2020-12-07 13:56:17

by Zhihao Cheng

Subject: [PATCH v2] btrfs: free-space-cache: Fix error return code in __load_free_space_cache

Fix to return the error code(instead always 0) when memory allocating
failed in __load_free_space_cache().

This lacks the analysis of consequences, so there's only one caller and
that will treat values <=0 as 'cache not loaded'. There's no functional
change but otherwise the error values should be there for clarity.

Fixes: a67509c30079f4c50 ("Btrfs: add a io_ctl struct and helpers for dealing with the space cache")
Reported-by: Hulk Robot <[email protected]>
Signed-off-by: Zhihao Cheng <[email protected]>
---
fs/btrfs/free-space-cache.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index af0013d3df63..ae4059ce2f84 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -744,8 +744,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
while (num_entries) {
e = kmem_cache_zalloc(btrfs_free_space_cachep,
GFP_NOFS);
- if (!e)
+ if (!e) {
+ ret = -ENOMEM;
goto free_cache;
+ }

ret = io_ctl_read_entry(&io_ctl, e, &type);
if (ret) {
@@ -764,6 +766,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
e->trim_state = BTRFS_TRIM_STATE_TRIMMED;

if (!e->bytes) {
+ ret = -1;
kmem_cache_free(btrfs_free_space_cachep, e);
goto free_cache;
}
@@ -784,6 +787,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
e->bitmap = kmem_cache_zalloc(
btrfs_free_space_bitmap_cachep, GFP_NOFS);
if (!e->bitmap) {
+ ret = -ENOMEM;
kmem_cache_free(
btrfs_free_space_cachep, e);
goto free_cache;
--
2.25.4

2020-12-15 17:30:18

by David Sterba

Subject: Re: [PATCH v2] btrfs: free-space-cache: Fix error return code in __load_free_space_cache

On Mon, Dec 07, 2020 at 09:56:12PM +0800, Zhihao Cheng wrote:
> Fix to return the error code(instead always 0) when memory allocating
> failed in __load_free_space_cache().
>
> This lacks the analysis of consequences, so there's only one caller and

By "This lacks the analysis of consequences" I was referring to
changelog in your patch and I did not expect you copy&paste it verbatim
to the next patch :)

Anyway, updated patch added to misc-next, thanks.