eb->io_pages is set in read_extent_buffer_pages().
In case of readpage failure, for pages that have been added to bio,
it calls bio_endio and later readpage_io_failed_hook() does the work.
When this eb's page (couldn't be the 1st page) fails to add itself to bio
due to failure in merge_bio(), it cannot decrease eb->io_pages via bio_endio,
and ends up with a memory leak eventually.
This lets __do_readpage propagate errors to callers and adds the
'atomic_dec(&eb->io_pages)'.
Signed-off-by: Liu Bo <bo.li....@oracle.com>
---
v2: - Move 'dec io_pages' to the caller so that we're consistent with
write_one_eb()
v3: - Bail out once we fail to read a page and do the cleanup work
for eb->io_pages
fs/btrfs/extent_io.c | 25 ++++++++++++++++++++++---
1 file changed, 22 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ac1a696..7303e5a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2878,6 +2878,7 @@ __get_extent_map(struct inode *inode, struct page *page,
size_t pg_offset,
* into the tree that are removed when the IO is done (by the end_io
* handlers)
* XXX JDM: This needs looking at to ensure proper page locking
+ * return 0 on success, otherwise return error
*/
static int __do_readpage(struct extent_io_tree *tree,
struct page *page,
@@ -2899,7 +2900,7 @@ static int __do_readpage(struct extent_io_tree *tree,
sector_t sector;
struct extent_map *em;
struct block_device *bdev;
- int ret;
+ int ret = 0;
int nr = 0;
size_t pg_offset = 0;
size_t iosize;
@@ -3080,6 +3081,7 @@ static int __do_readpage(struct extent_io_tree *tree,
} else {
SetPageError(page);
unlock_extent(tree, cur, cur + iosize - 1);
+ goto out;
}
cur = cur + iosize;
pg_offset += iosize;
@@ -3090,7 +3092,7 @@ out:
SetPageUptodate(page);
unlock_page(page);
}
- return 0;
+ return ret;
}
static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
@@ -5230,14 +5232,31 @@ int read_extent_buffer_pages(struct extent_io_tree
*tree,
atomic_set(&eb->io_pages, num_reads);
for (i = start_i; i < num_pages; i++) {
page = eb->pages[i];
+
if (!PageUptodate(page)) {
+ if (ret) {
+ atomic_dec(&eb->io_pages);
+ unlock_page(page);
+ continue;
+ }
+
ClearPageError(page);
err = __extent_read_full_page(tree, page,
get_extent, &bio,
mirror_num, &bio_flags,
READ | REQ_META);
- if (err)
+ if (err) {
ret = err;
+ /*
+ * We use &bio in above __extent_read_full_page,
+ * so we ensure that if it returns error, the
+ * current page fails to add itself to bio and
+ * it's been unlocked.
+ *
+ * We must dec io_pages by ourselves.
+ */
+ atomic_dec(&eb->io_pages);
+ }
} else {
unlock_page(page);
}
--
2.5.5
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
