Commit dd802406 authored Dec 18, 2014 by Jaegeuk Kim

f2fs: avoid double lock for cp_rwsem



The __f2fs_add_link is covered by cp_rwsem all the time.
This calls init_inode_metadata, which conducts some acl operations including
memory allocation with GFP_KERNEL previously.
But, under memory pressure, f2fs_write_data_page can be called, which also
grabs cp_rwsem too.

In this case, this incurs a deadlock pointed by Chao.
Thread #1        Thread #2
 down_read
                 down_write
  down_read
 -> here down_read should wait forever.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

parent db9f7c1a

fs/f2fs/acl.c

+2 −2

Original line number	Diff line number	Diff line
		@@ -62,7 +62,7 @@ static struct posix_acl f2fs_acl_from_disk(const char value, size_t size)
		if (count == 0)
		return NULL;

		acl = posix_acl_alloc(count, GFP_KERNEL);
		acl = posix_acl_alloc(count, GFP_NOFS);
		if (!acl)
		return ERR_PTR(-ENOMEM);

		@@ -116,7 +116,7 @@ static void f2fs_acl_to_disk(const struct posix_acl acl, size_t *size)
		int i;

		f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
		sizeof(struct f2fs_acl_entry), GFP_KERNEL);
		sizeof(struct f2fs_acl_entry), GFP_NOFS);
		if (!f2fs_acl)
		return ERR_PTR(-ENOMEM);