock_page(page);
+		folio_unlock(folio);
 		goto fail;
 	}
 
-	kaddr = kmap_local_page(page);
-	memset(kaddr, 0, PAGE_SIZE);
+	kaddr = kmap_local_folio(folio, 0);
+	memset(kaddr, 0, folio_size(folio));
 
 	if (sbi->s_version == MINIX_V3) {
 		minix3_dirent *de3 = (minix3_dirent *)kaddr;
@@ -345,10 +344,10 @@ int minix_make_empty(struct inode *inode, struct inode *dir)
 	}
 	kunmap_local(kaddr);
 
-	dir_commit_chunk(page, 0, 2 * sbi->s_dirsize);
+	dir_commit_chunk(folio, 0, 2 * sbi->s_dirsize);
 	err = minix_handle_dirsync(inode);
 fail:
-	put_page(page);
+	folio_put(folio);
 	return err;
 }
 
@@ -357,7 +356,7 @@ fail:
  */
 int minix_empty_dir(struct inode * inode)
 {
-	struct page *page = NULL;
+	struct folio *folio = NULL;
 	unsigned long i, npages = dir_pages(inode);
 	struct minix_sb_info *sbi = minix_sb(inode->i_sb);
 	char *name, *kaddr;
@@ -366,7 +365,7 @@ int minix_empty_dir(struct inode * inode)
 	for (i = 0; i < npages; i++) {
 		char *p, *limit;
 
-		kaddr = dir_get_page(inode, i, &page);
+		kaddr = dir_get_folio(inode, i, &folio);
 		if (IS_ERR(kaddr))
 			continue;
 
@@ -395,44 +394,44 @@ int minix_empty_dir(struct inode * inode)
 					goto not_empty;
 			}
 		}
-		unmap_and_put_page(page, kaddr);
+		folio_release_kmap(folio, kaddr);
 	}
 	return 1;
 
 not_empty:
-	unmap_and_put_page(page, kaddr);
+	folio_release_kmap(folio, kaddr);
 	return 0;
 }
 
 /* Releases the page */
-int minix_set_link(struct minix_dir_entry *de, struct page *page,
+int minix_set_link(struct minix_dir_entry *de, struct folio *folio,
 		struct inode *inode)
 {
-	struct inode *dir = page->mapping->host;
+	struct inode *dir = folio->mapping->host;
 	struct minix_sb_info *sbi = minix_sb(dir->i_sb);
-	loff_t pos = page_offset(page) + offset_in_page(de);
+	loff_t pos = folio_pos(folio) + offset_in_folio(folio, de);
 	int err;
 
-	lock_page(page);
-	err = minix_prepare_chunk(page, pos, sbi->s_dirsize);
+	folio_lock(folio);
+	err = minix_prepare_chunk(folio, pos, sbi->s_dirsize);
 	if (err) {
-		unlock_page(page);
+		folio_unlock(folio);
 		return err;
 	}
 	if (sbi->s_version == MINIX_V3)
 		((minix3_dirent *)de)->inode = inode->i_ino;
 	else
 		de->inode = inode->i_ino;
-	dir_commit_chunk(page, pos, sbi->s_dirsize);
+	dir_commit_chunk(folio, pos, sbi->s_dirsize);
 	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
 	mark_inode_dirty(dir);
 	return minix_handle_dirsync(dir);
 }
 
-struct minix_dir_entry * minix_dotdot (struct inode *dir, struct page **p)
+struct minix_dir_entry *minix_dotdot(struct inode *dir, struct folio **foliop)
 {
 	struct minix_sb_info *sbi = minix_sb(dir->i_sb);
-	struct minix_dir_entry *de = dir_get_page(dir, 0, p);
+	struct minix_dir_entry *de = dir_get_folio(dir, 0, foliop);
 
 	if (!IS_ERR(de))
 		return minix_next_entry(de, sbi);
@@ -441,20 +440,19 @@ struct minix_dir_entry * minix_dotdot (struct inode *dir, struct page **p)
 
 ino_t minix_inode_by_name(struct dentry *dentry)
 {
-	struct page *page;
-	struct minix_dir_entry *de = minix_find_entry(dentry, &page);
+	struct folio *folio;
+	struct minix_dir_entry *de = minix_find_entry(dentry, &folio);
 	ino_t res = 0;
 
 	if (de) {
-		struct address_space *mapping = page->mapping;
-		struct inode *inode = mapping->host;
+		struct inode *inode = folio->mapping->host;
 		struct minix_sb_info *sbi = minix_sb(inode->i_sb);
 
 		if (sbi->s_version == MINIX_V3)
 			res = ((minix3_dirent *) de)->inode;
 		else
 			res = de->inode;
-		unmap_and_put_page(page, de);
+		folio_release_kmap(folio, de);
 	}
 	return res;
 }

fs/minix/inode.c

@@ -427,9 +427,9 @@ static int minix_read_folio(struct file *file, struct folio *folio)
 	return block_read_full_folio(folio, minix_get_block);
 }
 
-int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len)
+int minix_prepare_chunk(struct folio *folio, loff_t pos, unsigned len)
 {
-	return __block_write_begin(page, pos, len, minix_get_block);
+	return __block_write_begin(folio, pos, len, minix_get_block);
 }
 
 static void minix_write_failed(struct address_space *mapping, loff_t to)
@@ -444,11 +444,11 @@ static void minix_write_failed(struct address_space *mapping, loff_t to)
 
 static int minix_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, pagep, minix_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, minix_get_block);
 	if (unlikely(ret))
 		minix_write_failed(mapping, pos + len);
 

fs/minix/minix.h

@@ -42,18 +42,18 @@ struct minix_sb_info {
 	unsigned short s_version;
 };
 
-extern struct inode *minix_iget(struct super_block *, unsigned long);
-extern struct minix_inode * minix_V1_raw_inode(struct super_block *, ino_t, struct buffer_head **);
-extern struct minix2_inode * minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **);
-extern struct inode * minix_new_inode(const struct inode *, umode_t);
-extern void minix_free_inode(struct inode * inode);
-extern unsigned long minix_count_free_inodes(struct super_block *sb);
-extern int minix_new_block(struct inode * inode);
-extern void minix_free_block(struct inode *inode, unsigned long block);
-extern unsigned long minix_count_free_blocks(struct super_block *sb);
-extern int minix_getattr(struct mnt_idmap *, const struct path *,
-			 struct kstat *, u32, unsigned int);
-extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
+struct inode *minix_iget(struct super_block *, unsigned long);
+struct minix_inode *minix_V1_raw_inode(struct super_block *, ino_t, struct buffer_head **);
+struct minix2_inode *minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **);
+struct inode *minix_new_inode(const struct inode *, umode_t);
+void minix_free_inode(struct inode *inode);
+unsigned long minix_count_free_inodes(struct super_block *sb);
+int minix_new_block(struct inode *inode);
+void minix_free_block(struct inode *inode, unsigned long block);
+unsigned long minix_count_free_blocks(struct super_block *sb);
+int minix_getattr(struct mnt_idmap *, const struct path *,
+		struct kstat *, u32, unsigned int);
+int minix_prepare_chunk(struct folio *folio, loff_t pos, unsigned len);
 
 extern void V1_minix_truncate(struct inode *);
 extern void V2_minix_truncate(struct inode *);
@@ -64,15 +64,15 @@ extern int V2_minix_get_block(struct inode *, long, struct buffer_head *, int);
 extern unsigned V1_minix_blocks(loff_t, struct super_block *);
 extern unsigned V2_minix_blocks(loff_t, struct super_block *);
 
-extern struct minix_dir_entry *minix_find_entry(struct dentry*, struct page**);
-extern int minix_add_link(struct dentry*, struct inode*);
-extern int minix_delete_entry(struct minix_dir_entry*, struct page*);
-extern int minix_make_empty(struct inode*, struct inode*);
-extern int minix_empty_dir(struct inode*);
-int minix_set_link(struct minix_dir_entry *de, struct page *page,
+struct minix_dir_entry *minix_find_entry(struct dentry *, struct folio **);
+int minix_add_link(struct dentry*, struct inode*);
+int minix_delete_entry(struct minix_dir_entry *, struct folio *);
+int minix_make_empty(struct inode*, struct inode*);
+int minix_empty_dir(struct inode*);
+int minix_set_link(struct minix_dir_entry *de, struct folio *folio,
 		struct inode *inode);
-extern struct minix_dir_entry *minix_dotdot(struct inode*, struct page**);
-extern ino_t minix_inode_by_name(struct dentry*);
+struct minix_dir_entry *minix_dotdot(struct inode*, struct folio **);
+ino_t minix_inode_by_name(struct dentry*);
 
 extern const struct inode_operations minix_file_inode_operations;
 extern const struct inode_operations minix_dir_inode_operations;

fs/minix/namei.c

@@ -141,15 +141,15 @@ out_fail:
 static int minix_unlink(struct inode * dir, struct dentry *dentry)
 {
 	struct inode * inode = d_inode(dentry);
-	struct page * page;
+	struct folio *folio;
 	struct minix_dir_entry * de;
 	int err;
 
-	de = minix_find_entry(dentry, &page);
+	de = minix_find_entry(dentry, &folio);
 	if (!de)
 		return -ENOENT;
-	err = minix_delete_entry(de, page);
-	unmap_and_put_page(page, de);
+	err = minix_delete_entry(de, folio);
+	folio_release_kmap(folio, de);
 
 	if (err)
 		return err;
@@ -180,28 +180,28 @@ static int minix_rename(struct mnt_idmap *idmap,
 {
 	struct inode * old_inode = d_inode(old_dentry);
 	struct inode * new_inode = d_inode(new_dentry);
-	struct page * dir_page = NULL;
+	struct folio * dir_folio = NULL;
 	struct minix_dir_entry * dir_de = NULL;
-	struct page * old_page;
+	struct folio *old_folio;
 	struct minix_dir_entry * old_de;
 	int err = -ENOENT;
 
 	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
 
-	old_de = minix_find_entry(old_dentry, &old_page);
+	old_de = minix_find_entry(old_dentry, &old_folio);
 	if (!old_de)
 		goto out;
 
 	if (S_ISDIR(old_inode->i_mode)) {
 		err = -EIO;
-		dir_de = minix_dotdot(old_inode, &dir_page);
+		dir_de = minix_dotdot(old_inode, &dir_folio);
 		if (!dir_de)
 			goto out_old;
 	}
 
 	if (new_inode) {
-		struct page * new_page;
+		struct folio *new_folio;
 		struct minix_dir_entry * new_de;
 
 		err = -ENOTEMPTY;
@@ -209,11 +209,11 @@ static int minix_rename(struct mnt_idmap *idmap,
 			goto out_dir;
 
 		err = -ENOENT;
-		new_de = minix_find_entry(new_dentry, &new_page);
+		new_de = minix_find_entry(new_dentry, &new_folio);
 		if (!new_de)
 			goto out_dir;
-		err = minix_set_link(new_de, new_page, old_inode);
-		unmap_and_put_page(new_page, new_de);
+		err = minix_set_link(new_de, new_folio, old_inode);
+		folio_release_kmap(new_folio, new_de);
 		if (err)
 			goto out_dir;
 		inode_set_ctime_current(new_inode);
@@ -228,22 +228,22 @@ static int minix_rename(struct mnt_idmap *idmap,
 			inode_inc_link_count(new_dir);
 	}
 
-	err = minix_delete_entry(old_de, old_page);
+	err = minix_delete_entry(old_de, old_folio);
 	if (err)
 		goto out_dir;
 
 	mark_inode_dirty(old_inode);
 
 	if (dir_de) {
-		err = minix_set_link(dir_de, dir_page, new_dir);
+		err = minix_set_link(dir_de, dir_folio, new_dir);
 		if (!err)
 			inode_dec_link_count(old_dir);
 	}
 out_dir:
 	if (dir_de)
-		unmap_and_put_page(dir_page, dir_de);
+		folio_release_kmap(dir_folio, dir_de);
 out_old:
-	unmap_and_put_page(old_page, old_de);
+	folio_release_kmap(old_folio, old_de);
 out:
 	return err;
 }

fs/mnt_idmapping.c

@@ -228,15 +228,15 @@ static int copy_mnt_idmap(struct uid_gid_map *map_from,
 		return 0;
 	}
 
-	forward = kmemdup(map_from->forward,
-			  nr_extents * sizeof(struct uid_gid_extent),
-			  GFP_KERNEL_ACCOUNT);
+	forward = kmemdup_array(map_from->forward, nr_extents,
+				sizeof(struct uid_gid_extent),
+				GFP_KERNEL_ACCOUNT);
 	if (!forward)
 		return -ENOMEM;
 
-	reverse = kmemdup(map_from->reverse,
-			  nr_extents * sizeof(struct uid_gid_extent),
-			  GFP_KERNEL_ACCOUNT);
+	reverse = kmemdup_array(map_from->reverse, nr_extents,
+				sizeof(struct uid_gid_extent),
+				GFP_KERNEL_ACCOUNT);
 	if (!reverse) {
 		kfree(forward);
 		return -ENOMEM;

fs/mount.h

@@ -153,5 +153,17 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
 	list_add_tail(&mnt->mnt_list, dt_list);
 }
 
-extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
 bool has_locked_children(struct mount *mnt, struct dentry *dentry);
+struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mnt_ns, bool previous);
+static inline struct mnt_namespace *lookup_next_mnt_ns(struct mnt_namespace *mntns)
+{
+	return __lookup_next_mnt_ns(mntns, false);
+}
+static inline struct mnt_namespace *lookup_prev_mnt_ns(struct mnt_namespace *mntns)
+{
+	return __lookup_next_mnt_ns(mntns, true);
+}
+static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct mnt_namespace, ns);
+}

fs/namei.c

@@ -1639,6 +1639,20 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 }
 EXPORT_SYMBOL(lookup_one_qstr_excl);
 
+/**
+ * lookup_fast - do fast lockless (but racy) lookup of a dentry
+ * @nd: current nameidata
+ *
+ * Do a fast, but racy lookup in the dcache for the given dentry, and
+ * revalidate it. Returns a valid dentry pointer or NULL if one wasn't
+ * found. On error, an ERR_PTR will be returned.
+ *
+ * If this function returns a valid dentry and the walk is no longer
+ * lazy, the dentry will carry a reference that must later be put. If
+ * RCU mode is still in force, then this is not the case and the dentry
+ * must be legitimized before use. If this returns NULL, then the walk
+ * will no longer be in RCU mode.
+ */
 static struct dentry *lookup_fast(struct nameidata *nd)
 {
 	struct dentry *dentry, *parent = nd->path.dentry;
@@ -3521,6 +3535,9 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 		return dentry;
 	}
 
+	if (open_flag & O_CREAT)
+		audit_inode(nd->name, dir, AUDIT_INODE_PARENT);
+
 	/*
 	 * Checking write permission is tricky, bacuse we don't know if we are
 	 * going to actually need it: O_CREAT opens should work as long as the
@@ -3591,6 +3608,42 @@ out_dput:
 	return ERR_PTR(error);
 }
 
+static inline bool trailing_slashes(struct nameidata *nd)
+{
+	return (bool)nd->last.name[nd->last.len];
+}
+
+static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
+{
+	struct dentry *dentry;
+
+	if (open_flag & O_CREAT) {
+		if (trailing_slashes(nd))
+			return ERR_PTR(-EISDIR);
+
+		/* Don't bother on an O_EXCL create */
+		if (open_flag & O_EXCL)
+			return NULL;
+	}
+
+	if (trailing_slashes(nd))
+		nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+
+	dentry = lookup_fast(nd);
+	if (IS_ERR_OR_NULL(dentry))
+		return dentry;
+
+	if (open_flag & O_CREAT) {
+		/* Discard negative dentries. Need inode_lock to do the create */
+		if (!dentry->d_inode) {
+			if (!(nd->flags & LOOKUP_RCU))
+				dput(dentry);
+			dentry = NULL;
+		}
+	}
+	return dentry;
+}
+
 static const char *open_last_lookups(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
@@ -3608,28 +3661,22 @@ static const char *open_last_lookups(struct nameidata *nd,
 		return handle_dots(nd, nd->last_type);
 	}
 
-	if (!(open_flag & O_CREAT)) {
-		if (nd->last.name[nd->last.len])
-			nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
-		/* we _can_ be in RCU mode here */
-		dentry = lookup_fast(nd);
-		if (IS_ERR(dentry))
-			return ERR_CAST(dentry);
-		if (likely(dentry))
-			goto finish_lookup;
+	/* We _can_ be in RCU mode here */
+	dentry = lookup_fast_for_open(nd, open_flag);
+	if (IS_ERR(dentry))
+		return ERR_CAST(dentry);
 
+	if (likely(dentry))
+		goto finish_lookup;
+
+	if (!(open_flag & O_CREAT)) {
 		if (WARN_ON_ONCE(nd->flags & LOOKUP_RCU))
 			return ERR_PTR(-ECHILD);
 	} else {
-		/* create side of things */
 		if (nd->flags & LOOKUP_RCU) {
 			if (!try_to_unlazy(nd))
 				return ERR_PTR(-ECHILD);
 		}
-		audit_inode(nd->name, dir, AUDIT_INODE_PARENT);
-		/* trailing slashes? */
-		if (unlikely(nd->last.name[nd->last.len]))
-			return ERR_PTR(-EISDIR);
 	}
 
 	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
@@ -5304,7 +5351,7 @@ int page_symlink(struct inode *inode, const char *symname, int len)
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
 	bool nofs = !mapping_gfp_constraint(mapping, __GFP_FS);
-	struct page *page;
+	struct folio *folio;
 	void *fsdata = NULL;
 	int err;
 	unsigned int flags;
@@ -5312,16 +5359,16 @@ int page_symlink(struct inode *inode, const char *symname, int len)
 retry:
 	if (nofs)
 		flags = memalloc_nofs_save();
-	err = aops->write_begin(NULL, mapping, 0, len-1, &page, &fsdata);
+	err = aops->write_begin(NULL, mapping, 0, len-1, &folio, &fsdata);
 	if (nofs)
 		memalloc_nofs_restore(flags);
 	if (err)
 		goto fail;
 
-	memcpy(page_address(page), symname, len-1);
+	memcpy(folio_address(folio), symname, len - 1);
 
-	err = aops->write_end(NULL, mapping, 0, len-1, len-1,
-							page, fsdata);
+	err = aops->write_end(NULL, mapping, 0, len - 1, len - 1,
+						folio, fsdata);
 	if (err < 0)
 		goto fail;
 	if (err < len-1)

fs/namespace.c

@@ -1774,7 +1774,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		list_del_init(&p->mnt_child);
 	}
 
-	/* Add propogated mounts to the tmp_list */
+	/* Add propagated mounts to the tmp_list */
 	if (how & UMOUNT_PROPAGATE)
 		propagate_umount(&tmp_list);
 
@@ -2060,16 +2060,43 @@ static bool is_mnt_ns_file(struct dentry *dentry)
 	       dentry->d_fsdata == &mntns_operations;
 }
 
-static struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
-{
-	return container_of(ns, struct mnt_namespace, ns);
-}
-
 struct ns_common *from_mnt_ns(struct mnt_namespace *mnt)
 {
 	return &mnt->ns;
 }
 
+struct mnt_namespace *__lookup_next_mnt_ns(struct mnt_namespace *mntns, bool previous)
+{
+	guard(read_lock)(&mnt_ns_tree_lock);
+	for (;;) {
+		struct rb_node *node;
+
+		if (previous)
+			node = rb_prev(&mntns->mnt_ns_tree_node);
+		else
+			node = rb_next(&mntns->mnt_ns_tree_node);
+		if (!node)
+			return ERR_PTR(-ENOENT);
+
+		mntns = node_to_mnt_ns(node);
+		node = &mntns->mnt_ns_tree_node;
+
+		if (!ns_capable_noaudit(mntns->user_ns, CAP_SYS_ADMIN))
+			continue;
+
+		/*
+		 * Holding mnt_ns_tree_lock prevents the mount namespace from
+		 * being freed but it may well be on it's deathbed. We want an
+		 * active reference, not just a passive one here as we're
+		 * persisting the mount namespace.
+		 */
+		if (!refcount_inc_not_zero(&mntns->ns.count))
+			continue;
+
+		return mntns;
+	}
+}
+
 static bool mnt_ns_loop(struct dentry *dentry)
 {
 	/* Could bind mounting the mount namespace inode cause a
@@ -2921,8 +2948,15 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
 	if (!__mnt_is_readonly(mnt) &&
 	   (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) &&
 	   (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) {
-		char *buf = (char *)__get_free_page(GFP_KERNEL);
-		char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM);
+		char *buf, *mntpath;
+
+		buf = (char *)__get_free_page(GFP_KERNEL);
+		if (buf)
+			mntpath = d_path(mountpoint, buf, PAGE_SIZE);
+		else
+			mntpath = ERR_PTR(-ENOMEM);
+		if (IS_ERR(mntpath))
+			mntpath = "(unknown)";
 
 		pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n",
 			sb->s_type->name,
@@ -2930,8 +2964,9 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
 			mntpath, &sb->s_time_max,
 			(unsigned long long)sb->s_time_max);
 
-		free_page((unsigned long)buf);
 		sb->s_iflags |= SB_I_TS_EXPIRY_WARNED;
+		if (buf)
+			free_page((unsigned long)buf);
 	}
 }
 
@@ -5243,12 +5278,37 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req,
  * that, or if not simply grab a passive reference on our mount namespace and
  * return that.
  */
-static struct mnt_namespace *grab_requested_mnt_ns(u64 mnt_ns_id)
+static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq)
 {
-	if (mnt_ns_id)
-		return lookup_mnt_ns(mnt_ns_id);
-	refcount_inc(&current->nsproxy->mnt_ns->passive);
-	return current->nsproxy->mnt_ns;
+	struct mnt_namespace *mnt_ns;
+
+	if (kreq->mnt_ns_id && kreq->spare)
+		return ERR_PTR(-EINVAL);
+
+	if (kreq->mnt_ns_id)
+		return lookup_mnt_ns(kreq->mnt_ns_id);
+
+	if (kreq->spare) {
+		struct ns_common *ns;
+
+		CLASS(fd, f)(kreq->spare);
+		if (!f.file)
+			return ERR_PTR(-EBADF);
+
+		if (!proc_ns_file(f.file))
+			return ERR_PTR(-EINVAL);
+
+		ns = get_proc_ns(file_inode(f.file));
+		if (ns->ops->type != CLONE_NEWNS)
+			return ERR_PTR(-EINVAL);
+
+		mnt_ns = to_mnt_ns(ns);
+	} else {
+		mnt_ns = current->nsproxy->mnt_ns;
+	}
+
+	refcount_inc(&mnt_ns->passive);
+	return mnt_ns;
 }
 
 SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
@@ -5269,7 +5329,7 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req,
 	if (ret)
 		return ret;
 
-	ns = grab_requested_mnt_ns(kreq.mnt_ns_id);
+	ns = grab_requested_mnt_ns(&kreq);
 	if (!ns)
 		return -ENOENT;
 
@@ -5396,7 +5456,7 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	if (!kmnt_ids)
 		return -ENOMEM;
 
-	ns = grab_requested_mnt_ns(kreq.mnt_ns_id);
+	ns = grab_requested_mnt_ns(&kreq);
 	if (!ns)
 		return -ENOENT;
 
@@ -5605,7 +5665,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns,
 			/* Only worry about locked mounts */
 			if (!(child->mnt.mnt_flags & MNT_LOCKED))
 				continue;
-			/* Is the directory permanetly empty? */
+			/* Is the directory permanently empty? */
 			if (!is_empty_dir_inode(inode))
 				goto next;
 		}

fs/netfs/Makefile

@@ -5,12 +5,14 @@ netfs-y := \
 	buffered_write.o \
 	direct_read.o \
 	direct_write.o \
-	io.o \
 	iterator.o \
 	locking.o \
 	main.o \
 	misc.o \
 	objects.o \
+	read_collect.o \
+	read_pgpriv2.o \
+	read_retry.o \
 	write_collect.o \
 	write_issue.o
 

fs/netfs/buffered_read.c

@@ -9,214 +9,6 @@
 #include <linux/task_io_accounting_ops.h>
 #include "internal.h"
 
-/*
- * [DEPRECATED] Unlock the folios in a read operation for when the filesystem
- * is using PG_private_2 and direct writing to the cache from here rather than
- * marking the page for writeback.
- *
- * Note that we don't touch folio->private in this code.
- */
-static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq,
-					     size_t *account)
-{
-	struct netfs_io_subrequest *subreq;
-	struct folio *folio;
-	pgoff_t start_page = rreq->start / PAGE_SIZE;
-	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
-	bool subreq_failed = false;
-
-	XA_STATE(xas, &rreq->mapping->i_pages, start_page);
-
-	/* Walk through the pagecache and the I/O request lists simultaneously.
-	 * We may have a mixture of cached and uncached sections and we only
-	 * really want to write out the uncached sections.  This is slightly
-	 * complicated by the possibility that we might have huge pages with a
-	 * mixture inside.
-	 */
-	subreq = list_first_entry(&rreq->subrequests,
-				  struct netfs_io_subrequest, rreq_link);
-	subreq_failed = (subreq->error < 0);
-
-	trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2);
-
-	rcu_read_lock();
-	xas_for_each(&xas, folio, last_page) {
-		loff_t pg_end;
-		bool pg_failed = false;
-		bool folio_started = false;
-
-		if (xas_retry(&xas, folio))
-			continue;
-
-		pg_end = folio_pos(folio) + folio_size(folio) - 1;
-
-		for (;;) {
-			loff_t sreq_end;
-
-			if (!subreq) {
-				pg_failed = true;
-				break;
-			}
-
-			if (!folio_started &&
-			    test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) &&
-			    fscache_operation_valid(&rreq->cache_resources)) {
-				trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
-				folio_start_private_2(folio);
-				folio_started = true;
-			}
-
-			pg_failed |= subreq_failed;
-			sreq_end = subreq->start + subreq->len - 1;
-			if (pg_end < sreq_end)
-				break;
-
-			*account += subreq->transferred;
-			if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
-				subreq = list_next_entry(subreq, rreq_link);
-				subreq_failed = (subreq->error < 0);
-			} else {
-				subreq = NULL;
-				subreq_failed = false;
-			}
-
-			if (pg_end == sreq_end)
-				break;
-		}
-
-		if (!pg_failed) {
-			flush_dcache_folio(folio);
-			folio_mark_uptodate(folio);
-		}
-
-		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
-			if (folio->index == rreq->no_unlock_folio &&
-			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
-				_debug("no unlock");
-			else
-				folio_unlock(folio);
-		}
-	}
-	rcu_read_unlock();
-}
-
-/*
- * Unlock the folios in a read operation.  We need to set PG_writeback on any
- * folios we're going to write back before we unlock them.
- *
- * Note that if the deprecated NETFS_RREQ_USE_PGPRIV2 is set then we use
- * PG_private_2 and do a direct write to the cache from here instead.
- */
-void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
-{
-	struct netfs_io_subrequest *subreq;
-	struct netfs_folio *finfo;
-	struct folio *folio;
-	pgoff_t start_page = rreq->start / PAGE_SIZE;
-	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
-	size_t account = 0;
-	bool subreq_failed = false;
-
-	XA_STATE(xas, &rreq->mapping->i_pages, start_page);
-
-	if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) {
-		__clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags);
-		list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
-			__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
-		}
-	}
-
-	/* Handle deprecated PG_private_2 case. */
-	if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) {
-		netfs_rreq_unlock_folios_pgpriv2(rreq, &account);
-		goto out;
-	}
-
-	/* Walk through the pagecache and the I/O request lists simultaneously.
-	 * We may have a mixture of cached and uncached sections and we only
-	 * really want to write out the uncached sections.  This is slightly
-	 * complicated by the possibility that we might have huge pages with a
-	 * mixture inside.
-	 */
-	subreq = list_first_entry(&rreq->subrequests,
-				  struct netfs_io_subrequest, rreq_link);
-	subreq_failed = (subreq->error < 0);
-
-	trace_netfs_rreq(rreq, netfs_rreq_trace_unlock);
-
-	rcu_read_lock();
-	xas_for_each(&xas, folio, last_page) {
-		loff_t pg_end;
-		bool pg_failed = false;
-		bool wback_to_cache = false;
-
-		if (xas_retry(&xas, folio))
-			continue;
-
-		pg_end = folio_pos(folio) + folio_size(folio) - 1;
-
-		for (;;) {
-			loff_t sreq_end;
-
-			if (!subreq) {
-				pg_failed = true;
-				break;
-			}
-
-			wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
-			pg_failed |= subreq_failed;
-			sreq_end = subreq->start + subreq->len - 1;
-			if (pg_end < sreq_end)
-				break;
-
-			account += subreq->transferred;
-			if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
-				subreq = list_next_entry(subreq, rreq_link);
-				subreq_failed = (subreq->error < 0);
-			} else {
-				subreq = NULL;
-				subreq_failed = false;
-			}
-
-			if (pg_end == sreq_end)
-				break;
-		}
-
-		if (!pg_failed) {
-			flush_dcache_folio(folio);
-			finfo = netfs_folio_info(folio);
-			if (finfo) {
-				trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
-				if (finfo->netfs_group)
-					folio_change_private(folio, finfo->netfs_group);
-				else
-					folio_detach_private(folio);
-				kfree(finfo);
-			}
-			folio_mark_uptodate(folio);
-			if (wback_to_cache && !WARN_ON_ONCE(folio_get_private(folio) != NULL)) {
-				trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache);
-				folio_attach_private(folio, NETFS_FOLIO_COPY_TO_CACHE);
-				filemap_dirty_folio(folio->mapping, folio);
-			}
-		}
-
-		if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) {
-			if (folio->index == rreq->no_unlock_folio &&
-			    test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags))
-				_debug("no unlock");
-			else
-				folio_unlock(folio);
-		}
-	}
-	rcu_read_unlock();
-
-out:
-	task_io_account_read(account);
-	if (rreq->netfs_ops->done)
-		rreq->netfs_ops->done(rreq);
-}
-
 static void netfs_cache_expand_readahead(struct netfs_io_request *rreq,
 					 unsigned long long *_start,
 					 unsigned long long *_len,
@@ -271,6 +63,336 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in
 	return fscache_begin_read_operation(&rreq->cache_resources, netfs_i_cookie(ctx));
 }
 
+/*
+ * Decant the list of folios to read into a rolling buffer.
+ */
+static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq,
+					struct folio_queue *folioq)
+{
+	unsigned int order, nr;
+	size_t size = 0;
+
+	nr = __readahead_batch(rreq->ractl, (struct page **)folioq->vec.folios,
+			       ARRAY_SIZE(folioq->vec.folios));
+	folioq->vec.nr = nr;
+	for (int i = 0; i < nr; i++) {
+		struct folio *folio = folioq_folio(folioq, i);
+
+		trace_netfs_folio(folio, netfs_folio_trace_read);
+		order = folio_order(folio);
+		folioq->orders[i] = order;
+		size += PAGE_SIZE << order;
+	}
+
+	for (int i = nr; i < folioq_nr_slots(folioq); i++)
+		folioq_clear(folioq, i);
+
+	return size;
+}
+
+/*
+ * netfs_prepare_read_iterator - Prepare the subreq iterator for I/O
+ * @subreq: The subrequest to be set up
+ *
+ * Prepare the I/O iterator representing the read buffer on a subrequest for
+ * the filesystem to use for I/O (it can be passed directly to a socket).  This
+ * is intended to be called from the ->issue_read() method once the filesystem
+ * has trimmed the request to the size it wants.
+ *
+ * Returns the limited size if successful and -ENOMEM if insufficient memory
+ * available.
+ *
+ * [!] NOTE: This must be run in the same thread as ->issue_read() was called
+ * in as we access the readahead_control struct.
+ */
+static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	size_t rsize = subreq->len;
+
+	if (subreq->source == NETFS_DOWNLOAD_FROM_SERVER)
+		rsize = umin(rsize, rreq->io_streams[0].sreq_max_len);
+
+	if (rreq->ractl) {
+		/* If we don't have sufficient folios in the rolling buffer,
+		 * extract a folioq's worth from the readahead region at a time
+		 * into the buffer.  Note that this acquires a ref on each page
+		 * that we will need to release later - but we don't want to do
+		 * that until after we've started the I/O.
+		 */
+		while (rreq->submitted < subreq->start + rsize) {
+			struct folio_queue *tail = rreq->buffer_tail, *new;
+			size_t added;
+
+			new = kmalloc(sizeof(*new), GFP_NOFS);
+			if (!new)
+				return -ENOMEM;
+			netfs_stat(&netfs_n_folioq);
+			folioq_init(new);
+			new->prev = tail;
+			tail->next = new;
+			rreq->buffer_tail = new;
+			added = netfs_load_buffer_from_ra(rreq, new);
+			rreq->iter.count += added;
+			rreq->submitted += added;
+		}
+	}
+
+	subreq->len = rsize;
+	if (unlikely(rreq->io_streams[0].sreq_max_segs)) {
+		size_t limit = netfs_limit_iter(&rreq->iter, 0, rsize,
+						rreq->io_streams[0].sreq_max_segs);
+
+		if (limit < rsize) {
+			subreq->len = limit;
+			trace_netfs_sreq(subreq, netfs_sreq_trace_limited);
+		}
+	}
+
+	subreq->io_iter	= rreq->iter;
+
+	if (iov_iter_is_folioq(&subreq->io_iter)) {
+		if (subreq->io_iter.folioq_slot >= folioq_nr_slots(subreq->io_iter.folioq)) {
+			subreq->io_iter.folioq = subreq->io_iter.folioq->next;
+			subreq->io_iter.folioq_slot = 0;
+		}
+		subreq->curr_folioq = (struct folio_queue *)subreq->io_iter.folioq;
+		subreq->curr_folioq_slot = subreq->io_iter.folioq_slot;
+		subreq->curr_folio_order = subreq->curr_folioq->orders[subreq->curr_folioq_slot];
+	}
+
+	iov_iter_truncate(&subreq->io_iter, subreq->len);
+	iov_iter_advance(&rreq->iter, subreq->len);
+	return subreq->len;
+}
+
+static enum netfs_io_source netfs_cache_prepare_read(struct netfs_io_request *rreq,
+						     struct netfs_io_subrequest *subreq,
+						     loff_t i_size)
+{
+	struct netfs_cache_resources *cres = &rreq->cache_resources;
+
+	if (!cres->ops)
+		return NETFS_DOWNLOAD_FROM_SERVER;
+	return cres->ops->prepare_read(subreq, i_size);
+}
+
+static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error,
+					bool was_async)
+{
+	struct netfs_io_subrequest *subreq = priv;
+
+	if (transferred_or_error < 0) {
+		netfs_read_subreq_terminated(subreq, transferred_or_error, was_async);
+		return;
+	}
+
+	if (transferred_or_error > 0)
+		subreq->transferred += transferred_or_error;
+	netfs_read_subreq_terminated(subreq, 0, was_async);
+}
+
+/*
+ * Issue a read against the cache.
+ * - Eats the caller's ref on subreq.
+ */
+static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq,
+					  struct netfs_io_subrequest *subreq)
+{
+	struct netfs_cache_resources *cres = &rreq->cache_resources;
+
+	netfs_stat(&netfs_n_rh_read);
+	cres->ops->read(cres, subreq->start, &subreq->io_iter, NETFS_READ_HOLE_IGNORE,
+			netfs_cache_read_terminated, subreq);
+}
+
+/*
+ * Perform a read to the pagecache from a series of sources of different types,
+ * slicing up the region to be read according to available cache blocks and
+ * network rsize.
+ */
+static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
+{
+	struct netfs_inode *ictx = netfs_inode(rreq->inode);
+	unsigned long long start = rreq->start;
+	ssize_t size = rreq->len;
+	int ret = 0;
+
+	atomic_inc(&rreq->nr_outstanding);
+
+	do {
+		struct netfs_io_subrequest *subreq;
+		enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
+		ssize_t slice;
+
+		subreq = netfs_alloc_subrequest(rreq);
+		if (!subreq) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		subreq->start	= start;
+		subreq->len	= size;
+
+		atomic_inc(&rreq->nr_outstanding);
+		spin_lock_bh(&rreq->lock);
+		list_add_tail(&subreq->rreq_link, &rreq->subrequests);
+		subreq->prev_donated = rreq->prev_donated;
+		rreq->prev_donated = 0;
+		trace_netfs_sreq(subreq, netfs_sreq_trace_added);
+		spin_unlock_bh(&rreq->lock);
+
+		source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size);
+		subreq->source = source;
+		if (source == NETFS_DOWNLOAD_FROM_SERVER) {
+			unsigned long long zp = umin(ictx->zero_point, rreq->i_size);
+			size_t len = subreq->len;
+
+			if (subreq->start >= zp) {
+				subreq->source = source = NETFS_FILL_WITH_ZEROES;
+				goto fill_with_zeroes;
+			}
+
+			if (len > zp - subreq->start)
+				len = zp - subreq->start;
+			if (len == 0) {
+				pr_err("ZERO-LEN READ: R=%08x[%x] l=%zx/%zx s=%llx z=%llx i=%llx",
+				       rreq->debug_id, subreq->debug_index,
+				       subreq->len, size,
+				       subreq->start, ictx->zero_point, rreq->i_size);
+				break;
+			}
+			subreq->len = len;
+
+			netfs_stat(&netfs_n_rh_download);
+			if (rreq->netfs_ops->prepare_read) {
+				ret = rreq->netfs_ops->prepare_read(subreq);
+				if (ret < 0) {
+					atomic_dec(&rreq->nr_outstanding);
+					netfs_put_subrequest(subreq, false,
+							     netfs_sreq_trace_put_cancel);
+					break;
+				}
+				trace_netfs_sreq(subreq, netfs_sreq_trace_prepare);
+			}
+
+			slice = netfs_prepare_read_iterator(subreq);
+			if (slice < 0) {
+				atomic_dec(&rreq->nr_outstanding);
+				netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
+				ret = slice;
+				break;
+			}
+
+			rreq->netfs_ops->issue_read(subreq);
+			goto done;
+		}
+
+	fill_with_zeroes:
+		if (source == NETFS_FILL_WITH_ZEROES) {
+			subreq->source = NETFS_FILL_WITH_ZEROES;
+			trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+			netfs_stat(&netfs_n_rh_zero);
+			slice = netfs_prepare_read_iterator(subreq);
+			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+			netfs_read_subreq_terminated(subreq, 0, false);
+			goto done;
+		}
+
+		if (source == NETFS_READ_FROM_CACHE) {
+			trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+			slice = netfs_prepare_read_iterator(subreq);
+			netfs_read_cache_to_pagecache(rreq, subreq);
+			goto done;
+		}
+
+		pr_err("Unexpected read source %u\n", source);
+		WARN_ON_ONCE(1);
+		break;
+
+	done:
+		size -= slice;
+		start += slice;
+		cond_resched();
+	} while (size > 0);
+
+	if (atomic_dec_and_test(&rreq->nr_outstanding))
+		netfs_rreq_terminated(rreq, false);
+
+	/* Defer error return as we may need to wait for outstanding I/O. */
+	cmpxchg(&rreq->error, 0, ret);
+}
+
+/*
+ * Wait for the read operation to complete, successfully or otherwise.
+ */
+static int netfs_wait_for_read(struct netfs_io_request *rreq)
+{
+	int ret;
+
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
+	wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE);
+	ret = rreq->error;
+	if (ret == 0 && rreq->submitted < rreq->len) {
+		trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
+		ret = -EIO;
+	}
+
+	return ret;
+}
+
+/*
+ * Set up the initial folioq of buffer folios in the rolling buffer and set the
+ * iterator to refer to it.
+ */
+static int netfs_prime_buffer(struct netfs_io_request *rreq)
+{
+	struct folio_queue *folioq;
+	size_t added;
+
+	folioq = kmalloc(sizeof(*folioq), GFP_KERNEL);
+	if (!folioq)
+		return -ENOMEM;
+	netfs_stat(&netfs_n_folioq);
+	folioq_init(folioq);
+	rreq->buffer = folioq;
+	rreq->buffer_tail = folioq;
+	rreq->submitted = rreq->start;
+	iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0);
+
+	added = netfs_load_buffer_from_ra(rreq, folioq);
+	rreq->iter.count += added;
+	rreq->submitted += added;
+	return 0;
+}
+
+/*
+ * Drop the ref on each folio that we inherited from the VM readahead code.  We
+ * still have the folio locks to pin the page until we complete the I/O.
+ *
+ * Note that we can't just release the batch in each queue struct as we use the
+ * occupancy count in other places.
+ */
+static void netfs_put_ra_refs(struct folio_queue *folioq)
+{
+	struct folio_batch fbatch;
+
+	folio_batch_init(&fbatch);
+	while (folioq) {
+		for (unsigned int slot = 0; slot < folioq_count(folioq); slot++) {
+			struct folio *folio = folioq_folio(folioq, slot);
+			if (!folio)
+				continue;
+			trace_netfs_folio(folio, netfs_folio_trace_read_put);
+			if (!folio_batch_add(&fbatch, folio))
+				folio_batch_release(&fbatch);
+		}
+		folioq = folioq->next;
+	}
+
+	folio_batch_release(&fbatch);
+}
+
 /**
  * netfs_readahead - Helper to manage a read request
  * @ractl: The description of the readahead request
@@ -289,22 +411,17 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in
 void netfs_readahead(struct readahead_control *ractl)
 {
 	struct netfs_io_request *rreq;
-	struct netfs_inode *ctx = netfs_inode(ractl->mapping->host);
+	struct netfs_inode *ictx = netfs_inode(ractl->mapping->host);
+	unsigned long long start = readahead_pos(ractl);
+	size_t size = readahead_length(ractl);
 	int ret;
 
-	_enter("%lx,%x", readahead_index(ractl), readahead_count(ractl));
-
-	if (readahead_count(ractl) == 0)
-		return;
-
-	rreq = netfs_alloc_request(ractl->mapping, ractl->file,
-				   readahead_pos(ractl),
-				   readahead_length(ractl),
+	rreq = netfs_alloc_request(ractl->mapping, ractl->file, start, size,
 				   NETFS_READAHEAD);
 	if (IS_ERR(rreq))
 		return;
 
-	ret = netfs_begin_cache_read(rreq, ctx);
+	ret = netfs_begin_cache_read(rreq, ictx);
 	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
 		goto cleanup_free;
 
@@ -314,18 +431,15 @@ void netfs_readahead(struct readahead_control *ractl)
 
 	netfs_rreq_expand(rreq, ractl);
 
-	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &ractl->mapping->i_pages,
-			rreq->start, rreq->len);
+	rreq->ractl = ractl;
+	if (netfs_prime_buffer(rreq) < 0)
+		goto cleanup_free;
+	netfs_read_to_pagecache(rreq);
 
-	/* Drop the refs on the folios here rather than in the cache or
-	 * filesystem.  The locks will be dropped in netfs_rreq_unlock().
-	 */
-	while (readahead_folio(ractl))
-		;
+	/* Release the folio refs whilst we're waiting for the I/O. */
+	netfs_put_ra_refs(rreq->buffer);
 
-	netfs_begin_read(rreq, false);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
 	return;
 
 cleanup_free:
@@ -334,6 +448,117 @@ cleanup_free:
 }
 EXPORT_SYMBOL(netfs_readahead);
 
+/*
+ * Create a rolling buffer with a single occupying folio.
+ */
+static int netfs_create_singular_buffer(struct netfs_io_request *rreq, struct folio *folio)
+{
+	struct folio_queue *folioq;
+
+	folioq = kmalloc(sizeof(*folioq), GFP_KERNEL);
+	if (!folioq)
+		return -ENOMEM;
+
+	netfs_stat(&netfs_n_folioq);
+	folioq_init(folioq);
+	folioq_append(folioq, folio);
+	BUG_ON(folioq_folio(folioq, 0) != folio);
+	BUG_ON(folioq_folio_order(folioq, 0) != folio_order(folio));
+	rreq->buffer = folioq;
+	rreq->buffer_tail = folioq;
+	rreq->submitted = rreq->start + rreq->len;
+	iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, rreq->len);
+	rreq->ractl = (struct readahead_control *)1UL;
+	return 0;
+}
+
+/*
+ * Read into gaps in a folio partially filled by a streaming write.
+ */
+static int netfs_read_gaps(struct file *file, struct folio *folio)
+{
+	struct netfs_io_request *rreq;
+	struct address_space *mapping = folio->mapping;
+	struct netfs_folio *finfo = netfs_folio_info(folio);
+	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	struct folio *sink = NULL;
+	struct bio_vec *bvec;
+	unsigned int from = finfo->dirty_offset;
+	unsigned int to = from + finfo->dirty_len;
+	unsigned int off = 0, i = 0;
+	size_t flen = folio_size(folio);
+	size_t nr_bvec = flen / PAGE_SIZE + 2;
+	size_t part;
+	int ret;
+
+	_enter("%lx", folio->index);
+
+	rreq = netfs_alloc_request(mapping, file, folio_pos(folio), flen, NETFS_READ_GAPS);
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
+		goto alloc_error;
+	}
+
+	ret = netfs_begin_cache_read(rreq, ctx);
+	if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS)
+		goto discard;
+
+	netfs_stat(&netfs_n_rh_read_folio);
+	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_read_gaps);
+
+	/* Fiddle the buffer so that a gap at the beginning and/or a gap at the
+	 * end get copied to, but the middle is discarded.
+	 */
+	ret = -ENOMEM;
+	bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
+	if (!bvec)
+		goto discard;
+
+	sink = folio_alloc(GFP_KERNEL, 0);
+	if (!sink) {
+		kfree(bvec);
+		goto discard;
+	}
+
+	trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+
+	rreq->direct_bv = bvec;
+	rreq->direct_bv_count = nr_bvec;
+	if (from > 0) {
+		bvec_set_folio(&bvec[i++], folio, from, 0);
+		off = from;
+	}
+	while (off < to) {
+		part = min_t(size_t, to - off, PAGE_SIZE);
+		bvec_set_folio(&bvec[i++], sink, part, 0);
+		off += part;
+	}
+	if (to < flen)
+		bvec_set_folio(&bvec[i++], folio, flen - to, to);
+	iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
+	rreq->submitted = rreq->start + flen;
+
+	netfs_read_to_pagecache(rreq);
+
+	if (sink)
+		folio_put(sink);
+
+	ret = netfs_wait_for_read(rreq);
+	if (ret == 0) {
+		flush_dcache_folio(folio);
+		folio_mark_uptodate(folio);
+	}
+	folio_unlock(folio);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret < 0 ? ret : 0;
+
+discard:
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+alloc_error:
+	folio_unlock(folio);
+	return ret;
+}
+
 /**
  * netfs_read_folio - Helper to manage a read_folio request
  * @file: The file to read from
@@ -353,9 +578,13 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct address_space *mapping = folio->mapping;
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
-	struct folio *sink = NULL;
 	int ret;
 
+	if (folio_test_dirty(folio)) {
+		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+		return netfs_read_gaps(file, folio);
+	}
+
 	_enter("%lx", folio->index);
 
 	rreq = netfs_alloc_request(mapping, file,
@@ -374,54 +603,12 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
 
 	/* Set up the output buffer */
-	if (folio_test_dirty(folio)) {
-		/* Handle someone trying to read from an unflushed streaming
-		 * write.  We fiddle the buffer so that a gap at the beginning
-		 * and/or a gap at the end get copied to, but the middle is
-		 * discarded.
-		 */
-		struct netfs_folio *finfo = netfs_folio_info(folio);
-		struct bio_vec *bvec;
-		unsigned int from = finfo->dirty_offset;
-		unsigned int to = from + finfo->dirty_len;
-		unsigned int off = 0, i = 0;
-		size_t flen = folio_size(folio);
-		size_t nr_bvec = flen / PAGE_SIZE + 2;
-		size_t part;
+	ret = netfs_create_singular_buffer(rreq, folio);
+	if (ret < 0)
+		goto discard;
 
-		ret = -ENOMEM;
-		bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
-		if (!bvec)
-			goto discard;
-
-		sink = folio_alloc(GFP_KERNEL, 0);
-		if (!sink)
-			goto discard;
-
-		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
-
-		rreq->direct_bv = bvec;
-		rreq->direct_bv_count = nr_bvec;
-		if (from > 0) {
-			bvec_set_folio(&bvec[i++], folio, from, 0);
-			off = from;
-		}
-		while (off < to) {
-			part = min_t(size_t, to - off, PAGE_SIZE);
-			bvec_set_folio(&bvec[i++], sink, part, 0);
-			off += part;
-		}
-		if (to < flen)
-			bvec_set_folio(&bvec[i++], folio, flen - to, to);
-		iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
-	} else {
-		iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-				rreq->start, rreq->len);
-	}
-
-	ret = netfs_begin_read(rreq, true);
-	if (sink)
-		folio_put(sink);
+	netfs_read_to_pagecache(rreq);
+	ret = netfs_wait_for_read(rreq);
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
@@ -494,13 +681,10 @@ zero_out:
  *
  * Pre-read data for a write-begin request by drawing data from the cache if
  * possible, or the netfs if not.  Space beyond the EOF is zero-filled.
- * Multiple I/O requests from different sources will get munged together.  If
- * necessary, the readahead window can be expanded in either direction to a
- * more convenient alighment for RPC efficiency or to make storage in the cache
- * feasible.
+ * Multiple I/O requests from different sources will get munged together.
  *
  * The calling netfs must provide a table of operations, only one of which,
- * issue_op, is mandatory.
+ * issue_read, is mandatory.
  *
  * The check_write_begin() operation can be provided to check for and flush
  * conflicting writes once the folio is grabbed and locked.  It is passed a
@@ -528,8 +712,6 @@ int netfs_write_begin(struct netfs_inode *ctx,
 	pgoff_t index = pos >> PAGE_SHIFT;
 	int ret;
 
-	DEFINE_READAHEAD(ractl, file, NULL, mapping, index);
-
 retry:
 	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
 				    mapping_gfp_mask(mapping));
@@ -577,22 +759,13 @@ retry:
 	netfs_stat(&netfs_n_rh_write_begin);
 	trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin);
 
-	/* Expand the request to meet caching requirements and download
-	 * preferences.
-	 */
-	ractl._nr_pages = folio_nr_pages(folio);
-	netfs_rreq_expand(rreq, &ractl);
-
 	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-			rreq->start, rreq->len);
+	ret = netfs_create_singular_buffer(rreq, folio);
+	if (ret < 0)
+		goto error_put;
 
-	/* We hold the folio locks, so we can drop the references */
-	folio_get(folio);
-	while (readahead_folio(&ractl))
-		;
-
-	ret = netfs_begin_read(rreq, true);
+	netfs_read_to_pagecache(rreq);
+	ret = netfs_wait_for_read(rreq);
 	if (ret < 0)
 		goto error;
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
@@ -652,10 +825,13 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 	trace_netfs_read(rreq, start, flen, netfs_read_trace_prefetch_for_write);
 
 	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-			rreq->start, rreq->len);
+	ret = netfs_create_singular_buffer(rreq, folio);
+	if (ret < 0)
+		goto error_put;
 
-	ret = netfs_begin_read(rreq, true);
+	folioq_mark2(rreq->buffer, 0);
+	netfs_read_to_pagecache(rreq);
+	ret = netfs_wait_for_read(rreq);
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return ret;