Merge tag 'zonefs-6.3-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs

Pull zonefs fixes from Damien Le Moal:

 - Make sure to always invalidate the last page of an inode straddling
   inode->i_size to avoid data inconsistencies with appended data when
   the device zone write granularity does not match the page size.

 - Do not propagate iomap -ENOBLK error to userspace and use -EBUSY
   instead.

* tag 'zonefs-6.3-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs:
  zonefs: Do not propagate iomap_dio_rw() ENOTBLK error to user space
  zonefs: Always invalidate last cached page on append write

Author: torvalds

fs/zonefs/file.c

@@ -382,6 +382,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	struct zonefs_zone *z = zonefs_inode_zone(inode);
 	struct block_device *bdev = inode->i_sb->s_bdev;
 	unsigned int max = bdev_max_zone_append_sectors(bdev);
+	pgoff_t start, end;
 	struct bio *bio;
 	ssize_t size = 0;
 	int nr_pages;
@@ -390,6 +391,19 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
 	iov_iter_truncate(from, max);
 
+	/*
+	 * If the inode block size (zone write granularity) is smaller than the
+	 * page size, we may be appending data belonging to the last page of the
+	 * inode straddling inode->i_size, with that page already cached due to
+	 * a buffered read or readahead. So make sure to invalidate that page.
+	 * This will always be a no-op for the case where the block size is
+	 * equal to the page size.
+	 */
+	start = iocb->ki_pos >> PAGE_SHIFT;
+	end = (iocb->ki_pos + iov_iter_count(from) - 1) >> PAGE_SHIFT;
+	if (invalidate_inode_pages2_range(inode->i_mapping, start, end))
+		return -EBUSY;
+
 	nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
 	if (!nr_pages)
 		return 0;
@@ -567,11 +581,21 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		append = sync;
 	}
 
-	if (append)
+	if (append) {
 		ret = zonefs_file_dio_append(iocb, from);
-	else
+	} else {
+		/*
+		 * iomap_dio_rw() may return ENOTBLK if there was an issue with
+		 * page invalidation. Overwrite that error code with EBUSY to
+		 * be consistent with zonefs_file_dio_append() return value for
+		 * similar issues.
+		 */
 		ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
 				   &zonefs_write_dio_ops, 0, NULL, 0);
+		if (ret == -ENOTBLK)
+			ret = -EBUSY;
+	}
+
 	if (zonefs_zone_is_seq(z) &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)