Merge tag 'vfs-6.10-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "Misc:

   - Don't misleadingly warn during filesystem thaw operations.

     It's possible that a block device which was frozen before it was
     mounted can cause a failing thaw operation if someone concurrently
     tried to mount it while that thaw operation was issued and the
     device had already been temporarily claimed for the mount (The
     mount will of course be aborted because the device is frozen).

  netfs:

   - Fix io_uring based write-through. Make sure that the total request
     length is correctly set.

   - Fix partial writes to folio tail.

   - Remove some xarray helpers that were intended for bounce buffers
     which got defered to a later patch series.

   - Make netfs_page_mkwrite() whether folio->mapping is vallid after
     acquiring the folio lock.

   - Make netfs_page_mkrite() flush conflicting data instead of waiting.

  fsnotify:

   - Ensure that fsnotify creation events are generated before fsnotify
     open events when a file is created via ->atomic_open(). The
     ordering was broken before.

   - Ensure that no fsnotify events are generated for O_PATH file
     descriptors. While no fsnotify open events were generated, fsnotify
     close events were. Make it consistent and don't produce any"

* tag 'vfs-6.10-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  netfs: Fix netfs_page_mkwrite() to flush conflicting data, not wait
  netfs: Fix netfs_page_mkwrite() to check folio->mapping is valid
  netfs: Delete some xarray-wangling functions that aren't used
  netfs: Fix early issue of write op on partial write to folio tail
  netfs: Fix io_uring based write-through
  vfs: generate FS_CREATE before FS_OPEN when ->atomic_open used.
  fsnotify: Do not generate events for O_PATH file descriptors
  fs: don't misleadingly warn during thaw operations

8 files changed, 45 insertions, 105 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 37fb0a8aa09a..1e05a0f3f04d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3572,8 +3572,12 @@ static const char *open_last_lookups(struct nameidata *nd,
 	else
 		inode_lock_shared(dir->d_inode);
 	dentry = lookup_open(nd, file, op, got_write);
-	if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED))
-		fsnotify_create(dir->d_inode, dentry);
+	if (!IS_ERR(dentry)) {
+		if (file->f_mode & FMODE_CREATED)
+			fsnotify_create(dir->d_inode, dentry);
+		if (file->f_mode & FMODE_OPENED)
+			fsnotify_open(file);
+	}
 	if (open_flag & O_CREAT)
 		inode_unlock(dir->d_inode);
 	else
@@ -3700,6 +3704,8 @@ int vfs_tmpfile(struct mnt_idmap *idmap,
 	mode = vfs_prepare_mode(idmap, dir, mode, mode, mode);
 	error = dir->i_op->tmpfile(idmap, dir, file, mode);
 	dput(child);
+	if (file->f_mode & FMODE_OPENED)
+		fsnotify_open(file);
 	if (error)
 		return error;
 	/* Don't check for other permissions, the inode was just created */
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 07bc1fd43530..d583af7a2209 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -523,6 +523,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	struct netfs_group *group;
 	struct folio *folio = page_folio(vmf->page);
 	struct file *file = vmf->vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file_inode(file);
 	struct netfs_inode *ictx = netfs_inode(inode);
 	vm_fault_t ret = VM_FAULT_RETRY;
@@ -534,6 +535,11 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 
 	if (folio_lock_killable(folio) < 0)
 		goto out;
+	if (folio->mapping != mapping) {
+		folio_unlock(folio);
+		ret = VM_FAULT_NOPAGE;
+		goto out;
+	}
 
 	if (folio_wait_writeback_killable(folio)) {
 		ret = VM_FAULT_LOCKED;
@@ -549,9 +555,9 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
 	group = netfs_folio_group(folio);
 	if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) {
 		folio_unlock(folio);
-		err = filemap_fdatawait_range(inode->i_mapping,
-					      folio_pos(folio),
-					      folio_pos(folio) + folio_size(folio));
+		err = filemap_fdatawrite_range(mapping,
+					       folio_pos(folio),
+					       folio_pos(folio) + folio_size(folio));
 		switch (err) {
 		case 0:
 			ret = VM_FAULT_RETRY;
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index e14cd53ac9fd..88f2adfab75e 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -92,8 +92,9 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
 	if (async)
 		wreq->iocb = iocb;
+	wreq->len = iov_iter_count(&wreq->io_iter);
 	wreq->cleanup = netfs_cleanup_dio_write;
-	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), iov_iter_count(&wreq->io_iter));
+	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
 	if (ret < 0) {
 		_debug("begin = %zd", ret);
 		goto out;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 95e281a8af78..acd9ca14e264 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -63,15 +63,6 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
 /*
  * misc.c
  */
-#define NETFS_FLAG_PUT_MARK		BIT(0)
-#define NETFS_FLAG_PAGECACHE_MARK	BIT(1)
-int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
-			    struct folio *folio, unsigned int flags,
-			    gfp_t gfp_mask);
-int netfs_add_folios_to_buffer(struct xarray *buffer,
-			       struct address_space *mapping,
-			       pgoff_t index, pgoff_t to, gfp_t gfp_mask);
-void netfs_clear_buffer(struct xarray *buffer);
 
 /*
  * objects.c
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index bc1fc54fb724..83e644bd518f 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -8,87 +8,6 @@
 #include <linux/swap.h>
 #include "internal.h"
 
-/*
- * Attach a folio to the buffer and maybe set marks on it to say that we need
- * to put the folio later and twiddle the pagecache flags.
- */
-int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
-			    struct folio *folio, unsigned int flags,
-			    gfp_t gfp_mask)
-{
-	XA_STATE_ORDER(xas, xa, index, folio_order(folio));
-
-retry:
-	xas_lock(&xas);
-	for (;;) {
-		xas_store(&xas, folio);
-		if (!xas_error(&xas))
-			break;
-		xas_unlock(&xas);
-		if (!xas_nomem(&xas, gfp_mask))
-			return xas_error(&xas);
-		goto retry;
-	}
-
-	if (flags & NETFS_FLAG_PUT_MARK)
-		xas_set_mark(&xas, NETFS_BUF_PUT_MARK);
-	if (flags & NETFS_FLAG_PAGECACHE_MARK)
-		xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK);
-	xas_unlock(&xas);
-	return xas_error(&xas);
-}
-
-/*
- * Create the specified range of folios in the buffer attached to the read
- * request.  The folios are marked with NETFS_BUF_PUT_MARK so that we know that
- * these need freeing later.
- */
-int netfs_add_folios_to_buffer(struct xarray *buffer,
-			       struct address_space *mapping,
-			       pgoff_t index, pgoff_t to, gfp_t gfp_mask)
-{
-	struct folio *folio;
-	int ret;
-
-	if (to + 1 == index) /* Page range is inclusive */
-		return 0;
-
-	do {
-		/* TODO: Figure out what order folio can be allocated here */
-		folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0);
-		if (!folio)
-			return -ENOMEM;
-		folio->index = index;
-		ret = netfs_xa_store_and_mark(buffer, index, folio,
-					      NETFS_FLAG_PUT_MARK, gfp_mask);
-		if (ret < 0) {
-			folio_put(folio);
-			return ret;
-		}
-
-		index += folio_nr_pages(folio);
-	} while (index <= to && index != 0);
-
-	return 0;
-}
-
-/*
- * Clear an xarray buffer, putting a ref on the folios that have
- * NETFS_BUF_PUT_MARK set.
- */
-void netfs_clear_buffer(struct xarray *buffer)
-{
-	struct folio *folio;
-	XA_STATE(xas, buffer, 0);
-
-	rcu_read_lock();
-	xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) {
-		folio_put(folio);
-	}
-	rcu_read_unlock();
-	xa_destroy(buffer);
-}
-
 /**
  * netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
  * @mapping: The mapping the folio belongs to.
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 3aa86e268f40..ec6cf8707fb0 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -483,7 +483,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 	if (!debug)
 		kdebug("R=%x: No submit", wreq->debug_id);
 
-	if (flen < fsize)
+	if (foff + flen < fsize)
 		for (int s = 0; s < NR_IO_STREAMS; s++)
 			netfs_issue_write(wreq, &wreq->io_streams[s]);
 
diff --git a/fs/open.c b/fs/open.c
index 50e45bc7c4d8..278b3edcda44 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1004,11 +1004,6 @@ static int do_dentry_open(struct file *f,
 		}
 	}
 
-	/*
-	 * Once we return a file with FMODE_OPENED, __fput() will call
-	 * fsnotify_close(), so we need fsnotify_open() here for symmetry.
-	 */
-	fsnotify_open(f);
 	return 0;
 
 cleanup_all:
@@ -1085,8 +1080,19 @@ EXPORT_SYMBOL(file_path);
  */
 int vfs_open(const struct path *path, struct file *file)
 {
+	int ret;
+
 	file->f_path = *path;
-	return do_dentry_open(file, NULL);
+	ret = do_dentry_open(file, NULL);
+	if (!ret) {
+		/*
+		 * Once we return a file with FMODE_OPENED, __fput() will call
+		 * fsnotify_close(), so we need fsnotify_open() here for
+		 * symmetry.
+		 */
+		fsnotify_open(file);
+	}
+	return ret;
 }
 
 struct file *dentry_open(const struct path *path, int flags,
@@ -1177,8 +1183,10 @@ struct file *kernel_file_open(const struct path *path, int flags,
 	error = do_dentry_open(f, NULL);
 	if (error) {
 		fput(f);
-		f = ERR_PTR(error);
+		return ERR_PTR(error);
 	}
+
+	fsnotify_open(f);
 	return f;
 }
 EXPORT_SYMBOL_GPL(kernel_file_open);
diff --git a/fs/super.c b/fs/super.c
index b72f1d288e95..095ba793e10c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1502,8 +1502,17 @@ static int fs_bdev_thaw(struct block_device *bdev)
 
 	lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
 
+	/*
+	 * The block device may have been frozen before it was claimed by a
+	 * filesystem. Concurrently another process might try to mount that
+	 * frozen block device and has temporarily claimed the block device for
+	 * that purpose causing a concurrent fs_bdev_thaw() to end up here. The
+	 * mounter is already about to abort mounting because they still saw an
+	 * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
+	 * NULL in that case.
+	 */
 	sb = get_bdev_super(bdev);
-	if (WARN_ON_ONCE(!sb))
+	if (!sb)
 		return -EINVAL;
 
 	if (sb->s_op->thaw_super)