[PATCH v2] smb: client: fix possible double free in smb2_set_ea()

Su Hui posted 1 patch 1 month, 1 week ago
fs/smb/client/smb2ops.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
[PATCH v2] smb: client: fix possible double free in smb2_set_ea()
Posted by Su Hui 1 month, 1 week ago
Clang static checker(scan-build) warning:
fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
 1304 |         kfree(ea);
      |         ^~~~~~~~~

There is a double free in such case:
'ea is initialized to NULL' -> 'first successful memory allocation for
ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
-> 'goto replay_again' -> 'second goto sea_exit before allocate memory
for ea' -> 'second memory release for ea resulted in double free'.

Re-initialie 'ea' to NULL near to the replay_again label, it can fix this
double free problem.

Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
Signed-off-by: Su Hui <suhui@nfschina.com>
---
v2: 
- Move 'ea = NULL' near to the replay_again label.(Dan's suggestion)

 fs/smb/client/smb2ops.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 6b385fce3f2a..24a2aa04a108 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1158,7 +1158,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_fid fid;
 	unsigned int size[1];
 	void *data[1];
-	struct smb2_file_full_ea_info *ea = NULL;
+	struct smb2_file_full_ea_info *ea;
 	struct smb2_query_info_rsp *rsp;
 	int rc, used_len = 0;
 	int retries = 0, cur_sleep = 1;
@@ -1179,6 +1179,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 	if (!utf16_path)
 		return -ENOMEM;
 
+	ea = NULL;
 	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;
 	vars = kzalloc(sizeof(*vars), GFP_KERNEL);
 	if (!vars) {
-- 
2.30.2

Re: [PATCH v2] smb: client: fix possible double free in smb2_set_ea()
Posted by Dan Carpenter 1 month, 1 week ago
On Tue, Oct 15, 2024 at 06:20:37PM +0800, Su Hui wrote:
> Clang static checker(scan-build) warning:
> fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
>  1304 |         kfree(ea);
>       |         ^~~~~~~~~
> 
> There is a double free in such case:
> 'ea is initialized to NULL' -> 'first successful memory allocation for
> ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
> -> 'goto replay_again' -> 'second goto sea_exit before allocate memory
> for ea' -> 'second memory release for ea resulted in double free'.
> 
> Re-initialie 'ea' to NULL near to the replay_again label, it can fix this
> double free problem.
> 
> Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
> Signed-off-by: Su Hui <suhui@nfschina.com>
> ---
> v2: 
> - Move 'ea = NULL' near to the replay_again label.(Dan's suggestion)

Thanks!

Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>

regards,
dan carpenter

Re: [PATCH v2] smb: client: fix possible double free in smb2_set_ea()
Posted by Steve French 1 month, 1 week ago
merged into cifs-2.6.git for-next pending additional testing

On Tue, Oct 15, 2024 at 5:45 AM Dan Carpenter <dan.carpenter@linaro.org> wrote:
>
> On Tue, Oct 15, 2024 at 06:20:37PM +0800, Su Hui wrote:
> > Clang static checker(scan-build) warning:
> > fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
> >  1304 |         kfree(ea);
> >       |         ^~~~~~~~~
> >
> > There is a double free in such case:
> > 'ea is initialized to NULL' -> 'first successful memory allocation for
> > ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
> > -> 'goto replay_again' -> 'second goto sea_exit before allocate memory
> > for ea' -> 'second memory release for ea resulted in double free'.
> >
> > Re-initialie 'ea' to NULL near to the replay_again label, it can fix this
> > double free problem.
> >
> > Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
> > Signed-off-by: Su Hui <suhui@nfschina.com>
> > ---
> > v2:
> > - Move 'ea = NULL' near to the replay_again label.(Dan's suggestion)
>
> Thanks!
>
> Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
>
> regards,
> dan carpenter
>
>


-- 
Thanks,

Steve