Merge tag 'vfs-6.10-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "Misc:
   - Restore debugfs behavior of ignoring unknown mount options
   - Fix kernel doc for netfs_wait_for_oustanding_io()
   - Fix struct statx comment after new addition for this cycle
   - Fix a check in find_next_fd()

  iomap:
   - Fix data zeroing behavior when an extent spans the block that
     contains i_size
   - Restore i_size increasing in iomap_write_end() for now to avoid
     stale data exposure on xfs with a realtime device

  Cachefiles:
   - Remove unneeded fdtable.h include
   - Improve trace output for cachefiles_obj_{get,put}_ondemand_fd()
   - Remove requests from the request list to prevent accessing already
     freed requests
   - Fix UAF when issuing restore command while the daemon is still
     alive by adding an additional reference count to requests
   - Fix UAF by grabbing a reference during xarray lookup with xa_lock()
     held
   - Simplify error handling in cachefiles_ondemand_daemon_read()
   - Add consistency checks read and open requests to avoid crashes
   - Add a spinlock to protect ondemand_id variable which is used to
     determine whether an anonymous cachefiles fd has already been
     closed
   - Make on-demand reads killable allowing to handle broken cachefiles
     daemon better
   - Flush all requests after the kernel has been marked dead via
     CACHEFILES_DEAD to avoid hung-tasks
   - Ensure that closed requests are marked as such to avoid reusing
     them with a reopen request
   - Defer fd_install() until after copy_to_user() succeeded and thereby
     get rid of having to use close_fd()
   - Ensure that anonymous cachefiles on-demand fds are reused while
     they are valid to avoid pinning already freed cookies"

* tag 'vfs-6.10-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  iomap: Fix iomap_adjust_read_range for plen calculation
  iomap: keep on increasing i_size in iomap_write_end()
  cachefiles: remove unneeded include of <linux/fdtable.h>
  fs/file: fix the check in find_next_fd()
  cachefiles: make on-demand read killable
  cachefiles: flush all requests after setting CACHEFILES_DEAD
  cachefiles: Set object to close if ondemand_id < 0 in copen
  cachefiles: defer exposing anon_fd until after copy_to_user() succeeds
  cachefiles: never get a new anonymous fd if ondemand_id is valid
  cachefiles: add spin_lock for cachefiles_ondemand_info
  cachefiles: add consistency check for copen/cread
  cachefiles: remove err_put_fd label in cachefiles_ondemand_daemon_read()
  cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read()
  cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd()
  cachefiles: remove requests from xarray during flushing requests
  cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd
  statx: Update offset commentary for struct statx
  netfs: fix kernel doc for nets_wait_for_outstanding_io()
  debugfs: continue to ignore unknown mount options

6 files changed, 206 insertions, 90 deletions

diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 6465e2574230..06cdf1a8a16f 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -133,7 +133,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void cachefiles_flush_reqs(struct cachefiles_cache *cache)
+void cachefiles_flush_reqs(struct cachefiles_cache *cache)
 {
 	struct xarray *xa = &cache->reqs;
 	struct cachefiles_req *req;
@@ -159,6 +159,7 @@ static void cachefiles_flush_reqs(struct cachefiles_cache *cache)
 	xa_for_each(xa, index, req) {
 		req->error = -EIO;
 		complete(&req->done);
+		__xa_erase(xa, index);
 	}
 	xa_unlock(xa);
 
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index d33169f0018b..6845a90cdfcc 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -55,6 +55,7 @@ struct cachefiles_ondemand_info {
 	int				ondemand_id;
 	enum cachefiles_object_state	state;
 	struct cachefiles_object	*object;
+	spinlock_t			lock;
 };
 
 /*
@@ -138,6 +139,7 @@ static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache)
 struct cachefiles_req {
 	struct cachefiles_object *object;
 	struct completion done;
+	refcount_t ref;
 	int error;
 	struct cachefiles_msg msg;
 };
@@ -186,6 +188,7 @@ extern int cachefiles_has_space(struct cachefiles_cache *cache,
  * daemon.c
  */
 extern const struct file_operations cachefiles_daemon_fops;
+extern void cachefiles_flush_reqs(struct cachefiles_cache *cache);
 extern void cachefiles_get_unbind_pincount(struct cachefiles_cache *cache);
 extern void cachefiles_put_unbind_pincount(struct cachefiles_cache *cache);
 
@@ -424,6 +427,8 @@ do {							\
 	pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__);	\
 	fscache_io_error((___cache)->cache);		\
 	set_bit(CACHEFILES_DEAD, &(___cache)->flags);	\
+	if (cachefiles_in_ondemand_mode(___cache))	\
+		cachefiles_flush_reqs(___cache);	\
 } while (0)
 
 #define cachefiles_io_error_obj(object, FMT, ...)			\
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 4ba42f1fa3b4..bce005f2b456 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -1,22 +1,42 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-#include <linux/fdtable.h>
 #include <linux/anon_inodes.h>
 #include <linux/uio.h>
 #include "internal.h"
 
+struct ondemand_anon_file {
+	struct file *file;
+	int fd;
+};
+
+static inline void cachefiles_req_put(struct cachefiles_req *req)
+{
+	if (refcount_dec_and_test(&req->ref))
+		kfree(req);
+}
+
 static int cachefiles_ondemand_fd_release(struct inode *inode,
 					  struct file *file)
 {
 	struct cachefiles_object *object = file->private_data;
-	struct cachefiles_cache *cache = object->volume->cache;
-	struct cachefiles_ondemand_info *info = object->ondemand;
-	int object_id = info->ondemand_id;
+	struct cachefiles_cache *cache;
+	struct cachefiles_ondemand_info *info;
+	int object_id;
 	struct cachefiles_req *req;
-	XA_STATE(xas, &cache->reqs, 0);
+	XA_STATE(xas, NULL, 0);
+
+	if (!object)
+		return 0;
+
+	info = object->ondemand;
+	cache = object->volume->cache;
+	xas.xa = &cache->reqs;
 
 	xa_lock(&cache->reqs);
+	spin_lock(&info->lock);
+	object_id = info->ondemand_id;
 	info->ondemand_id = CACHEFILES_ONDEMAND_ID_CLOSED;
 	cachefiles_ondemand_set_object_close(object);
+	spin_unlock(&info->lock);
 
 	/* Only flush CACHEFILES_REQ_NEW marked req to avoid race with daemon_read */
 	xas_for_each_marked(&xas, req, ULONG_MAX, CACHEFILES_REQ_NEW) {
@@ -76,12 +96,12 @@ static loff_t cachefiles_ondemand_fd_llseek(struct file *filp, loff_t pos,
 }
 
 static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl,
-					 unsigned long arg)
+					 unsigned long id)
 {
 	struct cachefiles_object *object = filp->private_data;
 	struct cachefiles_cache *cache = object->volume->cache;
 	struct cachefiles_req *req;
-	unsigned long id;
+	XA_STATE(xas, &cache->reqs, id);
 
 	if (ioctl != CACHEFILES_IOC_READ_COMPLETE)
 		return -EINVAL;
@@ -89,10 +109,15 @@ static long cachefiles_ondemand_fd_ioctl(struct file *filp, unsigned int ioctl,
 	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
 		return -EOPNOTSUPP;
 
-	id = arg;
-	req = xa_erase(&cache->reqs, id);
-	if (!req)
+	xa_lock(&cache->reqs);
+	req = xas_load(&xas);
+	if (!req || req->msg.opcode != CACHEFILES_OP_READ ||
+	    req->object != object) {
+		xa_unlock(&cache->reqs);
 		return -EINVAL;
+	}
+	xas_store(&xas, NULL);
+	xa_unlock(&cache->reqs);
 
 	trace_cachefiles_ondemand_cread(object, id);
 	complete(&req->done);
@@ -116,10 +141,12 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 {
 	struct cachefiles_req *req;
 	struct fscache_cookie *cookie;
+	struct cachefiles_ondemand_info *info;
 	char *pid, *psize;
 	unsigned long id;
 	long size;
 	int ret;
+	XA_STATE(xas, &cache->reqs, 0);
 
 	if (!test_bit(CACHEFILES_ONDEMAND_MODE, &cache->flags))
 		return -EOPNOTSUPP;
@@ -143,10 +170,18 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 	if (ret)
 		return ret;
 
-	req = xa_erase(&cache->reqs, id);
-	if (!req)
+	xa_lock(&cache->reqs);
+	xas.xa_index = id;
+	req = xas_load(&xas);
+	if (!req || req->msg.opcode != CACHEFILES_OP_OPEN ||
+	    !req->object->ondemand->ondemand_id) {
+		xa_unlock(&cache->reqs);
 		return -EINVAL;
+	}
+	xas_store(&xas, NULL);
+	xa_unlock(&cache->reqs);
 
+	info = req->object->ondemand;
 	/* fail OPEN request if copen format is invalid */
 	ret = kstrtol(psize, 0, &size);
 	if (ret) {
@@ -166,6 +201,32 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 		goto out;
 	}
 
+	spin_lock(&info->lock);
+	/*
+	 * The anonymous fd was closed before copen ? Fail the request.
+	 *
+	 *             t1             |             t2
+	 * ---------------------------------------------------------
+	 *                             cachefiles_ondemand_copen
+	 *                             req = xa_erase(&cache->reqs, id)
+	 * // Anon fd is maliciously closed.
+	 * cachefiles_ondemand_fd_release
+	 * xa_lock(&cache->reqs)
+	 * cachefiles_ondemand_set_object_close(object)
+	 * xa_unlock(&cache->reqs)
+	 *                             cachefiles_ondemand_set_object_open
+	 *                             // No one will ever close it again.
+	 * cachefiles_ondemand_daemon_read
+	 * cachefiles_ondemand_select_req
+	 *
+	 * Get a read req but its fd is already closed. The daemon can't
+	 * issue a cread ioctl with an closed fd, then hung.
+	 */
+	if (info->ondemand_id == CACHEFILES_ONDEMAND_ID_CLOSED) {
+		spin_unlock(&info->lock);
+		req->error = -EBADFD;
+		goto out;
+	}
 	cookie = req->object->cookie;
 	cookie->object_size = size;
 	if (size)
@@ -175,9 +236,15 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 	trace_cachefiles_ondemand_copen(req->object, id, size);
 
 	cachefiles_ondemand_set_object_open(req->object);
+	spin_unlock(&info->lock);
 	wake_up_all(&cache->daemon_pollwq);
 
 out:
+	spin_lock(&info->lock);
+	/* Need to set object close to avoid reopen status continuing */
+	if (info->ondemand_id == CACHEFILES_ONDEMAND_ID_CLOSED)
+		cachefiles_ondemand_set_object_close(req->object);
+	spin_unlock(&info->lock);
 	complete(&req->done);
 	return ret;
 }
@@ -205,14 +272,14 @@ int cachefiles_ondemand_restore(struct cachefiles_cache *cache, char *args)
 	return 0;
 }
 
-static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
+static int cachefiles_ondemand_get_fd(struct cachefiles_req *req,
+				      struct ondemand_anon_file *anon_file)
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
 	struct cachefiles_open *load;
-	struct file *file;
 	u32 object_id;
-	int ret, fd;
+	int ret;
 
 	object = cachefiles_grab_object(req->object,
 			cachefiles_obj_get_ondemand_fd);
@@ -224,35 +291,53 @@ static int cachefiles_ondemand_get_fd(struct cachefiles_req *req)
 	if (ret < 0)
 		goto err;
 
-	fd = get_unused_fd_flags(O_WRONLY);
-	if (fd < 0) {
-		ret = fd;
+	anon_file->fd = get_unused_fd_flags(O_WRONLY);
+	if (anon_file->fd < 0) {
+		ret = anon_file->fd;
 		goto err_free_id;
 	}
 
-	file = anon_inode_getfile("[cachefiles]", &cachefiles_ondemand_fd_fops,
-				  object, O_WRONLY);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
+	anon_file->file = anon_inode_getfile("[cachefiles]",
+				&cachefiles_ondemand_fd_fops, object, O_WRONLY);
+	if (IS_ERR(anon_file->file)) {
+		ret = PTR_ERR(anon_file->file);
 		goto err_put_fd;
 	}
 
-	file->f_mode |= FMODE_PWRITE | FMODE_LSEEK;
-	fd_install(fd, file);
+	spin_lock(&object->ondemand->lock);
+	if (object->ondemand->ondemand_id > 0) {
+		spin_unlock(&object->ondemand->lock);
+		/* Pair with check in cachefiles_ondemand_fd_release(). */
+		anon_file->file->private_data = NULL;
+		ret = -EEXIST;
+		goto err_put_file;
+	}
+
+	anon_file->file->f_mode |= FMODE_PWRITE | FMODE_LSEEK;
 
 	load = (void *)req->msg.data;
-	load->fd = fd;
+	load->fd = anon_file->fd;
 	object->ondemand->ondemand_id = object_id;
+	spin_unlock(&object->ondemand->lock);
 
 	cachefiles_get_unbind_pincount(cache);
 	trace_cachefiles_ondemand_open(object, &req->msg, load);
 	return 0;
 
+err_put_file:
+	fput(anon_file->file);
+	anon_file->file = NULL;
 err_put_fd:
-	put_unused_fd(fd);
+	put_unused_fd(anon_file->fd);
+	anon_file->fd = ret;
 err_free_id:
 	xa_erase(&cache->ondemand_ids, object_id);
 err:
+	spin_lock(&object->ondemand->lock);
+	/* Avoid marking an opened object as closed. */
+	if (object->ondemand->ondemand_id <= 0)
+		cachefiles_ondemand_set_object_close(object);
+	spin_unlock(&object->ondemand->lock);
 	cachefiles_put_object(object, cachefiles_obj_put_ondemand_fd);
 	return ret;
 }
@@ -294,14 +379,28 @@ static struct cachefiles_req *cachefiles_ondemand_select_req(struct xa_state *xa
 	return NULL;
 }
 
+static inline bool cachefiles_ondemand_finish_req(struct cachefiles_req *req,
+						  struct xa_state *xas, int err)
+{
+	if (unlikely(!xas || !req))
+		return false;
+
+	if (xa_cmpxchg(xas->xa, xas->xa_index, req, NULL, 0) != req)
+		return false;
+
+	req->error = err;
+	complete(&req->done);
+	return true;
+}
+
 ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 					char __user *_buffer, size_t buflen)
 {
 	struct cachefiles_req *req;
 	struct cachefiles_msg *msg;
-	unsigned long id = 0;
 	size_t n;
 	int ret = 0;
+	struct ondemand_anon_file anon_file;
 	XA_STATE(xas, &cache->reqs, cache->req_id_next);
 
 	xa_lock(&cache->reqs);
@@ -330,42 +429,37 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 
 	xas_clear_mark(&xas, CACHEFILES_REQ_NEW);
 	cache->req_id_next = xas.xa_index + 1;
+	refcount_inc(&req->ref);
+	cachefiles_grab_object(req->object, cachefiles_obj_get_read_req);
 	xa_unlock(&cache->reqs);
 
-	id = xas.xa_index;
-
 	if (msg->opcode == CACHEFILES_OP_OPEN) {
-		ret = cachefiles_ondemand_get_fd(req);
-		if (ret) {
-			cachefiles_ondemand_set_object_close(req->object);
-			goto error;
-		}
+		ret = cachefiles_ondemand_get_fd(req, &anon_file);
+		if (ret)
+			goto out;
 	}
 
-	msg->msg_id = id;
+	msg->msg_id = xas.xa_index;
 	msg->object_id = req->object->ondemand->ondemand_id;
 
-	if (copy_to_user(_buffer, msg, n) != 0) {
+	if (copy_to_user(_buffer, msg, n) != 0)
 		ret = -EFAULT;
-		goto err_put_fd;
-	}
 
-	/* CLOSE request has no reply */
-	if (msg->opcode == CACHEFILES_OP_CLOSE) {
-		xa_erase(&cache->reqs, id);
-		complete(&req->done);
+	if (msg->opcode == CACHEFILES_OP_OPEN) {
+		if (ret < 0) {
+			fput(anon_file.file);
+			put_unused_fd(anon_file.fd);
+			goto out;
+		}
+		fd_install(anon_file.fd, anon_file.file);
 	}
-
-	return n;
-
-err_put_fd:
-	if (msg->opcode == CACHEFILES_OP_OPEN)
-		close_fd(((struct cachefiles_open *)msg->data)->fd);
-error:
-	xa_erase(&cache->reqs, id);
-	req->error = ret;
-	complete(&req->done);
-	return ret;
+out:
+	cachefiles_put_object(req->object, cachefiles_obj_put_read_req);
+	/* Remove error request and CLOSE request has no reply */
+	if (ret || msg->opcode == CACHEFILES_OP_CLOSE)
+		cachefiles_ondemand_finish_req(req, &xas, ret);
+	cachefiles_req_put(req);
+	return ret ? ret : n;
 }
 
 typedef int (*init_req_fn)(struct cachefiles_req *req, void *private);
@@ -395,6 +489,7 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 		goto out;
 	}
 
+	refcount_set(&req->ref, 1);
 	req->object = object;
 	init_completion(&req->done);
 	req->msg.opcode = opcode;
@@ -454,9 +549,19 @@ static int cachefiles_ondemand_send_req(struct cachefiles_object *object,
 		goto out;
 
 	wake_up_all(&cache->daemon_pollwq);
-	wait_for_completion(&req->done);
-	ret = req->error;
-	kfree(req);
+wait:
+	ret = wait_for_completion_killable(&req->done);
+	if (!ret) {
+		ret = req->error;
+	} else {
+		ret = -EINTR;
+		if (!cachefiles_ondemand_finish_req(req, &xas, ret)) {
+			/* Someone will complete it soon. */
+			cpu_relax();
+			goto wait;
+		}
+	}
+	cachefiles_req_put(req);
 	return ret;
 out:
 	/* Reset the object to close state in error handling path.
@@ -578,6 +683,7 @@ int cachefiles_ondemand_init_obj_info(struct cachefiles_object *object,
 		return -ENOMEM;
 
 	object->ondemand->object = object;
+	spin_lock_init(&object->ondemand->lock);
 	INIT_WORK(&object->ondemand->ondemand_work, ondemand_object_worker);
 	return 0;
 }
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index dc51df0b118d..8fd928899a59 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -107,8 +107,16 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param
 	int opt;
 
 	opt = fs_parse(fc, debugfs_param_specs, param, &result);
-	if (opt < 0)
+	if (opt < 0) {
+		/*
+                * We might like to report bad mount options here; but
+                * traditionally debugfs has ignored all mount options
+                */
+		if (opt == -ENOPARAM)
+			return 0;
+
 		return opt;
+	}
 
 	switch (opt) {
 	case Opt_uid:
diff --git a/fs/file.c b/fs/file.c
index 8076aef9c210..a3b72aa64f11 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -486,12 +486,12 @@ struct files_struct init_files = {
 
 static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)
 {
-	unsigned int maxfd = fdt->max_fds;
+	unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */
 	unsigned int maxbit = maxfd / BITS_PER_LONG;
 	unsigned int bitbit = start / BITS_PER_LONG;
 
 	bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG;
-	if (bitbit > maxfd)
+	if (bitbit >= maxfd)
 		return maxfd;
 	if (bitbit > start)
 		start = bitbit;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c5802a459334..d46558990279 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -241,6 +241,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	unsigned block_size = (1 << block_bits);
 	size_t poff = offset_in_folio(folio, *pos);
 	size_t plen = min_t(loff_t, folio_size(folio) - poff, length);
+	size_t orig_plen = plen;
 	unsigned first = poff >> block_bits;
 	unsigned last = (poff + plen - 1) >> block_bits;
 
@@ -277,7 +278,7 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	 * handle both halves separately so that we properly zero data in the
 	 * page cache for blocks that are entirely outside of i_size.
 	 */
-	if (orig_pos <= isize && orig_pos + length > isize) {
+	if (orig_pos <= isize && orig_pos + orig_plen > isize) {
 		unsigned end = offset_in_folio(folio, isize - 1) >> block_bits;
 
 		if (first <= end && last > end)
@@ -877,22 +878,37 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 		size_t copied, struct folio *folio)
 {
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	loff_t old_size = iter->inode->i_size;
+	size_t written;
 
 	if (srcmap->type == IOMAP_INLINE) {
 		iomap_write_end_inline(iter, folio, pos, copied);
-		return true;
+		written = copied;
+	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
+		written = block_write_end(NULL, iter->inode->i_mapping, pos,
+					len, copied, &folio->page, NULL);
+		WARN_ON_ONCE(written != copied && written != 0);
+	} else {
+		written = __iomap_write_end(iter->inode, pos, len, copied,
+					    folio) ? copied : 0;
 	}
 
-	if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
-		size_t bh_written;
-
-		bh_written = block_write_end(NULL, iter->inode->i_mapping, pos,
-					len, copied, &folio->page, NULL);
-		WARN_ON_ONCE(bh_written != copied && bh_written != 0);
-		return bh_written == copied;
+	/*
+	 * Update the in-memory inode size after copying the data into the page
+	 * cache.  It's up to the file system to write the updated size to disk,
+	 * preferably after I/O completion so that no stale data is exposed.
+	 * Only once that's done can we unlock and release the folio.
+	 */
+	if (pos + written > old_size) {
+		i_size_write(iter->inode, pos + written);
+		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
 	}
+	__iomap_put_folio(iter, pos, written, folio);
 
-	return __iomap_write_end(iter->inode, pos, len, copied, folio);
+	if (old_size < pos)
+		pagecache_isize_extended(iter->inode, old_size, pos);
+
+	return written == copied;
 }
 
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
@@ -907,7 +923,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 
 	do {
 		struct folio *folio;
-		loff_t old_size;
 		size_t offset;		/* Offset into folio */
 		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
@@ -959,23 +974,6 @@ retry:
 		written = iomap_write_end(iter, pos, bytes, copied, folio) ?
 			  copied : 0;
 
-		/*
-		 * Update the in-memory inode size after copying the data into
-		 * the page cache.  It's up to the file system to write the
-		 * updated size to disk, preferably after I/O completion so that
-		 * no stale data is exposed.  Only once that's done can we
-		 * unlock and release the folio.
-		 */
-		old_size = iter->inode->i_size;
-		if (pos + written > old_size) {
-			i_size_write(iter->inode, pos + written);
-			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
-		}
-		__iomap_put_folio(iter, pos, written, folio);
-
-		if (old_size < pos)
-			pagecache_isize_extended(iter->inode, old_size, pos);
-
 		cond_resched();
 		if (unlikely(written == 0)) {
 			/*
@@ -1346,7 +1344,6 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 			bytes = folio_size(folio) - offset;
 
 		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
-		__iomap_put_folio(iter, pos, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
@@ -1412,7 +1409,6 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		folio_mark_accessed(folio);
 
 		ret = iomap_write_end(iter, pos, bytes, bytes, folio);
-		__iomap_put_folio(iter, pos, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;