Re: fs, net: deadlock between bind/splice on af_unix

[Cong Wang]

On Wed, Jan 18, 2017 at 1:17 AM, Dmitry Vyukov <dvyu...@google.com> wrote:
> On Tue, Jan 17, 2017 at 10:21 PM, Cong Wang <xiyou.wangc...@gmail.com> wrote:
>> On Mon, Jan 16, 2017 at 1:32 AM, Dmitry Vyukov <dvyu...@google.com> wrote:
>>> On Fri, Dec 9, 2016 at 7:41 AM, Al Viro <v...@zeniv.linux.org.uk> wrote:
>>>> On Thu, Dec 08, 2016 at 10:32:00PM -0800, Cong Wang wrote:
>>>>
>>>>> > Why do we do autobind there, anyway, and why is it conditional on
>>>>> > SOCK_PASSCRED?  Note that e.g. for SOCK_STREAM we can bloody well get
>>>>> > to sending stuff without autobind ever done - just use socketpair()
>>>>> > to create that sucker and we won't be going through the connect()
>>>>> > at all.
>>>>>
>>>>> In the case Dmitry reported, unix_dgram_sendmsg() calls unix_autobind(),
>>>>> not SOCK_STREAM.
>>>>
>>>> Yes, I've noticed.  What I'm asking is what in there needs autobind 
>>>> triggered
>>>> on sendmsg and why doesn't the same need affect the SOCK_STREAM case?
>>>>
>>>>> I guess some lock, perhaps the u->bindlock could be dropped before
>>>>> acquiring the next one (sb_writer), but I need to double check.
>>>>
>>>> Bad idea, IMO - do you *want* autobind being able to come through while
>>>> bind(2) is busy with mknod?
>>>
>>>
>>> Ping. This is still happening on HEAD.
>>>
>>
>> Thanks for your reminder. Mind to give the attached patch (compile only)
>> a try? I take another approach to fix this deadlock, which moves the
>> unix_mknod() out of unix->bindlock. Not sure if there is any unexpected
>> impact with this way.
>
>
> I instantly hit:
>

Oh, sorry about it, I forgot to initialize struct path...

Attached is the updated version, I just did a boot test, no crash at least. ;)

Thanks!

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 127656e..cef7987 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -995,6 +995,7 @@ static int unix_bind(struct socket *sock, struct sockaddr 
*uaddr, int addr_len)
        unsigned int hash;
        struct unix_address *addr;
        struct hlist_head *list;
+       struct path path = { NULL, NULL };
 
        err = -EINVAL;
        if (sunaddr->sun_family != AF_UNIX)
@@ -1010,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct 
sockaddr *uaddr, int addr_len)
                goto out;
        addr_len = err;
 
+       if (sun_path[0]) {
+               umode_t mode = S_IFSOCK |
+                      (SOCK_INODE(sock)->i_mode & ~current_umask());
+               err = unix_mknod(sun_path, mode, &path);
+               if (err) {
+                       if (err == -EEXIST)
+                               err = -EADDRINUSE;
+                       goto out;
+               }
+       }
+
        err = mutex_lock_interruptible(&u->bindlock);
        if (err)
-               goto out;
+               goto out_put;
 
        err = -EINVAL;
        if (u->addr)
@@ -1029,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct 
sockaddr *uaddr, int addr_len)
        atomic_set(&addr->refcnt, 1);
 
        if (sun_path[0]) {
-               struct path path;
-               umode_t mode = S_IFSOCK |
-                      (SOCK_INODE(sock)->i_mode & ~current_umask());
-               err = unix_mknod(sun_path, mode, &path);
-               if (err) {
-                       if (err == -EEXIST)
-                               err = -EADDRINUSE;
-                       unix_release_addr(addr);
-                       goto out_up;
-               }
                addr->hash = UNIX_HASH_SIZE;
                hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 
1);
                spin_lock(&unix_table_lock);
@@ -1065,6 +1067,9 @@ static int unix_bind(struct socket *sock, struct sockaddr 
*uaddr, int addr_len)
        spin_unlock(&unix_table_lock);
 out_up:
        mutex_unlock(&u->bindlock);
+out_put:
+       if (err)
+               path_put(&path);
 out:
        return err;
 }